Animation playback method, device, and electronic device

Abstract

The present invention discloses an animation playback method, device and electronic device. The method comprises: receiving an application startup request, wherein the application startup request is used to request the startup of a target application. In response to the application startup request, when the startup mode of the target application is to convert from a closed state to a startup state, push parameters of a plurality of animations to be selected are determined. Based on the push parameters of the plurality of animations to be selected, a first target animation is determined from the plurality of animations to be selected. The first target animation is played when the target application is started. The present invention solves the technical problem in the related art that when the application is started, the opening screen animation played fails to attract users, resulting in a low click-through rate of the opening screen animation page.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an animation playing method, device and electronic equipment. Background Art

[0002] Splash screen animations are an important component of animated content promotion, and accurate animation push is crucial for animation promotion. Currently, the main method for determining the splash screen animation that plays when an app launches is to prioritize quality and make real-time decisions. However, this method not only fails to address the low click-through rate of splash screen animations, but also leads to long app startup times.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide an animation playback method, device, and electronic device to at least solve the technical problem in related technologies that when an application is started, the splash screen animation played fails to attract users, resulting in a low click-through rate of the splash screen animation page.

[0005] According to one aspect of an embodiment of the present invention, there is provided an animation playback method, comprising: receiving an application startup request, wherein the application startup request is used to request the startup of a target application; in response to the application startup request, when the startup mode of the target application is to convert from an off state to an on state, determining push parameters of multiple animations to be selected, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value and an animation click value, the predicted playback value is used to predict the number of times the corresponding animation to be selected will be played when the target application is started this time, the predicted total playback value is used to predict the total number of times the corresponding animation to be selected will be played, the loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold, the click value is used to represent the value generated after the animation to be selected is selected, and the animation click value is used to represent the ratio of the predicted number of clicks of the animation to be selected to the predicted total playback value; based on the push parameters of the multiple animations to be selected, determining a first target animation from the multiple animations to be selected; and playing the first target animation when the target application is started.

[0006] Optionally, when the target application is started from a background state to a foreground state, the animation storage result is read, wherein the animation storage result is used to determine the animation to be played when the target application is started this time; a second target animation corresponding to the animation storage result is determined; and the second target animation is played when the target application is started.

[0007] Optionally, in response to an application startup request, when the startup mode of the target application is to convert from a closed state to a started state, push parameters for multiple animations to be selected are determined, including: obtaining behavior data of the target account corresponding to the target application, and animation data corresponding to the multiple animations to be selected; and determining push parameters corresponding to the multiple animations to be selected based on the behavior data and the animation data corresponding to the multiple animations to be selected.

[0008] Optionally, based on the push parameters of multiple animations to be selected, a first target animation is determined from the multiple animations to be selected, including: determining a first function based on the push parameters corresponding to the multiple animations to be selected, wherein the first function is used to represent the total loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold; determining a second function based on the push parameters corresponding to the multiple animations to be selected, wherein the second function is used to represent the predicted total value generated by the corresponding animation to be selected; determining an objective function with the goal of maximizing click-through rate and multiple constraints corresponding to the objective function based on the first function, the second function and the push parameters corresponding to the multiple animations to be selected, wherein the constraints include quantity preservation constraints, which are used to constrain the predicted playback value of the corresponding animation to be selected; solving the objective function under the constraints corresponding to the multiple animations to be selected, and determining the first target animation from the multiple animations to be selected.

[0009] Optionally, based on the push parameters corresponding to the multiple animations to be selected, a first function is determined, including: based on the push parameters corresponding to the multiple animations to be selected, a playback threshold corresponding to the multiple animations to be selected and a difference between the difference and the predicted total playback value corresponding to the multiple animations to be selected, to obtain a difference item corresponding to the multiple animations to be selected; and a product of the difference item corresponding to the multiple animations to be selected and the loss value corresponding to the multiple animations to obtain the first function.

[0010] Optionally, based on the push parameters corresponding to the multiple animations to be selected, a second function is determined, including: based on the push parameters corresponding to the multiple animations to be selected, the animation click values ​​corresponding to the multiple animations to be selected are determined, and the product of the click values ​​of the multiple animations to be selected is obtained to obtain the product terms corresponding to the multiple animations to be selected; based on the push parameters corresponding to the multiple animations to be selected, the product of the predicted total playback values ​​corresponding to the multiple animations to be selected is determined to obtain the second function.

[0011] Optionally, after playing the target animation when starting the target application, the method further includes: triggering an animation storage request; and updating the animation storage result in response to the animation storage request to obtain an updated stored animation.

[0012] According to one aspect of an embodiment of the present invention, an animation playback device is provided, comprising: a receiving module for receiving an application startup request, wherein the application startup request is used to request the startup of a target application; a first determining module for, in response to the application startup request, determining push parameters of multiple animations to be selected when the startup mode of the target application is to switch from an off state to an on state, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value, and an animation click value; the predicted playback value is used to predict the number of times the corresponding animation to be selected will be played when the target application is currently started; the predicted total playback value is used to predict the total number of times the corresponding animation to be selected will be played; the loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold; the click value is used to represent the value generated after the animation to be selected is selected; and the animation click value is used to represent the ratio of the predicted number of clicks of the animation to the predicted total playback value; a second determining module for determining a first target animation from multiple animations to be selected based on the push parameters of the multiple animations to be selected; and a playback module for playing the first target animation when the target application is started.

[0013] According to one aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the above-mentioned animation playback methods.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned animation playback methods.

[0015] In an embodiment of the present invention, an application launch request is received, wherein the application launch request is used to request the launch of a target application. In response to the application launch request, when the target application is launched from a closed state to an active state, push parameters for multiple selected animations are determined. The push parameters include: a play threshold, a predicted play value, a predicted total play value, a loss value, a click value, and an animation click value. The predicted play value is used to predict the number of plays of the corresponding selected animation when the target application is launched. The predicted total play value is used to predict the total number of plays of the corresponding selected animation. The loss value is used to represent the loss incurred if the predicted total play value of the corresponding selected animation does not reach the play threshold. The click value is used to represent the value generated after the corresponding selected animation is selected. The animation click value is used to represent the ratio of the predicted number of clicks to the predicted total play value of the corresponding selected animation. Based on the push parameters of the multiple selected animations, a first target animation is determined from the multiple selected animations. The first target animation is played when the target application is launched. It can be seen that by determining the first target animation from the multiple selected animations based on the push parameters of the multiple selected animations, the purpose of playing the first target animation when the target application is launched is achieved. Since the push parameters can reflect the playback volume threshold that the corresponding selected animation itself needs to meet, the loss caused by non-playing, and the value generated by clicks, at the same time, the playback parameters can also predict the playback volume and click volume through user behavior data. Therefore, the first selected animation determined by the push parameters can attract users to the greatest extent on the basis of meeting the playback volume, thereby solving the technical problem in related technologies that when the application is started, the opening screen animation played cannot attract users, resulting in a low click-through rate of the opening screen animation page. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flowchart of an animation playing method according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of determining the opening screen animation when the mobile phone application software is started according to an optional embodiment of the present invention;

[0019] Figure 3 is a parameter adjustment flow chart of a hot start according to an optional embodiment of the present invention;

[0020] Figure 4 is a structural block diagram of an animation playback device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] According to an embodiment of the present invention, an embodiment of an animation playback method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flowchart of an animation playing method according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0026] Step S102: receiving an application start request, wherein the application start request is used to request starting a target application.

[0027] In step S102 provided in this application, a start request of a target application is received.

[0028] Among them, it involves application launch requests. Application launch requests refer to a signal sent by the user by clicking the application icon, waking up the application from the background, or through other means, such as from the notification bar, shortcuts, third-party launchers, etc., indicating that the user wants to start or switch to a specific application.

[0029] The target application is the specific application that the user wants to launch or switch to. This can be any software installed on the device, such as social media applications, games, office software, music players, news clients, etc.

[0030] Through this step, an application start request from the user to start the target application can be received, which is a basic step for subsequently determining the target animation to be played.

[0031] Step S104, in response to the application startup request, when the startup mode of the target application is to convert from a closed state to a started state, determine the push parameters of multiple animations to be selected, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value and an animation click value, the predicted playback value is used to predict the number of times the target application will be played when the corresponding animation to be selected is started this time, the predicted total playback value is used to predict the total number of times the corresponding animation to be selected is played, the loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold, the click value is used to represent the value generated after the corresponding animation to be selected is selected, and the animation click value is used to represent the ratio of the predicted number of clicks of the corresponding animation to the predicted total playback value.

[0032] In step S104 provided in the present application, in response to the application startup request, when the startup mode of the target application is to convert from a closed state to a started state, push parameters of a plurality of animations to be selected are determined.

[0033] Among them, the startup method is involved, which refers to the way the application transitions from different states to the running state.

[0034] Among them, it involves the animation to be selected. The animation to be selected refers to the animation material displayed to the user when the application is launched, such as application introduction, brand promotion, etc., which is used to attract user attention and enhance the visual effects and brand awareness of the application.

[0035] This involves push parameters, which are a series of indicators or set values ​​used to guide and optimize content push decisions. These parameters typically reflect push objectives, user preferences, content effectiveness, system limitations, and business goals, and are crucial for determining push content.

[0036] This involves the playback threshold, which is the system-set minimum number of playbacks for a selected animation, used to measure whether the animation has achieved the expected exposure. The playback threshold is the basis for animation effect evaluation and contractual obligations, ensuring that the animation reaches a certain number of impressions.

[0037] This involves the predicted play value, which refers to the number of times the system predicts a selected animation will be played when the app is launched, based on historical data and current environmental conditions. The predicted play value reflects the potential exposure of the animation in the current launch scenario.

[0038] Among them, the predicted total playback value is involved. The predicted total playback value refers to the predicted total number of playback times of the selected animation within a certain time period. It is used to evaluate the potential exposure of the animation, which helps to formulate the overall strategy and rationally allocate resources.

[0039] Among them, the loss value is involved. The loss value refers to the loss that will be generated when the predicted total playback value of the animation does not reach the playback threshold. It is used to measure the severity of the situation when the playback volume does not reach the playback threshold in different selected animations.

[0040] Among them, click value is involved. Click value refers to the value generated when a user clicks on an animation. It can be direct monetary gain, or it can be increased user engagement or brand exposure value.

[0041] Among them, the animation click value is involved. The animation click value refers to the ratio of the number of times a specific animation is clicked to the total number of times it is played. This is an important indicator to measure the attractiveness of the animation and the degree of user interaction.

[0042] Among them, the predicted number of clicks is involved. The predicted number of clicks refers to the estimated number of times the corresponding selected animation may be clicked by users when it is displayed based on historical data, user behavior patterns, characteristics and the current startup scenario.

[0043] In this step, first, respond to the application startup request, and then, when the startup mode of the target application is to switch from the closed state to the started state, determine the push parameters of multiple animations to be selected. These parameters include the playback volume threshold, predicted playback value, predicted total playback value, loss value, click value and animation click value, etc.

[0044] Through this step, the push parameters of multiple animations to be selected can be determined. These parameters reflect the playback threshold that the animation needs to reach, the potential losses that may be caused by not playing the animation, and the user's interest in the animation content and predicted participation. They can fully reflect the key needs and market performance expectations of the animation itself, and provide a basis for the precise promotion of the animation.

[0045] Step S106 : determining a first target animation from the plurality of animations to be selected based on the push parameters of the plurality of animations to be selected.

[0046] In step S106 provided in the present application, a first target animation is determined from the plurality of animations to be selected based on the push parameters of the plurality of animations to be selected.

[0047] This involves the first target animation, which is the animation selected to be displayed to the user when the target app is launched from a closed state to an active state, after analyzing and comparing the push parameters of all candidate animations. This animation is the one that is considered the most optimized and best meets the system's set goals.

[0048] In this step, a first target animation is determined from the plurality of candidate animations based on the push parameters of the plurality of candidate animations. In this way, the animation that best matches the user's preference can be intelligently selected while meeting the animation playback requirements.

[0049] It should be noted that you can monitor network conditions and device performance in real time, adjust the loading priority and format of animations, and ensure that animations are displayed quickly and smoothly under any network conditions, avoiding affecting the user experience due to long loading times.

[0050] Step S108: Play the first target animation when starting the target application.

[0051] In step S108 provided in this application, a first target animation is played when the target application is started.

[0052] Through the above steps S102-S108, it is possible to receive an application startup request, wherein the application startup request is used to request the startup of the target application. In response to the application startup request, when the startup mode of the target application is to convert from a closed state to a startup state, the push parameters of multiple animations to be selected are determined, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value and an animation click value. The predicted playback value is used to predict the number of times the target application will play the corresponding animation to be selected when it is started this time. The predicted total playback value is used to predict the total number of times the corresponding animation to be selected is played. The loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold. The click value is used to represent the value generated after the corresponding animation to be selected is selected. The animation click value is used to represent the ratio of the predicted number of clicks of the corresponding animation to be selected to the predicted total playback value. Based on the push parameters of multiple animations to be selected, a first target animation is determined from the multiple animations to be selected. The first target animation is played when the target application is started. It can be seen that by determining the first target animation from multiple candidate animations based on the push parameters of multiple candidate animations, the purpose of playing the first target animation when the target application is started is achieved. Since the push parameters can reflect the playback volume threshold that the corresponding candidate animation itself needs to meet, the loss caused by non-playing, and the value generated by clicks, at the same time, the playback parameters can also predict the playback volume and click volume through user behavior data. Therefore, the first candidate animation determined by the push parameters can attract users to the greatest extent on the basis of meeting the playback volume, thereby solving the technical problem in the related technology that when the application is started, the opening screen animation played cannot attract users, resulting in a low click-through rate of the opening screen animation page.

[0053] As an optional embodiment, when the target application is started from a background state to a foreground state, the animation storage result is read, wherein the animation storage result is used to determine the animation to be played when the target application is started this time; a second target animation corresponding to the animation storage result is determined; and the second target animation is played when the target application is started.

[0054] In this embodiment, specific steps for playing the second target animation when the target application is started in a mode of switching from a background state to a foreground state are described.

[0055] This involves the background state, which refers to the state in which the application is running but inactive. That is, the application does not directly interact with the user, but runs as a process in the background of the device's system. In this state, the application may be suspended or partially running due to system resource management, but it is still part of the system.

[0056] Among them, the foreground state is involved. The foreground state refers to the active state of the application where the user can directly interact with it. At this time, the interface and functions of the application are fully visible and available to the user.

[0057] This involves animation storage results, which are calculated and cached when the app was last closed or in the background state. This result is used to display the animation selection result the next time the app is launched. This result contains the animation information selected by the system, such as the animation name and display parameters, and is used to quickly restore the app's opening screen display.

[0058] Among them, the second target animation is involved. The second target animation refers to the predetermined animation in the animation storage result read when the startup mode of the target application is to switch from the background state to the foreground state, that is, the animation played when the target application is started this time.

[0059] In this step, if the target application is launched from the background to the foreground, the previously cached animation result is directly read. This result includes the second target animation information determined when the previous splash screen animation finished playing, which is used to quickly determine the splash screen content to be displayed upon the current launch. This method avoids the delays of real-time requests and online decision-making, thereby reducing application startup time and improving the user experience.

[0060] As an optional embodiment, in response to an application startup request, when the startup mode of the target application is to convert from a closed state to a started state, push parameters of multiple animations to be selected are determined, including: obtaining behavior data of the target account corresponding to the target application, and animation data corresponding to the multiple animations to be selected; based on the behavior data and the animation data corresponding to the multiple animations to be selected, push parameters corresponding to the multiple animations to be selected are determined.

[0061] In this embodiment, specific steps of determining push parameters of multiple animations to be selected when the startup mode of the target application is to switch from a closed state to a started state are described.

[0062] This involves the target account, which refers to the user account associated with the currently launched target app. This account contains various user behavior data, preferences, historical interaction records, and other information during the user's use of the app, and is an important data source for personalized animation recommendations and decision-making.

[0063] Among them, behavioral data is involved. Behavioral data refers to the data related to animation playback contained in the user's account information, such as animation preferences, history of clicked animations, etc. These data help analyze user behavior patterns and predict their reactions to animation content.

[0064] Among them, animation data is involved. Animation data refers to data related to animation, such as the target number of playbacks, type, content, length, format, number of impressions, number of clicks, animation business information, etc.

[0065] In this step, first, the behavioral data of the target account corresponding to the target application and the animation data corresponding to multiple selected animations are obtained. Then, the push parameters corresponding to the selected animations are determined by combining the data. These parameters reflect the potential performance of each selected animation in the current startup scenario, including their playback possibility and expected number of clicks.

[0066] It should be noted that to further optimize the user experience and animation effects, other intelligent strategies can be combined to enrich push parameters. For example, the user's device's geographic location and time information can be used to predict the user's animation preferences at different time periods and locations, thereby incorporating geographic location and time factors into push parameters.

[0067] As an optional embodiment, based on the push parameters of multiple animations to be selected, a first target animation is determined from the multiple animations to be selected, including: determining a first function based on the push parameters corresponding to the multiple animations to be selected, wherein the first function is used to represent the total loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold; determining a second function based on the push parameters corresponding to the multiple animations to be selected, wherein the second function is used to represent the predicted total value generated by the corresponding animation to be selected; determining an objective function with the goal of maximizing click-through rate and multiple constraints corresponding to the objective function based on the first function, the second function and the push parameters corresponding to the multiple animations to be selected, wherein the constraints include quantity preservation constraints, which are used to constrain the predicted playback value of the corresponding animation to be selected; solving the objective function under the constraints corresponding to the multiple animations to be selected, and determining the first target animation from the multiple animations to be selected.

[0068] In this embodiment, specific steps of determining a first target animation from a plurality of animations to be selected based on the push parameters of the plurality of animations to be selected are described.

[0069] Among them, the first function is involved. The first function refers to the total loss function faced when the total predicted playback value of the selected animation does not reach the playback volume threshold. The total loss includes direct cost loss and potential effect loss.

[0070] Among them, the second function is involved, which refers to the total value function generated by displaying the prediction of the selected animation. The total value includes the investment brought by clicks and indirect value such as potential user conversions.

[0071] Among them, the click-through rate is involved. The click-through rate refers to the ratio of the number of times users actually click on the animation to the total number of times the animation is displayed.

[0072] Among them, the objective function is involved. The objective function refers to the mathematical expression defined in the optimization problem to quantify and guide the goal of the decision-making process.

[0073] Among them, constraints are involved. Constraints refer to a series of rules or restrictions that must be followed in the decision-making process.

[0074] Among them, the quantity constraint is involved. The quantity constraint refers to the requirement for the number of times the selected animations are displayed, ensuring that multiple selected animations can achieve a certain amount of exposure.

[0075] In this step, first, based on the push parameters corresponding to multiple selected animations, a first function for measuring the total loss of the animation and a second function for measuring the total value of the animation are determined. Then, based on the first function, the second function and the push parameters corresponding to the multiple selected animations, an objective function with the goal of maximizing the click-through rate and multiple constraints corresponding to the objective function are determined. Finally, based on the constraints, the objective function is solved to determine the first target animation.

[0076] This step allows us to assess the potential risks and benefits of animation presentations, such as the loss from failing to reach a certain threshold of views and the value of clicks. By solving the objective function, we can balance these risks and benefits while maximizing click-through rate. Furthermore, constraints such as the quantity guarantee ensure that the minimum exposure requirements for the selected animations are met, allowing for better allocation of animation resources.

[0077] It should be noted that machine learning models, such as deep neural networks (DNN) or recurrent neural networks (RNN), can be used to predict the click-through rate and playback volume of different animations in the future based on historical data and user behavior, so as to more accurately calculate the first function term and the second function term, and improve the predictability and optimization effect of the objective function.

[0078] As an optional embodiment, a first function is determined based on push parameters corresponding to multiple animations to be selected, including: determining the playback volume thresholds corresponding to multiple animations to be selected based on the push parameters corresponding to multiple animations to be selected, and obtaining difference items corresponding to multiple animations to be selected by multiplying the difference items corresponding to multiple animations to be selected and the loss values ​​corresponding to multiple animations to be selected to obtain the first function.

[0079] In this embodiment, the specific steps of determining the first function according to the push parameters corresponding to the plurality of animations to be selected are described.

[0080] Among them, the difference item is involved, and the difference item refers to the difference between the predicted total playback value of the selected animation and the corresponding playback volume threshold.

[0081] In this step, first, the playback volume thresholds corresponding to multiple selected animations and the predicted total playback values ​​corresponding to multiple selected animations are determined, then the difference items corresponding to multiple selected animations are determined, and finally, the product of the difference items corresponding to multiple selected animations and the loss value of the corresponding selected animation is determined to determine the first function.

[0082] Through this step, the first function is constructed to quantify the total expected loss when the playback volume threshold is not reached when displaying the animation. When determining the first target animation, it can ensure that the playback volume of each animation order reaches or is close to the playback volume threshold, fully considering the risk cost of the animation display strategy.

[0083] As an optional embodiment, a second function is determined based on the push parameters corresponding to multiple animations to be selected, including: determining the animation click values ​​corresponding to multiple animations to be selected based on the push parameters corresponding to multiple animations to be selected, and multiplying the products of the click values ​​of the animations to be selected and the click values ​​to be selected to obtain product terms corresponding to the multiple animations to be selected; determining the product terms corresponding to multiple animations to be selected, and multiplying the products of the predicted total playback values ​​corresponding to the multiple animations to obtain the second function.

[0084] In this embodiment, the specific steps of determining the second function according to the push parameters corresponding to the plurality of animations to be selected are described.

[0085] Among them, the product term is involved, which refers to the product of the animation click value and the click value of the selected animation.

[0086] In this step, first, determine the animation click values ​​and click values ​​corresponding to the multiple animations to be selected, then determine the product terms corresponding to the multiple animations to be selected, and finally, determine the product of the product terms corresponding to the multiple animations to be selected and the predicted total playback value of the corresponding animation to be selected to determine the second function.

[0087] Through this step, a second function is constructed, which comprehensively considers the actual click value of the animation and the benefits under the expected number of playbacks, quantifies the value that the selected animation can bring, and ensures that the overall benefits are maximized when the first target animation is determined.

[0088] As an optional embodiment, after playing the target animation when starting the target application, the method further includes: triggering an animation storage request; and updating the animation storage result in response to the animation storage request to obtain an updated stored animation.

[0089] In this embodiment, the specific steps of obtaining the updated stored animation after playing the target animation when starting the target application are described.

[0090] Among them, the target animation is involved. The target animation refers to the animation played when the target application is started this time, including the first target animation and the second target animation.

[0091] This involves an animation storage request, which aims to obtain and store the data for the splash animation displayed the next time the target app transitions from the background state to the foreground. This request is usually issued after the target app is launched and the user sees the splash animation.

[0092] Among them, it involves updating the stored animation. Updating the stored animation refers to updating the locally stored animation based on the latest animation storage request and storage result.

[0093] In this step, after playing the target animation, first, send an animation storage request to determine the data of the opening screen animation displayed when the target application switches from the background state to the foreground state next time. Then, respond to the animation storage request, update the animation storage result, and obtain the updated stored animation.

[0094] Through this step, when the target application switches from the background state to the foreground state, the animation can be loaded quickly, avoiding the real-time request sending at startup, determining the delay caused by the animation, shortening the user's waiting time, and improving the user experience.

[0095] It should be noted that in order to further improve the efficiency of the animation storage process and user experience, the client's storage space and usage can be monitored, and old or no longer needed animation data can be automatically cleared to make room for the storage of new animations and avoid storage space bottlenecks.

[0096] Based on the above embodiment and optional embodiment, an optional implementation manner is provided, which is described in detail below.

[0097] An optional implementation method of the present invention is a method for loading a mobile phone application software (APP) opening screen animation based on a dynamic decision-making mechanism, and the specific steps are as follows.

[0098] S1. Receive an APP startup request.

[0099] S2. In response to the APP startup request, determine the APP startup method and introduce a dynamic decision-making mechanism.

[0100] Figure 2 1 is a flowchart of determining the opening screen animation when the mobile phone application software is started according to an optional embodiment of the present invention, such as Figure 2 As shown, the opening screen animation is divided into hot start pictures and cold start pictures according to the type of APP startup.

[0101] The hot startup animation mainly refers to the opening screen animation when the APP switches from the background to the foreground. At this time, the startup process of the APP is very short, and the animation displayed at this startup is determined by directly reading the existing asynchronous decision results.

[0102] The cold start animation is the opening screen animation when the APP is started from a state without a background. Since it involves processes such as APP initialization, the startup time is relatively long. A real-time request solution can be adopted to execute the entire "animation request → online decision → result delivery" process.

[0103] Through "hot start + asynchronous decision-making" and "cold start + real-time decision-making", a dynamic decision-making mechanism for the opening screen animation is realized.

[0104] The following describes in detail the animation playback process under the two startup methods.

[0105] The specific steps of the cold start picture playback process are as follows.

[0106] A1. Determine push parameters for multiple animations to be selected.

[0107] The definition of the all-day display traffic (PV) is:

[0108] {PV i |i=1,2,3,…,n}

[0109] The animation order set is:

[0110] {order j |j=1,2,3,…,n|}

[0111] The quantity guarantee target for each animation order is d, d j Represents the quantity guarantee target for the j-th animation order.

[0112] x i,j represents the traffic optimization result of the j-th order on the i-th traffic, where x i,j ∈[0,1],x i,j =1 means that the i-th flow is allocated to the j-th order.

[0113] pctr represents the page click rate of the animation, pctr i,j It represents the page click rate of the j-th order in the i-th flow.

[0114] Considering that in some specific business scenarios, some orders need to optimize the click-through rate (CTR), the click value weight v is introduced to represent the importance of CTR optimization for different orders, where v j Represents the click value weight of the j-th animation order.

[0115] A2. Based on the push parameters, determine an objective function with the goal of maximizing the click-through rate, as well as multiple constraints corresponding to the objective function.

[0116] Based on the above parameters, the flow optimization problem can be modeled.

[0117] The objective function for maximizing click-through rate is determined as:

[0118]

[0119] The first constraint corresponding to the objective function is:

[0120]

[0121] The second constraint corresponding to the objective function is:

[0122]

[0123] The third constraint corresponding to the objective function is:

[0124]

[0125] Among them, the first constraint condition indicates that each order must meet the quantity guarantee constraint, and the second constraint condition indicates that each flow can only be allocated to one order at most.

[0126] Considering that in actual launch, it may be impossible to maintain the quantity due to excessive sales, the above problem has no solution.

[0127] Therefore, the order shortage penalty weight w is introduced, w j Indicates the out-of-stock penalty weight for the j-th order.

[0128] At this time, the objective function is:

[0129]

[0130] The first constraint corresponding to the objective function is:

[0131]

[0132] The second constraint corresponding to the objective function is:

[0133]

[0134] The third constraint corresponding to the objective function is:

[0135]

[0136] A3. Solve the objective function based on the constraints and determine the screen opening animation.

[0137] The objective function is derived through dual transformation and complementary relaxation theorem, and the optimal ranking score (rank_score) calculation formula is obtained as follows:

[0138] rank_score i,j =pctr i,j ·v j +w j -α j

[0139] where α j is the dual variable of the quantity constraint for the j-th order.

[0140] A traffic optimization strategy is formulated based on this formula. The specific contents are as follows.

[0141] All orders on the same flow calculate their rank_score based on the above formula.

[0142] If the rank_score of an order is greater than 0, the order with the largest rank_score will win the traffic.

[0143] If the rank_score of all orders is less than 0, no order will compete for the traffic, and the user will not see the opening animation when launching the app this time.

[0144] Assuming that the full-day traffic set is known, the optimal solution for each order can be directly obtained through linear programming (LP), and then the rank_score of each order in the entire traffic can be calculated to obtain the traffic optimization result.

[0145] In actual implementation, considering that the animation traffic of the screen opening every day will fluctuate to a certain extent, the online traffic is difficult to predict, so it is impossible to solve it directly. Instead, the LP problem is converted into a parameter control problem. Figure 3 is a parameter adjustment flow chart of hot start according to an optional embodiment of the present invention, such as Figure 3 As shown, the feedback adjustment method is used to dynamically update the α of each order. j , and finally realize the whole process of "animation request → online decision → result delivery".

[0146] The specific steps of the hot start picture playback process are as follows.

[0147] B1. Read the animation storage results.

[0148] B2. Determine the target animation corresponding to the animation storage result.

[0149] B3. Play the target animation when launching the APP.

[0150] S3. Update the animation storage result.

[0151] By introducing an asynchronous decision-making mechanism, we shift the online real-time decision-making mechanism from deciding on the "current" content to the "next" content for the splash screen. Through asynchronous interaction, the result returned by each animation request is used for the next user's splash screen exposure. This eliminates restrictions on app launch time and enables traffic optimization for splash screen animations.

[0152] After the user completes the exposure of the opening screen animation, the APP will initiate an animation request. The animation system will decide the display content of the user's next opening screen animation based on traffic optimization and return it. The client will cache the returned result locally.

[0153] The next time the user opens the app, the app's local cache is read, the corresponding animation is displayed to the user, and the next animation content is requested after the exposure is completed.

[0154] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0155] (1) Model the splash animation traffic, determine the objective function with the goal of maximizing the click-through rate, and multiple constraints corresponding to the objective function, to obtain the optimal traffic allocation strategy and optimize the CTR of the splash animation;

[0156] (2) The asynchronous decision-making mechanism adjusts the online real-time decision-making mechanism from deciding the content of the opening screen exposure "this time" to deciding the content of the opening screen exposure "next time", which is not limited by the length of the APP startup time and realizes the traffic optimization of the opening screen animation;

[0157] (3) According to the type of APP startup, the animation traffic is divided into hot start and cold start. Through "hot start + asynchronous decision" and "cold start + real-time decision", a dynamic decision mechanism for the opening screen animation is realized. The dynamic decision scheme has basically no effect on the APP startup time, shortens the user's waiting time as much as possible, and ensures the user experience of the APP opening screen.

[0158] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, 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 this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0159] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, 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 enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0160] Example 2

[0161] According to an embodiment of the present invention, a device for implementing the above animation playing method is also provided. Figure 4 is a structural block diagram of an animation playback device according to an embodiment of the present invention. Figure 4 As shown, the device includes: a receiving module 402, a first determining module 404, a second determining module 406 and a playing module 408. The device will be described in detail below.

[0162] The receiving module 402 is used to receive an application startup request, wherein the application startup request is used to request the startup of a target application; the first determining module 404 is connected to the above-mentioned receiving module 402, and is used to respond to the application startup request, and when the startup mode of the target application is to switch from a closed state to a startup state, determine the push parameters of multiple animations to be selected, wherein the push parameters include: playback volume threshold, predicted playback value, predicted total playback value, loss value, click value and animation click value, the predicted playback value is used to predict the number of playbacks of the corresponding animation to be selected when the target application is started this time, and the predicted total playback value is used to predict the corresponding The total number of times the animation to be selected is played, the loss value is used to represent the loss generated when the predicted total value of the corresponding animation to be selected does not reach the playback threshold, the click value is used to represent the value generated after the corresponding animation to be selected is selected, and the animation click value is used to represent the ratio of the predicted number of clicks of the corresponding animation to be selected to the predicted total value of playback; the second determination module 406 is connected to the above-mentioned first determination module 404, and is used to determine the first target animation from multiple animations to be selected based on the push parameters of multiple animations to be selected; the playback module 408 is connected to the above-mentioned second determination module 406, and is used to play the first target animation when the target application is started.

[0163] It should be noted here that the above-mentioned receiving module 402, first determination module 404, second determination module 406 and playback module 408 correspond to steps S102 to S108 in implementing the animation playback method, and the instances and application scenarios implemented by multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0164] Example 3

[0165] According to another aspect of an embodiment of the present invention, an electronic device is provided, including: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement any of the above-mentioned animation playback methods.

[0166] Example 4

[0167] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above animation playback methods.

[0168] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0169] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0171] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0172] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0173] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0174] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. An animation playing method, characterized in that: include: receiving an application startup request, wherein the application startup request is used to request startup of a target application; In response to the application startup request, when the startup mode of the target application is to convert from a closed state to a started state, push parameters of multiple animations to be selected are determined, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value and an animation click value, the predicted playback value is used to predict the number of playbacks of the corresponding animation to be selected when the target application is started this time, the predicted total playback value is used to predict the total number of playbacks of the corresponding animation to be selected, the loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold, the click value is used to represent the value generated after the animation to be selected is selected, and the animation click value is used to represent the ratio of the predicted number of clicks of the corresponding animation to the predicted total playback value; Determining a first target animation from the plurality of animations to be selected based on the push parameters of the plurality of animations to be selected; Playing the first target animation when starting the target application; Among them, based on the push parameters of the multiple animations to be selected, a first target animation is determined from the multiple animations to be selected, including: determining a first function according to the push parameters corresponding to the multiple animations to be selected, wherein the first function is used to represent the total loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold; determining a second function according to the push parameters corresponding to the multiple animations to be selected, wherein the second function is used to represent the predicted total value generated by the corresponding animation to be selected; determining an objective function with the goal of maximizing click-through rate and multiple constraints corresponding to the objective function according to the first function, the second function and the push parameters corresponding to the multiple animations to be selected, wherein the constraints include quantity preservation constraints, and the quantity preservation constraints are used to constrain the predicted playback value of the corresponding animation to be selected; solving the objective function under the constraints corresponding to the multiple animations to be selected, and determining the first target animation from the multiple animations to be selected.

2. The method according to claim 1, characterized in that The method further comprises: When the target application is started in a mode of switching from a background state to a foreground state, reading an animation storage result, wherein the animation storage result is used to determine an animation to be played when the target application is started this time; Determining a second target animation corresponding to the animation storage result; The second target animation is played when the target application is started.

3. The method according to claim 1, characterized in that In response to the application startup request, when the startup mode of the target application is to switch from a closed state to a started state, push parameters of a plurality of animations to be selected are determined, including: Obtaining behavior data of a target account corresponding to the target application, and animation data corresponding to each of the plurality of animations to be selected; According to the behavior data and the animation data corresponding to the plurality of animations to be selected, push parameters corresponding to the plurality of animations to be selected are determined.

4. The method according to claim 1, wherein Determining a first function based on the push parameters corresponding to the plurality of selected animations includes: Determine, based on the push parameters corresponding to the plurality of selected animations, the playback volume thresholds corresponding to the plurality of selected animations, and obtain the difference items corresponding to the plurality of selected animations by comparing the difference between the predicted total playback values ​​corresponding to the plurality of selected animations and the playback volume thresholds. Determine the difference items corresponding to the multiple animations to be selected, and multiply them by the loss values ​​corresponding to the multiple animations to be selected, to obtain a first function.

5. The method according to claim 1, wherein Determining a second function based on the push parameters corresponding to the plurality of selected animations includes: Determine, based on the push parameters corresponding to the plurality of animations to be selected, animation click values ​​corresponding to the plurality of animations to be selected, and multiply the animation click values ​​corresponding to the plurality of animations to obtain product terms corresponding to the plurality of animations to be selected; Determine the product terms corresponding to the plurality of animations to be selected, and multiply them by the product of the predicted total playback values ​​corresponding to the plurality of animations to be selected, to obtain a second function.

6. The method according to any one of claims 1 to 5, characterized in that After playing the target animation when starting the target application, the method further includes: Trigger animation storage request; In response to the animation storage request, the animation storage result is updated to obtain an updated stored animation.

7. An animation playback device, characterized in that: include: A receiving module, configured to receive an application startup request, wherein the application startup request is used to request startup of a target application; A first determination module is configured to, in response to the application startup request, determine push parameters of a plurality of animations to be selected when the startup mode of the target application is to switch from a closed state to a started state, wherein the push parameters include: a playback volume threshold, a predicted playback value, a predicted total playback value, a loss value, a click value, and an animation click value; the predicted playback value is used to predict the number of playbacks of the corresponding animation to be selected when the target application is started this time; the predicted total playback value is used to predict the total number of playbacks of the corresponding animation to be selected; the loss value is used to represent the loss generated when the predicted total playback value of the corresponding animation to be selected does not reach the playback volume threshold; the click value is used to represent the value generated after the animation to be selected is selected; and the animation click value is used to represent the ratio of the predicted number of clicks of the corresponding animation to be selected to the predicted total playback value; A second determining module is configured to determine a first target animation from the plurality of animations to be selected based on the push parameters of the plurality of animations to be selected; A playing module, configured to play the first target animation when the target application is started; Among them, the playback module is used to determine a first function based on the push parameters corresponding to the multiple selected animations, wherein the first function is used to represent the total loss generated when the predicted total playback value of the corresponding selected animation does not reach the playback volume threshold; determine a second function based on the push parameters corresponding to the multiple selected animations, wherein the second function is used to represent the predicted total value generated by the corresponding selected animation; determine an objective function with the goal of maximizing the click-through rate and multiple constraints corresponding to the objective function based on the first function, the second function and the push parameters corresponding to the multiple selected animations, wherein the constraints include quantity preservation constraints, and the quantity preservation constraints are used to constrain the predicted playback value of the corresponding selected animation; solve the objective function under the constraints corresponding to the multiple selected animations, and determine the first target animation from the multiple selected animations.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the animation playing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the animation playing method according to any one of claims 1 to 6.

Images