Page resource loading method and device based on teaching equipment and electronic equipment
By acquiring multi-dimensional interactive behavior data from teaching devices and using machine learning to predict operation probabilities, code blocks are preloaded and executed, solving the loading delay problem of existing devices and achieving smooth interaction on teaching device pages.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU HAILIANG MINGYOU ONLINE EDUCATION TECH CO LTD
- Filing Date
- 2025-12-26
- Publication Date
- 2026-05-01
AI Technical Summary
Existing teaching equipment suffers from performance limitations and insufficient loading efficiency when loading web pages, resulting in interaction delays and affecting the progress of course instruction.
By acquiring multi-dimensional interactive behavior data of users in the target display interface, a lightweight machine learning model is used to predict the probability distribution of operations, preload and execute code blocks in high-probability areas, and render in response to user operation commands.
It improved the response speed of the teaching equipment's page operations, avoided page lag and response delays, and ensured the smoothness of the interface interaction during the course teaching process.
Smart Images
Figure CN121958677A_ABST
Abstract
Description
Methods, devices, and electronic equipment for loading page resources based on teaching equipment Technical Field
[0001] This application relates to the field of educational technology, and in particular to a method, apparatus, and electronic device for loading page resources based on teaching equipment. Background Technology
[0002] In the process of modernizing teaching, the demand for web pages in school settings is increasing. The use of large screens in classroom teaching and the operation of school computers during lesson preparation both require frequent loading of web pages. However, in practice, the existing multimedia equipment in schools is relatively fixed and has low specifications. When loading large web projects, the existing multimedia equipment generally suffers from performance limitations and insufficient loading efficiency, making it difficult to meet the web page loading requirements of modern teaching.
[0003] Currently, the main approach is to break down the complete code package into multiple smaller code blocks during application building. During the interface display process, only the code blocks required for the display interface are loaded, and then the corresponding code blocks are loaded only when the user performs certain operations through the operable controls in the display interface.
[0004] However, this loading method mostly relies on high-performance devices to achieve smooth loading, which is not suitable for the application scenarios of the school's existing low-configuration devices. The loading of page code blocks is a passive resource loading, which depends entirely on the user's explicit active operation. The network request to load resources can only be initiated after the user triggers the operation. The user must wait for the resources to be downloaded and executed, resulting in a perceptible interaction delay, which in turn affects the course teaching progress. Summary of the Invention
[0005] In view of this, this application provides a page resource loading method, apparatus and electronic device based on teaching equipment. The main purpose is to improve the technical problem that the loading of page code blocks in the current technology is a passive resource loading method that relies entirely on the explicit active operation of the user. The network request to load resources can only be initiated after the user triggers the operation, and the user must wait for the resources to be downloaded and executed, resulting in a perceptible interaction delay, which in turn affects the course teaching progress.
[0006] In a first aspect, this application provides a method for loading page resources based on teaching equipment, comprising: acquiring multi-dimensional interactive behavior data of a user in a target display interface; predicting the user's operation behavior in the target display interface based on the multi-dimensional interactive behavior data, and generating operation probability distribution data of the user on multiple areas of the target display interface; determining a target area that meets preprocessing conditions from the multiple areas based on the operation probability distribution data, loading resources and executing at least one code block corresponding to the target area; and rendering the execution result of the at least one code block in response to the user's operation instruction on the target area, so as to respond to the operation instruction.
[0007] Optionally, determining a target region that meets the preprocessing conditions from the plurality of regions based on the operation probability distribution data, and loading and executing at least one code block corresponding to the target region, includes: determining candidate regions that meet the preloading conditions from the plurality of regions based on the operation probability distribution data, loading resources for candidate code blocks corresponding to the candidate regions; and, in response to a target region in the candidate regions meeting the pre-execution conditions, executing at least one code block corresponding to the target region in the candidate code blocks based on the target resources loaded in the target region.
[0008] Optionally, the step of determining candidate regions that meet the preloading conditions from the plurality of regions based on the operation probability distribution data, and loading resources for the plurality of candidate code blocks corresponding to the candidate regions, includes: determining the operation probability data corresponding to the plurality of regions based on the operation probability distribution data; determining the regions in the plurality of regions whose operation probability data is greater than or equal to a first probability threshold as the candidate regions; obtaining the resource configuration file corresponding to the candidate regions; and loading resources for the candidate code blocks corresponding to the candidate regions according to the resource configuration file.
[0009] Optionally, loading resources for multiple candidate code blocks corresponding to the candidate region based on the resource configuration file includes: determining the candidate code block corresponding to the candidate region and the resource identification information corresponding to the candidate code block based on the resource configuration file; verifying the code version of the candidate code block based on the resource identification information, and generating a resource acquisition request corresponding to the candidate region based on the candidate code block if the verification passes; sending the resource acquisition request to the server, wherein the resource acquisition request is used to request the server to send the resource to be loaded corresponding to the candidate region; and loading resources for the multiple candidate code blocks in response to receiving the resource to be loaded.
[0010] Optionally, the step of executing at least one code block corresponding to the target region in the candidate code blocks based on the target resources loaded in the target region in response to the target region in the candidate region meeting the pre-execution conditions includes: performing resource parsing on the target resources loaded in the target region in response to the target region being operated on being greater than or equal to a second probability threshold; executing at least one code block corresponding to the target region in the candidate code blocks based on the parsing result of the target resources to obtain the code execution result corresponding to the at least one code block; and pre-storing the code execution result in the target storage location.
[0011] Optionally, the step of rendering the execution result of the at least one code block in response to the user's operation instruction on the target area to respond to the operation instruction includes: in response to the user's operation instruction on the target area, retrieving the code execution result corresponding to the at least one code block from the target storage location; and rendering the target display interface based on the code execution result to respond to the operation instruction.
[0012] Optionally, the step of predicting the user's operation behavior on the target display interface based on the multi-dimensional interaction behavior data and generating operation probability distribution data of the user on multiple areas of the target display interface includes: generating an interaction behavior feature vector corresponding to the user based on the multi-dimensional interaction behavior data; and predicting the user's operation behavior on the target display interface based on the interaction behavior feature vector to generate operation probability distribution data of the user on multiple areas of the target display interface.
[0013] Secondly, this application provides a page resource loading device based on teaching equipment, comprising: an acquisition module configured to acquire multi-dimensional interactive behavior data of a user in a target display interface; a generation module configured to predict the user's operation behavior in the target display interface based on the multi-dimensional interactive behavior data, and generate operation probability distribution data of the user on multiple areas in the target display interface; a loading module configured to determine a target area that meets preprocessing conditions from the multiple areas based on the operation probability distribution data, load resources and execute at least one code block corresponding to the target area; and a rendering module configured to render the execution result of the at least one code block in response to the user's operation instruction on the target area, so as to respond to the operation instruction.
[0014] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the page resource loading method described in the first aspect.
[0015] Fourthly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the page resource loading method described in the first aspect.
[0016] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the page resource loading method described in the first aspect.
[0017] Using the above technical solution, this application provides a page resource loading method, apparatus, and electronic device based on teaching equipment, comprising: acquiring multi-dimensional interactive behavior data of a user in a target display interface; predicting the user's operation behavior in the target display interface based on the multi-dimensional interactive behavior data, generating operation probability distribution data of the user on multiple areas of the target display interface; determining a target area that meets the preprocessing conditions from multiple areas based on the operation probability distribution data, loading resources and executing at least one code block corresponding to the target area; and rendering the execution result of at least one code block in response to the user's operation command on the target area, so as to respond to the operation command. Compared with existing technologies, this application addresses the page resource loading scenario of teaching equipment. Teachers' teaching behaviors follow teaching plans, lesson plans, and procedural norms, and these behaviors are highly predictable. The multi-dimensional interactive behavior data within these behaviors is clearly directional, accurately reflecting operational logic and providing a reliable foundation for behavior prediction. By predicting user actions on the target display interface based on multi-dimensional interactive behavior data, it generates probability distribution data of user actions on multiple areas of the target display interface, accurately predicting the potential operational intentions of teachers and students in the teaching scenario. By identifying target areas that meet preprocessing conditions from multiple areas based on the operation probability distribution data, it loads and executes resources for at least one code block corresponding to the target area. Pre-loading and executing resources for the code block corresponding to the target area avoids page lag and response delays caused by passively loading resources after user-triggered operations during teaching. By responding to user commands on the target area and rendering the execution results of at least one code block to respond to the command, it improves the response speed of page operations on teaching equipment, effectively ensuring the smoothness of interface interaction during course teaching and preventing interruptions to the teaching rhythm due to resource loading delays. Attached Figure Description
[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 shows a flowchart of a page resource loading method based on teaching equipment provided in an embodiment of this application; Figure 2 shows a flowchart of a page resource loading method based on teaching equipment provided in an embodiment of this application; Figure 3 shows a flowchart of an example of a dynamic resource loading and execution system based on behavior prediction and resource fingerprint provided in an embodiment of this application; Figure 4 shows a structural schematic diagram of a page resource loading device based on teaching equipment provided in an embodiment of this application; Figure 5 shows a structural schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0021] The embodiments of this application will now be described in more detail with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.
[0022] To address the technical problem of passive resource loading of page code blocks in existing technologies, which relies entirely on explicit user actions and only initiates network requests to load resources after the user triggers the action, resulting in noticeable interaction delays and impacting course progress, this embodiment provides a page resource loading method based on teaching equipment, as shown in Figure 1. This method includes: Step 101, acquiring multi-dimensional interactive behavior data of the user on the target display interface.
[0023] In this embodiment of the application, the target display interface can be the interface presented on a large screen used in a modern school teaching scenario, or it can be a single web page interface displayed on a school computer during the teacher's lesson preparation process. The target display interface can be used to carry teaching-related content and can include functional modules such as courseware display, teaching video playback, online interactive exercises, and teaching resource download portal.
[0024] In this embodiment, multi-dimensional interactive behavior data can be data that reflects a user's behavioral characteristics when the user operates on the target display interface. This multi-dimensional interactive behavior data can provide basic data support for subsequently predicting the user's operational intentions. For example, the multi-dimensional interactive behavior data in this embodiment may specifically include mouse movement trajectory, mouse movement speed, mouse movement acceleration, the duration of the user's hover over interactive elements (such as buttons, links, input boxes, etc.), page scrolling depth, and page scrolling mode (such as uniform scrolling, rapid scrolling followed by a pause, etc.).
[0025] In this embodiment of the application, the acquisition of multi-dimensional interactive behavior data of users in the target display interface can be achieved by a behavior acquisition and quantification module deployed on the client. The behavior acquisition and quantification module can monitor the micro-interaction behavior of users on the page in real time and continuously capture various types of raw behavior data.
[0026] For example, teachers' teaching behaviors in teaching scenarios are highly predictable. These behaviors can follow teaching plans, lesson plans, and standardized teaching processes. For instance, after explaining a certain knowledge point, a teacher is likely to click on the practice exercises module. After playing a teaching video, the teacher will usually enter the knowledge point summary area. During lesson preparation, the teacher will click on the courseware browsing entry in the order of chapters. The regularity of teaching behaviors makes the multi-dimensional interactive behavior data directional. The multi-dimensional interactive behavior data captured by the behavior collection and quantification module can accurately reflect the operational logic in the teaching scenario, providing basic data for subsequent predictions.
[0027] Step 102: Based on multi-dimensional interactive behavior data, predict the user's operation behavior in the target display interface and generate the probability distribution data of the user's operation on multiple areas of the target display interface.
[0028] In this embodiment, the operation probability distribution data can be data used to characterize the likelihood of a user performing an operation corresponding to each operable area in the target display interface. This operation probability distribution data can provide a clear basis for subsequent selection of areas that need to be pre-processed. For example, if the target display interface includes four operable areas: courseware download, online quiz, teaching video playback, and knowledge point expansion, the generated operation probability distribution data can show that the user has an 85% probability of clicking the courseware download area, a 10% probability of clicking the online quiz area, a 3% probability of clicking the teaching video playback area, and a 2% probability of clicking the knowledge point expansion area.
[0029] In this embodiment of the application, predicting user actions on the target display interface based on multi-dimensional interactive behavior data can be accomplished through a local prediction module deployed on the client. This local prediction module has a built-in lightweight machine learning model, which may include, but is not limited to, logistic regression, decision tree, and random forest models. This lightweight machine learning model can specifically learn contextual features such as teaching processes, course structures, and teacher operating habits to establish customized prediction logic, further improving prediction accuracy.
[0030] In the embodiments of this application, generating probability distribution data of user operations on multiple areas of the target display interface can be achieved by inputting the collected multi-dimensional interactive behavior data into a lightweight machine learning model. The lightweight machine learning model performs feature extraction, pattern recognition, and probability calculation on the data through algorithms, and can output probability distribution data of user operations on multiple areas of the target display interface, thereby realizing the prediction of the user's potential operation intentions.
[0031] Step 103: Based on the operation probability distribution data, determine the target region that meets the preprocessing conditions from multiple regions, and load and execute at least one code block corresponding to the target region.
[0032] In this embodiment of the application, the preprocessing conditions can be judgment conditions used to filter areas that need to be loaded and executed in advance. The preprocessing conditions can be flexibly adjusted according to the performance requirements of the actual teaching scenario, network conditions and other factors.
[0033] In this embodiment of the application, the target area can be a region selected from multiple operable areas that meets the preprocessing conditions. The target area can be the area where the user is highly likely to perform the next operation. Loading and executing the code block corresponding to the target area in advance can ensure a fast response when the user operates. For example, in a teaching scenario, based on the high predictability of teacher operations, the accuracy of target area determination is greatly improved. The system can load and execute the code block corresponding to the target area in advance to ensure that there is no delay when the teacher or student switches.
[0034] In the embodiments of this application, a code block can be a basic code unit that constitutes the functionality of a web page. A code block can include JavaScript code blocks, CSS style files, etc. Each code block corresponds to a specific page function. For example, the code block corresponding to the courseware download area can implement specific functions such as rendering the courseware list, generating download links, and displaying download progress.
[0035] In this embodiment, loading and executing resources for at least one code block corresponding to the target area can be achieved by querying a resource configuration file generated by the resource dependency graph module. This resource configuration file can be a static configuration file generated during the application build phase. The resource configuration file can define the resources such as code blocks and style files that each operable area, route, or functional module depends on, and can also generate unique resource identification information for each resource. After obtaining the code block information corresponding to the target area, a resource loading request can be initiated through the browser's resource pre-loading API or flexible network request API. The API can silently download resources in the background without affecting the user's current page operation experience. After the resources are loaded, the code block can be executed according to the execution logic.
[0036] For example, by combining the predictability of teaching scenarios, resource loading becomes more targeted. For instance, in lesson preparation scenarios, teachers often operate in the order of teaching objectives - teaching process - class summary. The system can preload the corresponding code blocks in logical order, which can ensure a rapid response for each teaching link while avoiding resource waste, and further improve the practicality and accuracy of the solution.
[0037] Step 104: In response to the user's operation command on the target area, render the execution result of at least one code block to respond to the operation command.
[0038] In this embodiment, the user operation command can be a function call command initiated by the user to the target area through mouse click, keyboard shortcut, touch operation, etc. The user operation command can trigger the system to respond to the page function corresponding to the target area.
[0039] In this embodiment of the application, since the code block corresponding to the target area has already completed resource loading and execution in advance, when the user triggers the operation command, the system does not need to go through time-consuming processes such as network request to download resources and code parsing. Instead, it can directly call the code execution result stored in memory, render the target display interface through the browser's rendering engine, and present the page content corresponding to the execution result to the user in real time.
[0040] Compared with existing technologies, this embodiment addresses the page resource loading scenario of teaching equipment. Teachers' teaching behaviors follow teaching plans, lesson plans, and procedural norms, and these behaviors are highly predictable. The multi-dimensional interactive behavior data within these behaviors is clearly directional, accurately reflecting operational logic and providing a reliable foundation for behavior prediction. By predicting user actions on the target display interface based on multi-dimensional interactive behavior data, it generates probability distribution data of user actions on multiple areas of the target display interface, accurately predicting the potential operational intentions of teachers and students in the teaching scenario. By identifying target areas that meet preprocessing conditions from multiple areas based on the operation probability distribution data, it loads and executes resources for at least one code block corresponding to the target area. Pre-loading and executing resources for the code block corresponding to the target area avoids page lag and response delays caused by passively loading resources after user-triggered operations during teaching. By responding to user commands on the target area and rendering the execution results of at least one code block to respond to the command, it improves the response speed of page operations on teaching equipment, effectively ensuring the smoothness of interface interaction during course teaching and preventing interruptions to the teaching rhythm due to resource loading delays.
[0041] As an optional approach, when performing the task of "determining target regions that meet preprocessing conditions from multiple regions based on operation probability distribution data, loading resources and executing at least one code block corresponding to the target region", the following method can be used, but is not limited to it, as shown in Figure 2. The method includes: step 201, determining candidate regions that meet preloading conditions from multiple regions based on operation probability distribution data, and loading resources for candidate code blocks corresponding to the candidate regions.
[0042] In this embodiment, the preloading condition can be a judgment condition used to filter regions that need to be preloaded with resources, and the preloading condition can be set based on the probability of the region being operated on. For example, in the teaching scenario of this embodiment, the preloading condition can be dynamically adjusted in combination with scenario-based factors such as teaching time period, course type, and teaching progress to ensure a delay-free response for real-time teaching.
[0043] In this embodiment, the candidate region can be a region selected from multiple operable regions that meets the preloading conditions. The candidate region can be a region where the user has a certain probability of performing an operation next. Preloading the candidate code block corresponding to the candidate region can save response time for subsequent possible user operations. For example, in the teaching scenario of this embodiment, the teacher's actions are constrained by the teaching plan and curriculum outline. The scope of the candidate region is more concentrated and its direction is more specific. The system does not need to preload irrelevant regions, which can save bandwidth resources and improve the accuracy of preloading.
[0044] In the embodiments of this application, a candidate code block can be a set of code blocks that implement the function of the candidate region, and the candidate code block can include relevant code that implements the basic display and interactive logic of the region.
[0045] In this embodiment of the application, candidate regions that meet the preloading conditions are determined from multiple regions based on operation probability distribution data. Resource loading of candidate code blocks corresponding to the candidate regions can be performed by extracting the operation probability data of each region based on the operation probability distribution data, and determining the regions whose operation probability data meets the preloading conditions as candidate regions. By querying the resource configuration file generated by the resource dependency graph, the candidate code block information corresponding to the candidate regions is obtained. The candidate code block information may include the storage path, dependency relationship, resource identifier, etc. of the code block. Resource loading requests can be initiated to the server through the relevant API of the browser to obtain the resources corresponding to the candidate code blocks and complete the loading, ensuring that the candidate code blocks can respond to subsequent execution instructions at any time.
[0046] Step 202: In response to the target region in the candidate region meeting the pre-execution conditions, execute at least one code block corresponding to the target region in the candidate code block based on the target resources loaded in the target region.
[0047] In this embodiment of the application, the pre-execution condition can be a more stringent judgment criterion than the pre-loading condition. The pre-execution condition can set a higher probability threshold for being operated on, ensuring that code blocks can be pre-executed in areas with extremely high user operation probability.
[0048] In this embodiment, the target resource can be all loaded resources corresponding to the target region in the candidate region. For example, the target resource in this embodiment may specifically include candidate code blocks, dependent style files, data files, etc.
[0049] In the embodiments of this application, the execution of at least one code block corresponding to the target region in the candidate code block based on the target resource loaded in the target region can first be performed by the browser's parsing engine to parse the target resource. The parsing process may include operations such as syntax verification of the code block, dependency sorting, and variable initialization. Based on the parsing result, at least one code block corresponding to the target region can be executed according to the execution logic of the code block. During the execution process, document object model rendering (DOM rendering) is not performed, only code calculation, data processing, and result storage are completed. The execution result of the code is stored in a preset target storage location.
[0050] Optionally, when performing the action of "determining candidate regions that meet the preloading conditions from multiple regions based on operation probability distribution data, and loading resources for multiple candidate code blocks corresponding to the candidate regions", the following methods may be used, but are not limited to: determining the operation probability data corresponding to multiple regions based on operation probability distribution data; determining regions in multiple regions whose operation probability data is greater than or equal to a first probability threshold as candidate regions, and obtaining the resource configuration file corresponding to the candidate regions; and loading resources for the candidate code blocks corresponding to the candidate regions according to the resource configuration file.
[0051] In this embodiment of the application, determining the probability of being manipulated for multiple regions based on the operation probability distribution data can be achieved by accurately calculating the probability of being manipulated for each region using a machine learning model in the local prediction module. The calculation process can be the result obtained by the model after analyzing the input interaction behavior features and comparing historical behavior patterns. The first probability threshold can be adjusted according to the performance requirements and bandwidth of the actual application scenario. Regions with operation probability data greater than or equal to the first probability threshold can be identified as candidate regions to ensure that the candidate regions are regions where users have a high probability of operation. The resource configuration file can be generated by the resource dependency graph module during the application building phase. The resource configuration file can record in detail the candidate code block name, storage address, resource dependency relationship, and resource identification information corresponding to each candidate region. Based on the information recorded in the resource configuration file, the relevant resources of each candidate code block can be located. By obtaining the corresponding resources from the server through network requests, the resource loading of multiple candidate code blocks can be completed.
[0052] For example, in the teaching scenario of this application embodiment, the historical behavior pattern is highly consistent with the teaching process and curriculum structure. The machine learning model can learn the teaching rules of different subjects and grades to further optimize the calculation logic of the operation probability. The machine learning model can accurately predict the operation probability of each link, so that the determination of the candidate region is more in line with the actual teaching, and greatly improve the accuracy and effectiveness of preloading.
[0053] Optionally, when performing "loading resources for multiple candidate code blocks corresponding to candidate regions based on resource configuration files", the following methods may be used, but are not limited to: determining the candidate code blocks corresponding to the candidate regions and the resource identification information corresponding to the candidate code blocks based on the resource configuration files; verifying the code version of the candidate code blocks based on the resource identification information, and generating a resource acquisition request corresponding to the candidate regions based on the candidate code blocks if the verification passes; sending a resource acquisition request to the server, the resource acquisition request being used to request the server to send the resources to be loaded corresponding to the candidate regions; and loading resources for multiple candidate code blocks in response to receiving the resources to be loaded.
[0054] In this embodiment, the resource identification information can be an identification string generated for each resource during the application building phase. The resource identification information can be used to distinguish different versions of the resource. For example, the resource identification information in this embodiment can specifically be a resource fingerprint.
[0055] In this embodiment of the application, the resource acquisition request may include resource identification information, candidate code block identification, and other content.
[0056] In this embodiment, determining the candidate code block corresponding to the candidate region based on the resource configuration file, and the resource identifier information corresponding to the candidate code block, can be achieved by extracting the specific information of the candidate code block corresponding to the candidate region from the resource configuration file, and simultaneously obtaining the resource identifier information corresponding to each candidate code block; the code version of the candidate code block is verified based on the resource identifier information. The verification method can be to compare the resource identifier information of the locally cached code block with the resource identifier information in the resource configuration file; if the resource identifier information of the locally cached code block is consistent with the resource identifier information in the resource configuration file, it can be said that the code version of the candidate code block is correct and the verification passes; if the resource identifier information of the locally cached code block is inconsistent with the resource identifier information in the resource configuration file, it can be said that the locally cached resource version is outdated and the latest version of the resource needs to be obtained again.
[0057] For example, in the teaching scenario of this application embodiment, the updates of teaching resources are regular. The system can optimize the version verification logic in combination with the teaching cycle to ensure that the preloaded candidate code block version meets the current teaching needs, and further improve the adaptability and accuracy of the teaching plan in the teaching scenario.
[0058] In this embodiment, if the resource identifier information of the locally cached code block passes the verification with the resource identifier information in the resource configuration file, a resource acquisition request corresponding to the candidate region can be generated based on the name, storage path, and other information of the candidate code block; the resource acquisition request is sent to the server, and the server can find the corresponding resource to be loaded according to the information in the request and return the resource to the client in the form of a stream; in response to receiving the resource to be loaded, the client can load the resources of multiple candidate code blocks according to the dependency relationship of the candidate code blocks.
[0059] For example, in the teaching scenario of this application embodiment, since the dependency relationship of candidate regions in the teaching scenario is relatively fixed, loading in sequence can ensure the integrity and effectiveness of resource loading. At the same time, based on the predictability of teaching behavior, the timing of resource loading is highly matched with the teaching process, avoiding the disconnect between resource loading and teaching operation, and improving the overall efficiency of the solution.
[0060] Optionally, when executing "in response to the target region in the candidate region meeting the pre-execution conditions, execute at least one code block corresponding to the target region in the candidate code block based on the target resources loaded in the target region", the following methods may be used, but are not limited to: in response to the target being operated probability data of the target region in the candidate region being greater than or equal to the second probability threshold, perform resource parsing on the target resources loaded in the target region; based on the parsing result of the target resources, execute at least one code block corresponding to the target region in the candidate code block to obtain the code execution result corresponding to at least one code block; and pre-store the code execution result in the target storage location.
[0061] In this embodiment of the application, the second probability threshold may be higher than the first probability threshold. The specific value of the second probability threshold may be adjusted according to the need for balancing the accuracy of pre-execution and resource consumption in the actual scenario. When the probability data of the target region being operated on in the candidate region is greater than or equal to the second probability threshold, it can be determined that the target region meets the pre-execution conditions.
[0062] In the embodiments of this application, the process of parsing the target resources loaded in the target area can be jointly completed by the browser's JavaScript engine and Cascading Style Sheets (CSS) parser. Specifically, it can include syntax analysis of JavaScript code blocks, parsing of variable and function declarations, parsing of selectors in CSS style files, and construction of style rules.
[0063] In the embodiments of this application, based on the resource parsing results, at least one code block corresponding to the target area in the candidate code blocks can be executed according to the execution order of the code blocks. During the execution process, only code calculation and data processing are performed, without DOM node creation and page rendering operations, which can avoid affecting the current user's page interaction experience. After the execution is completed, the code execution result corresponding to at least one code block is obtained, such as data calculation results, function initialization status, etc.; the code execution result is pre-stored in the target storage location.
[0064] In this embodiment of the application, the target storage location can be selected according to actual needs. Specifically, the target storage location in this embodiment of the application may include the client's memory cache, a specified directory in the local storage device, etc. The high-speed read and write characteristics of memory can ensure that the execution results can be quickly retrieved when the user performs subsequent operations.
[0065] Optionally, when performing the action of "rendering the execution result of at least one code block in response to the user's operation command on the target area, in response to the operation command", the following methods may be used, but are not limited to: in response to the user's operation command on the target area, calling the code execution result corresponding to at least one code block from the target storage location; and rendering the target display interface based on the code execution result in response to the operation command.
[0066] In the embodiments of this application, in response to the user's operation command on the target area, the code execution result corresponding to at least one code block can be retrieved from the target storage location. When the user initiates an operation command on the target area by clicking the left mouse button, pressing the touch button, etc., the client's event listening mechanism can capture the operation command in real time and identify the target area identifier corresponding to the operation command through event bubbling or event delegation mechanism. Based on the target area identifier, the code execution result of at least one code block corresponding to the target area can be quickly found and retrieved from the target storage location (such as memory cache) where the code execution result was previously stored. Since the execution result has been stored in advance, there is no need to perform code compilation and execution process again.
[0067] In the embodiments of this application, the target display interface can be rendered by the browser's rendering engine (such as WebKit, Gecko, etc.) based on the code execution result, and the page elements, styles and interactive functions corresponding to the execution result can be presented. For example, pop-ups, lists, forms and other content corresponding to the target area can be rendered, which can realize the real-time response to user operation commands and allow users to have a smooth operation experience in teaching scenarios.
[0068] Optionally, when performing the task of "predicting user actions on the target display interface based on multi-dimensional interactive behavior data and generating probability distribution data of user actions on multiple areas of the target display interface", the following methods may be used, but are not limited to: generating user-corresponding interactive behavior feature vectors based on multi-dimensional interactive behavior data; predicting user actions on the target display interface based on the interactive behavior feature vectors and generating probability distribution data of user actions on multiple areas of the target display interface.
[0069] In this embodiment of the application, the interaction behavior feature vector can be a numerical vector obtained by quantifying multi-dimensional interaction behavior data. The interaction behavior feature vector can be used to transform unstructured behavior data into structured data that can be processed by machine learning models.
[0070] In this embodiment of the application, the generation of user interaction behavior feature vectors based on multi-dimensional interaction behavior data can be accomplished by the behavior acquisition and quantification module. Each dimension of behavior data corresponds to one dimension of the feature vector, and the behavior data of each dimension can together constitute a complete interaction behavior feature vector.
[0071] In this embodiment of the application, the generated interactive behavior feature vector is input into the lightweight machine learning model of the local prediction module. The lightweight machine learning model can be trained by a large amount of historical interactive behavior data to learn the mapping relationship between different behavioral features and user operation intentions. The lightweight machine learning model can generate the probability distribution data of user operation on multiple areas in the target display interface by performing feature weighting, pattern matching, probability calculation and other processing on the input interactive behavior feature vector.
[0072] For example, in the teaching scenario of this application embodiment, since the historical interaction behavior data in the teaching scenario is highly related to the teaching process, the samples trained by the lightweight machine learning model are more targeted. The lightweight machine learning model can accurately grasp the operational logic of each link in mathematics teaching. The prediction accuracy of the lightweight machine learning model is significantly higher than that of general scenarios, providing a reliable decision basis for resource loading and execution.
[0073] Optionally, this application embodiment also provides an example of a dynamic resource loading and execution system based on behavior prediction and resource fingerprint. A flowchart of an example of a dynamic resource loading and execution system based on behavior prediction and resource fingerprint is shown in Figure 3. Figure 3 includes the following steps: Step 1, the user starts interacting on the page.
[0074] Step 2: The behavior acquisition module captures behavior data (i.e., the multi-dimensional interactive behavior data in this application embodiment) and quantizes it (i.e., generates the user's corresponding interactive behavior feature vector in this application embodiment).
[0075] Step 3: The prediction model receives vectors, calculates and outputs probabilities (i.e., the probability distribution data of user operations on multiple areas of the target display interface in this embodiment of the application).
[0076] Step 4: The intelligent loading controller determines whether the probability exceeds the threshold (i.e., the first probability threshold in this embodiment).
[0077] Step 5: If the time limit is not exceeded, return to continue listening.
[0078] Step 6: If the number of requests exceeds the limit, obtain the resource URL from the resource graph (i.e., the resource configuration file in this application embodiment).
[0079] Step 7: Initiate a preloading request (i.e., a resource acquisition request in this application embodiment) and download resources (i.e., load resources for candidate code blocks in this application embodiment).
[0080] Step 8: Further determine whether pre-execution is required (i.e., whether the target region in the candidate region meets the pre-execution conditions in this embodiment of the application).
[0081] Step 9: If yes, then parse and execute the JavaScript code (i.e., at least one code block corresponding to the target region in this application embodiment), and cache the result in memory (i.e., the target storage location in this application embodiment).
[0082] Step 10: When the user's actual operation is triggered (i.e., the user's operation instruction on the target area in this embodiment), the data is directly read from memory and rendered (i.e., the execution result of at least one code block is rendered in this embodiment), and the process ends.
[0083] As an optional approach, this application provides an example of a dynamic resource loading and execution system based on behavior prediction and resource fingerprinting. Compared with traditional lazy loading technology, this example can change the resource loading mode from passively responding to explicit user operations to actively predictive loading based on user interaction behavior. This not only eliminates the interaction latency caused by network requests and code parsing, but also significantly improves the response speed and user experience of web applications (especially suitable for scenarios such as large-screen teaching in schools and teacher lesson preparation). By preloading only high-probability resources and combining them with resource fingerprinting, it achieves efficient bandwidth utilization and accurate caching, improving the cache hit rate. At the same time, the system can learn and adapt to the usage habits of different users, providing personalized performance optimization and making the application run more smoothly. By distributing the calculation and prediction tasks to various clients, it effectively reduces the peak load pressure on the server under sudden requests, achieving a comprehensive improvement in performance, efficiency, and practicality.
[0084] Compared with existing technologies, this embodiment determines candidate regions that meet pre-loading conditions based on operation probability distribution data and loads corresponding candidate code blocks. It then executes the code blocks corresponding to target regions that meet pre-execution conditions, achieving layered control over resource loading and execution. This avoids excessive resource consumption affecting the performance of teaching equipment and improves the rationality of resource scheduling. Furthermore, by determining the probability of each region being operated on based on operation probability distribution data, regions greater than or equal to a first probability threshold are identified as candidate regions, and corresponding candidate code blocks are loaded according to the resource configuration file, improving the targeting of resource loading and the efficiency of teaching equipment resource utilization. Finally, by determining candidate code blocks based on the resource configuration file... Resource identification information is used to verify the code version and generate a resource acquisition request to load candidate code blocks. This effectively avoids page anomalies caused by loading incorrect versions of code blocks on teaching devices, ensuring the accuracy of the loaded teaching resources and the stability of the teaching interface. When the probability data of the target area being operated on is greater than or equal to a second probability threshold, the target resource is parsed and the corresponding code block is executed, and the execution result is pre-stored, enabling the pre-reservation of code execution results on the teaching device page. By responding to user operation commands on the target area, the code execution results are retrieved from the target storage location and rendered, achieving rapid response to user operations and further improving the interactive experience of the teaching devices and the efficiency of classroom teaching.
[0085] Furthermore, as a specific implementation of the methods shown in Figures 1 and 2, this embodiment provides a page resource loading device based on teaching equipment, as shown in Figure 4. The device includes: an acquisition module 31, a generation module 32, a loading module 33, and a rendering module 34.
[0086] The acquisition module 31 is configured to acquire multi-dimensional interactive behavior data of the user in the target display interface; the generation module 32 is configured to predict the user's operation behavior in the target display interface based on the multi-dimensional interactive behavior data, and generate operation probability distribution data of the user on multiple areas in the target display interface; the loading module 33 is configured to determine the target area that meets the preprocessing conditions from multiple areas based on the operation probability distribution data, load resources and execute at least one code block corresponding to the target area; the rendering module 34 is configured to render the execution result of at least one code block in response to the user's operation command on the target area, so as to respond to the operation command.
[0087] In some examples of this embodiment, the loading module 33 is specifically configured to determine candidate regions that meet the preloading conditions from multiple regions based on operation probability distribution data, load resources for candidate code blocks corresponding to the candidate regions, and execute at least one code block corresponding to the target region in the candidate code blocks based on the target resources loaded in the target region when the target region in the candidate regions meets the pre-execution conditions.
[0088] In some examples of this embodiment, the loading module 33 is further configured to determine the operation probability data corresponding to multiple regions based on the operation probability distribution data; determine the regions in the multiple regions whose operation probability data is greater than or equal to a first probability threshold as candidate regions; obtain the resource configuration file corresponding to the candidate region; and load the candidate code block corresponding to the candidate region according to the resource configuration file.
[0089] In some examples of this embodiment, the loading module 33 is further configured to determine the candidate code block corresponding to the candidate region and the resource identification information corresponding to the candidate code block based on the resource configuration file; verify the code version of the candidate code block based on the resource identification information, and generate a resource acquisition request corresponding to the candidate region based on the candidate code block if the verification passes; send the resource acquisition request to the server, the resource acquisition request being used to request the server to send the resource to be loaded corresponding to the candidate region; and load the resource for multiple candidate code blocks in response to receiving the resource to be loaded.
[0090] In some examples of this embodiment, the loading module 33 is further configured to, in response to the target operation probability data of the target region in the candidate region being greater than or equal to the second probability threshold, perform resource parsing on the target resource loaded in the target region; based on the parsing result of the target resource, execute at least one code block corresponding to the target region in the candidate code block to obtain the code execution result corresponding to at least one code block; and pre-store the code execution result in the target storage location.
[0091] In some examples of this embodiment, the rendering module 34 is specifically configured to, in response to a user's operation command on the target area, retrieve the code execution result corresponding to at least one code block from the target storage location; and render the target display interface based on the code execution result to respond to the operation command.
[0092] In some examples of this embodiment, the identification module 33 is further configured to generate a user-corresponding interactive behavior feature vector based on multi-dimensional interactive behavior data; predict the user's operation behavior in the target display interface based on the interactive behavior feature vector, and generate the user's operation probability distribution data for multiple areas in the target display interface.
[0093] It should be noted that other corresponding descriptions of the functional units involved in the page resource loading device based on teaching equipment provided in this embodiment can be found in the corresponding descriptions in Figures 1 and 2, and will not be repeated here.
[0094] Based on the methods shown in Figures 1 and 2, this embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the methods shown in Figures 1 and 2.
[0095] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.
[0096] Figure 5 shows a schematic diagram of the hardware structure of an electronic device according to the present invention, including: at least one processor 401; and a memory 402 communicatively connected to at least one processor 401; wherein, the memory 402 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to perform the page resource loading method as described above.
[0097] Figure 5 uses a processor 401 as an example.
[0098] The electronic device may also include an input device 403 and an output device 404.
[0099] The processor 401, memory 402, input device 403 and output device 404 can be connected by a bus or other means. Figure 5 shows an example of connection by bus.
[0100] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the page resource loading method in the embodiments of this application, for example, the method flow shown in Figures 1 and 2. Processor 401 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in memory 402, thereby implementing the page resource loading method in the above embodiments.
[0101] Memory 402 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created according to the use of the page resource loading method, etc. Furthermore, memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 402 may optionally include memory remotely located relative to processor 401, and these remote memories may be connected via a network to the apparatus performing the page resource loading method. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0102] Input device 403 can receive user clicks and generate signal inputs related to user settings and function control of page resource loading methods. Output device 404 may include display devices such as a display screen.
[0103] One or more modules are stored in memory 402, and when run by one or more processors 401, the page resource loading method in any of the above method embodiments is executed.
[0104] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.
[0105] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.
[0106] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.
[0107] 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 platform, or it can be implemented by hardware. Compared with existing technologies, this embodiment addresses the page resource loading scenario of teaching equipment. Teachers' teaching behaviors follow teaching plans, lesson plans, and procedural norms, exhibiting high predictability. The multi-dimensional interactive behavior data within the teaching behavior is clearly directional, accurately reflecting operational logic and providing a reliable foundation for behavior prediction. By predicting user actions on the target display interface based on multi-dimensional interactive behavior data, it generates probability distribution data for user actions on multiple areas of the target display interface, accurately predicting the potential operational intentions of teachers and students in the teaching scenario. By determining target areas that meet preprocessing conditions from multiple areas based on the operation probability distribution data, it loads and executes resources for at least one code block corresponding to the target area. Pre-loading and executing resources for the code block corresponding to the target area avoids page lag and response delays caused by passive resource loading after user-triggered operations during teaching. By rendering the execution result of at least one code block in response to user operation commands on the target area, it improves the response speed of the teaching equipment's page operations, effectively ensuring the smoothness of interface interaction during course teaching and preventing interruptions to the teaching rhythm due to resource loading delays. Furthermore, by using operation probability distribution data... The system identifies candidate regions that meet pre-loading conditions based on data distribution and loads corresponding candidate code blocks. It also executes code blocks corresponding to target regions that meet pre-execution conditions, achieving layered control over resource loading and execution. This prevents excessive resource consumption from affecting the performance of teaching equipment and improves the rationality of resource scheduling. By determining the probability of each region being operated on based on operation probability distribution data, regions with a probability greater than or equal to a first probability threshold are identified as candidate regions, and corresponding candidate code blocks are loaded according to resource configuration files, improving the targeting of resource loading and the efficiency of teaching equipment resource utilization. By determining candidate code blocks and resource identification information based on resource configuration files, verifying code versions, and generating resource acquisition requests to load candidate code blocks, the system effectively avoids page anomalies caused by loading incorrect versions of code blocks, ensuring the accuracy of teaching resource loading versions and the stability of the teaching interface. When the probability of a target region being operated on is greater than or equal to a second probability threshold, the system parses the target resource, executes the corresponding code block, and pre-stores the execution results, achieving advance storage of code execution results for the teaching equipment page. Finally, by responding to user operation commands for the target region, the system retrieves and renders the code execution results from the target storage location, achieving rapid response to user operations and further improving the interactive experience of the teaching equipment and classroom teaching efficiency.
[0108] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.
[0109] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for loading page resources based on teaching equipment, characterized in that, include: Acquire multi-dimensional interactive behavior data of users on the target display interface; Based on the multi-dimensional interactive behavior data, predict the user's operation behavior in the target display interface, and generate the probability distribution data of the user's operation on multiple areas in the target display interface; Based on the operation probability distribution data, a target region that meets the preprocessing conditions is determined from the multiple regions, and at least one code block corresponding to the target region is loaded with resources and executed. In response to the user's operation command on the target area, the execution result of the at least one code block is rendered to respond to the operation command.
2. The method according to claim 1, characterized in that, The step of determining a target region that meets the preprocessing conditions from the plurality of regions based on the operation probability distribution data, and loading and executing at least one code block corresponding to the target region, includes: determining a candidate region that meets the preloading conditions from the plurality of regions based on the operation probability distribution data, loading resources for the candidate code block corresponding to the candidate region; and executing at least one code block corresponding to the target region in the candidate code block based on the target resources loaded in the target region, in response to a target region in the candidate region meeting the pre-execution conditions.
3. The method according to claim 2, characterized in that, The step of determining candidate regions that meet the preloading conditions from the plurality of regions based on the operation probability distribution data, and loading resources for the plurality of candidate code blocks corresponding to the candidate regions, includes: determining the operation probability data corresponding to the plurality of regions based on the operation probability distribution data; determining the regions in the plurality of regions whose operation probability data is greater than or equal to a first probability threshold as the candidate regions; obtaining the resource configuration file corresponding to the candidate regions; and loading resources for the candidate code blocks corresponding to the candidate regions according to the resource configuration file.
4. The method according to claim 3, characterized in that, The step of loading resources for multiple candidate code blocks corresponding to the candidate region based on the resource configuration file includes: determining the candidate code blocks corresponding to the candidate region and the resource identification information corresponding to the candidate code blocks based on the resource configuration file; verifying the code version of the candidate code blocks based on the resource identification information, and generating a resource acquisition request corresponding to the candidate region based on the candidate code blocks if the verification passes; sending the resource acquisition request to the server, wherein the resource acquisition request is used to request the server to send the resources to be loaded corresponding to the candidate region; and loading resources for the multiple candidate code blocks in response to receiving the resources to be loaded.
5. The method according to claim 3, characterized in that, The step of executing at least one code block corresponding to the target region in the candidate code blocks based on the target resources loaded in the target region in response to the target region in the candidate region meeting the pre-execution conditions includes: performing resource parsing on the target resources loaded in the target region in response to the target region being operated on being greater than or equal to a second probability threshold; executing at least one code block corresponding to the target region in the candidate code blocks based on the parsing result of the target resources to obtain the code execution result corresponding to the at least one code block; and pre-storing the code execution result in the target storage location.
6. The method according to claim 5, characterized in that, The step of rendering the execution result of the at least one code block in response to the user's operation instruction on the target area, in response to the user's operation instruction on the target area, includes: retrieving the code execution result corresponding to the at least one code block from the target storage location in response to the user's operation instruction on the target area; and rendering the target display interface based on the code execution result in response to the operation instruction.
7. The method according to any one of claims 1 to 6, characterized in that, The step of predicting the user's operation behavior on the target display interface based on the multi-dimensional interaction behavior data and generating operation probability distribution data of the user on multiple areas of the target display interface includes: generating an interaction behavior feature vector corresponding to the user based on the multi-dimensional interaction behavior data; predicting the user's operation behavior on the target display interface based on the interaction behavior feature vector and generating operation probability distribution data of the user on multiple areas of the target display interface.
8. A page resource loading device based on teaching equipment, characterized in that, include: The acquisition module is configured to acquire multi-dimensional interactive behavior data of the user in the target display interface; The generation module is configured to predict the user's operation behavior in the target display interface based on the multi-dimensional interaction behavior data, and generate the user's operation probability distribution data for multiple areas in the target display interface; The loading module is configured to determine a target region that meets the preprocessing conditions from the plurality of regions based on the operation probability distribution data, and to load and execute at least one code block corresponding to the target region. The rendering module is configured to render the execution result of the at least one code block in response to the user's operation command on the target area, in response to the operation command.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.
10. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.