Intelligent learning scene pushing system based on space-time sequence

Abstract

The invention relates to the technical field of online education, in particular to an intelligent learning scene pushing system based on a spatio-temporal sequence, which comprises a spatio-temporal data acquisition module, a spatio-temporal feature analysis module, a learning scene recommendation module, a feedback collection module, a self-adaptive optimization module and a data security protection module, the spatio-temporal data acquisition module is used for acquiring learning time and spatial data of a user in real time, the spatio-temporal feature analysis module extracts a user learning rule based on data analysis, the learning scene recommendation module pushes learning content suitable for a current environment according to an analysis result, and the adaptive optimization module dynamically adjusts a learning strategy according to user feedback. Personalized learning experience is ensured, and the data security protection module guarantees user privacy and data security through encryption and authority management; according to the invention, accurate and efficient learning pushing can be realized under different learning situations, and the method is suitable for the fields of online education, intelligent learning platforms and the like.

Description

Technical Field

[0001] The present invention relates to the field of online education technology, and in particular to an intelligent learning scene push system based on spatiotemporal sequences. Background Art

[0002] With the continuous development of intelligent learning systems, personalized learning has become a hot topic in the field of education. Through intelligent technology, the system can provide highly adaptable learning content based on the user's learning habits, schedule, and environmental conditions, helping users achieve the best learning results in different situations. However, as the complexity of learning scenarios increases, how to dynamically adjust learning content and tasks to ensure that personalized learning scenarios are pushed under different time and space conditions has become an important technical challenge. Existing intelligent learning systems often only make recommendations based on users' historical learning records or simple behavioral feedback, lack a comprehensive analysis of users' real-time learning status and environment, and cannot fully meet personalized learning needs.

[0003] Existing technologies expose multiple technical problems during application. First, traditional learning systems lack effective collection and analysis of temporal and spatial data, and cannot dynamically capture users' learning behaviors in different time periods and spatial environments, thus limiting the precise push of learning scenarios. Second, although some systems can recommend content based on historical learning data, they cannot dynamically adjust the difficulty of learning content, task sorting, and learning time arrangements based on real-time feedback from users, resulting in a rigid learning experience and an inability to effectively improve users' learning outcomes. Summary of the invention

[0004] The present invention provides an intelligent learning scene push system based on spatiotemporal sequences.

[0005] The intelligent learning scenario push system based on spatiotemporal sequence includes a spatiotemporal data acquisition module, a spatiotemporal feature analysis module, a learning scenario recommendation module, a feedback collection module, an adaptive optimization module and a data security protection module, among which;

[0006] The spatiotemporal data acquisition module is used to collect the user's time data and space data in real time. The time data includes the user's learning start time, end time, learning duration and learning period. The space data includes the user's geographical location information, the light intensity and noise level of the environment where the learning device is located, and the connection status of the device;

[0007] The spatiotemporal feature analysis module is used to analyze time data and spatial data, extract the user's learning rules, analyze the user's learning efficiency in different time periods, and the learning performance in different spatial environments. The analysis content includes the user's efficient learning time period in a day, the degree of concentration in a quiet environment, and the changes in attention after long-term learning;

[0008] The learning scenario recommendation module is used to push learning content suitable for the current time and space environment based on the analysis results of the spatiotemporal feature analysis module and in combination with the system's learning resource library. The learning content includes video courses, graphic materials and interactive exercises.

[0009] The feedback collection module is used to collect feedback information generated by users during the learning process in real time, including the completion progress of the user in the learning task, the accuracy of answering questions, the learning time, and the changes in the learning emotional state;

[0010] The adaptive optimization module is used to dynamically adjust the learning scenario push strategy based on the user feedback information provided by the feedback collection module by adjusting the difficulty of the learning content, changing the order of the learning tasks and optimizing the learning time arrangement to improve the user's learning effect;

[0011] The data security protection module is used to securely process the user's time data, space data and learning behavior data using encryption technology, and to limit data access and sharing through a rights management mechanism to ensure the security of the user's privacy data.

[0012] Optionally, the spatiotemporal data acquisition module specifically includes:

[0013] Learning start time collection: Through the application or timer of the user's learning device, the time when the user starts the learning-related application is automatically recorded, and the time is marked as the learning start time;

[0014] Learning end time collection: By detecting that the user actively closes the learning application or does not operate for a period of time (for example, exceeds the set inactivity time), the learning end time is recorded;

[0015] Study time calculation: Automatically calculate the user's single study time based on the difference between the study start time and the end time as a record of study time;

[0016] Study period recognition: automatically marks study activities into specific periods (such as morning, afternoon or evening) based on the specific time of day, and classifies them according to preset time intervals (such as 6:00 to 12:00 in the morning);

[0017] Geographic location information collection: Use the GPS function of the user's learning device to obtain geographic location information in real time and record the user's current location;

[0018] Learning device environment light intensity collection: Use the built-in light sensor of the learning device to monitor and record the light intensity around the learning device in real time to analyze the user's learning situation in different lighting environments;

[0019] Learning device environment noise level collection: Use the learning device's microphone or external noise sensor to collect noise level data in the learning environment in real time;

[0020] Device connection status monitoring: Real-time monitoring of the network connection status of learning devices, including Wi-Fi and mobile data connection strength (such as signal strength in dBm) and stability (such as packet loss rate and latency). If the device loses network connection or the connection is unstable, the duration and frequency of disconnection will be recorded to analyze the impact of the network on the learning process.

[0021] Optionally, the spatiotemporal feature analysis module includes:

[0022] Study time period analysis: Based on the time data provided by the spatiotemporal data acquisition module, the system analyzes the user's study time period in a day, divides the time period, and counts the study time, learning task completion rate and learning efficiency in each time period to generate a time period learning efficiency curve;

[0023] Time regularity analysis: Based on the user's learning habits over a period of time (such as learning records for a week or a month), cluster analysis methods are used to identify whether the user has a fixed learning time period and extract the user's time regularity;

[0024] Correlation analysis between learning efficiency and spatial environment: By performing regression analysis on the light intensity and noise level of the environment where the user's learning device is located, the user's learning efficiency in different spatial environments is calculated;

[0025] Learning environment impact analysis: Compare the learning performance of users in quiet and noisy environments, and extract the differences in learning efficiency of users in different spatial environments;

[0026] Model building: Generate a user learning behavior model based on comprehensive analysis of temporal data and spatial data.

[0027] Optionally, the learning scenario recommendation module includes:

[0028] Content classification and labeling: The system classifies the content in the learning resource library. The learning content includes video courses, graphic materials and interactive exercises. Each learning content is labeled with difficulty level, expected learning time, suitable learning environment (such as quiet environment or noisy environment), and learning objectives (such as knowledge point reinforcement or skill training);

[0029] Matching learning content with time and space conditions: Based on the analysis results provided by the time and space feature analysis module, the system selects learning content that is suitable for the current learning time period and space environment;

[0030] Task push based on user learning behavior model: Based on the user learning behavior model, the system automatically generates a personalized learning task list and dynamically adjusts the push content based on the user's historical learning performance;

[0031] Task priority adjustment: Set priorities for learning tasks based on the user's learning performance in different time periods. For example, more challenging learning tasks are pushed to the user during the time period with the highest learning efficiency, while relatively simple learning tasks are recommended during the time period with lower efficiency.

[0032] Real-time feedback analysis: The system collects users’ learning feedback information (such as task completion rate, correct answer rate, learning time, etc.) in real time through the feedback collection module, and dynamically adjusts the learning task push based on the feedback information;

[0033] Learning content update: Based on feedback information, the system regularly updates the recommendation rules for learning content and optimizes the personalized push algorithm.

[0034] Optionally, the learning scenario recommendation module further includes:

[0035] Learning task display and screening: The system provides users with a learning task selection interface, allowing users to independently select different types of learning content in addition to the learning tasks recommended by the system;

[0036] Task preview and selection: Allow users to preview summary information of learning content in the task selection interface and select appropriate learning tasks based on their personal learning needs, current status and available time;

[0037] Cross-device synchronization of learning tasks: The system supports users to seamlessly switch learning tasks on multiple devices, and supports real-time synchronization of learning progress, task completion status and learning content between devices. For example, a video course started on a smartphone can be continued on a tablet or desktop computer without manual progress adjustment;

[0038] Device adaptation and content adjustment: The system dynamically adjusts the presentation of learning content based on the characteristics of the user's current device (such as screen size, processing power, network connection speed, etc.);

[0039] Real-time learning progress synchronization and notification: When a user completes a learning task or reaches a certain progress on a certain device, the system will provide feedback to the user on the learning progress through notifications or message reminders, and synchronize the task progress when switching devices.

[0040] Optionally, the feedback collection module includes:

[0041] Learning task monitoring: The system monitors the user's progress in each learning task in real time and records the completion percentage of the learning task;

[0042] Answer result analysis: When users complete interactive exercises, the system automatically records the answer results of each question and calculates the user's correct answer rate;

[0043] Study time tracking: The system automatically records the user's study time, including the start and end time of each study task;

[0044] Biometric monitoring: The system collects the user's biometric data in real time, including heart rate, skin conductance and breathing rate, by connecting to smart devices worn by the user (such as smart bracelets, smart watches, etc.) to infer the user's emotional state.

[0045] Optionally, the adaptive optimization module includes:

[0046] Feedback information analysis: The system analyzes user feedback information in real time, including answer accuracy, learning progress, completion time, and user emotional state. Based on the feedback data, the system determines the user's current understanding of the learning content and automatically adjusts the difficulty of the learning content;

[0047] Diversified learning content push: Based on the difficulty adaptation feedback from users, the system recommends different types of learning content to improve users' adaptability to learning content;

[0048] Difficulty change monitoring: The system continuously tracks users' responses to the adjusted learning content and optimizes the difficulty adjustment strategy based on the latest user feedback data.

[0049] Optionally, the adaptive optimization module further includes:

[0050] Task priority calculation: The system sets a priority for each learning task based on user feedback (such as learning progress, accuracy, and learning time);

[0051] Rest time reminder: When the system detects that the user's learning efficiency has decreased (such as a decrease in accuracy or slow progress), the user will be reminded to take a break.

[0052] Optionally, the data security protection module includes:

[0053] Data encryption: The system encrypts the user's time data, space data, and learning behavior data;

[0054] Use of secure transmission protocol: During the data transmission process, the HTTPS protocol is used, combined with SSL / TLS encryption technology to ensure the security of user data when it is transmitted on the network;

[0055] Role permission setting: The system uses the permission management mechanism to set different data access permissions for users with different roles (such as administrators, ordinary users, and third-party applications);

[0056] Data sharing control: When users choose to share data with third-party applications or other users, the system will prompt users to authorize and limit the scope of shared data.

[0057] Beneficial effects of the present invention:

[0058] The present invention uses a spatiotemporal data acquisition module and a spatiotemporal feature analysis module, so that the system can accurately capture the user's time data and spatial data, extract learning rules and analyze the user's learning efficiency in different time periods and spatial environments. Through the learning scenario recommendation module, the system combines the analysis results and the learning resource library to dynamically push personalized learning content suitable for the user's current environment and state, and adjusts the difficulty, task sorting and time arrangement of the learning content according to feedback through the adaptive optimization module. This efficient and accurate learning scenario push significantly improves the user's learning effect and ensures that the user completes the learning task in the most appropriate time period and environment.

[0059] The present invention obtains the user's learning progress, answer accuracy, learning time and emotional state changes in real time through the feedback collection module, and dynamically adjusts the difficulty of the learning content and the order of tasks based on these feedback information through the adaptive optimization module. For example, when the user performs well, the system automatically increases the difficulty of the learning task. When the user is tired or performs poorly, the system reduces the difficulty or adjusts the learning task. The optimized arrangement of learning time ensures that users can study efficiently during the best learning period, and prompts users to take a break in time to avoid overlearning. This dynamic optimization strategy can not only maximize the learning effect, but also enhance the user's learning experience through the planning of personalized learning paths. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0062] Figure 2 Schematic diagram of the spatiotemporal feature analysis module flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0064] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0065] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0066] like Figure 1-Figure 2 As shown, the intelligent learning scenario push system based on spatiotemporal sequence includes a spatiotemporal data acquisition module, a spatiotemporal feature analysis module, a learning scenario recommendation module, a feedback collection module, an adaptive optimization module and a data security protection module, wherein;

[0067] The spatiotemporal data collection module is used to collect the user's time data and space data in real time. The time data includes the user's learning start time, end time, learning duration and learning period. The space data includes the user's geographic location information, the light intensity and noise level of the learning device's environment and the device's connection status.

[0068] The spatiotemporal feature analysis module is used to analyze time data and spatial data, extract users' learning patterns, and analyze users' learning efficiency in different time periods and learning performance in different spatial environments. The analysis content includes the time period of efficient learning in a day, the degree of concentration in a quiet environment, and the changes in attention after long-term learning.

[0069] The learning scenario recommendation module is used to push learning content suitable for the current time and space environment based on the analysis results of the spatiotemporal feature analysis module and the system's learning resource library. The learning content includes video courses, graphic materials and interactive exercises. The learning mode includes personalized learning content pushed by the system and learning tasks manually selected by users.

[0070] The feedback collection module is used to collect feedback information generated by users during the learning process in real time, including the completion progress of the user in the learning task, the accuracy of answering questions, the learning time, and the changes in the learning emotional state;

[0071] The adaptive optimization module is used to dynamically adjust the learning scenario push strategy based on the user feedback information provided by the feedback collection module by adjusting the difficulty of the learning content, changing the order of learning tasks and optimizing the learning time arrangement to improve the user's learning effect;

[0072] The data security protection module is used to securely process the user's time data, spatial data and learning behavior data using encryption technology, and to limit data access and sharing through a permission management mechanism to ensure the security of user privacy data.

[0073] The spatiotemporal data acquisition module specifically includes:

[0074] Learning start time collection: Through the application or timer of the user's learning device, the time when the user starts the learning-related application is automatically recorded, and the time is marked as the learning start time;

[0075] Learning end time collection: By detecting that the user actively closes the learning application or does not operate for a period of time (for example, exceeds the set inactivity time), the learning end time is recorded;

[0076] Study time calculation: Automatically calculate the user's single study time based on the difference between the study start time and the end time as a record of study time;

[0077] Study period recognition: automatically marks study activities into specific periods (such as morning, afternoon or evening) based on the specific time of the day, and classifies them according to preset time intervals (such as 6:00 to 12:00 in the morning) to help analyze the user's study performance in different time periods;

[0078] Geographic location information collection: The user's learning device's GPS function is used to obtain geographic location information in real time and record the user's current location. If the device does not have a GPS function, Wi-Fi hotspots or Bluetooth beacons are used to assist in positioning to ensure the accuracy of the geographic location data.

[0079] Learning device environment light intensity collection: Use the built-in light sensor of the learning device to monitor and record the light intensity around the learning device in real time to analyze the user's learning situation in different lighting environments, and obtain data according to the set sampling frequency (for example, once a minute);

[0080] Learning device environment noise level collection: The noise level data in the learning environment is collected in real time through the learning device's microphone or external noise sensor. The noise level data will be used to analyze the changes in the user's learning efficiency in a noisy environment.

[0081] Device connection status monitoring: Real-time monitoring of the network connection status of learning devices, including Wi-Fi and mobile data connection strength (such as signal strength in dBm) and stability (such as packet loss rate and latency). If the device loses network connection or the connection is unstable, the duration and frequency of disconnection will be recorded to analyze the impact of the network on the learning process.

[0082] The spatiotemporal data acquisition module can provide the system with high-precision real-time data support through precise time and space data collection, environmental information monitoring and device connection status analysis. These data are an important basis for pushing intelligent learning scenarios, ensuring that the system can push the most appropriate content according to the user's actual learning environment and status, thereby improving learning outcomes and personalized experience.

[0083] The spatiotemporal feature analysis module includes:

[0084] Analysis of learning time periods: Based on the time data provided by the spatiotemporal data acquisition module, the system analyzes the user's learning time periods in a day. By dividing the time periods (such as 6:00-12:00 in the morning, 12:00-18:00 in the afternoon, and 18:00-24:00 in the evening), the system calculates the learning time, learning task completion rate, and learning efficiency in each time period, and generates a time period learning efficiency curve. The system determines the time period in which the user has the best learning performance based on historical data and marks it as "efficient learning period";

[0085] Time regularity analysis: Based on the user's learning habits over a period of time (such as learning records for a week or a month), cluster analysis methods are used to identify whether the user has a fixed learning time period and extract the user's time regularity;

[0086] Correlation analysis between learning efficiency and spatial environment: By performing regression analysis on the light intensity and noise level of the environment where the user's learning device is located, the user's learning efficiency in different spatial environments is calculated. The analysis results include learning efficiency curves under different lighting and noise conditions, identifying the user's optimal learning conditions in a specific environment;

[0087] Analysis of the impact of learning environment: Compare the learning performance of users in quiet and noisy environments, extract the differences in learning efficiency of users in different spatial environments, set an environmental noise level threshold (such as 40dB), and those below the threshold are considered quiet environments, and those above the threshold are considered noisy environments;

[0088] Model establishment: Based on the comprehensive analysis of time data and space data, a user learning behavior model is generated. The model takes the user's learning performance (such as the speed of completing tasks and the accuracy of answering questions) as the output variable, and the time period, spatial environment and learning duration as the input variables. The model is expressed as:

[0089] L eff (t,s)=αT eff (t)+βS eff (s)+γH hist (t,s);

[0090] Among them, L eff (t,s) represents the learning efficiency of the user in time t and space s, T eff (t) represents the time efficiency of the user in time t, S eff (s) represents the spatial efficiency of the user in the spatial environment s, H hist (t, s) is the historical learning behavior data of the user at time t and space s, α, β, γ are the weight parameters of the model, which are trained and optimized according to the user's learning data;

[0091] The spatiotemporal feature analysis module generates a user learning behavior model by conducting in-depth analysis of the user's time and space data. It can accurately describe the user's learning efficiency and performance under different time and space conditions. The establishment of this model provides data support for the system's personalized push learning scenarios, helping the system optimize the learning push strategy and improve learning outcomes.

[0092] The recommended learning scenario modules include:

[0093] Content classification and labeling: The system classifies the content in the learning resource library. The learning content includes video courses, graphic materials and interactive exercises. Each learning content is labeled with difficulty level, expected learning time, suitable learning environment (such as quiet environment or noisy environment), and learning objectives (such as knowledge point reinforcement or skill training);

[0094] Matching learning content with spatiotemporal conditions: Based on the analysis results provided by the spatiotemporal feature analysis module, the system selects learning content that is suitable for the current learning time period and spatial environment. In the efficient learning time period, deep learning resources such as long video courses or complex interactive exercises are pushed, and lightweight learning content such as short graphic materials or simple exercises are pushed in the inefficient time period.

[0095] Task push based on user learning behavior model: Combined with the user learning behavior model, the system automatically generates a personalized learning task list and prioritizes the push of moderately difficult learning content during the efficient learning time period. Based on the user's historical learning performance, the system dynamically adjusts the push content to ensure that the content difficulty matches the user's learning level.

[0096] Task priority adjustment: Set priorities for learning tasks based on the user's learning performance in different time periods. For example, more challenging learning tasks are pushed to the user during the time period with the highest learning efficiency, while relatively simple learning tasks are recommended during the time period with lower efficiency.

[0097] Real-time feedback analysis: The system collects users’ learning feedback information (such as task completion rate, correct answer rate, learning time, etc.) in real time through the feedback collection module, and dynamically adjusts the learning task push based on the feedback information. If the user’s performance in a certain type of task is lower than expected, the system will reduce the push frequency of such tasks and adjust the push difficulty;

[0098] Learning content update: Based on feedback information, the system regularly updates the recommendation rules for learning content and optimizes the personalized push algorithm to ensure that the push of learning content is adapted to the user's current learning needs and abilities;

[0099] The learning scenario recommendation module analyzes the user's current time and space conditions and combines the user's learning behavior model to accurately push learning content suitable for the user. The system dynamically adjusts the push strategy based on feedback to match the learning content with the user's learning efficiency, environment and time conditions.

[0100] The learning scenario recommendation module also includes:

[0101] Learning task display and screening: The system provides users with a learning task selection interface, allowing users to independently select different types of learning content in addition to the learning tasks recommended by the system. Each task displays detailed information in the interface, including task type (video, graphic, interactive exercise), expected completion time, difficulty level, recommended learning environment (such as suitable for quiet or noisy environment) and learning goals;

[0102] Task preview and selection: Allow users to preview summary information of learning content in the task selection interface and select appropriate learning tasks based on their personal learning needs, current status and available time. The system dynamically adjusts the recommended content of subsequent learning tasks based on the user's selection to adapt to the user's personalized learning preferences;

[0103] Cross-device synchronization of learning tasks: The system supports users to seamlessly switch learning tasks on multiple devices, and supports real-time synchronization of learning progress, task completion status and learning content between devices. For example, a video course started on a smartphone can be continued on a tablet or desktop computer without manual progress adjustment;

[0104] Device adaptation and content adjustment: The system dynamically adjusts the presentation of learning content based on the characteristics of the user's current device (such as screen size, processing power, network connection speed, etc.). For example, when the network connection is poor, the system will give priority to pushing graphic materials or low-bandwidth video content to ensure the smoothness of the learning process. If the user switches to a large-screen device, the system will optimize the presentation of learning content to enhance the learning experience.

[0105] Real-time learning progress synchronization and notification: When a user completes a learning task or reaches a certain progress on a certain device, the system will provide feedback to the user on the learning progress through notifications or message reminders, and synchronize the task progress when switching devices to ensure the consistency and continuity of learning;

[0106] Regular learning reminders: The system analyzes the user's learning behavior model, identifies the user's best learning time period, and pushes learning reminders during these time periods. For example, the system will send notifications during the user's "efficient learning period" to remind the user to start learning tasks, or provide optimization suggestions for the learning plan;

[0107] The learning scenario recommendation module enhances the flexibility of learning by providing users with the function of independently selecting tasks. At the same time, the multi-device synchronization function ensures that users can switch seamlessly between multiple devices and synchronize learning progress in real time, thereby improving the continuity and convenience of learning.

[0108] The feedback collection module includes:

[0109] Learning task monitoring: The system monitors the user's progress in each learning task in real time and records the completion percentage of the learning task. For example, in video courses, the system tracks the progress of video viewing; in graphic materials, the system monitors the progress of users browsing pages; in interactive exercises, the system records the number of answers and completion of users. Whenever a user completes a part of the learning task, the system automatically updates the learning progress bar and records the completion percentage in the user's learning data;

[0110] Answer result analysis: When the user completes the interactive exercises, the system automatically records the answer results of each question and calculates the user's answer accuracy. The answer accuracy is calculated as:

[0111]

[0112] Among them, A correctIndicates the correct answer rate (percentage), N correct is the number of questions answered correctly by the user, N total The total number of questions answered by the user;

[0113] Generate a user's performance report based on the correct answer rate, show the user the accuracy of the answers in the current task in real time, and provide feedback on whether the specific questions are correct or not, to help users understand their own mastery of the task;

[0114] Learning time tracking: The system automatically records the user's learning time, including the start and end time of each learning task, and divides the user's learning time into segments, distinguishing between effective learning time and pause time (such as exceeding the set period of no operation is considered as a pause in learning). If the user does not operate for a long time, the system will pause the timer and remind the user to continue learning through a notification;

[0115] Biometric monitoring: The system collects biometric data of users in real time, including heart rate, skin conductance and breathing rate, by connecting to smart devices worn by users (such as smart bracelets and smart watches). This data is used to infer the user's emotional state (such as anxiety, fatigue or relaxation). For example, the system determines whether the user is in a state of tension or concentration by the fluctuation amplitude of heart rate and changes in skin conductance.

[0116] The feedback collection module can collect various feedback information of users in learning tasks in real time and accurately, including learning progress, answering performance, learning time and changes in emotional state, to help optimize the learning scenario push strategy and further improve learning efficiency and user experience.

[0117] The adaptive optimization module includes:

[0118] Feedback information analysis: The system analyzes the user's feedback information in real time, including the accuracy of answering questions, learning progress, completion time, and the user's emotional state. Based on the feedback data, the system determines the user's current mastery of the learning content and automatically adjusts the difficulty of the learning content. Based on the user's feedback on learning performance, the system uses the following formula to calculate the difficulty index D of the learning content adjust ;

[0119] D adjust =D current +λ×(P correct -P target );

[0120] Among them, D adjust is the adjusted learning difficulty, D current is the difficulty of the current learning content, λ is the adjustment coefficient, P correct is the correct rate of the user's answer, P target The expected accuracy rate of the answers.

[0121] If the user's correct answer rate is lower than the preset target, the system will automatically reduce the difficulty of the learning content. Otherwise, the difficulty of the learning task will be gradually increased. Through gradual adjustments, the user is ensured to learn at an adaptive difficulty level, avoiding the impact of too high or too low difficulty on the learning effect.

[0122] Diversified learning content push: Based on user feedback on difficulty adaptation, the system recommends different types of learning content to improve user adaptability to learning content. According to different user learning styles, video courses, graphic materials or interactive exercises are pushed to ensure that the content form matches the difficulty.

[0123] Difficulty change monitoring: The system continuously tracks users’ responses to adjusted learning content and optimizes difficulty adjustment strategies based on the latest user feedback data. After each adjustment, the system generates an adjustment effect report to evaluate the impact of difficulty adjustment on learning outcomes.

[0124] The adaptive optimization module analyzes user feedback information in real time and dynamically adjusts the difficulty of learning content to ensure that users can learn at the most suitable learning difficulty, effectively improving learning outcomes.

[0125] The adaptive optimization module also includes:

[0126] Task priority calculation: The system sets a priority for each learning task based on user feedback (such as learning progress, accuracy, and learning time). The priority is calculated as follows:

[0127] P task =α×W performance +β×W difficulty ;

[0128] Among them, P task is the priority of the learning task, α and β are adjustment coefficients, W performance represents the user's learning performance (such as accuracy, progress, etc.), W difficulty is the difficulty weight of the learning task;

[0129] Rearrange learning tasks according to priority, ensuring that high-priority tasks are pushed during the time period when users are most efficient in learning, while low-priority tasks are pushed during less important time periods;

[0130] Rest time reminder: When the system detects that the user's learning efficiency has decreased (such as a decrease in accuracy or slow progress), the user will be reminded to take a break. The rest time period can be adjusted through personalized settings.

[0131] The data security protection module includes:

[0132] Data encryption: The system encrypts the user's time data, space data, and learning behavior data. The data will be encrypted using the AES (Advanced Encryption Standard) algorithm before transmission and storage to ensure that the data will not be illegally accessed or tampered with during transmission;

[0133] Use of secure transmission protocol: During the data transmission process, the HTTPS protocol is used, combined with SSL / TLS encryption technology to ensure the security of user data when it is transmitted on the network;

[0134] Role permission setting: The system uses the permission management mechanism to set different data access permissions for users of different roles (such as administrators, ordinary users, and third-party applications). The permission range includes reading, writing, modifying, and deleting data, ensuring that the user's data is only accessed within a specific permission range;

[0135] Data sharing control: When users choose to share data with third-party applications or other users, the system will prompt the user to authorize and limit the scope of shared data (such as time data, some learning data, etc.). The system limits the access time of shared data through encryption to ensure that shared data cannot be accessed after expiration.

[0136] Regular backup: The system automatically backs up user data regularly to ensure timely recovery in the event of data loss or accidents. The backup data is also protected by encryption algorithms and stored on remote cloud servers to ensure data security.

[0137] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Intelligent learning scene push system based on spatiotemporal sequence, characterized by: It includes spatiotemporal data acquisition module, spatiotemporal feature analysis module, learning scenario recommendation module, feedback collection module, adaptive optimization module and data security protection module, among which; The spatiotemporal data acquisition module is used to collect the user's time data and space data in real time. The time data includes the user's learning start time, end time, learning duration and learning period. The space data includes the user's geographical location information, the light intensity and noise level of the environment where the learning device is located, and the connection status of the device; The spatiotemporal feature analysis module is used to analyze time data and spatial data, extract the user's learning rules, analyze the user's learning efficiency in different time periods, and the learning performance in different spatial environments. The analysis content includes the user's efficient learning time period in a day, the degree of concentration in a quiet environment, and the changes in attention after long-term learning; The learning scenario recommendation module is used to push learning content suitable for the current time and space environment based on the analysis results of the spatiotemporal feature analysis module and in combination with the system's learning resource library. The learning content includes video courses, graphic materials and interactive exercises. The feedback collection module is used to collect feedback information generated by users during the learning process in real time, including the completion progress of the user in the learning task, the accuracy of answering questions, the learning time, and the changes in the learning emotional state; The adaptive optimization module is used to dynamically adjust the learning scenario push strategy based on the user feedback information provided by the feedback collection module by adjusting the difficulty of the learning content, changing the order of the learning tasks and optimizing the learning time arrangement to improve the user's learning effect; The data security protection module is used to use encryption technology to securely process the user's time data, space data and learning behavior data, and to limit data access and sharing through a rights management mechanism.

2. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 1 is characterized in that: The spatiotemporal data acquisition module specifically includes: Learning start time collection: Through the application or timer of the user's learning device, the time when the user starts the learning-related application is automatically recorded, and the time is marked as the learning start time; Learning end time collection: By detecting that the user actively closes the learning application or does not operate for a period of time, the learning end time is recorded; Study time calculation: Automatically calculate the user's single study time based on the difference between the study start time and the end time as a record of study time; Learning period identification: automatically marks learning activities into specific periods based on the specific time of day and classifies them according to preset time intervals; Geographic location information collection: Use the GPS function of the user's learning device to obtain geographic location information in real time and record the user's current location; Learning device environment light intensity collection: Use the built-in light sensor of the learning device to monitor and record the light intensity around the learning device in real time to analyze the user's learning situation in different lighting environments; Learning device environment noise level collection: Use the learning device's microphone or external noise sensor to collect noise level data in the learning environment in real time; Device connection status monitoring: Real-time monitoring of the network connection status of learning devices, including the connection strength and stability of Wi-Fi and mobile data. If the device loses network connection or the connection is unstable, the duration and frequency of disconnection will be recorded to analyze the impact of the network on the learning process.

3. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 2 is characterized in that: The spatiotemporal feature analysis module comprises: Study time period analysis: Based on the time data provided by the spatiotemporal data acquisition module, the system analyzes the user's study time period in a day, divides the time period, and counts the study time, learning task completion rate and learning efficiency in each time period to generate a time period learning efficiency curve; Time regularity analysis: Based on the user's learning habits over a period of time, cluster analysis methods are used to identify whether the user has a fixed learning time period and extract the user's time regularity; Correlation analysis between learning efficiency and spatial environment: By performing regression analysis on the light intensity and noise level of the environment where the user's learning device is located, the user's learning efficiency in different spatial environments is calculated; Learning environment impact analysis: Compare the learning performance of users in quiet and noisy environments, and extract the differences in learning efficiency of users in different spatial environments; Model building: Generate a user learning behavior model based on comprehensive analysis of temporal data and spatial data.

4. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 3 is characterized in that: The learning scenario recommendation module includes: Content classification and labeling: The system classifies the content in the learning resource library. The learning content includes video courses, graphic materials and interactive exercises. Each learning content is labeled with difficulty level, expected learning time, applicable learning environment and learning objectives. Matching learning content with time and space conditions: Based on the analysis results provided by the time and space feature analysis module, the system selects learning content that is suitable for the current learning time period and space environment; Task push based on user learning behavior model: Based on the user learning behavior model, the system automatically generates a personalized learning task list and dynamically adjusts the push content based on the user's historical learning performance; Task priority adjustment: set priorities for learning tasks based on the user's learning performance in different time periods; Real-time feedback analysis: The system collects users’ learning feedback information in real time through the feedback collection module, and dynamically adjusts the learning task push based on the feedback information; Learning content update: Based on feedback information, the system regularly updates the recommendation rules for learning content and optimizes the personalized push algorithm.

5. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 4 is characterized in that: The learning scenario recommendation module also includes: Learning task display and screening: The system provides users with a learning task selection interface, allowing users to independently select different types of learning content in addition to the learning tasks recommended by the system; Task preview and selection: Allow users to preview summary information of learning content in the task selection interface and select learning tasks based on their personal learning needs, current status and available time; Synchronize learning tasks across devices: The system supports users to seamlessly switch learning tasks on multiple devices, and supports real-time synchronization of learning progress, task completion status, and learning content between devices; Device adaptation and content adjustment: The system dynamically adjusts the presentation of learning content based on the characteristics of the user's current device; Real-time learning progress synchronization and notification: When a user completes a learning task or reaches a certain progress on a certain device, the system will provide feedback to the user on the learning progress through notifications or message reminders, and synchronize the task progress when switching devices.

6. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 5 is characterized in that: The feedback collection module comprises: Learning task monitoring: The system monitors the user's progress in each learning task in real time and records the completion percentage of the learning task; Answer result analysis: When users complete interactive exercises, the system automatically records the answer results of each question and calculates the user's correct answer rate; Study time tracking: The system automatically records the user's study time, including the start and end time of each study task; Biometric monitoring: The system collects the user's biometric data in real time, including heart rate, skin conductance, and breathing rate, by connecting to the smart device worn by the user, which is used to infer the user's emotional state.

7. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 6 is characterized in that: The adaptive optimization module comprises: Feedback information analysis: The system analyzes user feedback information in real time, including answer accuracy, learning progress, completion time, and user emotional state. Based on the feedback data, the system determines the user's current understanding of the learning content and automatically adjusts the difficulty of the learning content; Diversified learning content push: Based on the difficulty adaptation situation reported by users, the system recommends different types of learning content to improve users' adaptability to learning content; Difficulty change monitoring: The system continuously tracks users' responses to the adjusted learning content and optimizes the difficulty adjustment strategy based on the latest user feedback data.

8. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 7 is characterized in that: The adaptive optimization module also includes: Task priority calculation: The system sets a priority for each learning task based on user feedback; Rest time reminder: When the system detects that the user's learning efficiency has decreased, the user will be reminded to take a break.

9. The intelligent learning scenario push system based on spatiotemporal sequence according to claim 7 is characterized in that: The data security protection module includes: Data encryption: The system encrypts the user's time data, space data, and learning behavior data; Use of secure transmission protocol: During the data transmission process, the HTTPS protocol is used, combined with SSL / TLS encryption technology to ensure the security of user data when it is transmitted on the network; Role permission setting: The system uses the permission management mechanism to set different data access permissions for users with different roles; Data sharing control: When users choose to share data with third-party applications or other users, the system will prompt users to authorize and limit the scope of shared data.

Images