Responsive component dynamic arrangement method and device, electronic equipment and storage medium
The method and device use a component prediction model trained on user interaction data to optimize component loading in Web applications, addressing performance inefficiencies by predicting and preloading components based on usage patterns and performance data, thus enhancing loading efficiency.
Patent Information
- Application Number
- CN202411167533.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-20
AI Technical Summary
Existing Web applications face challenges in component performance optimization as they scale, particularly with frameworks like Vue.js, leading to inefficiencies in loading and delays.
A method and device that utilize a component prediction model trained on time series data from user interactions to predict and preload components, optimizing their sequence and priority based on usage patterns and performance data, thereby improving loading efficiency.
Enhances component loading performance by predicting user needs and preloading components, reducing delays and optimizing the loading process.
Smart Images
Figure CN119166477A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of page display, and in particular to a responsive component dynamic arrangement method, device, electronic device and storage medium. Background Art
[0002] In recent years, with the rapid development of Internet technology, Web applications have become more and more complex; Vue.js, as a popular front-end framework, is favored by developers for its responsive data binding and component system, but as the scale of applications expands, component performance optimization has become a major challenge in development. Summary of the invention
[0003] The main purpose of the present invention is to propose a responsive component dynamic orchestration method, device, electronic device and storage medium, aiming to solve the problem of how to improve component performance optimization in the prior art.
[0004] To achieve the above object, the present invention provides a responsive component dynamic arrangement method, the method comprising the steps of:
[0005] Acquire time series data generated by user operations on the page, and train the component prediction model based on the time series data to obtain a trained component prediction model;
[0006] When triggering a page jump, determine the target loading page for the page jump;
[0007] Obtaining page data corresponding to the target loading page, and inputting the page data into the trained component prediction model;
[0008] Running the trained component prediction model to obtain a target component corresponding to the target loading page;
[0009] The target component is loaded in the target loading page.
[0010] Optionally, the training of the component prediction model based on the time series data to obtain the trained component prediction model includes:
[0011] Obtaining page access history, component usage frequency, and user operation series in the time series data;
[0012] Generate training data based on the page access history, component usage frequency, and user operation series;
[0013] The component prediction model is trained using the training data to obtain a trained component prediction model.
[0014] Optionally, after loading the target component in the target loading page, the method includes:
[0015] Obtaining loading performance data of the target loading page;
[0016] The component prediction model after the training is completed is updated through the loading performance data.
[0017] Optionally, updating the trained component prediction model by using the loading performance data includes:
[0018] Obtaining the first screen loading time corresponding to each of the target components in the loading performance data;
[0019] Generate update data based on the first screen loading time and the target component;
[0020] The component prediction model after the training is completed is updated through the update data.
[0021] Optionally, loading the target component in the target loading page includes:
[0022] Perform dependency tracking on each of the target components to obtain a component priority corresponding to each of the target components;
[0023] In the target loading page, each target component is loaded in sequence based on the component priority.
[0024] Optionally, performing dependency tracing on each of the target components to obtain a component priority corresponding to each of the target components includes:
[0025] Obtaining historical loading data corresponding to the target loading page;
[0026] Determining the interactive response time corresponding to each of the target components in the historical loading data;
[0027] Dependency tracking is performed on the target components based on the interaction response time to obtain component priorities corresponding to the target components.
[0028] Optionally, loading the target component in the target loading page includes:
[0029] Obtaining the preset priority corresponding to each of the target components;
[0030] In the target loading page, each target component is loaded in sequence based on the preset priority.
[0031] To achieve the above object, the present invention further provides a responsive component dynamic arrangement device, the responsive component dynamic arrangement device comprising:
[0032] A first acquisition module is used to acquire time series data generated by a user's operation on a page, and train a component prediction model based on the time series data to obtain a trained component prediction model;
[0033] A first determination module is used to determine a target loading page for page jump when page jump is triggered;
[0034] A second acquisition module is used to acquire page data corresponding to the target loading page, and input the page data into the trained component prediction model;
[0035] A first running module is used to run the trained component prediction model to obtain a target component corresponding to the target loading page;
[0036] The first loading module is used to load the target component in the target loading page.
[0037] To achieve the above objectives, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the responsive component dynamic orchestration method as described above when executed by the processor.
[0038] To achieve the above objectives, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the responsive component dynamic orchestration method as described above are implemented.
[0039] The present invention proposes a responsive component dynamic arrangement method, device, electronic device and storage medium, which obtains time series data generated by user operations on a page, and trains a component prediction model based on the time series data to obtain a trained component prediction model; when a page jump is triggered, the target loading page of the page jump is determined; the page data corresponding to the target loading page is obtained, and the page data is input into the trained component prediction model; the trained component prediction model is run to obtain a target component corresponding to the target loading page; and the target component is loaded in the target loading page. The component prediction model is trained by time series data, so that the component prediction model can predict the components that need to be loaded based on the actual behavior of the user, so that when the page is loaded, the components can be preloaded, thereby improving the loading performance of the components and reducing loading delays. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0042] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0043] Figure 1 It is a flowchart of the first embodiment of the method for dynamic arrangement of responsive components of the present invention;
[0044] Figure 2 A schematic diagram of the training steps of the component prediction model in the responsive component dynamic orchestration method of the present invention;
[0045] Figure 3 A schematic diagram of updating a component prediction model in the responsive component dynamic orchestration method of the present invention;
[0046] Figure 4 A schematic diagram of loading a target component in the responsive component dynamic arrangement method of the present invention;
[0047] Figure 5 It is a schematic diagram of the module structure of the electronic device of the present invention. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0049] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present application.
[0051] The present invention provides a responsive component dynamic arrangement method, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a method for dynamic arrangement of responsive components according to the present invention, wherein the method comprises the following steps:
[0052] Step S10, obtaining time series data generated by the user's operation on the page, and training the component prediction model based on the time series data to obtain a trained component prediction model;
[0053] The pages in this embodiment and subsequent embodiments are loaded and displayed through a web application.
[0054] Time series data is relevant data generated when a user operates a page; it can be understood that time series data is generated based on user behavior, and therefore, time series data can reflect the user's operation needs for the page.
[0055] The component prediction model is used to predict the components that need to be loaded in the page. It is understandable that as the web application runs, time series data will be continuously generated based on user operations. Therefore, the component prediction model can be continuously trained based on new time series data to achieve automatic update.
[0056] The specific type of the component prediction model can be selected based on actual needs, such as LSTM (Long Short-Term Memory).
[0057] Step S20, when a page jump is triggered, determining a target loading page for the page jump;
[0058] Page jump indicates the loading of a new page; it is understandable that the page jump may be the loading of the first page when the web application is started, or may be a jump from a loaded page to a new page that needs to be loaded.
[0059] When triggering a page jump, the specific page to be jumped to, that is, the target loading page, can be determined based on the triggering method of the page jump.
[0060] Step S30, obtaining page data corresponding to the target loading page, and inputting the page data into the trained component prediction model;
[0061] Step S40, running the trained component prediction model to obtain the target component corresponding to the target loading page;
[0062] The page data includes relevant data of the target loading page; the page data may include but is not limited to the page type, included components, etc.; it can be understood that the component prediction model is trained through the time series data generated by the user behavior. Therefore, after the page data is input into the trained component prediction model, the component prediction model can analyze the page data based on the time series data, thereby predicting the user's operation tendency in the target loading page, and then determining the target component that needs to be loaded based on the user's operation tendency.
[0063] Step S50, loading the target component in the target loading page.
[0064] After determining the target component to be loaded, the target component can be loaded in the target loading page.
[0065] This embodiment trains the component prediction model through time series data, so that the component prediction model can predict the components that need to be loaded based on the user's actual behavior, so that when the page is loaded, the components can be preloaded, thereby improving the loading performance of the components and reducing loading delays.
[0066] Further, see Figure 2 In the second embodiment of the responsive component dynamic arrangement method of the present invention proposed based on the first embodiment of the present invention, step S10 includes the steps of:
[0067] Step S11, obtaining the page access history, component usage frequency and user operation series in the time series data;
[0068] Step S12, generating training data according to the page access history, component usage frequency and user operation series;
[0069] Step S13, training the component prediction model using the training data to obtain a trained component prediction model.
[0070] The page access history is a record of pages that have been loaded; through the page access history, relevant component information in the loaded pages can be determined.
[0071] The component usage frequency is used to indicate the number of times a specific component is used by the user; it is understandable that there are differences in the corresponding components in different pages, and the degree to which the same component is needed by users in different pages is also different. Therefore, when counting the component usage frequency, statistics can be made for specific components in specific pages, that is, different component usage frequencies corresponding to the same type of components in different pages; it should be noted that in other embodiments, the usage frequencies of components of the same type in different pages can also be combined to obtain the component usage frequency, thereby characterizing the degree to which users need the components in general.
[0072] The user operation series is used to indicate the specific operation of the user on the component; through the user operation series, the specific application status of the user's corresponding component can be known.
[0073] It can be understood that the source pages of the time series data can be known through the page access history, that is, the component prediction model is trained based on the relevant data of those pages; and in subsequent specific applications, after the page data is input into the trained component prediction model, the component prediction model can predict the target component according to the specific page type corresponding to the page data; for example, when training the component prediction model, the page access history includes page A, and the specific component usage frequency and user operation series corresponding to page A; after page A is input into the trained component prediction model, the component prediction model can focus more on the prediction of the target component based on the specific component usage frequency and user operation series corresponding to page A, so that the obtained target component can match page A.
[0074] The frequency of component use indicates the degree of user need for the component. It is understandable that the higher the frequency of component use, the longer the user uses the component. Therefore, when predicting the target component, there is a greater probability that it will be predicted as the target component.
[0075] In this embodiment, the component prediction model is trained specifically through page access history, component usage frequency, and user operation series, so that the predicted target component can meet the needs of specific pages and users.
[0076] It should be noted that when training the component prediction model, the specific training configuration can be set based on actual needs; for example, after obtaining the time series data, the time series data can be processed to obtain the training set, validation set and test set, which constitute the training data.
[0077] Specifically, data processing may include cleaning data, converting data, normalizing data, sequence conversion, and data segmentation; cleaning data is used to process missing values, outliers, and duplicate data in time series data; converting data is used to encode non-numeric data in time series data; data normalization is used to normalize data, such as normalization; sequence conversion is used to create data windows by predicting actions in the next step or several steps; data segmentation is used to specifically segment the data set into training sets, validation sets, and test sets. The specific type and method of data processing can be set based on actual needs. It should be noted that since data processing includes data normalization, the target component predicted by the trained component prediction model may also be output in the form of normalized data. In this case, the target component needs to be reversely converted and predicted, and the target component has been converted into the original data format corresponding to the component.
[0078] Furthermore, the specific structure of the component prediction model can be set based on actual needs, such as determining the number of LSTM layers and the number of units set in each layer based on actual needs; and determining the input and output I / O shapes to ensure that the model input matches the created data window.
[0079] The loss function, optimizer, and evaluation index in the specific training of the component prediction model can be set based on actual needs; for example, the loss function uses the mean square error MSE, and the optimizer uses adam; you can further set a callback function to prevent overfitting, or set a model checkpoint to save the best model in the training process. ; Callback functions such as Early Stopping can be used.
[0080] When training with the training set, validation set, and test set, the component prediction model can be specifically trained with the training set and the validation machine; then the performance of the component prediction model can be evaluated by monitoring the validation loss with the test machine. Specifically, the prediction error between the predicted value and the actual value of the component prediction model can be calculated, and the prediction error can be analyzed to determine whether there is a bias or variance problem with the component prediction model.
[0081] Before starting training, the batch size and number of iterations need to be trained; the specific values can be determined based on specific experiments; after the component prediction model is completed, the network architecture, learning rate, batch size and other hyperparameters can be adjusted according to the performance of the model.
[0082] It should be noted that the above is only an illustration of a feasible training method for the component prediction model, and the specific training of the component prediction model can be set based on actual needs.
[0083] Further, in a third embodiment of the responsive component dynamic arrangement method of the present invention proposed based on the first embodiment of the present invention, the step S50 includes the following steps:
[0084] Step S60, obtaining loading performance data of the target loading page;
[0085] Step S70: updating the trained component prediction model by using the loading performance data.
[0086] See also Figure 3 The loading performance data is used to indicate the relevant performance of the target loading page based on the target component for loading; it is understandable that different target components have an impact on the recording of the page, and some components will cause greater pressure on the page loading. Therefore, it is necessary to obtain the loading performance data obtained after the target loading page is loaded, and update the component prediction model by recording the performance data, so that the updated component prediction model can further predict the target component that better balances the page loading performance and user behavior.
[0087] It should be noted that different types of loading performance data may be determined for different aspects of the page, and the component prediction model may be updated based on the specific loading performance data.
[0088] Furthermore, the step S70 includes:
[0089] Step S71, obtaining the first screen loading time corresponding to each target component in the loading performance data;
[0090] Step S72, generating update data based on the first screen loading time and the target component;
[0091] Step S73: updating the trained component prediction model using the update data.
[0092] In this embodiment, the first screen loading time is used as loading performance data to update the component prediction model.
[0093] The first screen loading time is used to indicate the time it takes for the first screen of the page to load based on the target component after the target component is determined. It can be understood that the longer the first screen loading time is, the greater the loading pressure based on the target component is, and the shorter the first screen loading time is, the smaller the loading pressure based on the target component is. Therefore, the predicted loading pressure of the target component can be determined by the first screen loading time, and then the component prediction model can be updated based on the first screen loading time and the update data generated by the target component, so that the updated component prediction model can balance the predicted loading pressure of the target component, thereby avoiding the first screen loading time of the page being too long and affecting user use.
[0094] It should be noted that the specific method for updating the component prediction model based on the update data can be executed by analogy based on the training method of the component prediction model, which will not be elaborated here.
[0095] In other embodiments, the loading performance data may also include user interaction response time; the user interaction response time is used to indicate the time it takes for the page to execute related functions after the user operates the page; it can be understood that the longer the user interaction response time, the longer the page loading time is. Therefore, the component prediction model can also be updated based on the user interaction response time. The specific update method can be executed by analogy based on the first screen loading time, which will not be elaborated again.
[0096] Further, in a fourth embodiment of the responsive component dynamic arrangement method of the present invention proposed based on the first embodiment of the present invention, step S50 includes the following steps:
[0097] Step S51, performing dependency tracking on each of the target components to obtain a component priority corresponding to each of the target components;
[0098] Step S52: loading each of the target components in sequence based on the component priority in the target loading page.
[0099] Dependency tracking means that Vue's responsive system can track component dependencies so that when these dependencies change, Vue can automatically update the display of related components.
[0100] See also Figure 4, the component loader of Vue.js can be extended in advance, so that it can load the target components with higher priority first according to the prediction results and the dependency relationship of the target components; the component prediction model will output the target components in a sorted manner, such as the target components are navigation menu, tree control, search box, chart, and the component loader in vue.js will track the dependencies based on this sorting to determine the component priority corresponding to each target component; it can be understood that the higher the component priority, the earlier the corresponding target component is loaded. Specifically, a resource scheduler can be designed to determine the loading priority and time point of the target component based on the priority and dependency relationship of the target component and the current network conditions; combined with real-time monitoring data and component loading priority, the component resources are given network priority and efficiently transmitted through the multiplexing feature of HTTP / 2.
[0101] After the priorities corresponding to the target components are determined, the target components can be loaded in sequence based on the component priorities. When all target components are loaded, the target loading page is loaded.
[0102] Furthermore, the step S51 comprises the steps of:
[0103] Step S511, obtaining historical loading data corresponding to the target loading page;
[0104] Step S512, determining the interaction response time corresponding to each of the target components in the historical loading data;
[0105] Step S513: performing dependency tracking on the target components based on the interaction response time to obtain component priorities corresponding to the target components.
[0106] The historical loading data is the relevant data of the page loading based on the target component after the target component is determined.
[0107] It is understandable that the interaction response time indicates the time it takes for a page to execute related functions after the user operates on the page; it is understandable that when a user triggers a component in a page, if the corresponding interaction response time is too long, it can be considered that the loading time of the component is too long. Therefore, the component can be loaded faster, that is, the component priority of the component can be improved, and at the same time, the component priority of other components can be adjusted, so that the component priority determined based on the interaction response time can better meet the needs of users, thereby reducing the interaction response time.
[0108] Further, in a fifth embodiment of the responsive component dynamic arrangement method of the present invention proposed based on the first embodiment of the present invention, step S50 includes the following steps:
[0109] Step S53, obtaining the preset priority corresponding to each of the target components;
[0110] Step S54, loading each of the target components in sequence based on the preset priority in the target loading page.
[0111] The preset priority is the priority corresponding to each component set by default or set by the user; in some cases, the user requires a fixed component loading order. At this time, each target component can be loaded based on the determined preset priority.
[0112] Specifically, the priorities of all components are sorted in advance. After the target component is determined, the preset priority corresponding to each target component is matched, and then the target components are sorted based on the preset priority. Then, the target components are loaded in sequence based on the preset priority, so as to meet the user's specific loading needs.
[0113] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0115] The present application also provides a responsive component dynamic arrangement device for implementing the above-mentioned responsive component dynamic arrangement method, and the responsive component dynamic arrangement device includes:
[0116] A first acquisition module is used to acquire time series data generated by a user's operation on a page, and train a component prediction model based on the time series data to obtain a trained component prediction model;
[0117] A first determination module is used to determine a target loading page for page jump when page jump is triggered;
[0118] A second acquisition module is used to acquire page data corresponding to the target loading page, and input the page data into the trained component prediction model;
[0119] A first running module is used to run the trained component prediction model to obtain a target component corresponding to the target loading page;
[0120] The first loading module is used to load the target component in the target loading page.
[0121] The responsive component dynamic arrangement device trains the component prediction model through time series data, so that the component prediction model can predict the components that need to be loaded based on the actual behavior of the user, so that the components can be preloaded when the page is loaded, thereby improving the loading performance of the components and reducing the loading delay.
[0122] It should be noted that the first acquisition module in this embodiment can be used to execute step S10 in the embodiment of the present application, the first determination module in this embodiment can be used to execute step S20 in the embodiment of the present application, the second acquisition module in this embodiment can be used to execute step S30 in the embodiment of the present application, the first running module in this embodiment can be used to execute step S40 in the embodiment of the present application, and the first loading module in this embodiment can be used to execute step S50 in the embodiment of the present application.
[0123] Furthermore, the first acquisition module includes:
[0124] A first acquisition unit, used to acquire the page access history, component usage frequency and user operation series in the time series data;
[0125] A first generating unit, configured to generate training data according to the page access history, component usage frequency, and user operation series;
[0126] The first training unit is used to train the component prediction model using the training data to obtain a trained component prediction model.
[0127] Furthermore, the device also includes:
[0128] A third acquisition module, used to acquire the loading performance data of the target loading page;
[0129] The first updating module is used to update the component prediction model after the training is completed by using the loading performance data.
[0130] Furthermore, the first update module includes:
[0131] A second acquisition unit is used to acquire the first screen loading time corresponding to each of the target components in the loading performance data;
[0132] A second generating unit, configured to generate update data based on the first screen loading time and the target component;
[0133] The first updating unit is used to update the component prediction model after the training is completed through the update data.
[0134] Furthermore, the first loading module includes:
[0135] A first tracking unit, used for tracking the dependencies of each target component to obtain the component priority corresponding to each target component;
[0136] The first loading unit is used to load each of the target components in sequence based on the component priority in the target loading page.
[0137] Furthermore, the dependency tracking of each target component to obtain the component priority corresponding to each target component includes:
[0138] A third acquisition unit, used to acquire the historical loading data corresponding to the target loading page;
[0139] A first determining unit, configured to determine the interaction response time corresponding to each of the target components in the historical loading data;
[0140] The second tracking unit is used to perform dependency tracking on the target components based on the interaction response time to obtain component priorities corresponding to the target components.
[0141] Furthermore, the first loading module includes:
[0142] A fourth acquisition unit, used to acquire a preset priority corresponding to each of the target components;
[0143] The second loading unit is used to load each of the target components in sequence based on the preset priority in the target loading page.
[0144] Reference Figure 5 In terms of hardware structure, the electronic device may include components such as a communication module 10, a memory 20, and a processor 30. In the electronic device, the processor 30 is connected to the memory 20 and the communication module 10 respectively, and a computer program is stored in the memory 20. The computer program is executed by the processor 30 at the same time, and the steps of the above method embodiment are implemented when the computer program is executed.
[0145] The communication module 10 can be connected to an external communication device through a network. The communication module 10 can receive requests from an external communication device, and can also send requests, instructions and information to the external communication device, which can be other electronic devices, servers or Internet of Things devices, such as televisions, etc.
[0146] The memory 20 can be used to store software programs and various data. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as obtaining time series data generated by a user operating a page), etc.; the data storage area can include a database, and the data storage area can store data or information created according to the use of the system, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0147] The processor 30 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 20, and calling data stored in the memory 20, so as to monitor the electronic device as a whole. The processor 30 may include one or more processing units; optionally, the processor 30 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 30.
[0148] although Figure 5 Although not shown, the electronic device may further include a circuit control module, which is used to connect to a power source to ensure the normal operation of other components. Figure 5 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0149] The present invention also provides a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be Figure 5The memory 20 in the electronic device may also be at least one of a ROM (Read-Only Memory) / RAM (Random Access Memory), a magnetic disk, and an optical disk. The computer-readable storage medium includes a number of instructions for enabling a terminal device with a processor (which may be a television, a car, a mobile phone, a computer, a server, a terminal, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0150] In the present invention, the terms "first", "second", "third", "fourth" and "fifth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0151] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0152] Although the embodiments of the present invention have been shown and described above, the scope of protection of the present invention is not limited thereto. It is understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art can change, modify and replace the above embodiments within the scope of the present invention, and these changes, modifications and replacements should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.
Claims
1. A responsive component dynamic arrangement method, characterized in that: The responsive component dynamic arrangement method includes: Acquire time series data generated by user operations on the page, and train the component prediction model based on the time series data to obtain a trained component prediction model; When triggering a page jump, determine the target loading page for the page jump; Obtaining page data corresponding to the target loading page, and inputting the page data into the trained component prediction model; Running the trained component prediction model to obtain a target component corresponding to the target loading page; The target component is loaded in the target loading page.
2. The responsive component dynamic arrangement method according to claim 1, characterized in that: The training of the component prediction model based on the time series data to obtain the trained component prediction model includes: Obtaining page access history, component usage frequency, and user operation series in the time series data; Generate training data based on the page access history, component usage frequency, and user operation series; The component prediction model is trained using the training data to obtain a trained component prediction model.
3. The responsive component dynamic arrangement method according to claim 1, characterized in that: After loading the target component in the target loading page, the method further comprises: Obtaining loading performance data of the target loading page; The component prediction model after the training is completed is updated through the loading performance data.
4. The responsive component dynamic arrangement method according to claim 3, characterized in that: The updating of the component prediction model after the training is completed by using the loading performance data includes: Obtaining the first screen loading time corresponding to each of the target components in the loading performance data; Generate update data based on the first screen loading time and the target component; The component prediction model after the training is completed is updated through the update data.
5. The responsive component dynamic arrangement method according to claim 1, characterized in that: The loading of the target component in the target loading page includes: Perform dependency tracking on each of the target components to obtain a component priority corresponding to each of the target components; In the target loading page, each target component is loaded in sequence based on the component priority.
6. The responsive component dynamic arrangement method according to claim 5, characterized in that: The dependency tracking of each target component to obtain the component priority corresponding to each target component includes: Obtaining historical loading data corresponding to the target loading page; Determining the interactive response time corresponding to each of the target components in the historical loading data; Dependency tracking is performed on the target components based on the interaction response time to obtain component priorities corresponding to the target components.
7. The responsive component dynamic arrangement method according to claim 1, characterized in that: The loading of the target component in the target loading page includes: Obtaining the preset priority corresponding to each of the target components; In the target loading page, each target component is loaded in sequence based on the preset priority.
8. A responsive component dynamic arrangement device, characterized in that: The responsive component dynamic arrangement device comprises: A first acquisition module is used to acquire time series data generated by a user's operation on a page, and train a component prediction model based on the time series data to obtain a trained component prediction model; A first determination module is used to determine a target loading page for page jump when page jump is triggered; A second acquisition module is used to acquire page data corresponding to the target loading page, and input the page data into the trained component prediction model; A first running module is used to run the trained component prediction model to obtain a target component corresponding to the target loading page; The first loading module is used to load the target component in the target loading page.
9. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the responsive component dynamic orchestration method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the responsive component dynamic orchestration method according to any one of claims 1 to 7 are implemented.