Content adjustment interaction method and device, electronic equipment and readable storage medium

Abstract

The application discloses a content adjustment interaction method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: in response to a task trigger event, displaying task content on a graphical user interface; in response to a content adjustment event for the task content, determining at least one piece of content to be adjusted and an intention to be adjusted corresponding to the content to be adjusted, wherein the content to be adjusted comprises at least one piece of sequence information in the task content; adjusting the content to be adjusted based on the intention to be adjusted, obtaining at least one target content and displaying the target content on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted, and the target content can meet the personalized needs of a user when reading the content, thereby improving the learning efficiency of the user for specific content.

Description

Technical Field

[0001] This application relates to the field of content adjustment and interaction technology, specifically to a content adjustment and interaction method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] With the rise of the internet, people are paying more and more attention to learning different languages. When learning a particular language, people generally read a lot of articles in that language to gradually master it.

[0003] Currently, when people are learning a language, they can use language tools to translate the articles they are reading so that they can understand the meaning of the articles. However, because different users have different personalized needs when reading articles, simply using language tools to translate articles often cannot meet the needs of users well.

[0004] Especially during the learning process, users are often faced with content that is not limited to reading articles, but also includes subjective questions (such as reading comprehension and writing exercises) and objective questions (such as multiple choice and fill-in-the-blank questions). Because the same knowledge point can have questions of varying difficulty, and different users have different language levels and learning goals, a single content presentation method cannot solve the problem that more and more users want to learn according to their own cognitive abilities, learning goals, or preferences. Summary of the Invention

[0005] This application provides a content adjustment interaction method, device, electronic device, and computer-readable storage medium, which can meet users' personalized needs when reading content, thereby improving users' learning efficiency for specific content.

[0006] In a first aspect, embodiments of this application provide a content adjustment interaction method, including: In response to a task trigger event, display the task content on the graphical user interface; In response to a content adjustment event for the task content, at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted are determined, wherein the content to be adjusted includes at least one piece of sequence information in the task content; Adjust the content to be adjusted based on the intended adjustment, and obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0007] Secondly, embodiments of this application also provide a content adjustment interaction device, including: The content display module is used to display task content on the graphical user interface in response to task triggering events; An adjustment confirmation module is used to respond to a content adjustment event for the task content to determine at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content; The content display module is used to adjust the content to be adjusted based on the intention to be adjusted, to obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0008] Thirdly, embodiments of this application also provide an electronic device, including a memory storing a computer program, which, when executed by a processor, causes the processor to execute any of the content adjustment interaction methods provided in embodiments of this application.

[0009] Fourthly, embodiments of this application also provide a computer-readable storage medium including a computer program. When the computer program is run on an electronic device, the computer program is used to cause the electronic device to perform any of the content adjustment interaction methods provided in embodiments of this application.

[0010] In this embodiment, task content is displayed on a graphical user interface in response to a task triggering event; at least one piece of content to be adjusted and the corresponding adjustment intent are determined in response to a content adjustment event for the task content, wherein the content to be adjusted includes at least one piece of sequence information in the task content; the content to be adjusted is adjusted based on the adjustment intent to obtain at least one target piece of content and displayed on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted, thereby supporting the adjustment of content in the task content with a specific adjustment intent to meet the personalized needs of users when reading content and improve the learning efficiency of users for specific content. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of one embodiment of the content adjustment interaction method provided in this application. Figure 2 This is a schematic diagram of a difficulty adjustment control provided in an embodiment of this application; Figure 3 This is a schematic diagram of another difficulty adjustment control provided in the embodiments of this application; Figure 4 This is a schematic diagram of the dimension identifier provided in the embodiments of this application; Figure 5 This is a schematic diagram of the content adjustment prompt information provided in the embodiments of this application; Figure 6 This is a schematic diagram of the target content provided in the embodiments of this application; Figure 7 This is another schematic diagram of the target content provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of the content adjustment interaction device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] Before providing a detailed explanation of the embodiments of this application, some terms involved in the embodiments of this application will be explained.

[0015] In the description of the embodiments of this application, the terms "first," "second," etc., may be used herein to describe various concepts, but unless specifically stated otherwise, these concepts are not limited by these terms. These terms are used only to distinguish one concept from another. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes 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 these processes, methods, products, or devices.

[0016] This application provides a content adjustment interaction method, apparatus, electronic device, and computer-readable storage medium. Specifically, the content adjustment interaction method of this application can be executed by an electronic device, which can be a terminal or a server. The terminal can be a smartphone, tablet, laptop, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other terminal device. The terminal can also include a client, which can be a game application client, a browser client carrying a game program, or an instant messaging client. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0017] For example, this electronic device, taking a terminal as an example, can display task content on a graphical user interface in response to a task triggering event; in response to a content adjustment event for the task content, determine at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content; adjust the content to be adjusted based on the adjustment intention to obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0018] Based on the above problems, embodiments of this application provide a content adjustment interaction method, device, electronic device, and computer-readable storage medium, which can solve the technical problem that existing content display systems, such as smart learning machines, cannot dynamically adjust the difficulty mechanism of learning content based on different user ability levels or comprehension levels, so as to meet the personalized needs of users when reading content and improve the user's learning efficiency for specific content.

[0019] The following is a detailed description in conjunction with the accompanying drawings. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments. Although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be performed in a different order than that shown in the drawings.

[0020] In this embodiment, a terminal is used as an example for illustration. This embodiment provides a content adjustment interaction method, such as... Figure 1 As shown, the specific process for adjusting the interaction method of this content can be as follows: Step 101: In response to the task triggering event, display the task content on the graphical user interface.

[0021] Among them, the task trigger event is used to indicate the trigger event that prompts the current user to view or learn specific content. After the task trigger event is triggered, the task content can be displayed in the graphical user interface.

[0022] Specifically, task-triggered events can be triggered by uploading specific learning content or downloading and displaying specific learning content.

[0023] Optionally, the task triggering event can also be an event triggered by opening a certain function, such as opening a learning page, opening a pop-up window, or opening an app to display task content.

[0024] The task content can be what the user is currently viewing, including text, images and text, or video content; there are no restrictions here.

[0025] For example, the task content can be learning content that users can view through smart devices such as learning machines, including test questions and knowledge points; for example, learning content that includes multiple questions or knowledge points.

[0026] Optionally, the task content can also be text content such as articles or novels in a specific language, such as English, that users can view through smart devices such as mobile phones or learning machines.

[0027] Optionally, the task content can also be the images, videos, or other content that the user is currently viewing.

[0028] Step 102: In response to a content adjustment event for the task content, determine at least one piece of content to be adjusted and the adjustment intent corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content.

[0029] Among them, the content adjustment event is used to indicate an event that triggers an adjustment to at least part of the content of the task. After the content adjustment event is triggered, the method of adjusting the task content can be determined by identifying the intention to be adjusted.

[0030] Specifically, content adjustment events can be triggered by the current user's behavior or by a pre-set triggering mechanism on the terminal. The specific settings can be configured according to requirements and are not limited here.

[0031] The content adjustment event can be triggered by the current user's behavior in the following ways, including but not limited to: The current user performs a specific operation on the graphical user interface to trigger the event, such as operating the trigger control provided on the graphical user interface to trigger the content adjustment event; the current user performs a specific operation on the external input device associated with the electronic device to which the graphical user interface belongs (the terminal in this embodiment) to trigger the content adjustment event. The external input device can be a mouse, keyboard, stylus, etc., and can be set according to the needs, without limitation here.

[0032] Optionally, the content adjustment event can be triggered by a pre-set triggering mechanism on the terminal, and the generation methods may include, but are not limited to: The terminal can trigger the content adjustment event when it detects that the user behavior data meets the preset trigger conditions. For example, when it receives that the user stays on the current page for a longer period than a preset time threshold, it determines that the content displayed on the current page in the task content may be too difficult, and thus triggers the content adjustment event.

[0033] For example, when a user's test score for a task does not meet a preset score threshold, a content adjustment event for that task can be triggered. The specific settings can be configured according to requirements and are not limited here.

[0034] Optionally, the content adjustment event can be triggered by the user through voice control on the terminal, and may include, but is not limited to: Users can use voice control on the terminal to select the task content displayed on the graphical user interface, and trigger adjustments to the content of that task.

[0035] The content to be adjusted refers to the content that includes at least one sequence information in the task content. This sequence information refers to the information that includes the effective content in the task content, that is, the effective content unit in the task content that is selectable and processable.

[0036] It is understandable that the sequence information can be the smallest semantic unit of the task content, or it can be a larger semantic structure that includes multiple smallest semantic units.

[0037] Here, the intended adjustment refers to the processing purpose that is desired to be applied to the content to be adjusted, i.e., at least one sequence of information. For example, changing the content to be adjusted into simpler, more visual, or more academic content for display on a graphical user interface.

[0038] Step 103: Adjust the content to be adjusted based on the intended adjustment to obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0039] The target content refers to the content obtained by adjusting the content to be adjusted according to the intention to be adjusted. It should be noted that the target content and the content to be adjusted should match in terms of content expression. That is, the target content should be consistent with the content to be adjusted in terms of the main idea, knowledge core, or intention orientation, or should have a identifiable connection. In other words, although the content to be adjusted has been adjusted, the essential information or its meaning can remain unchanged.

[0040] For example, the content to be adjusted is: The cat is sitting on the mat. The intention of the adjustment is to reduce the overall difficulty of the above content to obtain the target content: A cat is on amat. In summary, for the content to be adjusted, the semantics of the content before and after the adjustment remain consistent, or in other words, basically unchanged.

[0041] For example, although the specific form of the question has changed, it still tests the basic properties of trigonometric functions (maximum value, period, etc.), so "the knowledge points remain consistent," which is a matter of matching the content expression.

[0042] In this embodiment, the purpose of teaching, learning, and viewing remains unchanged by maintaining consistency in the intended message before and after adjustment. Based on the user's intended message, the selected content is adjusted in terms of difficulty and type, while ensuring the same expressive content is presented. This enhances user learning adaptability and reduces cognitive load or increases challenge. Especially in student learning, maintaining consistency in the expressed content helps accurately convey teaching objectives, ensuring that the core knowledge points or assessment targets remain unchanged, preventing students from deviating from the learning focus due to changes in format.

[0043] Furthermore, even if different users, such as different students, use content of varying difficulty, the consistency of their learning path is ensured, meaning that the learning of knowledge points does not diverge. This also facilitates teachers' grading and synchronous progress management, and is conducive to personalized adjustments for different students in a large-scale teaching environment, enabling individualized instruction.

[0044] Moreover, the adjusted cognitive load is controllable, avoiding the sunk cost of students with weak foundations giving up on more difficult teaching content. For example, applying the technical solution of this application to a smart educational learning machine allows for different levels of difficulty and types of cases, questions, and expressions to be provided for different students when teaching the same knowledge point. This is especially beneficial in English teaching, particularly for users with reading difficulties or poor foreign language learning foundations, allowing them to gradually transition to the original difficulty level and improving teaching quality.

[0045] Understandably, the system can also parse the task content according to the task type and content structure, using preset structural division rules, to generate multiple optional sequence information, such as parsing based on whether the task type is subjective, objective, or reading comprehension, and the content structure of the task content, such as subjective, objective, or reading comprehension.

[0046] It is understandable that the sequence information can refer to information units in the task content that have structural or semantic recognizability, and can express a certain knowledge objective independently or in combination; The sequence information of the smallest unit can refer to the indivisible basic expression structure, such as words, numbers, code blocks, image units, etc. Combinatable sequence information can be an expressive structure composed of multiple smallest units, such as a sentence, a question stem, or a complete multiple-choice question; Structural partitioning rules can refer to configurable rules used by the system to parse the structure of task content, determining which segments can be used as sequence information: The structural partitioning rules include, but are not limited to: Linguistic levels: word, phrase, sentence; Structural markers: Question stem, options, and explanation; Semantic units: knowledge point expression, semantics of distractors; Independently editable marked areas: title annotations, image elements, etc.

[0047] For example, if the task type is a subjective question, the granularity of its sequence information can be refined as follows: Minimum granularity: a single word (verb, noun, adjective, adverb, etc.); Medium granularity: A complete sentence structure (such as a sentence containing a subject-verb-object structure); Larger granularity: a paragraph or question-and-answer structure; The system can identify the hierarchy based on language segmentation rules and syntactic analysis models, and generate multiple sequence information options for users to choose from.

[0048] When a user selects content to be adjusted, the content must include at least one sequence of information. This sequence of information can be a single word, a complete sentence at a medium granularity, or a paragraph or question-and-answer structure at a larger granularity.

[0049] Understandably, if the sequence information is a paragraph and the user's selection of content to be adjusted does not include a complete paragraph, then the user can choose to complete the paragraph through the large language model, or the user can redetermine the content to be adjusted.

[0050] For example, if the task type is objective questions, the granularity of its sequence information can be refined as follows: The question stem itself can be further divided into: (1) Background description (which may be simplified or have complex grammar added to increase reading difficulty) (2) Core test points expression section (synonyms can be used and sentence structure can be adjusted) The options area can be further divided into: (1) Correct option content (can be refined or semantically enhanced) (2) Distractors (can change their deceptiveness and enhance their contrast) Understandably, the system can generate corresponding sequence information independently for each part of the content, or it can generate sequence information for the overall task content.

[0051] It is understandable that, in addition to the examples above, sequence information can also be a question or a knowledge point in teaching / assessment content.

[0052] Optionally, the sequence information can also be an image, or an optional object in an image, such as a person, animal, or item.

[0053] Alternatively, the sequence information may also be a video sequence that can be divided into a single story unit, etc., without limitation here.

[0054] It should be noted that each sequence of information is a unit that can be individually identified, selected, and further manipulated, and can exist in multiple modal forms such as text, titles, images, and videos.

[0055] Understandably, to address the technical issue of inflexible operation when users are learning knowledge points, the task content is displayed on the graphical user interface in response to task trigger events, including: In response to a task triggering event, at least one sequence information uploaded or selected by the user is displayed on a graphical user interface to generate task content that matches the user's learning level based on at least one sequence information, and the task content is displayed on the graphical user interface.

[0056] For example, a large language model is instructed to generate task content that matches the user's learning level based on at least one sequence of information, and then display the task content on a graphical user interface.

[0057] It is understood that the task content can refer to articles in any first language, including but not limited to English, Spanish, French, German, Russian, Chinese, Turkish, Arabic, etc., without any limitation.

[0058] Accordingly, the first language can be the language that the current user is learning, the current user has set up a user account on the terminal, and the current user participates in the content adjustment interaction method by using the set user account on the terminal.

[0059] It should be noted that in scenarios where the task content is an article, sequence information can refer to words, phrases, sentences, paragraphs, etc.

[0060] Among them, the task trigger event is used to indicate the event that triggers the current user to view or learn the task content or related information such as the language and knowledge points to which the task content belongs. After the task trigger event is triggered, the corresponding task content can be displayed in the graphical user interface so that the current user can learn the language of the task content or related information to which the task content belongs by reading the task content.

[0061] Specifically, task trigger events can be generated by the current user's user behavior or by a pre-set trigger mechanism on the terminal. The specific settings can be configured according to the requirements and are not limited here.

[0062] The way in which this task trigger event can be generated by the current user's user behavior may include, but is not limited to: The event is triggered by the current user performing a specific operation on the graphical user interface, such as operating the trigger control provided on the graphical user interface to trigger the task trigger event; or the event is triggered by the current user performing a specific operation on an external input device associated with the electronic device to which the graphical user interface belongs (in this embodiment, the terminal). The external input device can be a mouse, keyboard, etc., and can be set according to the requirements, without limitation here.

[0063] The method by which this task trigger event can be generated by a pre-set triggering mechanism on the terminal may include, but is not limited to: The terminal can trigger the task trigger event when the current time meets the preset trigger time. The preset trigger time can be a periodic time, such as a specific time every day. The terminal can also trigger the task trigger event when the detected user behavior data meets the preset trigger conditions.

[0064] For example, when the system receives the target learning content input by the user, it determines that the user currently wants to learn that target learning content and triggers a task trigger event.

[0065] For example, a task trigger event can be triggered when a user's test score for a specific language does not meet a preset score threshold. The specific settings can be configured according to requirements and are not limited here.

[0066] Furthermore, the target learning content can refer to the user selecting at least one sequence of information, such as selecting several English words or sentences that they want to learn or use, and inputting these words or sentences into the large language model to instruct the large language model to generate an English article based on at least one word or sentence, or a combination of words and sentences, and display the English article on the graphical user interface.

[0067] Understandably, in order to meet the personalized needs of current users when learning languages ​​and to improve their learning efficiency, the overall difficulty level of the task content can be matched with the current user's learning level.

[0068] It is understandable that by displaying task content that matches the current user's current abilities, the current user can learn the task content or related information more efficiently.

[0069] It is understandable that, in response to a task triggering event, displaying task content for the current user on the graphical user interface may include: In response to a task trigger event, the system obtains the current user's learning level in the first language; based on the learning level, it generates task content and displays the task content on the graphical user interface, thereby achieving the goal of recommending task content with a difficulty level that matches the current user's learning level.

[0070] The first language is the language that the current user wants to learn. The current user can trigger the learning of the first language by operating in the terminal.

[0071] Understandably, based on the user's learning level and learning goals, the terminal can automatically generate corresponding task content: For example, language articles at the beginner level can contain simple vocabulary and sentence structures, mainly to help users build a foundation for memorization through frequent exposure to low-difficulty words; The language articles corresponding to the intermediate level can be suitable for the user's current learning level, avoiding overly complex sentence structures and difficult words, while ensuring that the new vocabulary that the user needs to learn is covered; Advanced level language articles can contain a large number of unfamiliar or advanced vocabulary words and involve complex grammatical structures, helping users challenge themselves and improve their vocabulary and grammar skills.

[0072] To address this, by controlling the difficulty level of the task content, the terminal generates articles of appropriate difficulty based on the user's vocabulary level, ensuring that the content the user is currently learning is neither too advanced nor too challenging.

[0073] Specifically, obtaining the current user's learning level in the first language can include: The terminal can display the learning level test content of the first language on the graphical user interface. Then, the terminal can receive the user's learning level test results for the first language, and determine the current user's learning level of the first language based on the learning level test results, so as to recommend language articles that match the current user's learning level.

[0074] The learning level can be indicated by the user's learning level. The higher the user's learning level, the higher the learning level. Specifically, the terminal can automatically assign a level to the current user based on the test results of the current user's learning level in the first language.

[0075] Understandably, the overall difficulty of the task content is positively correlated with the user's current level of proficiency in the first language. That is, the higher the proficiency, the greater the difficulty, and the lower the proficiency, the less difficult. This ensures that the language articles the user needs to read match the user's current ability, thus meeting the user's personalized needs.

[0076] Specifically, the display of the first language learning level test content on the graphical user interface can be triggered by the current user's behavior or by a pre-set triggering mechanism on the terminal. The specific settings can be configured according to the needs and are not limited here.

[0077] The methods for triggering the display based on the current user's behavior may include, but are not limited to: The current user performs a specific operation on the graphical user interface to trigger the display, such as operating the trigger control provided by the graphical user interface to trigger the display. It is understandable that the display can also be triggered by the current user performing a specific operation on an external input device associated with the electronic device (in this embodiment, the terminal) to which the graphical user interface belongs. This external input device can be a mouse, keyboard, etc.

[0078] The generation method triggered by a pre-set triggering mechanism on the terminal may include, but is not limited to: The terminal can trigger the display of the first language learning level test content when the user behavior data meets the preset trigger display conditions. For example, the display can be triggered when the current user is a user account that is logging in for the first time or registering.

[0079] Specifically, the content of the learning level test includes, but is not limited to: The test includes at least one dimension, such as vocabulary tests for the first language (e.g., tests on basic vocabulary), sentence tests for phrases in the first language (e.g., tests on everyday phrases), and grammar tests for the grammatical structures of the first language.

[0080] Specifically, the testing formats for learning level assessment content include, but are not limited to: Multiple-choice and fill-in-the-blank questions are used to assess a user's proficiency in their first language through different test formats, and the user is then assigned a level based on this testing mechanism.

[0081] For example, the first language can be set as English, and three learning levels can be preset for English: beginner (scores from 0 to 40), intermediate (scores from 41 to 80), and advanced (scores from 81 to 100). Based on the current user's English learning level test result of 30, the current user's corresponding learning level is determined, that is, the current user's English learning level is beginner, so as to provide the current user with a learning plan that is in line with the beginner level, such as recommending English articles that are in line with the beginner level.

[0082] It is understood that, in response to a task triggering event, displaying at least one sequence of information uploaded by the user on a graphical user interface to instruct a large language model to generate task content matching the user's learning level based on at least one sequence of information, and displaying the task content on the graphical user interface, may further include: The system retrieves the target learning content input by the current user to trigger a response task trigger event. This target learning content can indicate the user's expected learning content for their first language, such as articles or article types in a specific language (e.g., narrative texts, news reports), or vocabulary or vocabulary categories (e.g., business vocabulary, IELTS vocabulary). Specific settings can be configured according to needs and are not limited here. The terminal then generates task content based on the target learning content.

[0083] Understandably, the terminal can recommend language articles that match the user's current learning stage based on the user's current learning level.

[0084] Furthermore, user-inputted target learning content can be incorporated into this process to extract or generate task content that aligns with the target learning content from a language library that matches the current user's learning stage. This allows the terminal to more accurately recommend language articles that meet the current user's needs.

[0085] The user input methods corresponding to the target learning content may include, but are not limited to: Currently, users can input directly on the learning page provided by the graphical user interface, or they can trigger controls provided by the graphical user interface to input, etc.

[0086] For example, the terminal can translate language articles from other languages ​​into the first language. The current user can select the "Custom Learning" custom control on the learning page to display the article input window. The current user can paste or upload a language article (such as a Chinese news article) and / or language vocabulary (such as 10 medical terms) in the article input window to generate task content related to the first language (such as translating a Chinese news article into an English news article, or generating a scenario-based article containing the medical terms from 10 medical terms, such as an article simulating a doctor-patient dialogue).

[0087] For example, the terminal can input relevant language words about the first language that the user is interested in through the "Add Interest Words" entry provided on the graphical user interface, so as to generate a corresponding language vocabulary package by periodically summarizing the relevant language words about the first language, and generate task content based on the generated language vocabulary package.

[0088] For example, if a user enters a certain number of scientific and technological terms this week, an AI-generated popular science article can be generated from these terms as the task content.

[0089] It is understandable that, in response to a task triggering event, displaying task content on the graphical user interface may also include: In response to a user's task triggering event, display at least one target learning content triggered by the user and the user's learning level on the graphical user interface, and generate task content; Display the task content on the graphical user interface.

[0090] In some embodiments, the target learning content includes language articles in a second language. In response to a user's task triggering event, at least one target learning content triggered by the user and the user's learning level are displayed on a graphical user interface. The generated task content may include: Based on the user's learning level, the second language article is translated into the task content, and the second language article and the task content have the same semantics.

[0091] The first language and the second language are different languages.

[0092] In this embodiment, when the user inputs a language article in another language (i.e., a language article in a second language), the task content that meets the current user's needs is obtained through translation.

[0093] For example, if the first language is set to English and the second language to Chinese, the terminal can receive the Chinese text input by the current user and translate it into an English text. During the translation process, the difficulty level of the English text can be adjusted based on the user's learning level. For example, higher-level vocabulary in the English text can be replaced with lower-level vocabulary with the same meaning (e.g., "utilize" can be replaced with "use"), sentences in the English text can be simplified (e.g., clauses in English can be broken down), professional terms in business context texts can be preserved while adding explanations for the professional terms (a corresponding sidebar can be generated on the graphical user interface to avoid affecting the continuity of the task content), and cultural background information for related vocabulary can be added (a corresponding explanation can be added after the vocabulary using characters, such as "tea time" can be adjusted to "afternoon tea [British custom 3-5pm]"). In this way, while preserving the core semantics of the language text, the difficulty level is also adapted to the current user's learning level.

[0094] Specifically, when the target learning content includes language articles in a second language, obtaining the target learning content input by the current user can include: In response to a trigger operation on the language library, at least one candidate language article (such as a preset example article) is displayed. In response to a selection operation on the task content in the candidate language article, the selected task content is used as the target learning content.

[0095] The language resources in the language database can be obtained from public platforms or authorized corpora, including but not limited to collaborative resources between specific institutions, the Cambridge English Corpus, sample essays accompanying the Oxford 3000 / 5000 core vocabulary, the official TOEFL test bank (authorized by ETS TPO), SEC financial reports / Harvard business case databases, selected PubMed paper abstracts, and specific types of language resources.

[0096] Among these, specific types of language resources include, but are not limited to: News: Reuters / BBC Learning English (updated daily); Encyclopedia: Simple Wikipedia → Wikipedia graded crawling; Culture: TED-Ed subtitle text; Crowdsourced translation library: Non-English texts submitted by users are reviewed and then enter the generation pool to generate corresponding language resources; Error notebook corpus: High-frequency error sentence patterns are reconstructed by AI into a database of correct example sentences.

[0097] In some embodiments, the step of responding to a user's task triggering event by displaying at least one target learning content and the user's learning level in a graphical user interface, and generating task content, may include: Obtain the user association information for the current user in the first language; generate task content based on the user's learning level, target learning content, and user association information.

[0098] It is understandable that user-related information can be personal information input by the user through an interface provided by the terminal, or information automatically retrieved by the terminal that can influence the user's first language learning. Based on this user-related information, the current user's initial learning path can be obtained, and basic language articles can be recommended to the current user based on this initial learning path. When the user actively inputs content, the terminal can use the user's input as direct feedback on the current user's interest or needs, and optimize the recommendation strategy based on the target learning content input by the current user.

[0099] For example, the initial learning path may be set to "B1 level business English", but because the user has entered literary words multiple times (such as "metaphor" and "protagonist"), the terminal can automatically increase the push weight of "literature" content, so that the language articles generated later will prioritize language articles with literary themes (such as simplified excerpts from famous works, explanations of literary terms, etc.).

[0100] In this embodiment, a personalized learning path is automatically generated based on the user's associated information (such as learning goals and learning areas), vocabulary level, and target learning content that the user is interested in or has a need for. Personalized task content is then generated based on this personalized learning path, achieving personalized customization for each user and providing learning content that matches the difficulty level of the corresponding user (for example, business English learners and travel English learners will receive completely different learning paths and vocabulary sets), thereby improving learning efficiency.

[0101] In some embodiments, user-related information includes at least one of learning objectives, user attributes, learning domains, and learning styles.

[0102] User attributes may include, but are not limited to: user age, user gender, user occupation, etc.

[0103] The user's age can be represented by a specific numerical value, such as 20 years old, or by specific tags, such as child, teenager, or adult.

[0104] The learning objectives include, but are not limited to: learning type objectives, such as business language, exam language (such as IELTS), everyday language, and travel language; and learning stage objectives, such as learning content at different time periods. For example, a user can select "Business English" as their learning objective, and the terminal can automatically generate an article of a specific difficulty level on "Corporate Meeting Etiquette," highlighting the business terms used in the article to facilitate the user's learning.

[0105] The learning fields include, but are not limited to, the medical field, the IT field, the academic field, and the financial field. By setting the learning fields, the task content recommended and displayed on the graphical user interface is more in line with the actual use scenario required by the current user, so that the current user can apply and communicate in real-world scenarios, thus achieving a close fit between the learning content and the real-world use scenario.

[0106] Among them, learning style is used to indicate the style of language articles. Introducing learning style can increase the fun and practicality of learning and meet the diverse needs of current users. The learning style includes, but is not limited to, story style (suitable for users who like to listen to stories, learning by generating stories that are suitable for different age groups (such as children's stories)), news style (suitable for users who like to follow current events, generating articles based on current hot topics to help users learn the language while keeping up with the latest current events), popular science style, situational dialogue style, and advertising copy style.

[0107] Understandably, by using user-related information, user learning level, and target learning content, a personalized learning path can be generated that suits the current user. Based on this personalized learning path, appropriate vocabulary and learning materials can be selected to provide a tailored learning solution for the current user and automatically generate articles.

[0108] For example, the current user's personalized learning path could be: Intermediate - Business English - Adult - Finance - Stage Goals (1-3 months: Professional Email Writing; 4-6 months: Financial Statement Analysis Terminology).

[0109] It is understandable that the target learning content includes vocabulary from the first language. Based on the user's learning level, the target learning content, and user-related information, task content is generated, which may include: Based on the user's learning level and related information, identify the associated vocabulary corresponding to the language vocabulary; generate task content that includes at least some of the language vocabulary and associated vocabulary.

[0110] In this embodiment, the terminal can automatically generate a coherent article that includes at least some vocabulary from the first language to meet the current user's needs (such as inputting the language vocabulary "climate change" to generate a short article on the theme of environmental protection). Furthermore, during the task content generation process, in order to ensure the natural context in the language article, it can automatically expand related words for the language vocabulary (such as expanding related words such as "funding" and "pitch" for the input language vocabulary "startup") to improve the readability of the natural language article.

[0111] Specifically, the proportion of unfamiliar words in related vocabulary can be determined based on the user's learning level. For example, the proportion of unfamiliar words appearing in language articles of a certain difficulty level should not exceed a preset proportion threshold. For example, the preset proportion threshold for beginner level is 15%.

[0112] Specifically, based on the user's learning level, related words can be selected from those that match the user's learning domain in the associated information, or vocabulary descriptions can be added to language words that match the learning domain.

[0113] In some embodiments, language words in the task content are displayed in a different style from other words, so that the current user can more intuitively understand the target learning content they are currently inputting.

[0114] In some embodiments, multiple language words exist in a current user's input cycle. Generating task content containing at least some language words and related words may include: determining the vocabulary topic to which each language word belongs and the number of words corresponding to each vocabulary topic; determining the target topic with the most words based on the number of words corresponding to each vocabulary topic; and generating task content containing at least some language words and related words based on the target topic.

[0115] In this embodiment, the terminal can automatically mark the language words in the target learning content input by the current user, and adjust the topic of the subsequently recommended language articles based on the marked language words to dynamically calibrate the personalized needs of the current user. That is, by statistically analyzing the frequency of the word topics corresponding to the language words input by the current user in different input cycles, such as if literary words account for 30% in one input cycle, the push priority of the topic with the most words in one input cycle is increased to suppress topics with low usage frequency (such as reducing the push of related travel language articles if the user inputs few travel words).

[0116] In the absence of target learning content input by the current user, task content can be generated based on the user's learning level and user association information. However, when target learning content input by the current user exists, for example, when the input cycle reaches a certain number of times (such as 5 times), the matching degree between the generated task content and the user's interests is significantly improved.

[0117] To achieve finer-grained adjustment capabilities for task content and more controllable content expression dimension selection capabilities, thereby enhancing the adjustability of learning content and the personalized learning experience for users, it is understood that the intention to be adjusted includes at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension. The step of responding to a content adjustment event for the task content to determine at least one piece of content to be adjusted, and the intention to be adjusted corresponding to the content to be adjusted, includes: In response to a content triggering operation on the task content, at least one piece of content in the task content that has been triggered and needs to be adjusted is identified.

[0118] Content-triggered operations can refer to the selection or confirmation of at least one sequence of information within the task content. For example, selecting or clicking a word in an English article; or selecting or circling a multiple-choice question, its stem, or its options.

[0119] Accordingly, the content targeted by the content-triggered operation is determined as the content to be adjusted.

[0120] Alternatively, it can also refer to the selection of a specific image; or the selection of an object in an image, etc., without specific limitations here.

[0121] Among them, the content trigger operation is used to indicate the triggering of events on specific content in the task content, namely, selectable sequence information. After triggering this operation, the content to be adjusted in the task content can be determined.

[0122] Specifically, content triggering operations can be generated by the current user's user behavior or by a pre-set triggering mechanism on the terminal. The specific settings can be configured according to the needs and are not limited here.

[0123] The content triggering action can be generated by the current user's user behavior in ways including but not limited to: The current user performs a specific operation on the graphical user interface to trigger the content triggering operation, such as operating the trigger control provided by the graphical user interface. Optionally, the article content displayed on the graphical user interface can also be manipulated to trigger content-triggered actions; Optionally, the current user performs a specific operation on an external input device associated with the electronic device (in this embodiment, a terminal) to which the graphical user interface belongs, thereby triggering a content triggering operation. The external input device can be a mouse, keyboard, etc., and can be set according to requirements, without limitation here.

[0124] Specifically, the content triggering operation can be generated by a pre-set triggering mechanism on the terminal, and the methods include, but are not limited to: The terminal can trigger the content triggering operation when the detected user behavior data meets the preset triggering conditions. For example, when it receives that the user's stay time on the current page is greater than the preset time threshold, it determines that the article content displayed on the current page is the content triggering operation to be adjusted. Or, when it receives that the user's test score on an article does not meet the preset score threshold, it triggers the content triggering operation to be adjusted. The specific settings can be set according to the needs and are not limited here.

[0125] In response to the difficulty adjustment operation of the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted and a first difficulty level corresponding to the first content expression dimension are determined.

[0126] Among them, the first content expression dimension can be understood as the classification perspective of the content to be adjusted; the first difficulty level is the intended difficulty level relative to the current difficulty level of the first content expression dimension, which can be used to indicate the difficulty level of the task content in at least one content expression dimension, that is, to indicate the difficulty level of the task content in at least one content expression dimension.

[0127] Understandably, this difficulty level can be different from or the same as the current difficulty level.

[0128] Specifically, when the task content is an English article, the classification perspective refers to the perspective of different linguistic features, content characteristics, and reader acceptance levels that a certain English sentence in the task content may contain.

[0129] For example, the first content expression dimension includes at least one of the following: vocabulary dimension, sentence structure dimension, grammar dimension, or information density dimension; the first difficulty level corresponding to each first content expression dimension is the difficulty level.

[0130] Correspondingly, the first level of difficulty can refer to vocabulary difficulty, sentence structure complexity, information density difficulty, tone and intonation complexity, etc.

[0131] Among them, vocabulary difficulty can refer to the difficulty of the corresponding language vocabulary, and information density difficulty can refer to the amount of information in the corresponding content.

[0132] Optionally, when the task content is an objective question, the first content expression dimension may include at least one of the following: numerical complexity, distractor dimension, thought-provoking dimension, and question stem scenario dimension; The first difficulty level corresponding to numerical complexity includes numerical difficulty level; The first difficulty level corresponding to the interference dimension includes the interference difficulty level; The first difficulty level corresponding to the thought-guiding dimension includes the induction difficulty level; The first difficulty level corresponding to the scenario dimension of the question stem includes the scenario difficulty level.

[0133] It is understandable that the first content expression dimension can refer to any one of the dimensions that the objective question may include, such as numerical values, question stem scenario, expression method, number of steps, distractors, use of graphs / tables, misleading thinking, language traps, etc.

[0134] Correspondingly, the first level of difficulty can refer to numerical complexity, presence or absence of a context in the question stem, indirect or direct expression, simplification or increase in the number of steps, presence or absence of distractors, number of distractors, whether distractors are confusing or easily eliminated, addition or removal of graphs / tables, introduction or removal of language traps, etc.

[0135] Optionally, when the task content is a subjective question, the first content expression dimension may refer to at least one of the dimensions that the subjective question may include, such as style, cultural adaptation, vocabulary, sentence structure, use of allusions, and expression of subjectivity.

[0136] Correspondingly, the first level of difficulty can refer to whether the writing style is formal or colloquial, whether there is cultural adaptation, vocabulary level, sentence complexity or simplicity, whether allusions are used, and whether emotions / attitudes are expressed, etc.

[0137] Optionally, when the task content is an image, the first content expression dimension can refer to any one of the following dimensions: style, information density, context dependence, visual stimulation, learning objective coverage, etc. of the selected image.

[0138] Correspondingly, the style (cartoon / oil painting / photography), the number of elements in the image, the degree of context dependence, the complexity of visual stimuli, the level of learning objectives covered, etc.

[0139] Optionally, the first difficulty level of at least one first content expression dimension can be kept unchanged, while the first difficulty level of other first content expression dimensions can be changed to facilitate user learning.

[0140] For example, when the task content is an English article, a sentence in the article is identified as the content to be adjusted. The first content expression dimension is determined to be the sentence structure dimension, and the first difficulty level of this first content expression dimension is increased sentence structure difficulty. Other unselected first content expression dimensions (such as vocabulary dimension) and their corresponding difficulties remain unchanged, while only the sentence structure difficulty of the content to be adjusted is increased from the sentence structure dimension.

[0141] It is understood that the content to be adjusted can be all of the task content, or at least one word and / or at least one sentence in the task content.

[0142] Optionally, the content to be adjusted can be all the questions in a test paper, or at least one question in the test paper.

[0143] Optionally, the content to be adjusted can be all the images in a set of multiple images, or it can be just one of the images. The content to be adjusted is determined according to the specific type of the task content, which will not be elaborated here.

[0144] It is understandable that the content to be adjusted may correspond to multiple candidate content expression dimensions, and the first content expression dimension of the content to be adjusted to the first difficulty level may be multiple content expression dimensions, or it may be some of the content expression dimensions among multiple content expression dimensions.

[0145] It should be noted that, since the difficulty change information between the current difficulty level and the first difficulty level of the selected first content expression dimension can be an increase of at least one difficulty level, a decrease of at least one difficulty level, or no change, the content adjustment method corresponding to the first content expression dimension, as well as the degree of adjustment under that content adjustment method, are different.

[0146] Compared with traditional generative AI, the output of the technical solution in this application is not freely generated, but is constrained by the consistency or similarity of the content expression, such as knowledge points, examination dimensions, factual information, etc. The target content that matches the intention to be adjusted is generated through a pre-trained constrained optimization expression generation model, rather than a simple replacement of synonyms.

[0147] Understandably, before generating the target content, the system extracts the knowledge points, semantics, and other expressive content of the content to be adjusted, and inputs them into the model as invariable constraints to ensure that the target content is generated under the premise that the difficulty changes but the target does not deviate, or in other words, the target is consistent.

[0148] Understandably, adjusting the difficulty of the first content expression dimension for a given choice is not a blind replacement, but rather an adjustment based on the intended purpose. That is, the system needs to ensure that the expression changes but the meaning remains the same, or the meaning remains largely unchanged, or the original question's testing objective remains the same. Content adjustments are made under multi-objective constraints to achieve personalized learning and teaching goals.

[0149] It is understood that, in response to a content adjustment event for the task content, determining at least one piece of content to be adjusted, and the corresponding adjustment intent for the content to be adjusted, may include: In response to a content-triggered operation targeting task content, i.e., an English article, which selects at least a portion of the task content, the selected content is identified as the content to be adjusted. In response to a difficulty adjustment operation targeting the content, which indicates a corresponding difficulty level, the difficulty level indicated by the difficulty adjustment operation is designated as the first difficulty level to which the content to be adjusted is to be adjusted.

[0150] Content-triggered operations can be direct touch operations performed by the user on the article content displayed on the graphical user interface. These touch operations include, but are not limited to: click operations (such as single-click and double-click); press operations (such as pressing for a preset duration); and swipe operations (such as swiping in one direction). Content-triggered operations can also be performed by the user through manipulation of controls on the graphical user interface, or by performing specific operations on external input devices associated with the electronic device (in this embodiment, the terminal) to which the graphical user interface belongs. The specific details can be set according to requirements and are not limited here.

[0151] The difficulty adjustment operation can be a quick gesture operation performed directly by the user on the graphical user interface, such as swiping up with two fingers to increase the difficulty level and swiping down with two fingers to decrease the difficulty level. The difficulty adjustment operation can also be performed by the user through operating the controls on the graphical user interface, or by performing specific operations on the external input device associated with the electronic device to which the graphical user interface belongs (the terminal in this embodiment). The specific settings can be configured according to the needs and are not limited here.

[0152] Understandably, by allowing users to directly trigger content actions and adjust difficulty levels within the task content, the difficulty of the content to be adjusted can be personalized. This includes increasing or decreasing the difficulty to better meet the user's needs. For example, if the content to be adjusted is too difficult and makes it hard for the user to understand, the difficulty level can be lowered from at least one primary content expression dimension to help the user understand the meaning of the article and comprehend the corresponding difficult vocabulary or sentences without changing the overall meaning.

[0153] It is understandable that, apart from not changing the meaning of the text or the knowledge points being tested before and after the adjustment, the meaning and knowledge points of the text to be adjusted can be changed as needed. This can be set as needed, and will not be elaborated on in this article.

[0154] It is understandable that a graphical user interface can refer to the display interface of an electronic device held by a user, a pop-up window on the display interface, a designated area, or a virtual interface projected by a certain device, etc., without limitation.

[0155] The system described in this application can refer to learning machines, mobile phones, computers, VR glasses, AR head-mounted display devices, etc., and is not limited to these.

[0156] It is understood that the graphical user interface also includes a dimension selection control. The step of determining at least one first content expression dimension corresponding to the content to be adjusted, and a first difficulty level corresponding to the first content expression dimension, in response to the difficulty adjustment operation of the content to be adjusted, includes: A dimension selection control is displayed on the graphical user interface, wherein the dimension selection control includes at least one candidate content expression dimension generated based on the content to be adjusted; in response to a difficulty determination instruction for the dimension selection control, at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension are determined from the candidate content expression dimensions.

[0157] Among them, the candidate content expression dimension is all the classification perspectives in the content to be adjusted, or in other words, the adjustable, system-defined, and user-defined partial classification perspectives. This can be set as needed, and this article does not make specific limitations.

[0158] It is understood that, prior to displaying the dimension selection control on the graphical user interface, the following steps are also included: The system analyzes the content to be adjusted to identify the classification perspectives included in the content.

[0159] Understandably, dimensional prompts can be generated based on the content adjustment event and the content to be adjusted; then, the dimensional prompts are input into the large language model to instruct the large language model to generate all or part of the candidate content expression dimensions of the content to be adjusted, as well as the initial expression difficulty of each candidate content expression dimension, that is, the current difficulty level of the task content under that candidate content expression dimension.

[0160] Specifically, in this embodiment, the content adjustment event may include the user selecting at least one sequence of information of any type, such as an article, title, or image, in the graphical user interface to determine the content to be adjusted, thereby constructing prompt information to guide the large language model.

[0161] Then, the prompt information is input into the large language model to output the candidate dimension content expressions included in the content to be adjusted, as well as the current difficulty level of each candidate dimension content expression.

[0162] Specifically, the terminal can input dimension prompts into a preset large language model (such as the GPT series model) to generate at least one candidate content expression dimension included in the content to be adjusted, as well as the current difficulty level corresponding to each dimension.

[0163] The current difficulty level of each candidate content expression dimension can be obtained based on language model analysis of the corpus of the content to be adjusted, statistics of common error rates, and comparison with exam levels, for example, a level scoring system of 1 to 5.

[0164] After obtaining the expression dimensions and current difficulty level of the candidate content, the system can generate and display the corresponding dimension selection control on the graphical user interface. The dimension selection control can include obtaining at least one candidate content expression dimension, marking the current difficulty level of the candidate content expression dimension in the content to be adjusted, and the difficulty level that the content to be adjusted can be adjusted to under the candidate content expression dimension.

[0165] After receiving a user's selection operation for at least one candidate content expression dimension in the dimension selection control, the selected candidate content expression dimension is taken as the first expression dimension, and the difficulty level of the first expression dimension determined by the user is taken as the first difficulty level, or the system recommendation is directly accepted to determine the first content expression dimension and the first difficulty level.

[0166] Specifically, taking an English sentence selected by the user as an example, one implementation of the solution is illustrated: Content to be adjusted: "Typical of the grassland dwellers of the continent is the American antelope, or pronghorn." After system identification, the candidate content expression dimensions to be adjusted include vocabulary dimension, sentence structure dimension, information density dimension, concept abstraction level dimension, cultural background knowledge dimension, and reading reasoning dimension, as shown in Table 1 below, which lists some adjustable or non-adjustable candidate content expression dimensions and their corresponding levels:

[0167] Table 1 Optionally, if the task involves a paper-based math exam, the user can select a specific objective question from the exam by taking a photo. Title: Let the function be... Then the monotonically increasing interval of the function on the interval [-2, 2] is: A. [-2,-1] B.[-1,1] C.[1,2] D.[-2,0] After receiving the content to be adjusted, the system identifies the adjustable candidate content expression dimensions and their corresponding initial difficulty levels, as shown in Table 2 below:

[0168] Table 2 The core knowledge points tested in this question remain unchanged: the monotonicity of functions, and the determination of the maximum value of a function on an interval (extreme points, endpoints), i.e., using derivatives to find extreme values ​​and comparing function values. If the difficulty is increased to a higher level by selecting a more challenging dimension, and after constraining the pre-trained model, the target content is: Title: Let the function be... Then the monotonically increasing interval of the function on the interval [-2, 2] is: A. (- [,-1] B.[-1,0) C.(1, ) D.[-2, ] The comparison of the questions before and after the adjustment is shown in Table 3 below:

[0169] Table 3 If both the expression structure dimension and the distractor dimension are adjusted to a higher level of difficulty, the target content can be obtained: Problem: Given the function If a function is continuously differentiable on the closed interval [-2, 2], then which of the following descriptions of its monotonicity on this interval is correct? A. In monotonically increasing B. In monotonically decreasing C. In monotonically increasing D. In monotonically increasing The target content is more difficult in terms of expression structure compared to the content to be adjusted. It introduces continuous differentiable terms and more academic language, and adjusts the difficulty in terms of interference items in order to set up confusion intervals and induce memory errors.

[0170] Furthermore, to more clearly illustrate the implementation of this application's solution, we can take a high school physics multiple-choice question as an example. If the system recognizes a physics multiple-choice question that a user has circled or selected on the smart learning device, and the user feels confident in answering the question and wants to increase the difficulty of the question when testing the same knowledge point, it determines that the difficulty should be increased from the perspective of distractors to adjust the content to be adjusted. Question: An object falls freely from a height. Assuming negligible air resistance, which of the following statements about its falling process is correct? A. The object is always subject to gravity and air resistance. B. The object's velocity remains constant. C. The object's acceleration is always constant.

[0171] D. The speed of an object is inversely proportional to time. This question tests two main knowledge points: the fundamental characteristics of free fall motion and the constancy of gravitational acceleration (ignoring air resistance). Based on the above adjustments, the new options for the target content could be: A. The object is only subject to gravity, and its direction is always upward. B. The object's initial velocity is zero, and its acceleration gradually decreases. C. The object's velocity continuously increases, its direction is downward, and its acceleration is constant. D. The object is only subject to gravity, and its acceleration is 0. The answer to this question remains C, but the distractors are more semantically complex, incorporating words such as direction, initial velocity, and gradual, making it easy for users to mistakenly choose A (direction misleading) or B (mistaking velocity for acceleration change) under some subjective factors or other objective factors, thus increasing the test of users' understanding of concepts and their ability to use the elimination method.

[0172] If the difficulty is increased in the dimension of form and structure, the target content can be: Question: In an experiment, an object falls freely from rest. Ignoring air resistance, its motion data is observed and recorded. Which of the following physical descriptions of the experimental process is the most reasonable? A. The object is only subject to gravity, and its acceleration remains constant. B. Gravity and air resistance are in equilibrium, and the speed tends to be constant. C. Velocity increases with time, but acceleration decreases. D. The falling distance is directly proportional to the time, and the speed is constant. The adjusted target content incorporates experimental context and observer information as interference, and requires users to select the most reasonable option from multiple nearly correct statements. This will simultaneously test and examine the user's ability to distinguish test terms, understand language precision, and comprehend the physical essence.

[0173] For example, when teachers need to test students' mastery of a certain knowledge point at different learning stages, they can set questions of varying difficulty for that knowledge point at different learning stages as learning progresses. If the task content is a test question, the teacher uploads a photo of the question and selects at least one question to be adjusted. The system identifies multiple dimensions of the question, such as the problem dimension, formal structure dimension, clarity of the question stem, and variable dimension. If the user increases the difficulty from the formal structure dimension, then: Content to be adjusted: Problem: A car with a mass of 1000 kg travels at a constant speed of 20 m / s on a horizontal road. It brakes immediately in an emergency and comes to a stop within 50 m. Find: (1) The acceleration of the car; (2) The magnitude of the resistance experienced by the car during braking.

[0174] The core knowledge points for this question are the formula for uniformly decelerated linear motion and Newton's second law.

[0175] Target content: Question: An electric car weighing 1200kg is undergoing an emergency braking system test. When the emergency braking system is activated while the car is traveling at a constant speed of 18m / s on a level road, the car decelerates smoothly until it comes to a complete stop, with a braking distance of 40m.

[0176] (1) Find the braking acceleration; (2) Find the frictional force exerted by the ground on the car during this process; (3) If there are 3 additional passengers (70kg each) in the vehicle, please recalculate the friction.

[0177] The adjusted target content has more complex data settings and multivariate models. For example, there is additional information (passenger quality) that needs to be processed, and it also involves the impact of changes in quality on force. Although the core knowledge points remain the same, it places higher demands on students' expression dimensions, modeling ability, and variable analysis ability. It is suitable for learning scenarios that assess students' different abilities at different learning stages.

[0178] Understandably, teachers or systems can set the cognitive level and knowledge integration requirements of questions as needed, quickly generate questions of different difficulties, and accurately match teaching objectives. For example, in the same classroom, personalized questions can be provided for students with different ability levels, which can both cater to students with slower learning progress and challenge students with faster progress. In addition, the solution proposed in this application can also identify which dimensions students have cognitive blind spots in by adjusting their answer performance before and after the adjustment, such as problems in non-knowledge points such as weak sense of time and space or insufficient argumentation ability.

[0179] For example, under history questions, the system can generate questions focusing on different dimensions around the same knowledge point based on students' learning progress: If students have already mastered the knowledge points of "A voyage event" and "overseas relations of dynasty A" or related knowledge points, the system will focus on assessing students' ability to integrate time and space based on their learning progress. This will allow the system to generate target content by combining the above knowledge points from a time-space integration perspective. Question: Please compare and contrast “A voyage event” and “B voyage event” in terms of their purpose, impact, and historical significance.

[0180] If the focus is on examining the user's cognitive level, then target content can be generated: Question: Do you agree that "A voyage incident" had a lasting impact on "the overseas relations of dynasty A"? Please elaborate on your argument with historical facts.

[0181] Understandably, if the goal is simply to assess a user's basic understanding of the above knowledge points, then the target content can be generated as follows: Question: Who were the participants in "A Voyage Incident A"? What did they do? What impact did this have on Dynasty A? To comprehensively assess the above abilities, the target content can be generated as follows: Question: Some believe that the "A Voyage Incident" represented the pinnacle of "Dynasty A's overseas relations," while others see it as a waste of resources. What is your opinion? Please analyze this in conjunction with the relevant background information.

[0182] In summary, the generated target content not only increases the difficulty from the cognitive level dimension, but also adjusts the difficulty to a higher level from the spatiotemporal integration dimension.

[0183] Understandably, through the above methods, the system can personalize and intelligently adapt to dimensions such as cognitive level (memory, analysis, evaluation), spatiotemporal integration (single event, multi-party comparison), and expression mode, which is conducive to generating questions that are more in line with students' current abilities, so as to advance step by step. The expression goal remains unchanged before and after the adjustment, that is, it still revolves around the historical impact of "Event A".

[0184] The adjustable difficulty level of subjective history questions allows for more granular personalized teaching, breaking through the limitations of the traditional one-size-fits-all approach. It enables different questions for different students and different questions for the same student at different stages, while all questions test the same core knowledge, greatly improving teaching efficiency.

[0185] Based on the above core solution, a teaching experiment was conducted in a holiday experimental class (90 students). Using the controlled variable method, two groups (45 students in each group) of students with equal academic levels each answered an equal number of questions. They completed tests based on both existing technology's overall difficulty adjustments and content-adjusted solutions. Multiple indicators, including improved ability recognition accuracy, increased success rate, and reduced frustration rate, were obtained and compared, resulting in the experimental data shown in Table 4 below.

[0186] Table 4 It should be noted that the overall difficulty adjustment plan uses questions that test the same knowledge points but can be used at three difficulty levels: junior high, intermediate, and advanced.

[0187] Pre-test refers to a test conducted on students before teaching intervention or system use to understand their initial mastery of a certain knowledge point; post-test refers to a test conducted on students after teaching intervention or system use to assess their improved mastery of the same knowledge point after training.

[0188] Understandably, in this application, the pre-test refers to all students taking a set of objective or subjective questions on the same knowledge point before they come into contact with the system, in order to understand their original level; the system intervention test refers to two sets of test questions, one using existing questions with only three levels of difficulty (junior, intermediate, and senior) and the other using the technical solution of this application.

[0189] The post-test refers to using another set of equivalent questions to test students' mastery of the same knowledge points. The questions are different from those in the pre-test, but the knowledge points tested are the same, and the formats are more diverse.

[0190] Then, the changes in scores between the pre-test and post-test were compared and analyzed, and the comparative data shown in Table 4 were obtained.

[0191] Understandably, experimental data shows that by flexibly controlling the difficulty of test questions or explanations through dimensions such as vocabulary and structure, students can obtain learning content that aligns with their cognitive development while "keeping the knowledge points unchanged." Finally, targeted reinforcement and training of their weak points can achieve a more effective success rate in understanding compared to traditional static difficulty adjustments.

[0192] Furthermore, after the dimensions and difficulty are broken down in detail, it is possible to more accurately locate which type of expression students have difficulty understanding (such as causal relationship expression, complex structure), which has a significant effect on the accuracy of ability identification in the teaching system.

[0193] Most importantly, compared to the chaotic reasons for errors, users can accurately pinpoint their weaknesses after completing the task, which significantly reduces frustration and increases students' willingness and acceptance to continue trying after making mistakes.

[0194] Under the same knowledge point task conditions, by using the target content generated by this application, compared with the traditional static difficulty division teaching mechanism, it can improve students' post-test accuracy by 14.8%, increase their willingness to try again after failure by 32.7%, and improve the accuracy of identifying students' weak points in learning ability by 23.2%, thus having higher teaching adaptability and cognitive diagnosis efficiency.

[0195] Understandably, in addition to using pre-trained large language models for dimensionality and difficulty recognition, pre-trained constraint optimization of expression generation models is also possible.

[0196] Furthermore, it is understandable that the data before and after the adjustment can also be used to optimize constrained expression generation models or to optimize large language models.

[0197] Specifically, the system will record the user's reading time, pause points, and reading completion rate after the user finishes reading and answering questions. If there are subsequent questions, it will also record the answer status, including whether it is correct, the time taken, and the user's feedback on the before and after adjustments, such as whether it is too easy or too difficult.

[0198] Then, by combining the behavioral data after adjusting the difficulty of a certain first content expression dimension, we can optimize the difficulty judgment boundary of a certain dimension, such as judging the inverted structure as the real difficulty.

[0199] It can also improve the matching degree between the model-generated results and user expectations by using user feedback and behavioral consistency.

[0200] Understandably, the impact of different primary content expression dimensions on user learning outcomes can be quantified by analyzing changes in user reading comprehension and accuracy rates before and after adjustments.

[0201] It is understandable that the dimensional classification, difficulty identification, and generation of target content for adjustment can be achieved through different models or through a single model.

[0202] Generally, when implementing through multiple models, dimensional classification models, difficulty prediction models, content generation models, etc., can be used respectively.

[0203] During training, you can choose to continuously iterate the training of the model using user behavior data before and after adjustments to achieve better accuracy in dimensional classification, difficulty recognition, and content generation.

[0204] Understandably, this application's method of continuously iterating and training the model based on user feedback enables structured identification of multiple content expression dimensions of task content or content to be adjusted, accurately pinpointing the source of content difficulties, which is conducive to differentiated intervention in teaching; and the teaching content remains unchanged, but the teaching path can be kept stable by adjusting the difficulty to meet the needs of individualized instruction.

[0205] Furthermore, by generating content with constrained control dimensions, it addresses the technical problem of weak adaptability of fixed task content in existing technologies, providing a highly adaptable expression method with the same learning objectives and enhancing accessibility.

[0206] In addition, a user behavior-driven closed-loop feedback system is used to dynamically fine-tune the model, making the system more and more accurate with use. It supports personalized learning path optimization and adaptive upgrades of the system recommendation algorithm, achieving personalized teaching goals for different users.

[0207] Understandably, besides identifying the candidate expression dimensions of the content to be adjusted through a large language model, one can also set the candidate expression dimensions and current difficulty level of any one of the content to be adjusted in the given task content through pre-defined rules; or identify the candidate expression dimensions of the content to be adjusted through the following methods: First, perform syntactic analysis, part-of-speech tagging, and dependency syntax tree construction on the content to be adjusted. Then, construct an expression dimension system based on the defined general expression dimension framework. Finally, score the difficulty of each dimension to generate an expression dimension and score list for the content to be adjusted. Then, you can also render a difficulty adjustment control.

[0208] For example, if the content to be adjusted is: Typical of the grassland dwellers of the continent is the Americanantelope, or pronghorn. Then, by inputting this information, the candidate content expression dimensions included in the content to be adjusted and the corresponding scores for each dimension can be obtained based on the rules or the large language model.

[0209] Furthermore, this method can also be used to record and learn the content expression dimensions and target difficulty ranges of user preferences in different scenarios, thereby building user profiles and automatically matching the most suitable expression methods for their ability level and preferences for subsequent content.

[0210] For example, for users who prefer to reduce the difficulty of vocabulary, materials that are more suitable for their vocabulary level can be recommended first, avoiding repeated manual adjustments.

[0211] It can also understand which dimensions users have comprehension difficulties in the same type of task content, such as the same question type, based on user feedback data before and after content adjustment, such as question data and reading results, which facilitates ability diagnosis and targeted teaching.

[0212] For example: If it is found that most users frequently adjust to lower levels in the structural hierarchy dimension, it indicates that the content design may be beyond the scope of the curriculum in this dimension; or if it is not beyond the scope, the problem is that most users' weakness lies in this area, or that users do not understand a sentence not because they do not know the words, but because they do not know the sentence structure, thus tracing back to the root cause of the user's wrong answer.

[0213] Among them, the structural hierarchy dimension refers to the complexity of the nesting of grammatical or semantic structures in a sentence or a text, as well as the organizational hierarchy between these structures. It reflects the depth, complexity, and organizational hierarchy of information cues within the nested sentence structure, and is an important indicator of comprehension difficulty, especially in the following aspects: The clauses are nested in layers; Inserted sentences or non-linear sentence order; Modify chain depth; Long subject / object structures, etc.

[0214] By tracking and analyzing users' adjustment behaviors in terms of expression dimensions and difficulty levels, we can not only accurately adapt to individuals, but also continuously optimize content generation, instructional design, and intelligent control, forming a closed loop of intelligent content evolution centered on dimensions.

[0215] Understandably, the graphical user interface also includes a difficulty adjustment control, responding to a difficulty determination instruction for the dimension selection control, to determine at least one first content expression dimension from candidate content expression dimensions, and a first difficulty level corresponding to the first content expression dimension, including: In response to a selection operation on a candidate content expression dimension, the selected candidate content expression dimension is determined as the first content expression dimension; in response to a trigger operation on a difficulty adjustment control, the first difficulty level of the first content expression dimension is determined based on the triggered difficulty adjustment control.

[0216] Specifically, in response to a selection operation for any candidate content expression dimension, it is designated as the first content expression dimension, and a difficulty adjustment control corresponding to the first content expression dimension is simultaneously displayed on the graphical user interface. Then, in response to a trigger operation on the difficulty adjustment control, a first difficulty level corresponding to the first content expression dimension is determined. The difficulty adjustment control includes a control slide and a slider positioned on the control slide.

[0217] Understandably, the system can render the candidate content expression dimensions and the current difficulty level (initial expression difficulty) corresponding to each candidate content expression dimension as dimension selection controls and difficulty adjustment controls respectively, without limitation here.

[0218] Specifically, in response to a triggering operation on the difficulty adjustment control, based on the triggered difficulty adjustment control, a first difficulty level for the first content expression dimension is determined, including: In response to a sliding operation of a slider on the control track, a first difficulty level of a first content expression dimension is determined based on the position of the slider on the control track, wherein the initial position of the slider on the control track is determined based on the initial expression difficulty of the first content expression dimension.

[0219] For example, such as Figure 2 As shown, Figure 2 The text content within the black box in the graphical user interface is the content to be adjusted. Figure 2 The top area displays difficult-to-adjust controls, namely... Figure 2 The system features a "Beginner" to "Advanced" slider, allowing users to set the difficulty level by sliding along the slider.

[0220] For example, such as Figure 3 As shown, Figure 3 The content window in the graphical user interface shown ( Figure 3 The text above the shaded area (in the image) contains content that needs adjustment. Figure 3 The right side of the content window displays difficulty adjustment controls, namely the control slide on the right side of the window and the slider on the control slide. Figure 3 The slider in the image currently corresponds to the beginner difficulty level.

[0221] For example, such as Figure 4 The content window in the graphical user interface shown ( Figure 4 The text above the shaded area (in the image) contains content that needs adjustment. Figure 4 The right side of the content window displays difficulty adjustment controls, namely the control slide on the right side of the window and the slider on the control slide. Figure 4 The slider's position indicates the desired difficulty level, i.e., the highest difficulty level. Furthermore, Figure 4 The bottom left corner displays a dimension selection control, which includes dimension identifiers for three candidate content expression dimensions: “Sentence Structure Dimension”, “Vocabulary Dimension”, and “Information Density Dimension”.

[0222] in, Figure 4 The "Sentence Structure Dimension" is selected, indicating that... Figure 4 The “sentence structure dimension” is one of the first content expression dimensions.

[0223] It is understood that determining whether the content to be adjusted is adjusted to at least one of the first content expression dimensions corresponding to the first difficulty level may also include: Based on the preset expression dimension mapping relationship, at least one first content expression dimension corresponding to the first difficulty level is determined. The expression dimension mapping relationship is used to indicate the mapping relationship between the difficulty level and the content expression dimension.

[0224] Optionally, determining at least one first content expression dimension corresponding to the content to be adjusted may include: The default content expression dimension is used as the first content expression dimension.

[0225] Optionally, in response to a content triggering operation on task content, while determining at least one instance of content to be adjusted that has been triggered within the task content, the method may further include: Display difficulty adjustment controls on the graphical user interface.

[0226] In this embodiment, a content window can be displayed directly after the user selects the content to be adjusted, and difficulty adjustment controls can be displayed on either side of this content window. For example, as Figure 3 As shown, after the user selects the content to be adjusted, a content window is triggered, and a difficulty adjustment control is set on the right side of the content window. In this way, the user can adjust the content as a whole by triggering the difficulty adjustment control, without having to adjust a specific first content expression dimension.

[0227] Optionally, the step of responding to a content adjustment event for the task content to determine at least one piece of content to be adjusted, and the adjustment intent corresponding to the content to be adjusted, may include: In response to the difficulty adjustment operation for the task content, the entire content of the task content is set as the content to be adjusted; the difficulty level indicated by the difficulty adjustment operation is set as the first difficulty level of the task content.

[0228] For example, such as Figure 2 As shown, if Figure 2 If the difficulty adjustment control is fixed in the top area of ​​the graphical user interface and no content in the task content or all content in the task content is selected, then when the difficulty adjustment control is triggered, all the task content can be used as the content to be adjusted, and the corresponding first difficulty level is determined based on the triggered difficulty adjustment control.

[0229] In some embodiments, the graphical user interface further includes content adjustment prompts, which are used to indicate the difficulty change information from the first difficulty level, the first content expression dimension, and / or the initial expression difficulty to the first difficulty level.

[0230] For example, such as Figure 5 As shown, Figure 5 The content window in the graphical user interface shown ( Figure 5 The text above the shaded area (in the image) contains content that needs adjustment. Figure 5 The right side of the content window displays difficulty adjustment controls, namely the control slide on the right side of the window and the slider on the control slide. Figure 5 The position of the slider in the text indicates the first difficulty level to be adjusted to, i.e., the beginner difficulty level.

[0231] also, Figure 5 The bottom left corner displays the first content expression dimension as "sentence structure dimension".

[0232] also, Figure 5 The bottom left corner also displays information about the difficulty level, from the initial difficulty to the first difficulty level. Figure 5 The reduction in [the value / value].

[0233] Understandably, once the terminal obtains the first content expression dimension and the first difficulty level, it can directly adjust the content to be adjusted based on the first content expression dimension and the first difficulty level to obtain the target content.

[0234] Optionally, based on the first content expression dimension and the first difficulty level, as well as the content to be adjusted, target content that better meets the current user's needs in terms of difficulty level can be obtained, so as to enable the task content, or part of the task content, to meet the current user's personalized needs.

[0235] It should be noted that since the only difference between the target content and the content to be adjusted is the difficulty level, the semantic matching between the target content and the content to be adjusted maintains semantic matching while adjusting the difficulty level, ensuring that the content learned by the user is accurate.

[0236] The semantic matching can be that the target content and the content to be adjusted are semantically identical, or that the semantic similarity between the target content and the content to be adjusted is equal to or equal to a preset similarity threshold, or that the proportion of semantically identical content between the target content and the content to be adjusted in the content to be adjusted and / or the target content is greater than a preset proportion threshold.

[0237] Understandably, by allowing users to specifically adjust the difficulty and type of at least some content within the task, users are encouraged to personalize certain parts of the text to suit their needs, thus enhancing the personalization and flexibility of language learning tools in problem-solving. Furthermore, this significantly improves the user's learning experience and effectiveness, increasing practicality and learning efficiency.

[0238] It should be noted that the difficulty change information between the current difficulty level and the first difficulty level can be either an increase of at least one difficulty level to suit advanced learners or users who need a challenge to master more complex sentence structures and advanced vocabulary, or a decrease of at least one difficulty level to suit beginner learners or users who need to quickly understand the content to help them build a foundation of vocabulary and simple sentence structures. Therefore, the content adjustment method corresponding to the first content expression dimension, as well as the degree of adjustment under this content adjustment method, are different. Users can dynamically adjust the difficulty of the task content at any time according to their own learning needs to achieve personalized learning.

[0239] Furthermore, adjustments to content across different primary content dimensions can be applied to various scenarios. For example, regarding sentence structure, increasing the difficulty level can suit advanced learners, helping them master complex sentence structures, while decreasing the difficulty level can suit beginner learners, helping them understand simple sentence structures. Similarly, regarding vocabulary, increasing the difficulty level can suit learners who need to expand their advanced vocabulary, while decreasing the difficulty level can suit learners who need to consolidate their basic vocabulary. Therefore, different content expression dimensions can better meet users' personalized learning needs.

[0240] Optionally, in order to make more precise adjustments to the content to meet user expectations, the sentence structure, vocabulary, grammar, and information density dimensions can be further broken down.

[0241] Among them, the sentence structure dimension includes, but is not limited to, at least one of the following: sentence structure dimension, sentence length dimension, sentence rhetoric dimension, logical relationship dimension, and emotional relationship dimension.

[0242] Specifically, the adjustment method for the sentence structure dimension corresponding to the first difficulty level is as follows: The statement structure dimension is used to indicate adjustments to the statement structure, such as simplifying the statement structure by reducing the nesting levels of clauses, or complicating the statement structure by changing simple sentences into complex sentences. The statement length dimension is used to indicate adjustments to statement length, such as increasing or decreasing statement length. The rhetorical dimension of a sentence is used to indicate whether to add or remove rhetorical devices, such as the adjustment of rhetorical devices like metaphor, parallelism, and hyperbole; The logical relationship dimension is used to indicate whether to add or remove information from statements such as cause and effect, comparison, and condition. The emotional relationship dimension is used to indicate whether to add or remove emotional statement information, such as adding descriptive language and emotional vocabulary.

[0243] Specifically, the adjustment method for the grammar dimension corresponding to the first difficulty level is as follows: The grammatical dimension is used to indicate adjustments to the grammatical type of a statement, such as changing the passive voice to the active voice.

[0244] For example, the terminal can use language learning tools (such as Stanford NLP, spaCy) to analyze the sentences corresponding to the content to be adjusted, obtain the grammatical structure of the sentences, and then use a large language model (such as the GPT model) to split and reorganize the sentences based on the grammatical structure of the sentences.

[0245] Specifically, the adjustment method for the vocabulary dimension corresponding to the first difficulty level is as follows: adjust the difficulty of the vocabulary. For example, if the meaning is the same, replace the vocabulary with the lower difficulty level with the vocabulary with the higher difficulty level based on the difficulty level of the vocabulary with the same meaning. Alternatively, if the meaning is the same, replace the vocabulary with the higher difficulty level with the vocabulary with the lower difficulty level.

[0246] In addition, in adjusting the vocabulary dimension, the vocabulary replacement strategy can be optimized. For example, the selection can be made by using the user association information of the current user, such as obtaining the current user's historical adjusted vocabulary and determining the vocabulary whose adjustment frequency meets the preset frequency conditions from the content to be adjusted as the vocabulary to be replaced; or, based on the current user's vocabulary mastery of each word in the content to be adjusted, the vocabulary mastery of words below or above the preset threshold can be selected as the vocabulary to be replaced.

[0247] For example, the difficulty level of language words can be classified based on the CEFR (A1-C2) vocabulary level database. The terminal uses word vectors (Word2Vec / FastText) to find language words with similar meanings but different difficulty levels to replace the words to be replaced.

[0248] The information density dimension includes, but is not limited to, at least one of the cultural background dimension and the professional terminology dimension.

[0249] Specifically, the adjustment method for the information density dimension corresponding to the first difficulty level is as follows: Adjusting the amount of information means increasing or decreasing the amount of information. This amount of information can be explanatory information about the vocabulary in the content to be adjusted, such as explanatory information about the cultural background (i.e., inserting relevant background information next to the language vocabulary). This amount of information can also be technical terms and / or annotation information for technical terms in the content to be adjusted (i.e. explaining technical terms with complex or simple expressions), thereby achieving the expression of the semantics corresponding to the content to be adjusted in a simpler or more complex way.

[0250] For example, the terminal can identify the technical terms in the content to be adjusted from the terminology database and generate annotation information for the technical terms using a large language model. The corresponding annotation information can be displayed when the technical terms in the content to be adjusted are triggered by hovering, through the Tooltip method.

[0251] For example, if the first language is set to English, the content to be adjusted is "Typical of the grassland dwellers of the continent is the American antelope, or pronghorn." This content targets the user-inputted learning content: "The American antelope, or pronghorn, is a typical representative of the grassland habitat of this continent." The content to be adjusted uses simple compound sentences and moderately difficult vocabulary (such as "grassland dwellers" and "typical").

[0252] Example 1: Set the first content expression dimensions to be adjusted as sentence structure and vocabulary, and choose to increase both by one level based on their initial expression difficulty.

[0253] If the current difficulty level of the sentence structure dimension is 3 and the current difficulty level of the vocabulary dimension is 4, their corresponding first difficulty levels are 4 and 5, respectively.

[0254] After the system identifies the first difficulty level to be adjusted, it will raise the initial difficulty level by one level in both the sentence structure and vocabulary dimensions. The adjustment method for the sentence structure dimension is to moderately increase the sentence difficulty, such as using complex sentences (including relative clauses) or parenthetical phrases. The corresponding adjustment method for the vocabulary dimension is to moderately increase the difficulty of the vocabulary, such as using slightly more advanced words (e.g., "indigenous" or "exemplifies").

[0255] Therefore, the target content generated for Example 1 is: “The American antelope, also known as the pronghorn, which is indigenous to the grasslands of the continent, exemplifies the typicaldwellers of these regions.” The target content can be translated as "The pronghorn, also known as the American antelope, is a native species of this continental grassland and a representative of the typical inhabitants of these regions." The comparison of the content to be adjusted and the target content in terms of vocabulary before and after the adjustment is shown in Table 5 below:

[0256] Table 5 The changes in sentence structure are shown in Table 6 below:

[0257] Table 6 Among them, the difficulty of the sentence structure can be adjusted from the intermediate level of high school to the advanced level of high school or the introductory level of university.

[0258] In summary, the overall comparison of adjustments made in terms of vocabulary and sentence structure is shown in Table 7 below:

[0259] Table 7 Example 2: If the difficulty level between the initial expression difficulty and the first difficulty level is set to increase by two levels, the corresponding first content expression dimensions are sentence structure and vocabulary. Then, the adjustment method for the sentence structure dimension is to increase the sentence difficulty, such as using more complex sentence structures (such as adding nested clauses, parenthetical phrases, and adjusting the grammar to passive voice). The adjustment method for the vocabulary dimension is to increase the vocabulary difficulty, such as using more advanced vocabulary (such as "myriad of fauna", "quintessential representative") or professional terms.

[0260] For example, the target content generated in Example 2 is "Among the myriad of fauna inhabiting the vast expanses of the continental grasslands, the American antelope, scientifically designated as Antilocapra americana and colloquially referred to as the pronghorn, stands out as a quintessential representative." This target content can be translated as "Among the many animals inhabiting the vast expanses of the continental grasslands, the American antelope, scientifically named Antilocapra americana and colloquially referred to as the pronghorn, stands out as a quintessential representative." Example 3: If the difficulty change information between the initial expression difficulty and the first difficulty level is set to be a reduction of one level in both the sentence structure and vocabulary dimensions, then the adjustment method for the sentence structure dimension is to moderately reduce the sentence difficulty, such as breaking the sentence into simple sentences; the adjustment method for the vocabulary dimension is to moderately reduce the vocabulary difficulty, such as using more common words (e.g., "common animal" or "typical example").

[0261] Therefore, the target content generated for Example 3, "The American antelope, also called the pronghorn, is a common animal in the grasslands of this continent. It is a typical example of the animals that live there," can be translated as "The American antelope, also called the pronghorn, is a common animal in the grasslands of this continent. It is a typical example of the animals that live there."

[0262] Example 4: If the difficulty change information between the initial expression difficulty and the first difficulty level is set to be a reduction of two levels in both the sentence structure and vocabulary dimensions, then the adjustment method for the sentence structure dimension is to reduce the sentence difficulty, such as using the simplest sentence structure (subject-verb structure); the adjustment method for the vocabulary dimension is to reduce the vocabulary difficulty, such as using the most basic vocabulary (e.g., "lives in", "typical animal").

[0263] Therefore, the target content generated in Example 4, "The American antelope lives in the grasslands. It is a typical animal there," can be translated as "The American antelope lives on the grasslands. It is a typical animal there." Example 5, for the first content expression dimension being the sentence structure dimension, there are the following two cases: In the first scenario, increasing sentence complexity, such as using more intricate sentence structures like nested clauses or passive voice, can generate the target content: "The American antelope, which is commonly referred to as the pronghorn and is indigenous to the grasslands of the continent, represents a quintessential example of the fauna inhabiting these regions." This target content can be translated as "The American antelope, commonly referred to as the pronghorn, is an indigenous species to the grasslands of this continent and is a quintessential example of the fauna inhabiting these regions." Among these, relative clauses can be added (which is commonly referred to as the pronghorn); parallel structures can be added (and is indigenous to the grasslands of the continent); more complex sentence structures can be used (represents a quintessential example of…).

[0264] In the second scenario, reducing sentence complexity, such as splitting the original sentence into two simple sentences and removing complex sentence structures (like inversion), can generate the target content "The American antelope is a typical animal in the grasslands. It is also called the pronghorn." This target content can be translated as "The American antelope is a typical animal in the grasslands. It is also called the pronghorn." Example 6, for the first content expression dimension being the vocabulary dimension, there are the following two cases: In the first scenario, increasing the vocabulary difficulty, such as using more advanced words or technical terms, can generate the target content as "Exemplifying the quintessential fauna of the continental grasslands is the American antelope, scientifically designated as Antilocapra americana." This target content can be translated as "The American antelope, scientifically named Antilocapra americana, is a representative of typical continental grassland animals." Among these options, "typical" can be replaced with "quintessential"; technical terms can be added (scientifically designated as Antilocapra americana); and more advanced vocabulary (exemplifying) can be used.

[0265] In the second scenario, reducing vocabulary difficulty, such as using more basic words, could generate the target content "The American antelope is a common animal in the grasslands. It is also known as the pronghorn." This target content can be translated as "The American antelope is a common animal in the grasslands. It is also known as the pronghorn." Among these options, "typical" can be replaced with "common"; "dwellers" can be replaced with "animal"; and more basic vocabulary (known as) can be used.

[0266] Example 7: For the first content expression dimension, which is the sentence structure and grammar dimension, the difficulty can be adjusted by changing the grammatical structure of the sentence (such as tense, voice, clause type, etc.). There are two cases as follows: In the first scenario, by increasing the grammatical complexity, the target content that can be generated is: "The American antelope, which is commonly referred to as the pronghorn and is indigenous to the continent's grasslands, represents a quintessential example of the fauna inhabiting these regions." In the second scenario, by reducing the grammatical complexity, the target content that can be generated is "The American antelope, also called the pronghorn, is a typical animal in the grasslands of thiscontinent". Example 8: For the first content expression dimension being the information density dimension, the difficulty can be adjusted by increasing or decreasing the amount of information in the sentence. There are two possible scenarios: In the first scenario, increasing the information density can generate the target content as: "The American antelope, scientifically known as Antilocapra americana and colloquially called thepronghorn, is a quintessential representative of the grassland fauna native to the North American continent." In the second scenario, reducing the information density allows for the generation of target content such as "The American antelopelives in the grasslands. It is a typical animal there." Example 9: For the first content expression dimension being the cultural background dimension, the difficulty can be adjusted by increasing or decreasing the requirements for cultural background knowledge. There are two possible scenarios: In the first scenario, adding cultural context can generate target content such as "The pronghorn, a species unique to North America and often mistaken for an antelope due to its similar appearance, is a hallmark of the continent's grassland ecosystems." In the second scenario, by lowering the cultural context, the generated target content could be "The American antelope is a common animal in the grasslands of North America." Example 10: For the first content expression dimension, which is the rhetorical dimension, the difficulty can be adjusted by increasing or decreasing the use of rhetorical devices (such as metaphor, parallelism, hyperbole, etc.). There are two possible scenarios: In the first scenario, by increasing the rhetorical complexity of the sentence, the target content that can be generated is "Like a swift shadowracing across the endless plains, the American antelope, or pronghorn, embodies the spirit of the continent's grasslands." In the second scenario, by reducing the rhetorical complexity of the sentences, the target content that can be generated is "The Americanantelope is a typical animal in the grasslands". Example 11: For the first content expression dimension being sentence length, the difficulty can be adjusted by increasing or decreasing sentence length, with the following two scenarios: In the first scenario, increasing the sentence length can generate the target content as: "Among the diverse array of species that inhabit the vast grasslands of the continent, the Americanantelope, known scientifically as Antilocapra americana and colloquially as the pronghorn, stands out as a quintessential representative." In the second scenario, reducing the sentence length can generate the target content as "The American antelope is a typical grassland animal". Example 12: For the first content expression dimension being the logical relationship dimension, the difficulty can be adjusted by increasing or decreasing the logical relationships (such as cause and effect, contrast, condition, etc.) in the sentences. There are two cases as follows: In the first scenario, adding logical relationships can generate the target content as: "While many species inhabit the continent's grasslands, the American antelope, or pronghorn, is particularly notable due to its unique adaptations and ecological significance." In the second scenario, by simplifying the logical relationships, the target content that can be generated is "The American antelope is a typical animal in the grasslands". Example 13: For the first content expression dimension being the terminology dimension, the difficulty can be adjusted by increasing or decreasing the use of terminology, with the following two scenarios: In the first scenario, by increasing the difficulty of technical terminology, the target content that can be generated is: "The Antilocapra americana, commonly referred to as the pronghorn, is a keystone species in the grassland biome of North America." In the second scenario, by reducing the complexity of technical terms, the target content that can be generated is "The Americanantelope is a common animal in the grasslands". Example 14: For the first content expression dimension being the emotional relationship dimension, the difficulty can be adjusted by increasing or decreasing emotional coloring (such as descriptive language, emotional vocabulary, etc.), with the following two scenarios: In the first scenario, by adding emotional depth, the target content could be generated as "Graceful and swift, the American antelope, or pronghorn, roams the vast grasslands of the continent, symbolizing the untamed beauty of these ecosystems." In the second scenario, by reducing the emotional tone, the target content that can be generated is "The American antelope is a typical animal in the grasslands." Example 15: For the first content expression dimension, which includes multiple dimensions, there are two cases: In the first scenario, by increasing the difficulty of the content, the target content that can be generated is: "Among the myriad offauna that thrive in the expansive grasslands of the continent, the Americanantelope, scientifically designated as Antilocapra americana and colloquially known as the pronghorn, stands as a quintessential emblem of the seecosystems, embodying both their ecological richness and evolutionary marvels." This target content can be translated as: "Among the many animals that inhabit the vast grasslands of the continent, the Americanantelope, scientifically named Antilocapra americana and colloquially known as the pronghorn, stands as a quintessential emblem of the seecosystems, embodying both their ecological richness and evolutionary marvels." In the second scenario, by reducing the difficulty of the content, the target content that can be generated is "The American antelope lives in the grasslands. It is a typical animal there." This target content can be translated as "American antelopes live on the grasslands. It is a typical animal there." It is understandable that adjusting the content to be adjusted based on the intention to be adjusted, obtaining at least one target content and displaying it on the graphical user interface, may include: generating prompt information based on the intention to be adjusted and the content to be adjusted; inputting the prompt information into a large language model to generate the target content based on the prompt information and display it on the graphical user interface.

[0267] The prompt information is used to guide the large language model to generate target content related to the prompt information.

[0268] Understandably, the terminal can input the first content expression dimension, the first difficulty level, and the content to be adjusted into the Prompt project, so that the Prompt project can generate structured instructions. These structured instructions can then be input into the large language model as prompts to generate the corresponding target content.

[0269] Specifically, since the intention to be adjusted includes at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension, generating prompt information based on the intention to be adjusted and the content to be adjusted may include: determining the difficulty change information from the initial expression difficulty to the first difficulty level; determining the difficulty adjustment instruction information corresponding to each first content expression dimension based on the first difficulty level and the difficulty change information; and generating prompt information based on the difficulty adjustment instruction information corresponding to each first content expression dimension. For example, the difficulty adjustment instruction information corresponding to each first content expression dimension may be used as part of the prompt information.

[0270] Specifically, a corresponding prompt template can be determined based on the first content expression dimension, difficulty change information, and / or the first difficulty level. This prompt template includes template fields corresponding to each first content expression dimension. Then, the difficulty adjustment instruction information corresponding to each first content expression dimension is filled into the template fields corresponding to each first content expression dimension to generate the corresponding prompt information. The content to be adjusted can be filled into a specific area of ​​the prompt template.

[0271] For example, if the first language is set to English, the learning field is textbook editing, and the vocabulary corresponding to the first difficulty level is determined to be at the CEFR [B1] level based on the difficulty change information, then the prompt information can be represented as follows using structured instructions: You are an English textbook editor. Please adjust the following text to CEFR [B1] level from the perspectives of vocabulary and sentence structure: - Vocabulary: Using the basic 2000 words (A1-B1) - Sentence structure: Average sentence length ≤ 15 words, reduce passive voice. Information density: Technical terms ≤ 3 per 100 words; cultural terms require annotation. original: "The proliferation of renewable energy solutions is exacerbating the obsolescence of traditional power grids."

[0272] Among them, the vocabulary dimension indicates the basic and (A1-B1) difficulty levels of the vocabulary to be used, with 2000 words available; the sentence structure dimension indicates that the length of the sentences to be adjusted should be less than or equal to 15 words, and the passive voice of the sentences should be reduced; the information density dimension indicates that the proportion of professional terms should be less than or equal to 3 per 100 words, and that cultural terms in the content to be adjusted should be annotated.

[0273] Accordingly, based on the prompts in the example, the large language model can perform distribution adjustments, such as first replacing relevant words (e.g., replacing "proliferation" with "growing fast" and "exacerbating" with "making...less useful"), then adjusting the sentences (e.g., adjusting the original text in the example to "Renewable energy (clean energy like solar / wind) is growing fast. This is making old power systems (ways we deliver electricity) less useful."), and finally optimizing the information density (e.g., adding cultural annotations: "clean energy like solar / wind"). Furthermore, during the adjustment and generation of the target content, Temperature=0.3 (low randomness) can be used to ensure rewriting stability. In addition, NLP tools can be used with the large language model to check whether the adjusted text meets the target difficulty level for post-processing verification, ensuring that the generated target content meets the current user's personalized needs.

[0274] In some embodiments, determining the difficulty adjustment indication information corresponding to each first content expression dimension based on the first difficulty level and difficulty change information may include: determining at least one difficulty indicator information corresponding to each first content expression dimension based on the first difficulty level and difficulty change information; and determining the difficulty adjustment indication information corresponding to each first content expression dimension based on the difficulty indicator information corresponding to each first content expression dimension.

[0275] Among them, the difficulty index information is used to indicate the difficulty index that needs to be adjusted in the first content expression dimension. For example, in the vocabulary dimension, the corresponding words are basic, (A1-B1) and 2000 words; in the sentence structure dimension, the corresponding words are less than or equal to 15 words and the passive voice of sentences needs to be reduced; in the information density dimension, the number of professional terms is less than or equal to 3 per 100 words and cultural terms need to be annotated.

[0276] It is understandable that the task content is learning content, and in response to content adjustment events related to the task content, at least one piece of content to be adjusted, and the corresponding intention to adjust the content to be adjusted, including: In response to a content triggering operation on the learning content, at least one content to be adjusted in the learning content is identified; in response to a difficulty adjustment operation on the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted, and a first difficulty level corresponding to the first content expression dimension are identified.

[0277] It is understood that, in response to a content triggering operation on learning content, determining at least one content to be adjusted triggered in the learning content, such as a knowledge point, can be found in the steps of determining at least one content to be adjusted triggered in the task content in response to a content triggering operation on the task content; in response to a difficulty adjustment operation on a knowledge point, determining at least one content expression dimension corresponding to the knowledge point, and a first difficulty level corresponding to the first content expression dimension, can be found in the steps of determining at least one first content expression dimension corresponding to the content to be adjusted, and a first difficulty level corresponding to the first content expression dimension, in response to a difficulty adjustment operation on the content to be adjusted.

[0278] It is understandable that obtaining at least one target content and displaying it on a graphical user interface may include: replacing the content to be adjusted in the task content with the target content in the graphical user interface so as to directly display the target content.

[0279] Understandably, it's possible to display both the content to be adjusted and the target content on the graphical user interface simultaneously, allowing the current user to more intuitively view the content before and after the adjustment, such as... Figure 6 and Figure 7 As shown, Figure 6 The target content is displayed in the content window, and additional content to be adjusted is displayed outside the content window. Figure 7 The bolded words in the text are the content to be adjusted, and the target content is displayed in the floating window below the bolded words.

[0280] Accordingly, after obtaining at least one target content and displaying it on the graphical user interface, the method further includes: in response to a confirmation event for any target content, replacing the content to be adjusted with the target content in the graphical user interface.

[0281] The confirmation event is used to indicate the event that triggers confirmation of the target content. After the confirmation event is triggered, it means that the current user believes that the target content meets their personalized needs, that is, the content to be adjusted in the task content can be replaced with the target content.

[0282] Specifically, the target content is displayed in the content window of the graphical user interface, which also includes a confirmation control. In response to a confirmation event for any target content, the content to be adjusted is replaced with the target content in the graphical user interface. This can include: in response to a triggering operation of the confirmation control, the content to be adjusted in the task content is replaced with the target content in the graphical user interface.

[0283] Specifically, there are at least two target contents. In response to a confirmation event for any one of the target contents, in the graphical user interface, the content to be adjusted is replaced with the target content. This may include: in response to a selection operation for any one of the target contents, determining the selected target content to enable the user to select the preferred target content; and in the graphical user interface, replacing the content to be adjusted in the task content with the selected target content.

[0284] Specifically, there is one target content. In response to a confirmation event for any target content, the content to be adjusted is replaced with the target content in the graphical user interface. This can include: if no user operation is received from the current user within a preset time period, a confirmation event for the target content is triggered, and the content to be adjusted in the task content is replaced with the target content in the graphical user interface.

[0285] It is understandable that, in the graphical user interface, after replacing the content to be adjusted in the task content with the target content, it may also include: in the graphical user interface, displaying the target content in the task content with a preset display style to indicate that the target content is the adjusted content.

[0286] By displaying the adjusted content differently from the unadjusted content using a preset display style, it becomes more intuitive to see which content has been adjusted, making it easier for users to view and operate.

[0287] Understandably, in response to a confirmation event for the target content, before replacing the content to be adjusted in the task content with the target content in the graphical user interface, the difficulty of the generated target content can still be adjusted, such as... Figure 6 As shown, it can be done through Figure 6 The difficulty adjustment controls in the right area of ​​the content window further adjust the target content displayed in the content window. Specifically, this can include: in response to the difficulty adjustment operation of the target content, determining the new difficulty level to which the target content should be adjusted, and at least one first content expression dimension to be adjusted to the new difficulty level; adjusting the target content based on the first content expression dimension and the new difficulty level to obtain the adjusted target content that conforms to the new difficulty level in the first content expression dimension.

[0288] It is understandable that, in a graphical user interface, after replacing the content to be adjusted with the target content, it may also include: In response to viewing related content of the target content, the system displays the content to be adjusted before the target content is adjusted in the graphical user interface, providing users with a more convenient way to view content.

[0289] The related content viewing operation can be a user's direct touch operation on the target content displayed on the graphical user interface. This touch operation includes, but is not limited to: clicking (e.g., single-click, double-click); pressing (e.g., pressing for a preset duration); and swiping (e.g., swiping in one direction). The related content viewing operation can also be a user's operation of controls on the graphical user interface, or specific operations performed on external input devices associated with the electronic device (in this embodiment, the terminal) to which the graphical user interface belongs. The specific details can be set according to requirements and are not limited here.

[0290] Understandably, in a graphical user interface, after replacing the content to be adjusted with the target content, the following steps are also included: In response to the content restoration operation of the target content, the target content in the task content is restored to the content to be adjusted in the graphical user interface, so as to provide users with a more convenient operation channel for content restoration.

[0291] The content restoration operation can be a direct touch operation performed by the user on the target content displayed on the graphical user interface. This touch operation includes, but is not limited to: clicking (e.g., single-click, double-click); pressing (e.g., pressing for a preset duration); and swiping (e.g., swiping in one direction). The content restoration operation can also be performed by the user through manipulation of controls on the graphical user interface (e.g., a restore control or a difficulty adjustment control), or by performing specific operations on external input devices associated with the electronic device (in this embodiment, a terminal) to which the graphical user interface belongs. The specific details can be set according to requirements and are not limited here.

[0292] In some embodiments, the method may further include: receiving content feedback information from the current user regarding the task content; and updating the current user's learning level based on the content feedback information.

[0293] In this embodiment, the user's learning level is dynamically adjusted based on the user's feedback on the task content. The difficulty of the learning content is then automatically adjusted based on the adjusted learning level to ensure that the user is always at a learning difficulty level that matches their ability and interest. This ensures that the user is always at an appropriate challenge level and avoids encountering learning materials that are too difficult or too easy. This two-way interaction between user feedback and difficulty adjustment enhances the user's learning interest and efficiency.

[0294] The content feedback information can be generated in real time based on the user's current behavior data, or it can be obtained by analyzing the user's accumulated behavior data over a period of time. The specific settings can be configured according to the needs, and there are no restrictions here.

[0295] In some embodiments, the content feedback information includes at least one of the following: the current user's learning status, the user feedback information input by the current user, the current user's content adjustment information for the task content, and the current user's test results for the test content corresponding to the task content.

[0296] The learning status can indicate the current user's learning progress, their mastery of the first language, and the time spent reading the task content. For example, if the user's mastery of a certain vocabulary word in the task content is poor, the terminal can automatically push more application examples or related test content for that word to help the user deepen their memory.

[0297] In this context, user feedback can be displayed on the terminal after the user has finished reading the task content. The user can ask whether they are satisfied with the difficulty level of the task content, or whether they are satisfied with the adjusted content. If the user provides unsatisfactory feedback, an information input window can be provided to encourage the user to enter their dissatisfaction as feedback. This allows the accuracy of subsequent adjustments to the difficulty level to better meet the user's expectations.

[0298] The content adjustment information can be the user's history of adjusting the difficulty of the article content recorded by the terminal. Based on the difficulty level corresponding to at least one content expression dimension in the difficulty adjustment history (such as sentence structure difficulty, vocabulary difficulty), the user's current learning level can be further calibrated. Based on the calibrated learning level, content that matches the user's learning level can be recommended for reading or learning, such as content of the same or higher level. In this way, by monitoring the user's reading behavior of each article content, the user's personalized learning path can be updated in a targeted manner to improve the accuracy of the user's learning level.

[0299] The test results can include the user's accuracy rate and test score in the test content corresponding to the task content.

[0300] For example, if an intermediate learner reads a science article and replaces "proliferation" with "spread" and "exacerbating n" with "making worse," but still performs poorly on tests related to the article, or if the user directly reports that the adjusted content is still too difficult, or if the user continues to adjust the difficulty level of the article, then the difficulty level will be lowered more significantly in the next generated article. Conversely, if an intermediate learner achieves 100% accuracy on a science article multiple times after reading it 10 times, then the difficulty level will be increased.

[0301] In some embodiments, receiving content feedback information from the current user regarding the task content may include: displaying test content for the task content on a graphical user interface in response to a learning completion event for the task content; and receiving the test results of the current user regarding the test content for the task content.

[0302] In this embodiment, the terminal can trigger a learning completion event after the user completes the learning of the task content. By setting up corresponding teaching assistance functions, that is, generating corresponding test content for the task content, the terminal can test the user, help the current user consolidate the content learned in the task content and practical application ability, and understand the current user's mastery of the task content, thereby clarifying the current user's learning level of the first language.

[0303] During the generation of test content, corresponding test questions can be generated based on the current user's adjustment information of the task content, which can serve as at least part of the test content. These test questions include, but are not limited to, vocabulary fill-in-the-blank and sentence rewriting, etc. The specific settings can be configured according to the requirements and are not limited here.

[0304] Specifically, to further help users deepen their memory of the task content, the terminal provides a vocabulary recognition mode under the teaching assistance function. When the learning completion event is triggered, the terminal can pop up a window to prompt users to take a test. Users can click on the window to trigger the test and enter the vocabulary recognition mode. In this mode, the terminal can randomly select some target words from the articles that the user has read in the past period or select them according to preset rules to test the current user, so as to ensure the relevance between the test content and the current learning content and achieve contextualized memory.

[0305] For example, in multiple-choice questions, the terminal may present four options, requiring the current user to select the correct definition of a word. In fill-in-the-blank questions, the terminal may provide an information input area for the user to fill in the correct word based on the context. In matching questions, the terminal may provide a matching method for the user to match the correct definition of a word.

[0306] In one possible implementation, after the current user completes reading the task content, the terminal can collect the user's behavioral data during the reading process and / or the test results of the test content to analyze the user's accuracy rate and / or reading time. Based on the accuracy rate and / or reading time, the terminal can determine the user's learning level in the first language. The terminal can also assess the difficulty level of the task content to generate a new difficulty level. Based on the new difficulty level, the terminal can update the user's personalized learning path to recommend language articles that are more suitable for the user, thereby dynamically adjusting the difficulty of the articles that the user can accept.

[0307] Optionally, the terminal can employ an interval repetition algorithm, which is based on the Ebbinghaus forgetting curve, to intelligently push review tasks, such as test content for at least one language article that the current user has already read, in order to strengthen the current user's long-term memory.

[0308] In some embodiments, the task content is configured with display modes, the display modes including at least a first display mode and a second display mode, the first display mode being used to indicate the display of the task content on a graphical user interface, and the second display mode being used to indicate the display of the task content and auxiliary explanatory information for the task content on a graphical user interface, the method further comprising: in response to a trigger event of a target display mode in the display modes, displaying the task content on the graphical user interface in the target display mode.

[0309] The display mode can indicate the privacy status of the task content when it is displayed on the graphical user interface. Different display modes correspond to different privacy statuses. By providing at least two display modes, users can personalize the display of task content according to their needs.

[0310] The target display mode trigger event is used to indicate the event that triggers the display in the target display mode. After the target display mode trigger event is triggered, the corresponding content can be displayed in the target display mode in the graphical user interface.

[0311] Specifically, the trigger event for the target display mode can be generated by the current user's behavior or by a pre-set trigger mechanism on the terminal. The specific settings can be configured according to the requirements and are not limited here.

[0312] The triggering event for the target display mode can be generated by the user's behavior, including but not limited to: the current user performing a specific operation on the graphical user interface, such as operating the mode switching control provided on the graphical user interface to determine the target display mode from at least two display modes, thereby triggering the triggering event for the target display mode; or the current user performing a specific operation on an external input device associated with the electronic device (in this embodiment, the terminal) to which the graphical user interface belongs, such as a mouse, keyboard, etc., which can be set according to requirements and is not limited here.

[0313] The triggering event for the target display mode can be generated by a pre-set triggering mechanism on the terminal. This can be achieved in ways including but not limited to: the terminal can trigger the target display mode triggering event when user behavior data meets the preset triggering conditions. For example, if no user operation is received from the current user within a preset time period, the target display mode triggering event is triggered.

[0314] Specifically, the display modes can be divided into a hidden mode (first display mode) and a non-hidden mode (second display mode) based on the level of privacy. The hidden mode only displays specific types of information about the task content, such as the content of the task itself. Alternatively, it can further display some content of the task itself in a preset display style (such as highlighting the language vocabulary of the target learning content entered by the user, or highlighting professional terms). The non-hidden mode can display the task content itself, as well as related auxiliary information, such as the translation, part of speech and definition of the accompanying vocabulary, to help users better memorize and understand the words.

[0315] In this embodiment, to meet the needs of different users, the terminal can provide both covert and non-covert modes, allowing users to choose the appropriate learning method based on their learning needs or the terminal to choose the appropriate learning method based on the user's learning situation.

[0316] The hidden mode displays only the original text, with vocabulary highlighted to stimulate the user's thinking and encourage inference of word meanings from context, thus aiding in long-term memorization and practical application. The non-hidden mode provides detailed explanations of new vocabulary, such as part of speech, definition, and example sentences, accelerating comprehension and mastery.

[0317] In some embodiments, the graphical user interface further includes a mode switching control. In response to a trigger event of a target display mode in the display modes, displaying the task content in the target display mode on the graphical user interface may include: when the task content is displayed in a first display mode, in response to a trigger operation of the mode switching control, or when the current user's learning situation does not meet preset learning conditions, switching the second display mode as the target display mode; and displaying the task content in the target display mode on the graphical user interface.

[0318] It should be noted that users can switch modes at any time using the mode switching control to adapt to different learning needs. For example, when learning new vocabulary, the non-hidden mode can be used to aid understanding and memorization; while when consolidating known vocabulary, the hidden mode can be used to enhance memory.

[0319] Furthermore, the terminal can also consider the user's learning progress. For example, if the user makes multiple mistakes on certain words (e.g., the error rate reaches 80% in the vocabulary recognition mode), or if it detects that the user is focusing on the article content for a long time without performing any operations, it may determine that the user's current learning progress does not meet the learning conditions and automatically trigger the logic to switch from hidden mode to non-hidden mode.

[0320] In some embodiments, the content adjustment interaction method is integrated into a language learning system. The operation flow for this language learning system is as follows: First, the current user registers / logs in to the language learning system; second, the language learning system performs a language proficiency test on the current user to obtain the test results, and based on these results, the current user is assigned a level, such as beginner (generating a low-difficulty learning path), intermediate (generating a medium-difficulty learning path), or advanced (generating a high-difficulty learning path); third, the current user can input relevant user-related information through the language learning system, such as selecting a learning goal, to generate personalized articles based on the current user's learning level and user-related information obtained by the language learning system; fourth, the current user... The language learning system allows users to customize the display mode, such as choosing a hidden mode (yes - only highlighted words, no - word definitions displayed). Fifth, the current user can adjust the article difficulty through the system, and the system updates the learning path to provide adjusted content tailored to the user's individual needs. Sixth, after reading the article, the user can take a vocabulary recognition test and receive the results. Based on the test results (whether the test is passed; if yes, the learning level is upgraded; if not, reinforcement exercises are pushed), a learning report is generated. This provides a dynamic and personalized learning platform that helps users improve their vocabulary and enhance their language application skills in real-world contexts.

[0321] As can be seen from the above, by responding to a task triggering event, task content is displayed on a graphical user interface; by responding to a content adjustment event for the task content, at least one piece of content to be adjusted and the corresponding adjustment intent for the content to be adjusted are determined, wherein the content to be adjusted includes at least one piece of sequence information in the task content; the content to be adjusted is adjusted based on the adjustment intent to obtain at least one target content and displayed on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted, thereby supporting the adjustment of content in the task content with a specific adjustment intent to meet the personalized needs of users when reading content, thereby improving the user's learning efficiency for specific content.

[0322] To better implement the above methods, this application also provides a content adjustment interaction device, which can be integrated into an electronic device, such as a computer device, which can be a terminal, server or other device.

[0323] The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers.

[0324] For example, in this embodiment, the method of this application embodiment will be described in detail by taking the content adjustment interaction device specifically integrated into the terminal as an example. This embodiment provides a content adjustment interaction device, such as... Figure 8 As shown, the content adjustment interaction device may include: The content display module 801 is used to display task content on the graphical user interface in response to a task triggering event; The adjustment confirmation module 802 is used to respond to a content adjustment event for the task content to determine at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content; The content display module 803 is used to adjust the content to be adjusted based on the intention to be adjusted, to obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0325] In some embodiments, the content display module 801 is specifically used for: In response to the task triggering event, at least one sequence information uploaded by the user is displayed on the graphical user interface to instruct the large language model to generate task content matching the user's learning level based on at least one sequence information, and the task content is displayed on the graphical user interface.

[0326] In some embodiments, the intention to be adjusted includes at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension, and the adjustment confirmation module 802 is specifically used for: In response to a content triggering operation on the task content, determine at least one piece of content in the task content that has been triggered and needs to be adjusted; In response to the difficulty adjustment operation of the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted and a first difficulty level corresponding to the first content expression dimension are determined, wherein the first content expression dimension is the classification perspective of the content to be adjusted.

[0327] In some embodiments, the adjustment confirmation module 802 is specifically used for: A dimension selection control is displayed on the graphical user interface, wherein the dimension selection control includes at least one candidate content expression dimension generated based on the content to be adjusted; In response to a difficulty determination instruction for the dimension selection control, at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension are determined from the candidate content expression dimensions.

[0328] In some embodiments, the graphical user interface further includes a difficulty adjustment control, and the adjustment confirmation module 802 is specifically used for: In response to the selection operation for the candidate content expression dimension, the selected candidate content expression dimension is determined as the first content expression dimension; In response to a triggering operation on the difficulty adjustment control, a first difficulty level for the first content expression dimension is determined based on the triggered difficulty adjustment control.

[0329] In some embodiments, the difficulty adjustment control includes a control slide and a slider on the control slide, and the adjustment confirmation module 802 is specifically used for: In response to a sliding operation of the slider on the control track, a first difficulty level of the first content expression dimension is determined based on the position of the slider on the control track, wherein the initial position of the slider on the control track is the initial expression difficulty confirmation based on the first content expression dimension.

[0330] In some embodiments, the content adjustment interaction device further includes a dimension generation module, which is specifically used for: Based on the content, adjust the event and the intention to be adjusted to generate dimension prompt information; The dimensional prompts are input into a large language model to generate candidate content expression dimensions based on the content to be adjusted, as well as the initial expression difficulty of each candidate content expression dimension.

[0331] In some embodiments, the content adjustment interaction device further includes a content replacement module, which is specifically used for: In response to a confirmation event for any target content, the content to be adjusted is replaced with the target content in the graphical user interface.

[0332] In some embodiments, the content adjustment interaction device further includes a content restoration module, which is specifically used for: In response to the content restoration operation of the target content, the target content in the task content is restored to the content to be adjusted in the graphical user interface.

[0333] In some embodiments, the content display module 803 is specifically used for: A prompt message is generated based on the intended adjustment and the content to be adjusted. The prompt information is input into the large language model to generate target content based on the prompt information and display it on the graphical user interface.

[0334] In some embodiments, the task content is configured with display modes, the display modes including at least a first display mode and a second display mode. The first display mode is used to indicate that the task content is displayed on the graphical user interface, and the second display mode is used to indicate that the task content and auxiliary explanatory information for the task content are displayed on the graphical user interface. The content adjustment interaction device further includes a mode triggering module, which is specifically used for: In response to a trigger event for the target display mode in the display modes, the task content is displayed on the graphical user interface in the target display mode.

[0335] In some embodiments, the task content is at least one of the following: a language article in a first language, or learning content including at least one knowledge point.

[0336] In some embodiments, the task content is learning content, and the adjustment confirmation module 802 is specifically used for: In response to a content triggering operation on the learning content, at least one piece of content in the learning content that has been triggered and needs to be adjusted is identified; In response to the difficulty adjustment operation of the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted and a first difficulty level corresponding to the first content expression dimension are determined.

[0337] In some embodiments, the first content expression dimension includes at least one of the following: vocabulary dimension, sentence structure dimension, grammar dimension, or information density dimension.

[0338] In some embodiments, the first content expression dimension includes at least one of numerical complexity, distractor dimension, thought-provoking dimension, and question stem scenario dimension; As can be seen from the above, the content adjustment interaction device of this embodiment displays task content on a graphical user interface in response to a task triggering event; in response to a content adjustment event for the task content, it determines at least one piece of content to be adjusted and the adjustment intent corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content; and adjusts the content to be adjusted based on the adjustment intent to obtain at least one target content and displays it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted. This allows the device to support the adjustment of content in the task content with a specific adjustment intent, thereby meeting the personalized needs of users when reading content and improving the learning efficiency of users for specific content.

[0339] Accordingly, this application also provides an electronic device, which can be a terminal, such as a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other terminal device. Figure 9 As shown, Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 900 includes a processor 901 with one or more processing cores, a memory 902 with one or more computer-readable storage media, and a computer program stored on the memory 902 and executable on the processor. The processor 901 and the memory 902 are electrically connected. Those skilled in the art will understand that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0340] The processor 901 is the control center of the electronic device 900. It connects various parts of the electronic device 900 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 902, and calling data stored in the memory 902, it executes various functions of the electronic device 900 and processes data, thereby performing overall monitoring of the electronic device 900.

[0341] In this embodiment, the processor 901 in the electronic device 900 loads the computer program corresponding to the process of one or more application programs into the memory 902 according to the following steps, and the processor 901 runs the application programs stored in the memory 902 to realize various functions: In response to a task trigger event, display the task content on the graphical user interface; In response to a content adjustment event for the task content, at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted are determined, wherein the content to be adjusted includes at least one piece of sequence information in the task content; Adjust the content to be adjusted based on the intended adjustment, and obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0342] Therefore, the electronic device 900 provided in this embodiment can bring the following technical effects: meet the personalized needs of users when reading content, so as to improve the user's learning efficiency of specific content.

[0343] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0344] Optional, such as Figure 9 As shown, the electronic device 900 also includes: a touch display screen 903, a radio frequency circuit 904, an audio circuit 905, an input unit 906, and a power supply 907. The processor 901 is electrically connected to the touch display screen 903, the radio frequency circuit 904, the audio circuit 905, the input unit 906, and the power supply 907. Those skilled in the art will understand that... Figure 9 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0345] The touch display screen 903 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The touch display screen 903 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar technologies. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program according to the operation commands. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 901. It can also receive and execute commands from the processor 901. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 901 to determine the difficulty of the touch event. Subsequently, the processor 901 provides corresponding visual output on the display panel based on the difficulty of the touch event. In this embodiment, the touch panel and the display panel can be integrated into the touch display screen 903 to achieve input and output functions. However, in some embodiments, the touch panel and the touch display screen 903 can be implemented as two independent components to achieve input and output functions. That is, the touch display screen 903 can also be used as part of the input unit 906 to achieve input functions.

[0346] The radio frequency circuit 904 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices, and to transmit and receive signals with network devices or other electronic devices.

[0347] Audio circuitry 905 can be used to provide an audio interface between a user and an electronic device via a speaker and a microphone. Audio circuitry 905 converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuitry 905, converted back into audio data, and then processed by processor 901 before being transmitted via radio frequency circuitry 904 to, for example, another electronic device, or output to memory 902 for further processing. Audio circuitry 905 may also include an earphone jack to facilitate communication between peripheral headphones and electronic devices.

[0348] The input unit 906 can be used to receive input numbers, characters, or user characteristic information (such as fingerprints, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0349] Power supply 907 is used to supply power to various components of electronic device 900. Optionally, power supply 907 can be logically connected to processor 901 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Power supply 907 may also include one or more DC or AC power supplies, charging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0350] although Figure 9 As not shown in the diagram, the electronic device 900 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0351] In the embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0352] Those skilled in the art will understand that all or part of the steps in the various methods of the embodiments can be performed by a computer program, or by a computer program controlling related hardware, and the computer program can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0353] Therefore, embodiments of this application provide a computer-readable storage medium storing multiple computer programs that can be loaded by a processor to execute any of the content adjustment interaction methods provided in embodiments of this application. For example, the computer program can perform the following steps: In response to a task trigger event, display the task content on the graphical user interface; In response to a content adjustment event for the task content, at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted are determined, wherein the content to be adjusted includes at least one piece of sequence information in the task content; Adjust the content to be adjusted based on the intended adjustment, and obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

[0354] As can be seen, the computer program can be loaded by the processor to execute any of the content adjustment and interaction methods provided in the embodiments of this application, thereby bringing about the following technical effects: meeting the user's personalized needs when reading content, so as to improve the user's learning efficiency of specific content.

[0355] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0356] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0357] Since the computer program stored in the computer-readable storage medium can execute any of the content adjustment interaction methods provided in the embodiments of this application, it can achieve the beneficial effects that any of the content adjustment interaction methods provided in the embodiments of this application can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0358] The foregoing has provided a detailed description of a content adjustment interaction method, apparatus, electronic device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A content adjustment interaction method, characterized in that, The method includes: In response to a task trigger event, display the task content on the graphical user interface; In response to a content adjustment event for the task content, at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted are determined, wherein the content to be adjusted includes at least one piece of sequence information in the task content; Adjust the content to be adjusted based on the intended adjustment, and obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

2. The method as described in claim 1, characterized in that, The process of displaying task content on a graphical user interface in response to a task triggering event includes: In response to the task triggering event, at least one sequence information uploaded by the user is displayed on the graphical user interface to instruct the large language model to generate task content matching the user's learning level based on at least one sequence information, and the task content is displayed on the graphical user interface.

3. The method as described in claim 1, characterized in that, The intent to be adjusted includes at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension. The step of determining at least one piece of content to be adjusted, and the intent to be adjusted corresponding to the content to be adjusted, in response to a content adjustment event for the task content, includes: In response to a content triggering operation on the task content, determine at least one piece of content in the task content that has been triggered and needs to be adjusted; In response to the difficulty adjustment operation of the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted and a first difficulty level corresponding to the first content expression dimension are determined, wherein the first content expression dimension is the classification perspective of the content to be adjusted.

4. The method as described in claim 3, characterized in that, The step of responding to the difficulty adjustment operation of the content to be adjusted by determining at least one first content expression dimension corresponding to the content to be adjusted, and a first difficulty level corresponding to the first content expression dimension, includes: A dimension selection control is displayed on the graphical user interface, wherein the dimension selection control includes at least one candidate content expression dimension generated based on the content to be adjusted; In response to a difficulty determination instruction for the dimension selection control, at least one first content expression dimension and a first difficulty level corresponding to the first content expression dimension are determined from the candidate content expression dimensions.

5. The method as described in claim 4, characterized in that, The graphical user interface also includes a difficulty adjustment control. The step of responding to a difficulty determination instruction for the dimension selection control to determine at least one first content expression dimension from the candidate content expression dimensions, and a first difficulty level corresponding to the first content expression dimension, includes: In response to the selection operation for the candidate content expression dimension, the selected candidate content expression dimension is determined as the first content expression dimension; In response to a triggering operation on the difficulty adjustment control, a first difficulty level for the first content expression dimension is determined based on the triggered difficulty adjustment control.

6. The method as described in claim 5, characterized in that, The difficulty adjustment control includes a control slide and a slider on the control slide. The step of determining a first difficulty level for the first content expression dimension based on the triggered difficulty adjustment control, in response to a trigger operation on the difficulty adjustment control, includes: In response to a sliding operation of the slider on the control track, a first difficulty level of the first content expression dimension is determined based on the position of the slider on the control track, wherein the initial position of the slider on the control track is the initial expression difficulty confirmation based on the first content expression dimension.

7. The method as described in claim 4, characterized in that, Before displaying the dimension selection control on the graphical user interface, the method further includes: Based on the content adjustment event and the content to be adjusted, generate dimension prompt information; The dimensional prompts are input into a large language model to generate candidate content expression dimensions for the content to be adjusted, as well as the initial expression difficulty of each candidate content expression dimension.

8. The method as described in claim 1, characterized in that, After obtaining at least one target content and displaying it on the graphical user interface, the process also includes: In response to a confirmation event for any target content, the content to be adjusted is replaced with the target content in the graphical user interface.

9. The method as described in claim 8, characterized in that, In the graphical user interface, after replacing the content to be adjusted with the target content, the following is also included: In response to the content restoration operation of the target content, the target content in the task content is restored to the content to be adjusted in the graphical user interface.

10. The method as described in claim 1, characterized in that, The step of adjusting the content to be adjusted based on the intended adjustment, to obtain at least one target content and display it on the graphical user interface, includes: A prompt message is generated based on the intended adjustment and the content to be adjusted. The prompt information is input into the large language model to generate target content based on the prompt information and display it on the graphical user interface.

11. The method as described in claim 1, characterized in that, The task content is configured with display modes, which include at least a first display mode and a second display mode. The first display mode is used to indicate that the task content is displayed on the graphical user interface, and the second display mode is used to indicate that the task content and auxiliary explanatory information for the task content are displayed on the graphical user interface. The method further includes: In response to a trigger event for the target display mode in the display modes, the task content is displayed on the graphical user interface in the target display mode.

12. The method as described in claim 1, characterized in that, The task content is at least one of the following: a language article in the first language, or learning content including at least one knowledge point.

13. The method as described in claim 1, characterized in that, The task content is learning content, and the response to a content adjustment event for the task content, to determine at least one piece of content to be adjusted, and the corresponding adjustment intention for the content to be adjusted, includes: In response to a content triggering operation on the learning content, at least one piece of content in the learning content that has been triggered and needs to be adjusted is identified; In response to the difficulty adjustment operation of the content to be adjusted, at least one first content expression dimension corresponding to the content to be adjusted and a first difficulty level corresponding to the first content expression dimension are determined.

14. The method as described in claim 3, characterized in that, The first content expression dimension includes at least one of the following: vocabulary dimension, sentence structure dimension, grammar dimension, or information density dimension.

15. The method as described in claim 3, characterized in that, The first content expression dimension includes at least one of the following: numerical complexity, distractor dimension, thought-provoking dimension, and question stem scenario dimension.

16. A content adjustment device, characterized in that, The device includes: The content display module is used to display task content on the graphical user interface in response to task triggering events; An adjustment confirmation module is used to respond to a content adjustment event for the task content to determine at least one piece of content to be adjusted and the adjustment intention corresponding to the content to be adjusted, wherein the content to be adjusted includes at least one piece of sequence information in the task content; The content display module is used to adjust the content to be adjusted based on the intention to be adjusted, to obtain at least one target content and display it on the graphical user interface, wherein the content expression of the target content matches the content expression of the content to be adjusted.

Images