Recitation guidance method, related device and computer program product

Abstract

The application discloses a recitation guiding method, related equipment and a computer program product. The application provides two recitation guiding modes, namely, a whole recitation mode and a hierarchical recitation mode. In the whole recitation mode, a user can be guided to recite the whole text to be recited. In the hierarchical recitation mode, the text to be recited is divided into a plurality of sub-modules, and the user is guided to recite the content of each sub-module in sequence, so that the recitation difficulty is reduced. The application constructs a closed loop of "stuttering detection-condition feedback-mode switching". Instead of simply splicing the two modes together, the application creates an adaptive recitation guiding method for dynamically adjusting the teaching strategy according to the real-time cognitive load of the user (quantified by "stuttering"). The application overcomes the problem that the guiding mode of the traditional scheme is single and cannot adapt to the change of the cognitive load of the user, and improves the recitation efficiency through the intelligent guiding strategy.

Description

Technical Field

[0001] This application relates to the field of intelligent education technology, and more specifically, to a memorization guidance method, related equipment, and computer program products. Background Technology

[0002] In real-world scenarios, users often need to memorize texts, such as students memorizing lessons or speakers memorizing speeches. One method is for users to print out the text and memorize it from the printed document. Another method is for users to display the text on an electronic device and memorize it based on the display.

[0003] Some solutions can guide users in memorizing texts on the terminal, but the guidance mode is singular and cannot dynamically adapt to the different levels of memorization of different users or the same user at different stages, resulting in poor memorization guidance effect. Summary of the Invention

[0004] In view of the above problems, this application is made to provide a memorization guidance method, related equipment, and computer program product to improve the effectiveness of memorization guidance. The specific solution is as follows:

[0005] Firstly, it provides a method for guiding memorization, including:

[0006] The text to be memorized is acquired and the overall memorization mode is entered. In the overall memorization mode, the user's memorization voice is collected in real time.

[0007] If a pause in recitation is detected based on the recitation voice, the pause data is recorded;

[0008] If the memorization stutter data does not meet the set stutter conditions, a prompt message is output based on the current memorization progress. The prompt message is a text unit in the text to be memorized that is located after the current memorization progress.

[0009] If the first condition is met, the user enters the layered memorization mode. In the layered memorization mode, the user is guided to memorize the content of each sub-module in the order of the sub-modules after the text to be memorized is divided. The first condition includes that the memorization stutter data meets the set stutter conditions.

[0010] In one possible design, in another implementation of the first aspect of the embodiments of this application, the process of entering the layered backing mode when the first condition is met includes:

[0011] If the memorization stuttering data meets the set stuttering conditions, the user will be prompted whether to enter the layered memorization mode.

[0012] In response to the user's confirmation of entering the layered backing mode, the layered backing mode is entered.

[0013] In one possible design, another implementation of the first aspect of the embodiments of this application further includes:

[0014] In response to the user's instruction to refuse to enter the layered memorization mode, a prompt message is output based on the current memorization progress.

[0015] In one possible design, in another implementation of the first aspect of the embodiments of this application, the process of outputting prompt information based on the current memorization progress includes:

[0016] In the text to be memorized, determine the smallest text unit located after the current memorization progress, and output the determined smallest text unit as a prompt message;

[0017] or,

[0018] Based on the current memorization progress, locate the current sentence in the text to be memorized. If more than a set proportion of the text in the current memorization sentence are prompts, then all the text in the current memorization sentence that is after the current memorization progress will be output as prompts.

[0019] In one possible design, in another implementation of the first aspect of the embodiments of this application, the process of guiding a user to memorize the content of any one of the sub-modules in the layered memorization mode includes:

[0020] In the layered memorization mode, for a target sub-module to be memorized, the first text is displayed on the screen and the user is guided to memorize it. The first text is the result of partially masking the text of the target sub-module.

[0021] The system collects the user's recitation audio in real time, and outputs prompt information based on the current recitation progress when a recitation pause is detected based on the audio.

[0022] After the target submodule has finished memorizing, the recognized text corresponding to the user's memorized speech is displayed, and the prompt information in the recognized text is marked as a first mark, and the incorrectly memorized text in the recognized text is marked as a second mark.

[0023] In one possible design, another implementation of the first aspect of the embodiments of this application further includes:

[0024] In the layered memorization mode, in response to the user's instruction to enter the explanation interface of the target sub-module, the explanation content corresponding to the target sub-module is displayed, and the target sub-module is any one of the sub-modules after the text to be memorized is divided.

[0025] In one possible design, in another implementation of the first aspect of the embodiments of this application, the explanatory content corresponding to the target submodule includes at least one of the following:

[0026] The sub-modules include explanations of their core meanings, keyword hints, contextual association guidance, and mnemonic devices.

[0027] In one possible design, in another implementation of the first aspect of the embodiments of this application, the process of dividing the text to be memorized into sub-modules includes:

[0028] The text to be memorized is segmented into sentences to obtain multiple sentence units;

[0029] Syntactic analysis is performed on the multiple sentence units to obtain the logical relationships between adjacent sentence units;

[0030] Based on the logical relationship between the adjacent sentence units, the multiple sentence units are divided into event layers to obtain more than one event unit. Each event unit is a sub-module after division, and each event unit includes more than one consecutive sentence unit.

[0031] In a second aspect, an electronic device is provided, comprising: a memory and a processor;

[0032] The memory is used to store programs;

[0033] The processor is configured to execute the program to implement the various steps of the memorization guidance method described in any of the first aspects of this application.

[0034] Thirdly, a readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the memorization guidance method described in any of the first aspects of this application.

[0035] Fourthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the various steps of the memorization guidance method described in any of the first aspects of this application.

[0036] Using the above technical solutions, this application provides two memorization guidance modes: a holistic memorization mode and a layered memorization mode. In the holistic memorization mode, users are guided to memorize the entire text. In the layered memorization mode, the text is divided into several sub-modules, and users are guided to memorize each sub-module sequentially, reducing the difficulty of memorization. Simultaneously, this application also provides a trigger condition for switching from the holistic memorization mode to the layered memorization mode. This is based on real-time memorization stuttering data obtained from the user's recitation. The switch is triggered when a first condition is met (the first condition includes the memorization stuttering data meeting a set stuttering condition). This application constructs a closed loop of "stuttering detection - conditional feedback - mode switching," rather than simply piecing together two modes. It creates an adaptive memorization guidance method that dynamically adjusts the teaching strategy based on the user's real-time cognitive load (quantified through "stuttering"). This overcomes the problems of traditional methods being monotonous and unable to adapt to changes in the user's cognitive load, improving memorization efficiency through intelligent guidance strategies. Attached Figure Description

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0038] Figure 1 A schematic diagram of an implementation system architecture for the memorization guidance method provided in this application embodiment;

[0039] Figure 2 This is a schematic flowchart of a memorization guidance method provided in an embodiment of this application;

[0040] Figure 3 An interactive schematic diagram of selecting and reciting texts is provided as an embodiment of this application;

[0041] Figure 4 An interactive diagram illustrating a stuttering output prompt and confirmation of whether to enter the layered memorization mode in the overall memorization mode, provided as an embodiment of this application;

[0042] Figure 5 This application provides an example of an interaction diagram in a layered backing mode.

[0043] Figure 6 An interactive diagram illustrating the process of entering a sub-module explanation interface in a layered, back-guided mode, as provided in an embodiment of this application.

[0044] Figure 7 This is a schematic diagram of another memorization guidance method provided in an embodiment of this application;

[0045] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0046] 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.

[0047] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0048] Most applications related to memorizing texts use the following methods:

[0049] Users select a text or paragraph to memorize and then recite it. The system collects the user's recitation audio and provides feedback after the recitation is completed, such as a recitation score based on word matching.

[0050] Existing solutions offer a limited range of memorization modes and cannot adapt to the dynamic changes in a user's state during the learning process. For example, a user may start off confidently but then find that they have forgotten one or even several paragraphs during the memorization process, leading to low memorization efficiency.

[0051] This application provides a memorization guidance method that can be applied to various scenarios where users need to memorize, such as students memorizing texts or speakers memorizing speeches.

[0052] This application provides a method for guiding memorization, which can be applied to, for example... Figure 1 The system architecture shown may include a terminal 100 and a server 200. The server 200 may include one or more servers (…). Figure 1 (This example uses a server as an illustration).

[0053] Either terminal 100 or server 200 can be used independently to execute the memorization guidance method provided in the embodiments of this application. Alternatively, terminal 100 and server 200 can also be used collaboratively to execute the memorization guidance method provided in the embodiments of this application.

[0054] The following description Figure 1 The product form of the mid-terminal 100;

[0055] The terminal 100 in this application embodiment can be a mobile phone, tablet computer, learning machine, teaching large screen, wearable device, conference terminal, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc., and this application embodiment does not impose any restrictions on it.

[0056] This application provides a method for guiding memorization, exemplified by applying the method to a computer device. Specifically, the computer device may be... Figure 1 The system consists of terminal 100 or a combination of terminal 100 and server 200. (Refer to...) Figure 2 The specific steps of this memorization guidance method are as follows:

[0057] Step S100: Obtain the text to be memorized and enter the overall memorization mode. In the overall memorization mode, collect the user's memorization voice in real time.

[0058] Specifically, users can upload the text they want to memorize, or select the text from the text library. After obtaining the text, they enter the overall memorization mode. In this mode, users recite the selected text completely, and the system captures their recitation in real time using a microphone on the electronic device.

[0059] Combination Figure 3 As shown, users can select the text they want to memorize on the memorization content selection interface, such as the text "Sima Guang," and enter the overall memorization mode after clicking "Start Memorization." In the overall memorization mode, the user's real-time memorization voice is captured.

[0060] In one optional implementation, the real-time collected recitation audio can be transcribed using speech recognition, and the transcribed text can be displayed on the screen in real time so that users can understand the content they have memorized.

[0061] Step S110: If a recitation pause is detected based on the recitation voice, record the recitation pause data.

[0062] Specifically, this application can detect pauses based on collected user recitation audio and record pause data based on the detection results. The pause data may include: the number of pauses, the duration of each pause, the location of each pause, and the frequency of each pause.

[0063] In some possible implementations, pauses during recitation can be detected based on pre-configured pause rules. Examples of pause rules include: detecting pauses exceeding a set duration (no voice input), repeated words (the same word is repeated more than n times, where n is a set value such as 3 times), and meaningless filler words (examples such as "uh," "um," etc.).

[0064] In some other possible implementations, the transcribed text corresponding to the memorized speech and the memorized speech can be fed into a multimodal large model, which can then determine whether a stutter occurs and obtain the stutter detection result output by the large model.

[0065] In some other possible implementations, the physiological data of the user during the memorization process can be compared with pre-configured reference physiological data when the user experiences pauses in memorization, thereby determining whether a pause has occurred. Examples of physiological data include eye-tracking data and body movement data.

[0066] Step S120: If the memorization stuttering data does not meet the set stuttering conditions, output prompt information based on the current memorization progress. The prompt information is a text unit in the text to be memorized that is located after the current memorization progress.

[0067] When users experience pauses or stumbles during memorization, it indicates insufficient familiarity with the current text and a high cognitive load. This application quantifies the user's cognitive load by analyzing these pauses and stumble conditions. When these conditions are met, it signifies an excessively high cognitive load. Continuing with the overall memorization mode at this point would place undue pressure on the user and hinder memorization efficiency. Therefore, a tiered, guided memorization mode can be switched to.

[0068] The stuttering condition refers to the criteria used to measure whether the user's cognitive load exceeds the limit by measuring stuttering data during memorization. In this embodiment, when the memorization stuttering data does not meet the set stuttering condition, the user's cognitive load has not yet exceeded the limit. At this time, the overall memorization mode can be maintained, and prompts can be output to the user based on the current memorization progress to guide the user to continue memorizing.

[0069] In some possible implementations, there can be multiple stuttering conditions, including but not limited to:

[0070] The number of stutters exceeds the threshold, such as 3 times;

[0071] The stuttering frequency exceeded the set frequency, with 5 stutters occurring within 10 seconds.

[0072] For ease of explanation, the following examples will use more than 3 instances of lag as the condition for lag.

[0073] Reference Figure 3As shown, the user has already memorized the following audio: "A group of children played in the courtyard, one child climbed onto the jar, another child climbed onto the jar, um, hmm." By analyzing the memorized audio, word repetition and meaningless filler words were found, indicating a pause in memorization. Since this is the first time a pause has occurred, meaning the memorization data does not meet the criteria for a pause, the system can output a prompt message: "Foot," guiding the user to continue memorizing.

[0074] In some possible implementations, the prompt can be the smallest text unit in the text to be memorized, such as a single word or phrase. Therefore, the process of outputting prompts based on the current memorization progress can include:

[0075] Identify the smallest text unit in the text to be memorized that is following the current memorization progress, and output the identified smallest text unit as a prompt message.

[0076] By using a single character or word as the smallest text unit, and only prompting one smallest text unit at a time, the user can be guided to memorize to the greatest extent, avoiding the disruption of the user's memorization rhythm by prompting too much information at once.

[0077] In some other possible implementations, the process of outputting prompts based on the current memorization progress may include:

[0078] Based on the current memorization progress, locate the current sentence in the text to be memorized. If the text in the current memorization sentence exceeds a set proportion (e.g., 60%), it will be a prompt message. That is, the content in the current memorization sentence that exceeds the set proportion will be prompted by the system. This indicates that the user's memory of the current memorization sentence is too low, or even that the user does not remember the current memorization sentence at all. In this case, in order to improve memorization efficiency, all the text in the current memorization sentence that is after the current memorization progress can be output as prompt messages all at once.

[0079] Step S130: If the first condition is met, enter the layered memorization mode. In the layered memorization mode, the user is guided to memorize the content of each sub-module in the order of the sub-modules after the text to be memorized is divided. The first condition includes that the memorization stutter data meets the set stutter conditions.

[0080] This application sets a trigger condition for switching from the overall memorization mode to the layered memorization mode, namely the first condition. This first condition may include at least the following: the memorization pause data meets the set pause condition.

[0081] In some other possible implementations, the first condition may also include receiving user confirmation to enter the layered backrest mode. Specifically:

[0082] If the memorization stuttering data meets the set stuttering conditions, prompt the user whether to enter the layered memorization mode.

[0083] In response to the user's confirmation to enter the layered backing mode, enter the layered backing mode.

[0084] In this embodiment, when the memorization pause data determines that the pause conditions are met (e.g., the number of pauses exceeds a threshold), it indicates that the user's familiarity with the current text to be memorized is not high, and the user's current cognitive load is too high, making it unsuitable for memorization in the full-text memorization mode. At this time, the system can prompt the user through pop-ups, voice prompts, etc., whether to enter the layered memorization mode. After receiving confirmation from the user to enter the layered memorization mode, the system can switch to the layered memorization mode.

[0085] Conversely, if the user refuses to enter the layered memorization mode, the overall memorization mode can be maintained, and prompts can be output based on the current memorization progress, thus continuing to provide prompts when the user gets stuck.

[0086] In an optional example, the system's voice interaction script with the user is as follows: Figure 4 As shown, the user experienced three pauses in the overall memorization mode, and the system provided three notifications. When the user paused for the fourth time, the system detected that the number of pauses exceeded the threshold (3 times). At this point, a pop-up window appeared on the interface prompting the user to enable the guided memorization mode. The system could also provide voice prompts, such as, "You seem to be stuck a bit. Would you like to enable guided memorization mode and let me help you memorize the text?"

[0087] If the user selects to enter the layered strapback mode, they can be redirected to the layered strapback mode, such as... Figure 5 As shown.

[0088] In the layered memorization mode, the text to be memorized is divided into sub-modules, and the user is guided to memorize the content of each sub-module in sequence.

[0089] The memorization guidance method provided in this embodiment represents a qualitative leap from a "single mode" to an "adaptive hybrid mode".

[0090] Traditional methods are typically static and single-mode, either requiring full-length memorization or segmented memorization chosen by the user. This embodiment, however, constructs a closed loop of "stuttering detection - conditional feedback - mode switching," rather than simply piecing together two modes. It creates an adaptive memorization guidance method that dynamically adjusts teaching strategies based on the user's real-time cognitive load (quantified by "stuttering"). This can yield the following results:

[0091] 1. Achieve dynamic optimization and adaptation of learning paths.

[0092] Limitations of traditional approaches: Their guidance path is fixed. Users are either always in a macro perspective (overall) or always in a micro perspective (segmented). This approach cannot cope with the dynamic changes in the user's state during the learning process; for example, a user may start with great confidence but become frustrated after encountering difficulties at some point.

[0093] The effect of this application: This application constructs a real-time learning status assessment strategy by collecting and detecting "pauses" in real time, which can achieve:

[0094] Intelligent diagnosis: The judgment that "the memorization lag data meets the set lag conditions" is equivalent to the system automatically diagnosing that "the current memorization mode is invalid and the user is stuck in a learning bottleneck".

[0095] Mode switching: When the first condition is met, the system automatically switches to the tiered teaching mode. This is the optimal teaching strategy adjustment made automatically by the system based on the diagnostic results, simulating the teacher's real-time teaching decision-making process.

[0096] 2. Reduce user cognitive load and improve memorization success rate

[0097] Limitations of traditional solutions: When encountering continuous stuttering in the overall memorization mode, if only prompts (such as displaying the next word) are given, users are prone to anxiety, forming a vicious cycle of "the more stuttering, the more anxious, and the more anxious, the more stuttering," resulting in a poor memorization experience and a low success rate.

[0098] The effect of this application: This application achieves dynamic management of user cognitive load through "mode switching".

[0099] Psychological buffer: Switching from facing the entire text (high load) to focusing on only a sub-module (low load) can effectively reduce users' frustration and anxiety.

[0100] Precise Intervention: Switching to the tiered memorization mode signifies that the system begins guiding users to overcome difficulties. This "breaking down the whole into parts" approach makes it easier for users to experience phased successes, thereby fundamentally solving the problem of memorization interruptions caused by continuous lag and improving the memorization completion rate. This is a user-centric guidance mechanism.

[0101] In summary, this application integrates "holistic memorization" and "tiered memorization" into an organic and dynamic "adaptive memorization guidance system." This application utilizes speech recognition technology to monitor the key status indicator of "stuttering" in real time, and sets an intelligent switching threshold where "stuttering data meets the set stuttering conditions." When the first condition is met, a "tiered memorization guidance" mode from macro to micro is triggered, realizing dynamic adjustment of teaching strategies.

[0102] This method, which dynamically switches memorization modes based on real-time user status feedback, solves the technical problems of traditional solutions, such as the single guidance method and inability to adapt to changes in user cognitive load. It achieves the effects of improving memorization efficiency, optimizing user experience, and providing intelligent guidance paths.

[0103] In some embodiments of this application, the process of guiding a user to memorize the content of any sub-module in the layered memorization mode in step S130 is described. This embodiment provides an optional implementation of the layered memorization mode, including:

[0104] S1. In the layered memorization mode, for a target sub-module to be memorized, the first text is displayed on the screen and the user is guided to memorize it. The first text is the result of partially masking the text of the target sub-module.

[0105] S2. Real-time acquisition of user's recitation voice, and output of prompt information based on the current recitation progress when the recitation voice is detected to be stuck.

[0106] S3. After the target submodule has been memorized, display the recognized text corresponding to the user's memorized speech, and mark the prompts in the recognized text as first, and mark the incorrect memorized text in the recognized text as second.

[0107] Among them, the incorrectly memorized text is the text that is different from the text corresponding to the target submodule.

[0108] Reference Figure 5 As shown, taking the text "Sima Guang" as an example, its full text is as follows:

[0109] A group of children were playing in the courtyard when one child climbed onto a large earthenware jar, slipped, and fell into the water. The others all ran away, but Guang took a stone and smashed the jar, causing the water to gush out and the child to come back to life.

[0110] This application can be pre-divided into 3 sub-modules according to semantic logic, and the content of each sub-module is as follows:

[0111] Submodule 1: "A group of children were playing in the courtyard. One child climbed onto a large earthenware jar, slipped, and fell into the water."

[0112] Submodule 2: "Everyone abandoned it, and Guang took a stone and smashed the jar."

[0113] Submodule 3: "Water bursts forth, and the child is saved."

[0114] In the layered background mode, the first text corresponding to submodule 1 is displayed first. The first text is the result of partially masking the text of submodule 1. Figure 5 As shown, the first and last words of each clause (divided by punctuation marks) in the text of submodule 1 are exposed, while the rest of the content is covered.

[0115] Optionally, in addition to the above masking strategy, other masking strategies can be selected, such as randomly masking part of the content, masking keywords in the text of sub-modules, and masking the text with which the user has difficulty memorizing according to the user's historical memorization records, and so on.

[0116] In the hierarchical memorization mode, the user's memorization speech is collected, and memorization stuttering detection is performed based on the memorization speech. The process of memorization stuttering detection can refer to the relevant introduction above. In the case of detecting memorization stuttering, a prompt message can be output based on the current memorization progress. For example Figure 5 As shown, the user's memorization speech includes: "Qun'er, uh, um", and at this time, it is recognized that there is a memorization stutter. The system prompts the next character "Xi", and the user continues to memorize: "Qun'er xi yu ting, yi'er deng weng, zu die shui zhong".

[0117] During the user's memorization process, the user's memorization speech can be transcribed in real time, and the transcribed text is aligned with the text of the target sub-module being memorized currently, and the masked content of the memorized part in the text of the target sub-module is removed.

[0118] After the memorization of the text of the target sub-module is completed, the memorization result can be displayed. For example Figure 5 In the display interface at the bottom in the figure, the system prompt message is marked first in the current display interface, and the text wrongly memorized by the user is marked second.

[0119] Among them, the first mark and the second mark can be two different mark forms, such as using different colors for marking. Figure 5 In the scenario shown in the figure, since the character "Xi" belongs to the system prompt message, it can be specially marked on the interface with the first mark. Since the user missed memorizing the character "Mei", it can be specially marked on the interface with the second mark.

[0120] In this embodiment, by marking the system prompt message and the text wrongly memorized by the user in different forms, the user's memorization situation can be intuitively prompted, which is convenient for targeted memory enhancement.

[0121] In some embodiments of the present application, another memorization guidance method is further provided. Based on any of the foregoing embodiments, the method of this embodiment may further include the following steps:

[0122] In the hierarchical memorization mode, in response to an instruction for the user to enter the explanation interface of the target sub-module, the corresponding explanation content of the target sub-module is displayed, and the target sub-module is any one of the sub-modules obtained by dividing the text to be memorized. <0000​In some possible implementations, the explanation content corresponding to the target sub-module can be generated immediately upon the user entering the explanation interface of the target sub-module. Alternatively, the explanation content can be generated after obtaining the text to be memorized in step S100, by dividing the text into sub-modules and generating the explanation content for each sub-module. In yet another possible implementation, this application can pre-configure the explanation content for each sub-module corresponding to the text to be memorized, for example, by storing each sub-module corresponding to the text to be memorized, and the explanation content for each sub-module, in a database. When the explanation content of the target sub-module needs to be displayed in the hierarchical memorization mode, it can be retrieved from the database.

[0124] In one alternative implementation, in the layered, guided mode, the display interface can provide controls for entering the explanation interface, such as... Figure 6 The "question mark control" in the interface shown allows users to access the explanation interface corresponding to the target sub-module they are currently memorizing, displaying the explanation content.

[0125] The explanatory content corresponding to the target submodule is used to explain the text of the target submodule, making it easier for users to understand and remember.

[0126] In some embodiments of this application, the explanatory content corresponding to the target sub-module is described.

[0127] The content of the explanation may include at least one of the following:

[0128] The sub-modules include explanations of their core meanings, keyword hints, contextual association guidance, and mnemonic devices.

[0129] in:

[0130] The explanation of the core meaning of a submodule refers to a summary of the main content or central meaning expressed by the corresponding submodule, in order to help users quickly understand the role and significance of the submodule in the overall text before memorization.

[0131] Keyword prompts refer to selecting several representative words or phrases from the sub-modules as memory prompts to help users associate complete content with keywords during the memorization process.

[0132] Contextual association guidance refers to guiding users to establish corresponding contexts or image associations based on the content described in the sub-modules, in order to enhance the depth of understanding and assist in memory formation.

[0133] Mnemonic devices refer to summarizing the core information of a sub-module in a concise, structured, or rhythmic form to reduce the difficulty of memorization and improve the efficiency of recitation.

[0134] The following is an optional example of the explanation content for a submodule:

[0135] Submodule content: "A group of children were playing in the courtyard. One child climbed onto a vat, slipped, and fell into the water."

[0136] The content of the explanation includes:

[0137] Explanation of core meaning:

[0138] This sentence describes the background of the story: a group of children are playing in the yard. One child climbs onto a water vat and accidentally falls into it.

[0139] Keyword suggestions:

[0140] Children, courtyard, playing, climbing the urn, falling, in the water.

[0141] Scenario association guidance:

[0142] Imagine a group of children chasing and playing in a courtyard, the atmosphere relaxed and joyful. One child climbs onto a water vat, suddenly slips, and falls into the vat.

[0143] Mnemonic:

[0144] While playing in the courtyard, a child climbed onto a water vat and suddenly fell into the water.

[0145] The explanations for each sub-module of the text to be memorized can be pre-edited and generated by experts, or they can be automatically generated using natural language models, such as large models.

[0146] In this embodiment, by setting up explanations of the core meaning of sub-modules, keyword prompts, scenario association guidance, mnemonic devices, and other information in the explanation content, users can quickly understand and memorize the content to be memorized, reducing the difficulty of memorization.

[0147] In some embodiments of this application, the process of dividing the text to be memorized into several sub-modules is further described.

[0148] The sub-modules corresponding to the text to be memorized are divided according to semantic logic. Each sub-module, based on independent semantics, expresses a complete event. In some possible implementations, the sub-modules of the text to be memorized can be divided by human experts.

[0149] This application embodiment further provides a scheme for automatic text segmentation, which specifically includes the following steps:

[0150] S1. Segment the text to be memorized into sentences to obtain multiple sentence units.

[0151] Specifically, the text to be memorized can be divided into multiple sentence units based on punctuation marks (such as periods, commas, semicolons, etc.).

[0152] S2. Perform syntactic analysis on multiple sentence units to obtain the logical relationships between adjacent sentence units.

[0153] Logical relationships include, but are not limited to: cause and effect, contrast, parallelism, progression, and condition.

[0154] One alternative syntactic analysis approach is to use a pre-trained discourse relation analysis model (such as BERT) to classify discourse relations, taking adjacent sentence pairs as input and outputting relation categories.

[0155] Another alternative syntactic analysis approach is to perform dependency parsing on each sentence and then combine it with rules to infer the semantic logical relationships between sentences.

[0156] S3. Based on the logical relationship between the adjacent sentence units, perform event layering on the multiple sentence units to obtain one or more event units.

[0157] In this step, based on the logical relationship between sentences, consecutive sentences are merged into higher-level event units. Each event unit includes one or more consecutive sentence units, and each event unit corresponds to a submodule.

[0158] In one alternative implementation, merging rules can be predefined, meaning that if two adjacent sentences have a certain set logical relationship, they are merged into one event unit, ultimately resulting in an event unit that can independently express a complete event.

[0159] The method provided in this embodiment does not simply divide the text to be memorized into segments or fixed lengths, but rather divides the text into independent event units according to semantic logical relationships. Each event unit corresponds to a sub-module. This aligns with the principle that when people understand and memorize texts, they do not mechanically memorize word by word, but rather understand the event structure of the article, form an overall narrative framework based on the logical relationships between events, and then memorize them one by one according to the event units. Therefore, it can improve the user's memory efficiency.

[0160] Reference Figure 7 It provides an example of the implementation process for a memorization guidance method.

[0161] Users first select the text they want to memorize.

[0162] Further confirm whether to memorize the entire text or select specific paragraphs to memorize, obtain the final confirmed text to be memorized, and enter the overall memorization mode.

[0163] In the overall memorization mode, stuttering detection is performed based on the real-time collected user memorization voice. If no stuttering is detected, it is determined whether the text to be memorized has been finished. If not, the overall memorization mode is maintained; if so, a memorization report can be generated.

[0164] If a memorization pause is detected in the overall memorization mode, it is further determined whether the number of pauses (or prompts) does not exceed the set threshold. If it does not exceed the set threshold, a prompt message is output. If it exceeds the set threshold, the user is prompted whether they need to memorize with a guide (i.e., whether they need to enter the layered memorization mode).

[0165] If the user refuses to memorize, a prompt message will be output, and the overall memorization mode will be maintained to continue detecting pauses. When a pause is detected, a prompt message will be output until the memorization is completed and a memorization report is generated.

[0166] If the user selects the guided memorization mode, the system switches to the layered guided memorization mode. In this mode, the system retrieves the sub-modules of the text to be memorized and guides the user to memorize each sub-module in sequence until all sub-modules have been memorized. After memorizing all sub-modules, the system switches back to the overall memorization mode to execute the entire memorization process.

[0167] The method provided in this embodiment is designed to start with the overall memorization mode, using the number of memorization pauses as a quantitative indicator. When the number of pauses exceeds a set threshold, and the user confirms the need for further memorization, the system enters a tiered memorization mode. After the tiered memorization mode ends, the user can return to the overall memorization mode for memory consolidation and effect verification, forming a complete closed loop. This guides the user to reassemble the scattered sub-module content into a complete text, completing the transformation from "short-term memory" to "long-term memory," ensuring that the user not only memorizes each sub-module but also the entire text.

[0168] This application also provides an electronic device in its embodiments. (See reference...) Figure 8 The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as mobile phones, tablets, large-screen teaching displays, learning machines, wearable devices, etc. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0169] like Figure 8As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 2 or a program loaded from a storage device 8 into a random access memory (RAM) 3, to implement the memorization guidance method of the foregoing embodiments of this application. When the electronic device is powered on, the RAM 3 also stores various programs and data required for the operation of the electronic device. The processing unit 1, ROM 2, and RAM 3 are interconnected via a bus 4. An input / output (I / O) interface 5 is also connected to the bus 4.

[0170] Typically, the following devices can be connected to I / O interface 5: input devices 6 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 7 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 8 including, for example, memory cards, hard drives, etc.; and communication devices 9. Communication device 9 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0171] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the memorization guidance methods provided in this application.

[0172] This application also provides a computer-readable storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the memorization guidance methods provided in this application.

[0173] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0174] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0175] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0176] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0177] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

Claims

1. A method for guiding memorization, characterized in that, include: The text to be memorized is acquired and the overall memorization mode is entered. In the overall memorization mode, the user's memorization voice is collected in real time. If a pause in recitation is detected based on the recitation voice, the pause data is recorded; If the memorization stutter data does not meet the set stutter conditions, a prompt message is output based on the current memorization progress. The prompt message is a text unit in the text to be memorized that is located after the current memorization progress. If the first condition is met, the user enters the layered memorization mode. In the layered memorization mode, the user is guided to memorize the content of each sub-module in the order of the sub-modules after the text to be memorized is divided. The first condition includes that the memorization stutter data meets the set stutter conditions.

2. The method according to claim 1, characterized in that, The process of entering the layered backband mode when the first condition is met includes: If the memorization stuttering data meets the set stuttering conditions, the user will be prompted whether to enter the layered memorization mode. In response to the user's confirmation of entering the layered backing mode, the layered backing mode is entered.

3. The method according to claim 2, characterized in that, Also includes: In response to the user's instruction to refuse to enter the layered memorization mode, a prompt message is output based on the current memorization progress.

4. The method according to claim 1, characterized in that, The process of outputting prompts based on the current memorization progress includes: In the text to be memorized, determine the smallest text unit located after the current memorization progress, and output the determined smallest text unit as a prompt message; or, Based on the current memorization progress, locate the current sentence in the text to be memorized. If more than a set proportion of the text in the current memorization sentence are prompts, then all the text in the current memorization sentence that is after the current memorization progress will be output as prompts.

5. The method according to claim 1, characterized in that, In the layered memorization mode, the process of guiding the user to memorize the content of any one of the sub-modules includes: In the layered memorization mode, for a target sub-module to be memorized, the first text is displayed on the screen and the user is guided to memorize it. The first text is the result of partially masking the text of the target sub-module. The system collects the user's recitation audio in real time, and outputs prompt information based on the current recitation progress when a recitation pause is detected based on the audio. After the target submodule has finished memorizing, the recognized text corresponding to the user's memorized speech is displayed, and the prompt information in the recognized text is marked as a first mark, and the incorrectly memorized text in the recognized text is marked as a second mark.

6. The method according to claim 1, characterized in that, Also includes: In the layered memorization mode, in response to the user's instruction to enter the explanation interface of the target sub-module, the explanation content corresponding to the target sub-module is displayed, and the target sub-module is any one of the sub-modules after the text to be memorized is divided.

7. The method according to claim 6, characterized in that, The explanation content corresponding to the target sub-module includes at least one of the following: The sub-modules include explanations of their core meanings, keyword hints, contextual association guidance, and mnemonic devices.

8. The method according to any one of claims 1-7, characterized in that, The process of dividing the text to be memorized into sub-modules includes: The text to be memorized is segmented into sentences to obtain multiple sentence units; Syntactic analysis is performed on the multiple sentence units to obtain the logical relationships between adjacent sentence units; Based on the logical relationship between the adjacent sentence units, the multiple sentence units are divided into event layers to obtain more than one event unit. Each event unit is a sub-module after division, and each event unit includes more than one consecutive sentence unit.

9. An electronic device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the memorization guidance method as described in any one of claims 1 to 8.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the memorization guidance method as described in any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the memorization guidance method as described in any one of claims 1 to 8.

Images