Webpage view preloading method and device, electronic equipment and storage medium

Abstract

The invention provides a webpage view preloading method and device, electronic equipment and a storage medium, and relates to the technical field of mobile application development, in particular to the technical field of intelligent preloading. The method comprises the following steps: acquiring current context data; inputting the current context data into a first prediction model deployed at the client, and performing prediction through the first prediction model to obtain a preliminary prediction result; sending the preliminary prediction result and the enhanced context data to a second prediction model deployed in the server, and obtaining a final reasoning result through the second prediction model; and receiving a final reasoning result returned by the server, and determining a pre-loaded target webpage view according to the final reasoning result. According to the method, the user experience is remarkably improved, the waiting time is shortened, the resource utilization efficiency is optimized through accurate prediction and dynamic adjustment of the preloading strategy, unnecessary preloading operation is avoided, and efficient operation of the system and reasonable allocation of resources are ensured.

Description

Technical Field

[0001] The present disclosure relates to the field of mobile application development technology, specifically to the field of intelligent preloading technology, and more particularly to a method, device, electronic device, and storage medium for preloading a web page view. Background Art

[0002] In modern mobile apps, WebView (web view) is a commonly used technical component, primarily used to load and display web content, such as event pages, product details pages, and news pages. To improve the user experience, many apps use WebView preloading technology, which preloads web content before the user actually requests it. However, existing WebView preloading solutions have some significant issues that limit their effectiveness and user experience. Summary of the Invention

[0003] The present disclosure provides a method, device, electronic device, and storage medium for preloading a web page view.

[0004] According to one aspect of the present disclosure, a method for preloading a web page view is provided, which is applied to a client, and the method includes:

[0005] Acquire current context data, where the current context data includes the user's current behavior data and the user's current environment data;

[0006] Inputting the current context data into a first prediction model deployed on the client, and obtaining a preliminary prediction result through prediction by the first prediction model, wherein the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities;

[0007] Sending the preliminary prediction result and enhanced context data to a second prediction model deployed on a server, and obtaining a final inference result through the second prediction model, wherein the enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device status change trends;

[0008] Receive a final inference result returned from the server, and determine a preloaded target web page view according to the final inference result.

[0009] According to another aspect of the present disclosure, a method for preloading a web page view is provided, which is applied to a server, and the method includes:

[0010] Receiving a preliminary prediction result and enhanced context data sent from a client, the client being configured to obtain current context data, input the current context data into a first prediction model deployed on the client, and obtain a preliminary prediction result through prediction by the first prediction model; wherein the current context data includes the user's current behavior data and the user's current environment data, and the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities;

[0011] Inputting the preliminary prediction result and the enhanced context data into a second prediction model deployed on a server, and obtaining a final inference result through the second prediction model;

[0012] The final inference result is returned to the client, so that the client determines a preloaded target web page view according to the final inference result.

[0013] According to a third aspect of the present disclosure, a device for preloading a web page view is provided, the device comprising:

[0014] An acquisition module is used to acquire current context data, wherein the current context data includes the user's current behavior data and the user's current environment data;

[0015] a first prediction module, configured to input the current context data into a first prediction model deployed on the client, and obtain a preliminary prediction result through prediction by the first prediction model, wherein the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities;

[0016] a sending module, configured to send the preliminary prediction result and enhanced context data to a second prediction model deployed on a server, and obtain a final inference result through the second prediction model, wherein the enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device state change trends;

[0017] The loading module is used to receive the final inference result returned from the server and determine the preloaded target web page view according to the final inference result.

[0018] According to a fourth aspect of the present disclosure, a device for preloading a web page view is provided, the device comprising:

[0019] a receiving module, configured to receive preliminary prediction results and enhanced context data sent from a client, wherein the client is configured to obtain current context data, input the current context data into a first prediction model deployed on the client, and obtain preliminary prediction results through prediction by the first prediction model; wherein the current context data includes the user's current behavioral data and the user's current environment data, and the preliminary prediction results include web page views that the user may visit and their corresponding access probabilities;

[0020] A second prediction module, configured to input the preliminary prediction result and the enhanced context data into a second prediction model deployed on the server, and obtain a final inference result through the second prediction model;

[0021] The returning module is configured to return the final inference result to the client, so that the client determines a preloaded target web page view according to the final inference result.

[0022] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:

[0023] at least one processor; and

[0024] a memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the methods described in the above technical solutions.

[0026] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described above.

[0027] According to a seventh aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements any one of the methods described above when executed by a processor.

[0028] The present disclosure provides a method, apparatus, electronic device, and storage medium for preloading webpage views. This method obtains the user's current behavioral and environmental data as current context data and utilizes a first prediction model deployed on the client to quickly generate preliminary prediction results. The preliminary prediction results include the webpage views the user is likely to access and their access probabilities. This not only reduces reliance on the server but also improves system responsiveness, enabling preloading operations to more promptly respond to user needs. Furthermore, a second prediction model that sends the preliminary prediction results and enhanced context data to the server leverages the server's powerful computing power and more comprehensive data analysis capabilities, resulting in a more accurate final inference result. Ultimately, the target webpage view to be preloaded is determined based on the final inference result returned by the server, ensuring the accuracy and effectiveness of the preloading operation. This combination of features not only significantly improves the user experience and reduces wait time, but also optimizes resource utilization through accurate prediction and dynamic adjustment of preloading strategies, avoiding unnecessary preloading operations and ensuring efficient system operation and rational resource allocation.

[0029] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0031] Figure 1 is a schematic diagram of the steps of a method for preloading a web page view in an embodiment of the present disclosure;

[0032] Figure 2 is a schematic diagram of steps of a method for preloading a web page view in another embodiment of the present disclosure;

[0033] Figure 3 It is a schematic diagram of the overall process in the embodiment of the present disclosure;

[0034] Figure 4 A functional block diagram of a device for preloading a web page view in an embodiment of the present disclosure;

[0035] Figure 5 A functional block diagram of a device for preloading a web page view in another embodiment of the present disclosure;

[0036] Figure 6 It is a block diagram of an electronic device used to implement the method for preloading a web page view according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0038] In the prior art, WebView preloading usually adopts the following methods:

[0039] The first method is timed preloading. This method loads a set of web pages regularly in the background and caches the resources of these web pages. This method is generally used in scenarios such as news and event pages, and can reduce user waiting time to a certain extent. However, timed preloading has obvious limitations. For example, it only preloads within a specific time period and lacks flexibility. If the user's active behavior changes, time-based preloading may no longer be effective. In addition, if the preloaded data is not viewed or used by the user in a timely manner, it will lead to unnecessary performance consumption and power waste.

[0040] The second approach is rule-driven preloading. This approach sets fixed preloading rules based on business logic. For example, when a user opens the homepage, popular articles are preloaded; when a user enters a product category, the first few product detail pages are preloaded. While this approach can preload content based on certain user behaviors, it relies on fixed logic and lacks dynamic adjustment capabilities. Preloading tasks are too mechanical and unable to adapt to changes in user behavior in real time. This results in content not being loaded when the user needs it, and resources being occupied when the user doesn't need it, increasing the probability of loading invalid pages.

[0041] As can be seen, while existing WebView preloading technology has improved web page loading speeds to a certain extent, after review, we have found that existing preloading technologies have the following major problems: First, loading latency is high. Generally, WebView does not initiate network requests until the user clicks, resulting in long blank screens, which seriously affects the user experience. This delay not only increases user waiting time but can also lead to user churn. Second, it wastes resources. Existing WebView preloading methods typically preload a large number of web pages periodically, but most users may not access these pages. This preloading method not only wastes bandwidth resources but also increases device memory usage, potentially leading to performance degradation. Finally, existing preloading methods lack intelligent prediction. Existing solutions cannot accurately predict the web pages that users are about to visit. This results in preloading operations either being untimely and failing to meet user needs, or loading excessive and unnecessary content, further wasting resources. The lack of an intelligent prediction mechanism makes it difficult for preloading solutions to adapt to users' dynamic behavior and personalized needs.

[0042] In order to solve the above problems, the present disclosure provides a method for preloading a web page view. Figure 1 As shown, Figure 1 : is a schematic diagram of the steps of a method for preloading a web page view in an embodiment of the present disclosure, which is applied to a client and includes:

[0043] Step S101 : obtaining current context data, which includes the user's current behavior data and the user's current environment data.

[0044] Specifically, current context data refers to the comprehensive information collected about user behavior and the environment in which they are located at a specific moment. Specifically, the user's current behavioral data covers various operations of the user in the application, such as page browsing path, click behavior, dwell time, etc. These data can reflect the user's current interests and possible needs. The user's current environmental data includes time (such as whether it is a weekday or weekend, specifically morning or afternoon), geographic location (whether the user is at home, work or public place), network status (whether the user is connected to Wi-Fi or cellular network, and what is the network quality), device status (such as power, memory usage, whether the device is in the foreground or background), etc. These environmental information can help the system better understand the specific scenario of the user.

[0045] The implementation process of this solution includes collecting this data in real time through various sensors and APIs (Application Programming Interface) on the client side. For example, geographic location information is obtained through the device's positioning function, network status is obtained through the network framework, and the device's power and memory usage are obtained through the system API. At the same time, the user's behavior path and click behavior are recorded using tracking technology. These data are integrated into a structured contextual data model and then used for subsequent predictive analysis. In this way, the user's current behavior and environment can be fully captured, providing a rich information basis for subsequent preloading decisions, thereby achieving more accurate and personalized preloading services.

[0046] In step S102, the current context data is input into a first prediction model deployed on the client, and a preliminary prediction result is obtained through prediction by the first prediction model. The preliminary prediction result includes web page views that the user may visit and corresponding access probabilities.

[0047] Specifically, after obtaining the current context data, the current context data is input into the first prediction model. The first prediction model is a lightweight machine learning model deployed on the client (supporting Core ML). Its main function is to quickly perform preliminary inference based on the input current context data to predict the web page views that the user may visit and their corresponding access probabilities.

[0048] The specific implementation process of this solution includes obtaining the current context data and inputting it into the first prediction model. The first prediction model analyzes this data to identify web page views that the user may be interested in and calculates an access probability for each potential target web page view. The access probability is a value between 0 and 1, indicating the likelihood that the user will access the web page view. For example, if the user is currently browsing a work-related folder and it is a weekday morning, the first prediction model may predict that the probability of the user accessing a specific work document is 0.8, while the probability of accessing other unrelated web pages is lower.

[0049] In this way, the first prediction model can quickly generate preliminary prediction results on the client, providing an important basis for subsequent preloading decisions. This preliminary prediction not only helps the system quickly respond to changes in user behavior, but also reduces dependence on server-side resources to a certain extent, thereby improving overall system efficiency and user experience.

[0050] In step S103, the preliminary prediction results and enhanced context data are sent to the second prediction model deployed on the server, and the final inference result is obtained through the second prediction model. The enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device status change trends.

[0051] Specifically, the initial prediction result refers to the prediction information generated by the client's first prediction model based on the current context data, including the web page views that the user is likely to visit and their corresponding access probabilities. Enhanced context data builds on the initial context data by aggregating context data from multiple moments and combining it with the user's historical behavior patterns and device status change trends to generate more comprehensive and in-depth data. This data can provide richer information to the second prediction model, helping it make more accurate decisions.

[0052] The specific implementation process of this solution includes that after the client obtains the preliminary prediction results, it will further collect and process enhanced contextual data. This includes analyzing user behavior patterns in different time periods, such as the differences in user behavior on weekdays and weekends, and changing trends in device status, such as power consumption speed and network connection stability. After this information is integrated, it is sent together with the preliminary prediction results to the second prediction model deployed on the server. The second prediction model is usually a more complex deep learning model, which uses this comprehensive data for further analysis and reasoning, and ultimately generates more accurate reasoning results. This final reasoning result will serve as the basis for preloading decisions, helping the system determine whether to preload and which web page views to preload, thereby optimizing the user experience and improving resource utilization efficiency.

[0053] Step S104: receiving the final inference result returned from the server, and determining the preloaded target web page view according to the final inference result.

[0054] Specifically, the final inference result is the prediction information generated by the server-side second prediction model after comprehensively analyzing the preliminary prediction results and enhanced context data sent by the client. It contains the web views that the user is likely to visit and their corresponding access probabilities. The target web views to be preloaded are determined based on this prediction information, namely the web views that the user is most likely to visit. These views are preloaded to the client to optimize the user experience and reduce wait time.

[0055] The specific implementation process of this solution involves the client sending preliminary prediction results and enhanced context data to the server and then waiting for the server to return the final inference results. The server's secondary prediction model uses its powerful computing power and more comprehensive data analysis capabilities to deeply process the information provided by the client and generate more accurate prediction results. These results not only consider the user's current behavior and environmental status, but also incorporate historical user behavior patterns and device status trends, thereby more accurately predicting user needs.

[0056] After receiving the final inference result, the client will decide whether to preload based on the preset threshold (for example, the access probability exceeds a certain set value) and the device resource status (such as sufficient battery power, low memory usage, etc.). If the access probability in the final inference result exceeds the preset threshold and the device resource status meets the preset conditions, the client will determine to preload and select the corresponding candidate web page view as the preload target. This process not only improves the accuracy of preloading, but also ensures the efficient operation of the system and the rational use of resources by dynamically adjusting the preloading strategy.

[0057] The present disclosure provides a method, device, electronic device, and storage medium for preloading web page views. The present disclosure obtains the user's current behavioral data and environmental data as current context data and uses a first prediction model deployed on the client to quickly generate preliminary prediction results. The preliminary prediction results include the web page views that the user may access and their access probabilities. This not only reduces reliance on the server but also improves the system's response speed, enabling preloading operations to respond to user needs more promptly. Furthermore, the preliminary prediction results and enhanced context data are sent to the server's second prediction model, which can fully utilize the server's powerful computing power and more comprehensive data analysis capabilities to obtain a more accurate final inference result. Ultimately, the target web page view to be preloaded is determined based on the final inference result returned by the server, ensuring the accuracy and effectiveness of the preloading operation. The combination of these features not only significantly improves the user experience and reduces waiting time, but also optimizes resource utilization efficiency through accurate prediction and dynamic adjustment of preloading strategies, avoiding unnecessary preloading operations and ensuring efficient system operation and rational resource allocation.

[0058] In some optional embodiments, inputting current context data into a first prediction model deployed on a client includes:

[0059] Get historical context data;

[0060] Compare the current context data with the historical context data to extract the changed data and obtain differential data;

[0061] The differential data is input to a first prediction model deployed on the client.

[0062] Specifically, historical context data refers to user behavior and environmental information collected and stored before the current moment, which reflects the user's past usage patterns and preferences. Current context data refers to user behavior and environmental information collected at the current moment, which is used to reflect the user's current status and needs. By comparing current context data with historical context data, changes in user behavior and environment can be identified, thereby extracting differential data. Differential data refers to the difference between current context data and historical context data. This difference information usually includes changes in user behavior patterns or updates to environmental status.

[0063] The implementation of this solution involves first acquiring historical context data, which may be stored in a local database or cloud server. Next, current context data is collected, including user behavior data (such as page browsing paths, click behavior, and dwell time) and environmental data (such as time, location, network status, and device battery level). By comparing the current context data with the historical context data, changes can be identified, generating differential data. Since only the changed data is further processed, extracting differential data not only reduces data transmission but also protects user privacy. Finally, the differential data is input into a first prediction model deployed on the client. This first prediction model is a lightweight machine learning model that runs quickly on the client and predicts the webpage views a user is likely to visit and their probability of visiting them based on the differential data. This differential data-based prediction approach not only improves prediction efficiency but also, by focusing on recent changes in user behavior and environment, more accurately captures users' immediate needs. This approach enables rapid generation of preliminary prediction results on the client, providing users with more personalized and efficient services while reducing reliance on server resources.

[0064] In this way, by obtaining historical context data and comparing the current context data with the historical context data to extract the changed data (i.e., differential data), the dynamic changes in user behavior and environment can be accurately captured, and repeated processing of redundant data can be avoided, thereby improving the efficiency of data processing and protecting user privacy. Furthermore, the differential data is input into the first prediction model deployed on the client, so that the model can quickly make preliminary predictions based on these changing key information, which not only reduces dependence on the server side, but also speeds up the preloading decision-making process, significantly improving the system's responsiveness and user experience. This series of operations not only optimizes the efficiency of preloading, but also ensures the timeliness and accuracy of preloading decisions, providing users with more personalized and efficient services.

[0065] In some optional embodiments, determining the preloaded target web page view according to the final inference result includes:

[0066] Based on the final inference result, combined with the preset threshold and device resource status, it is determined whether to preload and the target web page view to be preloaded.

[0067] Specifically, the final inference result refers to the prediction information generated by the second prediction model on the server side after comprehensively analyzing the preliminary prediction results and enhanced context data sent by the client, which includes the web page views that the user may visit and their corresponding access probabilities. The preset threshold refers to a probability threshold set in advance, which is used to determine whether the possibility of a user accessing a certain web page view is high enough, thereby deciding whether to preload it. The device resource status refers to the status information of the current device, such as power, memory usage, and network connection. This information is used to evaluate whether the device has sufficient resources to support the preloading operation.

[0068] The specific implementation process of this solution includes that after the client receives the final inference result returned by the server, it will make a preloading decision based on the preset threshold and the device resource status. If the access probability in the final inference result exceeds the preset threshold, and the device resource status meets the preset conditions (such as sufficient power, low memory usage, and stable network connection), the system will determine to preload and select the corresponding candidate web page view as the preloading target. This decision-making process not only takes into account the user's behavior prediction, but also takes into account the actual operating status of the device, ensuring that the preloading operation meets user needs and does not negatively affect device performance. In this way, the system can achieve efficient and accurate preloading, optimize the user experience, and avoid unnecessary waste of resources.

[0069] In this way, by determining whether to preload and the target web page view to be preloaded based on the final reasoning result, combined with the preset threshold and device resource status, this solution can achieve efficient and accurate preloading decisions. Specifically, the final reasoning result provides an accurate prediction based on user behavior and contextual data, ensuring that the target web page view to be preloaded is highly relevant to user needs. Secondly, combined with the preset threshold, web page views with a low access probability can be effectively filtered out, avoiding unnecessary preloading operations, thereby saving device resources and network bandwidth. In addition, considering the device resource status (such as power, memory usage, network connection quality) can ensure that the preloading operation will not have a negative impact on device performance, while avoiding preloading under resource-constrained conditions, thereby improving user experience. This decision-making mechanism that comprehensively considers user needs, prediction probability and device status not only improves the accuracy and efficiency of preloading, but also optimizes resource utilization, ensuring the overall performance of the system and user satisfaction.

[0070] In some optional embodiments, determining whether to preload and the target web page view to be preloaded based on the final inference result, in combination with a preset threshold and device resource status, includes:

[0071] If the access probability in the final inference result exceeds a preset threshold and the device resource status meets the preset conditions, a preloading operation is determined to be performed, and a web page view that meets the conditions is selected as a target page view for preloading.

[0072] Specifically, the final inference result refers to the prediction information obtained after comprehensive analysis by the second prediction model on the server side, which includes the web page views that the user may visit and their corresponding access probabilities. The preset threshold is a pre-set probability value, which is used to determine whether the possibility of a user accessing a certain web page view is high enough, thereby deciding whether to trigger the preloading operation. The device resource status refers to the current operating status of the device, including power, memory usage, network connection quality, etc. This status information is used to evaluate whether the device has sufficient resources to support the preloading operation. The preset conditions refer to a series of conditions that the device resource status needs to meet, such as sufficient power, low memory usage, stable network connection, etc.

[0073] The specific implementation process of this solution includes first determining whether the access probability in the final inference result exceeds a preset threshold. If the access probability is higher than the threshold, it means that the user is more likely to access the web view, and the preloading operation has a higher value. At the same time, check whether the device resource status meets the preset conditions. For example, if the device has sufficient power, low memory usage, and a stable network connection, it is considered that the device has sufficient resources to support the preloading operation. Only when the access probability exceeds the threshold and the device resource status meets the preset conditions will the preloading operation be determined, and the web view that meets the conditions will be selected from the candidate web views as the target page view for preloading.

[0074] In this way, this solution not only accurately preloads apps based on actual user needs but also dynamically adjusts the preloading strategy to suit the device's current state, optimizing the user experience while avoiding performance issues caused by insufficient device resources. This decision-making mechanism, which comprehensively considers user behavior prediction and device status, significantly improves the efficiency and reliability of preloading, ensuring efficient system operation and user satisfaction.

[0075] In this way, by determining to preload only when the access probability in the final inference result exceeds a preset threshold and the device resource status meets the preset conditions, and selecting the web page view that meets the conditions as the preload target page view, accurate and efficient preloading decisions can be achieved. This mechanism ensures that preloading operations are only performed when the user is likely to access a specific web page view and the device has sufficient resources to support it, thereby avoiding unnecessary preloading, reducing resource waste and potential impacts on device performance. At the same time, it also improves the accuracy and success rate of preloading, ensuring that users can quickly access relevant web views when needed, significantly improving the user experience.

[0076] In some optional embodiments, the method further comprises:

[0077] If the user is currently in the information browsing stage, the preloading action is delayed until the user's behavior indicates an operation to access a specific page.

[0078] Specifically, the information browsing stage refers to the state in which the user is currently browsing information but has not yet expressed a clear intention to visit a page. For example, a user may be browsing a page containing multiple links but has not yet clicked on any of them. Delayed preloading refers to temporarily not performing preloading operations, but waiting for further user behavioral signals to more accurately determine the user's actual needs. Specific page access actions refer to actions that show a clear intention to visit a page, such as clicking a link or button.

[0079] The specific implementation process of this solution includes detecting the user's behavioral data to determine whether the user is in the information browsing stage. If the user's current behavior indicates that he or she is browsing information but has not yet made a clear access intention, the preloading action will be delayed. Then, the user's behavior is continuously detected until the user's behavior clearly indicates that he or she is about to visit a specific page (for example, the user hovers the mouse over a link for a long time, or begins to scroll the page to view the content of a specific area). Once such a specific page access operation is detected, the preloading action will be triggered immediately to load the target page that the user may visit.

[0080] This mechanism aims to avoid unnecessary preloading when the user hasn't explicitly expressed a need, thereby conserving device resources and network bandwidth. Furthermore, by waiting for user behavioral signals, it can more accurately predict the user's actual needs, improving the accuracy and efficiency of preloading. This approach not only optimizes resource utilization but also enhances the user experience, ensuring that users can quickly access relevant pages when they need them.

[0081] In this way, by delaying the preloading action when the user is in the information browsing stage and waiting for the user's behavior to indicate the operation of accessing a specific page, the accuracy and efficiency of preloading can be significantly improved. This mechanism avoids unnecessary preloading when the user has not clearly expressed the need, thereby saving device resources and network bandwidth and reducing the potential impact on device performance. At the same time, by waiting for the user's behavioral signals, the user's actual needs can be predicted more accurately, ensuring that the preloading operation is highly consistent with the user's intention, thereby improving the user experience and ensuring that the user can quickly access the relevant pages when needed. This method not only optimizes resource utilization, but also improves the success rate of preloading, reduces invalid loading, and ensures the efficient operation of the system and user satisfaction.

[0082] In some optional embodiments, the method further comprises:

[0083] After the target page view is loaded, the user interaction feedback option is displayed on the display page, the user's operation on the interaction feedback option is received, the feedback data is obtained, and the feedback data is sent to the server.

[0084] Specifically, a target page view refers to web content that is predicted and preloaded based on user behavior and contextual data. This content is considered the page most likely to be visited by the user. User interaction feedback options are the feedback options presented to the user on the page after the target page view has loaded, such as "Is the loading speed satisfactory?" and "Did the required pages load in advance?" Feedback data is the data generated after the user responds to these feedback options, reflecting the user's satisfaction with the preloading operation and their actual needs.

[0085] The specific implementation process of this solution involves displaying user interaction feedback options on the page after the target page view has loaded. These options typically appear in the form of simple interactive interfaces such as buttons, pop-ups, or sliders. Users can click, slide, or select the feedback options to express their evaluation of the preloading effect. After receiving the user's operation, feedback data is generated and sent to the server. After receiving the feedback data, the server can further analyze user satisfaction, optimize the preloading strategy, and improve the system's prediction accuracy and user experience.

[0086] In this way, our solution not only accurately preloads apps based on user behavior and contextual data, but also dynamically adjusts preloading strategies based on user feedback, ensuring that preloading operations meet actual user needs. This closed-loop feedback mechanism enables continuous system optimization, improving preloading accuracy and efficiency while enhancing user trust and satisfaction.

[0087] This solution enables real-time collection and analysis of user feedback by displaying user interaction feedback options after the target page view has loaded, receiving user actions to obtain feedback data, and then sending this data to the server. This mechanism not only allows users to directly express their satisfaction with the preloading effect but also provides a basis for continuous optimization. The server can adjust the preloading strategy based on user feedback data, improving prediction accuracy and overall system performance. This closed-loop feedback mechanism makes preloading operations more tailored to users' actual needs, enhances the user experience, and also improves the system's intelligence and resource utilization efficiency.

[0088] This disclosure provides a method for preloading a web page view. Figure 2 , Figure 21 is a schematic diagram of the steps of a method for preloading a web page view in another embodiment of the present disclosure, the method being applied to a server and comprising:

[0089] Step S201, receiving the preliminary prediction results and enhanced context data sent from the client, the client is used to obtain the current context data, input the current context data into the first prediction model deployed on the client, and obtain the preliminary prediction results through the prediction of the first prediction model; wherein, the current context data includes the user's current behavior data and the user's current environment data, and the preliminary prediction results include the web page views that the user may visit and the corresponding access probability.

[0090] Specifically, the client refers to the application on the device used by the user (such as a mobile phone, tablet or computer), which is responsible for collecting the user's behavioral data and environmental data and generating current context data. The current context data includes the user's current behavioral data (such as page browsing path, click behavior, and dwell time) and environmental data (such as time, geographic location, network status, and device power). These data are input into the first prediction model deployed on the client. The model is a lightweight machine learning model that can quickly process the current context data and generate preliminary prediction results. The preliminary prediction results include the web page views that the user may visit and their corresponding access probabilities. This information reflects the possibility of the user visiting a specific web page in the current context.

[0091] The specific implementation process of this solution includes that the client first collects current context data through various sensors and APIs. These data reflect the user's current behavior and environment. Then, the client inputs this data into the first prediction model. The first prediction model analyzes this data to predict the web page views that the user may visit and their access probability. The preliminary prediction results not only take into account the user's current behavior, but also combine environmental factors to make the prediction more in line with the user's actual needs. Finally, the client sends the preliminary prediction results and enhanced context data (which may include historical behavior patterns and device status change trends) to the server for further analysis and optimization. In this way, this solution can quickly generate preliminary predictions on the client side, while providing rich data support for in-depth analysis on the server side, thereby achieving more accurate preloading decisions.

[0092] Step S202: Input the preliminary prediction result and the enhanced context data into a second prediction model deployed on the server, and obtain the final inference result through the second prediction model.

[0093] Specifically, the preliminary prediction result refers to the prediction information generated by the client's first prediction model based on the current context data, including the web page views that the user is likely to visit and their corresponding access probabilities. Enhanced context data builds on the preliminary context data by aggregating context data from multiple moments and combining it with the user's historical behavior patterns and device status change trends to generate more comprehensive and in-depth data. This data can provide richer information to the prediction model, helping it make more accurate decisions.

[0094] The specific implementation process of this solution involves the client sending the initial prediction results and enhanced context data to the server. The second prediction model deployed on the server is a more complex deep learning model. It uses its powerful computing power and more comprehensive data analysis capabilities to further process and analyze the data sent by the client. The second prediction model not only considers the access probability in the initial prediction results, but also incorporates historical behavior patterns and device status change trends in the enhanced context data to generate a more accurate final inference result. The final inference result includes a more precise view of the webpage that the user is likely to visit and its access probability. This information will serve as an important basis for preloading decisions.

[0095] In this way, this solution leverages the strengths of both the client and server to achieve hierarchical prediction. The client's first prediction model quickly generates preliminary predictions, while the server's second prediction model performs more in-depth analysis and processing to generate the final inference results. This hierarchical prediction mechanism not only improves prediction accuracy and reliability, but also optimizes overall system performance and resource efficiency.

[0096] Step S203 : returning the final inference result to the client, so that the client determines the target web page view to be preloaded according to the final inference result.

[0097] Specifically, the final inference result refers to the prediction information generated by the server-side second prediction model after comprehensively analyzing the preliminary prediction results and enhanced context data sent by the client. This information includes the web page views that the user may visit and their corresponding access probabilities, reflecting the likelihood of the user visiting a specific web page in the current context. The preloaded target web page views are the web page views that the system determines are most likely to be visited by the user based on the final inference result. These views are preloaded to the client to optimize the user experience and reduce wait time.

[0098] The specific implementation process of this solution includes that after the server completes the reasoning of the second prediction model, it returns the final reasoning result to the client. After receiving these results, the client will decide whether to preload based on the preset threshold (for example, the access probability exceeds a certain set value) and the device resource status (such as sufficient power, low memory usage, etc.). If the access probability in the final reasoning result exceeds the preset threshold and the device resource status meets the preset conditions, the client will determine to preload and select the corresponding candidate web page view as the preloading target. This process not only takes into account the user's behavior prediction, but also takes into account the actual operating status of the device to ensure that the preloading operation meets user needs and does not have a negative impact on device performance.

[0099] In this way, by receiving the preliminary prediction results and enhanced context data sent by the client, this solution implements a hierarchical prediction mechanism, in which the client's first prediction model quickly generates preliminary prediction results based on the current context data (including user behavior and environmental information), while the server's second prediction model further analyzes this data to obtain a more accurate final inference result. Finally, the final inference result is returned to the client, allowing the client to determine the target web page view to be preloaded accordingly. This process not only utilizes the client's real-time data and the server's powerful computing power, but also improves the accuracy and efficiency of preloading through hierarchical prediction, reduces unnecessary preloading, saves resources, and improves the user experience, ensuring that users can quickly access relevant web page views when needed. In addition, this mechanism can also dynamically adapt to changes in user behavior and fluctuations in device status, further optimize preloading strategies, improve the system's intelligence level and resource utilization efficiency, and provide users with more personalized and efficient services.

[0100] In some optional embodiments, the method further comprises:

[0101] Receive feedback data from the client;

[0102] The second prediction model is optimized and updated according to the feedback data.

[0103] Specifically, feedback data refers to user evaluations and feedback on preloading operations, reflecting user satisfaction with the preloading effect and actual needs. The second prediction model is a deep learning model deployed on the server side. It is responsible for further analyzing the preliminary prediction results and enhanced context data sent by the client to generate the final inference results.

[0104] The specific implementation process of this solution involves the client displaying interactive feedback options after the user completes accessing the preloaded page, such as "Is the loading speed satisfactory?" or "Did the required pages load in advance?" The user interacts with these feedback options by clicking, swiping, or selecting, generating feedback data. The client sends this feedback data to the server. After receiving the feedback data, the server optimizes and updates the second prediction model. This optimization and update process typically involves adjusting model parameters, updating the training dataset, or refining the model's algorithmic logic to improve the model's prediction accuracy and adaptability.

[0105] In this way, this solution can dynamically adjust preloading strategies based on actual user experience. User feedback provides valuable real-time data, enabling the system to continuously learn and improve, thereby better meeting user needs and enhancing the user experience. This closed-loop feedback mechanism not only improves the accuracy and efficiency of preloading, but also enhances the system's intelligence, ensuring that preloading operations are highly consistent with actual user needs, while also optimizing resource utilization and reducing unnecessary preloading operations.

[0106] In this way, by receiving feedback data from the client and optimizing and updating the second prediction model, this solution implements a dynamic adjustment mechanism based on the user's actual experience. This process not only continuously improves the preloading strategy based on real-time user feedback, improving the accuracy and adaptability of the prediction, but also enhances the intelligence level of the system. User feedback, as valuable real-time data, directly reflects the satisfaction and actual needs of the preloading operation, allowing the system to more accurately meet user expectations, thereby significantly improving the user experience. At the same time, this closed-loop feedback mechanism optimizes resource utilization, reduces unnecessary preloading operations, ensures the efficient operation of the system, and further improves overall performance and user satisfaction.

[0107] In order to understand the present application as a whole, see Figure 3 As shown, Figure 3 This is a schematic diagram of the overall process of the embodiment of the present disclosure. The flow chart includes three main stages:

[0108] Step S301, data preprocessing stage;

[0109] The data preprocessing stage includes:

[0110] Collect tracking data, that is, first collect user behavior data in the application, which is usually obtained through tracking technology. Next, sample user behavior, and sample user behavior from the collected data for further analysis. Determine whether it is in the background, that is, determine whether the current application is running in the background. If it is running in the background, store the data in the local database so that it can be processed when the application returns to the foreground. If it is not running in the background, proceed to the next step. Synchronize the backend, synchronize the collected data to the backend server, so that the data synchronized to the backend can be used to train the prediction model and predict the user's future behavior.

[0111] Step S302, pre-processing decision stage;

[0112] During the preprocessing decision phase, the current context data is first obtained. This context data includes the user's current behavior and environment data. A preloading strategy is then used to determine whether to preload the page. The preloading strategy is the web view preloading method mentioned above. Since the web view preloading method has been described in detail above, it will not be repeated here. If the preloading conditions are met, the preloading operation is executed. Otherwise, the process enters a suspended waiting state until the conditions are met.

[0113] Step S303, feedback learning stage;

[0114] During the feedback learning phase, when a user opens a page, the target page content is loaded and the user is provided with interactive feedback options, through which they can provide feedback on loading speed and content relevance. The system then determines whether the feedback is negative, checking whether the user's feedback is negative. If so, the feedback data is synchronized with the backend for model optimization. If not, the system checks whether the page opens normally. If so, the preprocessing results are sent back to the backend for further optimization of the preprocessing strategy. If the page does not open normally, the system identifies the issue and makes appropriate adjustments.

[0115] The entire flowchart illustrates a closed-loop system where user feedback is used to continuously optimize prediction models and preprocessing strategies to improve application performance and user experience. This enables more intelligent prediction of user needs, reduces resource waste, and improves loading efficiency.

[0116] The following describes an embodiment of the device of the present application, which can be used to execute the method for preloading a web page view in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for preloading a web page view in the above embodiment of the present application.

[0117] The present disclosure also provides a web page view preloading device 400, such as Figure 4 Shown, including:

[0118] The acquisition module 401 is used to acquire current context data, which includes the user's current behavior data and the user's current environment data;

[0119] A first prediction module 402 is configured to input current context data into a first prediction model deployed on the client, and obtain a preliminary prediction result through prediction by the first prediction model. The preliminary prediction result includes web page views that the user may visit and corresponding access probabilities;

[0120] A sending module 403 is configured to send the preliminary prediction result and enhanced context data to a second prediction model deployed on the server, and obtain a final inference result through the second prediction model. The enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device status change trends.

[0121] The loading module 404 is configured to receive the final inference result returned from the server and determine a target web page view to be preloaded according to the final inference result.

[0122] In some optional embodiments, the first prediction module 402 inputs the current context data into a first prediction model deployed on the client, including:

[0123] Get historical context data;

[0124] Compare the current context data with the historical context data to extract the changed data and obtain differential data;

[0125] The differential data is input to a first prediction model deployed on the client.

[0126] In some optional embodiments, the loading module 404 determines the target web page view to be preloaded according to the final inference result, including:

[0127] Based on the final inference result, combined with the preset threshold and device resource status, it is determined whether to preload and the target web page view to be preloaded.

[0128] In some optional embodiments, the loading module 404 determines whether to preload and the target web page view to be preloaded based on the final inference result, a preset threshold, and the device resource status, including:

[0129] If the access probability in the final inference result exceeds a preset threshold and the device resource status meets the preset conditions, a preloading operation is determined to be performed, and a web page view that meets the conditions is selected as a target page view for preloading.

[0130] In some optional embodiments, the loading module 404 is further configured to:

[0131] If the user is currently in the information browsing stage, the preloading action is delayed until the user's behavior indicates an operation to access a specific page.

[0132] In some optional embodiments, the device also includes a feedback module for displaying user interaction feedback options on the display page after the target page view is loaded, receiving user operations performed on the interaction feedback options, obtaining feedback data, and sending the feedback data to the server.

[0133] The present disclosure also provides a web page view preloading device 500, such as Figure 5 Shown, including:

[0134] Receiving module 501 is configured to receive preliminary prediction results and enhanced context data sent from a client. The client is configured to obtain current context data, input the current context data into a first prediction model deployed on the client, and obtain preliminary prediction results through prediction by the first prediction model. The current context data includes the user's current behavior data and the user's current environment data. The preliminary prediction results include web page views that the user may visit and their corresponding access probabilities.

[0135] A second prediction module 502 is configured to input the preliminary prediction result and the enhanced context data into a second prediction model deployed on the server, and obtain a final inference result through the second prediction model;

[0136] The return module 503 is configured to return the final inference result to the client, so that the client determines a preloaded target web page view according to the final inference result.

[0137] In some optional embodiments, the receiving module 501 is further configured to:

[0138] Receive feedback data from the client;

[0139] The second prediction model is optimized and updated according to the feedback data.

[0140] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0141] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0142] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0143] like Figure 6 As shown, electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of device 600 can also be stored in RAM 603. Computing unit 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0144] Various components in device 600 are connected to I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 608, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0145] The computing unit 601 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the preloading method of the web page view. For example, in some embodiments, the preloading method of the web page view can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the applet distribution described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the preloading method of the web page view by any other appropriate means (e.g., by means of firmware).

[0146] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable web page view preloading device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0148] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0151] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0152] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0153] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for preloading a web page view, applied to a client, wherein: The method comprises: Acquire current context data, where the current context data includes the user's current behavior data and the user's current environment data; Inputting the current context data into a first prediction model deployed on the client, and obtaining a preliminary prediction result through prediction by the first prediction model, wherein the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities; Sending the preliminary prediction result and enhanced context data to a second prediction model deployed on a server, and obtaining a final inference result through the second prediction model, wherein the enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device status change trends; Receive a final inference result returned from the server, and determine a preloaded target web page view according to the final inference result.

2. The method according to claim 1, wherein Inputting the current context data into a first prediction model deployed on the client includes: Get historical context data; Comparing the current context data with the historical context data to extract changed data and obtain differential data; The differential data is input into a first prediction model deployed on the client.

3. The method according to claim 1, wherein Determining the preloaded target web page view according to the final inference result includes: According to the final inference result, combined with a preset threshold and device resource status, it is determined whether to preload and the target web page view to be preloaded.

4. The method according to claim 3, wherein: The determining whether to preload and the target webpage view to be preloaded based on the final inference result, in combination with a preset threshold and device resource status, includes: If the access probability in the final inference result exceeds the preset threshold and the device resource status meets the preset conditions, it is determined to perform a preloading operation and select a web page view that meets the conditions as a target page view for preloading.

5. The method according to claim 3, wherein The method further comprises: If the user is currently in the information browsing stage, the preloading action is delayed until the user's behavior indicates an operation to access a specific page.

6. The method according to any one of claims 1 to 5, wherein: The method further comprises: After the target page view is loaded, the user interaction feedback option is displayed on the display page, the user's operation on the interaction feedback option is received, feedback data is obtained, and the feedback data is sent to the server.

7. A method for preloading a web page view, applied to a server, wherein: The method comprises: Receiving a preliminary prediction result and enhanced context data sent from a client, the client being configured to obtain current context data, input the current context data into a first prediction model deployed on the client, and obtain a preliminary prediction result through prediction by the first prediction model; wherein the current context data includes the user's current behavior data and the user's current environment data, and the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities; Inputting the preliminary prediction result and the enhanced context data into a second prediction model deployed on a server, and obtaining a final inference result through the second prediction model; The final inference result is returned to the client, so that the client determines a preloaded target web page view according to the final inference result.

8. The method according to claim 7, wherein: The method further comprises: receiving feedback data from the client; The second prediction model is optimized and updated according to the feedback data.

9. A preloading device for a web page view, wherein: The device comprises: An acquisition module is used to acquire current context data, wherein the current context data includes the user's current behavior data and the user's current environment data; a first prediction module, configured to input the current context data into a first prediction model deployed on the client, and obtain a preliminary prediction result through prediction by the first prediction model, wherein the preliminary prediction result includes web page views that the user may visit and corresponding access probabilities; a sending module, configured to send the preliminary prediction result and enhanced context data to a second prediction model deployed on a server, and obtain a final inference result through the second prediction model, wherein the enhanced context data is generated by aggregating context data at multiple moments and combining historical behavior patterns and device state change trends; The loading module is used to receive the final inference result returned from the server and determine the preloaded target web page view according to the final inference result.

10. A preloading device for a web page view, wherein: The device comprises: a receiving module, configured to receive preliminary prediction results and enhanced context data sent from a client, wherein the client is configured to obtain current context data, input the current context data into a first prediction model deployed on the client, and obtain preliminary prediction results through prediction by the first prediction model; wherein the current context data includes the user's current behavioral data and the user's current environment data, and the preliminary prediction results include web page views that the user may visit and their corresponding access probabilities; A second prediction module, configured to input the preliminary prediction result and the enhanced context data into a second prediction model deployed on the server, and obtain a final inference result through the second prediction model; The returning module is configured to return the final inference result to the client, so that the client determines a preloaded target web page view according to the final inference result.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images