Interactive interface adjusting method and device, storage medium and electronic equipment

Abstract

The invention relates to an interactive interface adjusting method and device, a storage medium and electronic equipment, and relates to the technical field of man-machine interaction. The method comprises the steps that in response to a current interface touch event for a current interactive interface, current touch acceleration data is determined, inputting the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result; determining a to-be-touched interaction control based on the current touch intention prediction result, and dynamically adjusting an original control position of the to-be-touched interaction control to obtain a target control position; and performing picture redrawing on the current interactive interface based on the target control position to obtain a target interactive interface, and performing replacement display on the current interactive interface based on the target interactive interface. The system burden is reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of human-computer interaction technology, and in particular, to a method for adjusting an interactive interface, an apparatus for adjusting an interactive interface, a computer-readable storage medium, and an electronic device. Background Art

[0002] In some related technical solutions, a dynamic UI layout solution can be used to achieve game interface tracking. Specifically, in this solution, global coordinate transformation can be used to enable UI elements to follow screen movements in real time, thereby achieving the goal of maintaining synchronized displacement of all interface layers with camera movement. However, this solution has the following disadvantages: on the one hand, touch inaccuracy defects; that is, during actual gameplay, the inertial sliding of the screen can cause skill buttons to drift, causing players to accidentally touch the controls when operating skill buttons, reducing the user experience; on the other hand, in actual applications, the frame-by-frame redrawing of the entire UI layer causes a surge in GPU instructions, which in turn places a heavy burden on the system.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] The purpose of the present disclosure is to provide an interactive interface adjustment method, an interactive interface adjustment device, a computer-readable storage medium, and an electronic device, thereby at least to a certain extent overcoming the problems of accidental touch of controls and heavy system burden caused by the limitations and defects of related technologies.

[0005] According to one aspect of the present disclosure, a method for adjusting an interactive interface is provided, comprising:

[0006] In response to a current interface touch event on a current interactive interface, determining current touch acceleration data, and inputting the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result;

[0007] Determining an interactive control to be touched based on the current touch intention prediction result, and dynamically adjusting an original control position of the interactive control to be touched to obtain a target control position;

[0008] The current interactive interface is redrawn based on the target control position to obtain a target interactive interface, and the current interactive interface is replaced and displayed based on the target interactive interface.

[0009] According to one aspect of the present disclosure, a device for adjusting an interactive interface is provided, comprising:

[0010] a current touch intention prediction module, configured to determine current touch acceleration data in response to a current interface touch event on a current interactive interface, and input the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result;

[0011] a target control position determination module, configured to determine an interactive control to be touched based on the current touch intention prediction result, and dynamically adjust an original control position of the interactive control to be touched to obtain a target control position;

[0012] The interactive interface adjustment module is used to redraw the current interactive interface based on the target control position to obtain a target interactive interface, and replace the current interactive interface with the target interactive interface.

[0013] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements any one of the above-mentioned methods for adjusting the interactive interface.

[0014] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0015] processor; and

[0016] a memory for storing executable instructions of the processor;

[0017] The processor is configured to execute any one of the above-mentioned methods for adjusting the interactive interface by executing the executable instructions.

[0018] An embodiment of the present disclosure provides a method for adjusting an interactive interface. On the one hand, by responding to a current interface touch event for a current interactive interface, current touch acceleration data is determined, and the current touch acceleration data is input into a preset intention prediction model to obtain a current touch intention prediction result; then, based on the current touch intention prediction result, an interactive control to be touched is determined, and the original control position of the interactive control to be touched is dynamically adjusted to obtain a target control position; finally, based on the target control position, the current interactive interface is redrawn to obtain a target interactive interface, and the current interactive interface is replaced and displayed based on the target interactive interface; since the control position can be dynamically adjusted and the current interactive interface can be redrawn, the problem in the prior art that the skill button drifts due to the inertial sliding of the screen, thereby causing the player to accidentally touch the control when performing skill button operations, is solved; on the other hand, since the current interactive interface can be redrawn directly based on the target control position, there is no need to use the full UI layer frame-by-frame redrawing method for rush drawing, which reduces the drawing instructions required to be executed by the GPU and reduces the burden on the system.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0021] Figure 1 A flowchart schematically illustrates a method for adjusting an interactive interface according to an exemplary embodiment of the present disclosure.

[0022] Figure 2 A structural example diagram of a preset intention prediction model according to an exemplary embodiment of the present disclosure is schematically shown.

[0023] Figure 3 A flowchart schematically illustrates a method for training a preset intent prediction model according to an example embodiment of the present disclosure.

[0024] Figure 4 An example diagram of a scene obtained by vertically dividing the screen of a terminal device according to an example embodiment of the present disclosure is schematically shown.

[0025] Figure 5 An example diagram of a scene obtained by horizontally dividing the screen of a terminal device according to an example embodiment of the present disclosure is schematically shown.

[0026] Figure 6 A diagram schematically illustrates an example scenario of dynamic adjustment of an interactive control according to an example embodiment of the present disclosure.

[0027] Figure 7 A structural example diagram of an adjustment device for an interactive interface according to an exemplary embodiment of the present disclosure is schematically shown.

[0028] Figure 8 An electronic device for implementing a method for adjusting an interactive interface according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0030] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0031] In some related game interface following methods, dynamic adjustment of the interactive interface can be achieved based on the following methods:

[0032] In the first implementation scheme, the game interface can be followed based on a static UI (User Interface) layout scheme; specifically, in this scheme, a fixed coordinate system UI layer layout method can be used to achieve the game interface following; and, in this scheme, all interface elements maintain an absolute position unchanged in the screen coordinate system and do not adjust with the rotation of the viewing angle or the movement of the scene. However, this solution has the following disadvantages: on the one hand, there is a visual focus conflict; that is, in a specific game process, the UI layer blocks the key combat area (the blocking area is 18%-22% of the effective area of the screen), which makes it impossible to fully display a large part of the skill special effects in the combat area (relevant experiments show that the blocking ratio reaches 32%), thereby reducing the player's user experience; on the other hand, dynamic adaptation fails; that is, in the actual game process, due to the misalignment of the UI and the scene space when the perspective rotates (the offset is 60-80px), which will lead to cognitive dissonance in operation; on the other hand, there is a loss of layout zombieization; that is, the solution does not use the Z-axis depth compensation algorithm for compensation, which makes the difference between the depth of field of the UI in the 3D scene and the depth of field in the actual scene ≥2.5D, which will cause visual dizziness.

[0033] In the second implementation, the game interface can be followed using a dynamic UI layout scheme. Specifically, in this scheme, global coordinate transformations can be used to enable UI elements to follow screen motion in real time, thereby achieving the goal of synchronized displacement of all interface layers with camera motion. However, this scheme has the following drawbacks: First, touch inaccuracy. In actual gameplay, the inertial sliding of the screen can cause skill buttons to drift (with a maximum displacement difference of 45-60 points), resulting in players accidentally touching the skill buttons during operation, reducing the user experience. Furthermore, in relevant games, the skill touch error rate on mobile devices can be as high as 19.3%. Second, rendering performance overload. In actual applications, the frame-by-frame redrawing of the entire UI layer causes a surge in GPU (Graphics Processing Unit) instructions (≥380 Draw Calls per frame), and memory bandwidth usage exceeds 520MB / s. Third, synchronization delay loss. Because this scheme does not use a velocity vector compensation algorithm, UI response delays can reach up to 120-150ms during fast turns.

[0034] In the third implementation, the game interface can be followed based on a scenario-free UI layout. Specifically, in this solution, the UI layer can be forced to dynamically follow in specific scenarios such as plot dialogues, ensuring that interface elements remain visible. However, this solution has the following drawbacks: on the one hand, narrative immersion is destroyed; that is, in actual gameplay, the automatic UI following causes 63% of key plot frames to be blocked, and eye tracker data shows that user attention is distracted by 42%; on the other hand, audio and video synchronization is out of sync; that is, in actual gameplay, the UI movement sound effects and plot dialogue audio will produce frequency conflicts (the 200-400Hz frequency band has a superimposed attenuation of 12dB), which in turn causes audio and video synchronization out of sync; on the other hand, the situational logic is fragmented; that is, in actual gameplay, because this solution does not establish a state machine control model, there is a speed difference between the UI movement trajectory and the cinematic camera movement, resulting in a fragmented situational logic and a sense of cognitive dissonance.

[0035] In the fourth implementation scheme, the game interface can be followed according to the layout scheme of global redraw optimization; specifically, in this scheme, the dynamic UI performance loss can be compensated by increasing the GPU rendering frequency (such as the high-frequency refresh screen adaptation scheme). However, this scheme has the following defects: on the one hand, the energy efficiency ratio is unbalanced; that is, in the actual game process, a 120Hz full-frame redraw method is required to compensate for the dynamic UI performance loss; however, this method increases the GPU power consumption by 38%-45%, and the device surface temperature rises by ≥9°C; on the other hand, there is redundant resource waste; that is, in the actual game process, 78% of the UI redraw area is actually an invisible coverage area, which violates the mobile rendering optimization guidelines; on the other hand, there is a hardware compatibility risk; that is, in the actual game process, the hierarchical rendering strategy is not adopted, and the frame rate of low-end and mid-range devices (GPU≤Adreno618) plummets to 24-31FPS.

[0036] Based on this, this exemplary embodiment first provides a method for adjusting an interactive interface, which can be run on a terminal device; of course, those skilled in the art can also run the method disclosed in this disclosure on other platforms as needed, and this exemplary embodiment does not specifically limit this. Figure 1 As shown, the method for adjusting the interactive interface may include the following steps:

[0037] Step S110. In response to a current interface touch event on a current interactive interface, determining current touch acceleration data, and inputting the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result;

[0038] Step S120: determining the interactive control to be touched based on the current touch intention prediction result, and dynamically adjusting the original control position of the interactive control to be touched to obtain the target control position;

[0039] Step S130: redraw the current interactive interface based on the target control position to obtain a target interactive interface, and replace the current interactive interface with the target interactive interface.

[0040] In the above-described method for adjusting the interactive interface, on the one hand, by responding to the current interface touch event for the current interactive interface, the current touch acceleration data is determined, and the current touch acceleration data is input into a preset intention prediction model to obtain a current touch intention prediction result; then, based on the current touch intention prediction result, the interactive control to be touched is determined, and the original control position of the interactive control to be touched is dynamically adjusted to obtain a target control position; finally, based on the target control position, the current interactive interface is redrawn to obtain a target interactive interface, and the current interactive interface is replaced and displayed based on the target interactive interface; since the control position can be dynamically adjusted and the current interactive interface can be redrawn, the problem in the prior art that the skill button drifts due to the inertial sliding of the screen, thereby causing the player to accidentally touch the control when performing the skill button operation, is solved; on the other hand, since the current interactive interface can be redrawn directly based on the target control position, there is no need to use the full UI layer frame-by-frame redrawing method for rush drawing, which reduces the drawing instructions required to be executed by the GPU and reduces the burden on the system.

[0041] Hereinafter, the method for adjusting the interactive interface described in the exemplary embodiments of the present disclosure will be explained and illustrated in detail with reference to the accompanying drawings.

[0042] First, the terms involved in the exemplary embodiments of the present disclosure are explained and illustrated.

[0043] LSTM, Long Short-Term Memory, is a recurrent neural network that can be used to predict time series data.

[0044] SVM, Support Vector Machine, is a supervised learning model that can be used for feature classification and regression analysis.

[0045] GRU, Gated Recurrent Unit, is a model that can be used to capture semantic associations between long sequences.

[0046] DPI, Dots Per Inch, is the number of pixels per inch, which can be used to characterize the screen display accuracy of the terminal device's display.

[0047] FPS, Frames Per Second, frames per second, can be used to indicate the smoothness of the display screen of the terminal device.

[0048] LOD, Level of Detail, level of detail, which can be used to dynamically adjust rendering accuracy.

[0049] Secondly, the technical implementation principles of the exemplary embodiments of the present disclosure are explained and illustrated. Specifically, the method for adjusting the interactive interface described in the exemplary embodiments of the present disclosure dynamically adjusts the position and visibility of the UI layer by predicting the player's intention when a touch screen device performs a sliding operation, thereby achieving the purpose of dynamically adjusting the interactive interface. The dynamic adjustment method for the interactive interface described in the exemplary embodiments of the present disclosure is applicable to mobile MMORPG (Massive Multiplayer Online Role-Playing Game) and SLG (Simulation Game) game types that require frequent sliding operations.

[0050] Furthermore, the preset intention prediction model involved in the exemplary embodiment of the present disclosure is explained and illustrated. Specifically, refer to Figure 2 As shown, the preset intention prediction model may include a first input layer 201, multiple fully connected layers (fully connected layer 1, fully connected layer 2, ..., fully connected layer N) 202, a long short-term memory network LSTM 203, an intention prediction layer 204, and a first output layer 204. Among them, the role of each model layer in the intention prediction process will be described in detail later, and will not be further elaborated here. It should also be noted here that the long short-term memory network LSTM used here can also be replaced by GRU. In actual application, it can be selected according to actual needs. This example does not impose any special restrictions on this.

[0051] For further reference, Figure 3 As shown, the specific training process of the preset intention prediction model recorded here may include the following steps:

[0052] Step S310 , obtaining a historical event stream generated by a historical interface touch event within a time period consisting of a start timestamp to an end timestamp, and determining a historical coordinate sequence and a historical event result of the historical interface touch event according to the historical event stream.

[0053] Step S320 , determining historical touch acceleration data according to the historical coordinate sequence, and inputting the historical touch acceleration data, historical pressure values, historical contact areas, and historical game states into a network model to be trained to obtain a predicted event result.

[0054] Step S330: construct a loss function according to the historical event results and the predicted event results, and adjust the parameters of the network model to be trained based on the loss function to obtain a preset intention prediction model.

[0055] The following will further explain and illustrate the specific training process of the preset intention prediction model. Specifically, in the actual process of model training, data collection and labeling are required first; in the data collection process, MOBA (Multiplayer Online Battle Arena), FPS (First-person A data collection component is deployed in the game client corresponding to various game scenarios such as first-person shooting, SLG, and MMORPG, and based on the data collection component, raw touch event data (i.e., historical event stream), historical game state, and corresponding player final operation results generated by historical interface touch events are collected; further, the raw touch event data may include historical coordinate sequences, historical pressure values, and historical contact areas, etc. generated by historical interface touch events; wherein the historical coordinate sequences recorded here may include coordinate points and time points, the historical pressure values recorded here refer to the pressure exerted by the user when touching the interactive interface, and the historical contact areas recorded here refer to the contact area between the user and the interactive interface when touching the interactive interface; the historical game states recorded here may include combat states, map exploration states, and plot presentation stages, etc.; the player's final operation results recorded here may include continuous sliding distance, dwell position, and click confirmation, etc.; secondly, data labeling is required; specifically, during the data labeling process, the touch trajectory 200ms before each operation (accurate to 8ms intervals) may be recorded and annotated with action type labels (e.g., continuous sliding is marked as "1", click is marked as "0", etc.).

[0056] Secondly, the model is trained. Specifically, during the model training process, a cross-entropy loss function can be constructed based on historical event results and predicted event results, and model parameters can be optimized. In the specific optimization process, the Nadam optimizer can be used to achieve it.

[0057] The following will be combined Figure 2 as well as Figure 3 right Figure 1 The adjustment method of the interactive interface shown in the following is further explained and illustrated. Specifically:

[0058] In step S110 , in response to a current interface touch event on a current interactive interface, current touch acceleration data is determined, and the current touch acceleration data is input into a preset intention prediction model to obtain a current touch intention prediction result.

[0059] In this example embodiment, first, the current touch acceleration data is determined; specifically, it can be achieved in the following manner: in response to a current interface touch event for a current interactive interface, the start timestamp of the current interface touch event is determined, and the end timestamp is determined based on the start timestamp and a preset time interval; the current event stream generated by the current interface touch event in the time period consisting of the start timestamp to the end timestamp is obtained, and the current touch point sequence is determined based on the current event stream; the instantaneous touch speeds at different time points are determined based on the current touch point sequence, and the current touch acceleration data of the current interface touch event is determined based on the instantaneous touch speeds at different time points. Specifically, the preset time interval recorded here is 80ms; that is, when a current interface touch event for the current interactive interface is detected, the start timestamp is determined, and the end timestamp is determined after an interval of 80ms, and then the current event stream during this period is collected; wherein, the current event stream may include timestamps (μs level accuracy), event types such as EV_ABS, codes such as ABS_MT_POSITION_X, and coordinates or pressure values, etc.; further, the current touch point sequence recorded here, that is, the X / Y coordinate sequence aligned by timestamps, can be specifically shown as the following formula (1):

[0060] TouchPoint[i]=[(t0,x0,y0),(t1,x1,y1),...,(t2,x2,y2)]; Formula (1)

[0061] In an exemplary embodiment, determining the current touch acceleration data of a current interface touch event based on the instantaneous touch speed at different time points can be achieved by: determining the original acceleration components at different time points based on the instantaneous touch speed at different time points, and smoothing the original acceleration components at different time points to obtain target acceleration components at different time points; determining the maximum acceleration based on the device screen parameters of the terminal device, and normalizing the target acceleration components at different time points based on the maximum acceleration to obtain the current touch acceleration data at different time points. Specifically, in actual application, the specific process of determining the original acceleration components is as follows:

[0062] First, the five-point difference method is used to obtain the instantaneous touch speed. Specifically, the specific calculation process of the instantaneous speed can be shown in the following formula (2):

[0063]

[0064] Among them, v x(t) is the instantaneous velocity at time t, x is the horizontal coordinate of the coordinate point at time t, and Δt is the time interval between two adjacent moments in time.

[0065] Secondly, the original acceleration components at different time points are determined according to the instantaneous touch speed at different time points. Specifically, the specific calculation process of the original acceleration components at different time points can be shown in the following formula (3):

[0066]

[0067] Among them, a x(t) is the original acceleration component at time t.

[0068] Furthermore, in the process of smoothing the original acceleration components at different time points to obtain the target acceleration components at different time points, it can be implemented based on the Kalman filter method; wherein, the specific calculation process can be shown in the following formula (4):

[0069] a filtered =KalmanUpdate(a raw ); Formula (4)

[0070] Among them, a filtered is the target acceleration component, a raw Because of a x(t) The original acceleration component sequence is composed of KalmanUpdate(·), which is the Kalman filtering process. At the same time, in the Kalman filtering process, the process noise Q=0.01 and the observation noise R=0.1 are used.

[0071] Furthermore, in the process of determining the maximum acceleration, it is first necessary to map the physical parameters of the terminal device's screen; wherein, the terminal device recorded here is the terminal device that displays the current display interface, and the specific mapping process of the physical parameters can be shown in Table 1 below:

[0072] Table 1

[0073] parameter Calculation formula Example value (Huawei P50) Actual displacement Δx_mm=Δx_px / PPI×25.4 1px=0.106mm Acceleration range <![CDATA[a_max=(144Hz×Δx_max) / Δt 2 ]]> <![CDATA[3.5g(g=9.8m / s 2 )]]>

[0074] In the specific calculation process, after the actual displacement is obtained, the maximum displacement Δx_max can be determined from the actual displacement; then, the maximum acceleration a_max is determined based on the maximum displacement.

[0075] Finally, in the process of normalizing the target acceleration components at different time points, the following formula (5) can be used:

[0076]

[0077] Among them, a norm For the current touch acceleration data, device dpi The number of pixels per inch of the terminal device, devicerefresh_rate The frame refresh rate of the terminal device.

[0078] In an exemplary embodiment, inputting current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result can be achieved as follows: determining the current pressure value of the current interface touch event, the current contact area between the current interactive interface, and the current game state based on the current event stream generated by the current interface touch event within a time period consisting of a start timestamp and an end timestamp; using multiple fully connected layers to perform feature sorting on the current touch acceleration data, the current pressure value, the current contact area, and the current game state to obtain a current event feature corresponding to the current interface touch event; inputting the current event feature into a long short-term memory network to obtain a current touch intention prediction result; wherein the current touch intention prediction result includes any one of: continuous sliding, stopping sliding after a preset time interval, and performing a click operation after sliding to a preset position. That is, the obtained prediction result can include three categories of prediction probabilities: for example, the probability of continuous sliding, the probability of stopping sliding after a preset time interval, and the probability of performing a click operation after sliding to a preset position; of course, other categories can also be set according to actual needs, and this example does not impose any special restrictions on this.

[0079] In an example embodiment, after detecting the current interface touch event, it is also necessary to determine whether the current interface touch event is a false touch event; specifically, this can be achieved in the following manner: determine the current contact area between the current interface touch event and the current interactive interface, the current contact area of the current contact area, and the current pressure value; input the current contact area, current contact area, and current pressure value into a preset false touch event prediction model to obtain a false touch event prediction result; determine whether the current interface touch event is a false touch event based on the false touch event prediction result, and when determining that the current interface touch event is a normal event, determine the current touch acceleration data of the current interface touch event. That is, in the process of determining whether the current interface touch event is a false touch event, multiple dimensions such as contact area, contact area, and pressure value can be considered; the contact area recorded here refers to the event occurrence area of the current interface touch event; in actual application, the screen of the terminal device can be divided into a vertical nine-square grid (for details, please refer to Figure 4 As shown) or horizontal version of the nine-square grid (for details, please refer to Figure 5As shown), the contact area is determined according to the nine-square grid to which the specific event position of the current interface touch event belongs; the contact area recorded here refers to the contact area between the touch medium and the interface, and the touch medium can be a stylus or a finger, etc. This example does not impose special restrictions on this; the pressure value refers to the amount of pressure exerted during the touch process.

[0080] In an exemplary embodiment, the current contact area, current contact area, and current pressure value are input into a preset false touch event prediction model to obtain a false touch event prediction result, which can be achieved in the following manner: determining the touch shape regularity between the current interface touch event and the current interactive interface based on the current contact area, and determining the touch area change speed between the current interface touch event and the current interactive interface based on the current contact area; determining the pressing stability between the current interface touch event and the current interactive interface based on the current pressure value, and splicing the touch shape regularity, touch area change speed, and pressing stability to obtain an event feature splicing result; inputting the event feature splicing result into a preset false touch event prediction model to obtain the false touch event prediction result. Among them, the touch shape regularity recorded here can be determined based on the ellipticity of the current contact area; the touch area change speed recorded here can be determined based on the area gradient of the current contact area; the pressing stability recorded here can be achieved based on the mean square deviation of pressure fluctuations.

[0081] In an exemplary embodiment, the preset palm touch event prediction model described above may be a support vector machine (SVM). Meanwhile, the specific training process of the model may be implemented as follows: (1) data collection and annotation. Specifically, data of various terminal devices of different models (e.g., curved screens and flat screens) may be collected, and a large number of palm touch samples and normal operation samples may be collected. Then, the ellipticity, area gradient, and pressure fluctuation may be calculated respectively. The specific calculation process may be shown in Table 2 below:

[0082] Table 2

[0083] Feature Name Calculation method Physical meaning Ellipticity 1-(minor axis / major axis) Contact shape regularity Area gradient ΔS / Δt=(S_t-S_{t-5}) / 5Δt Contact surface change speed pressure fluctuations σ(P) (50ms window standard deviation) Compression stability

[0084] (2) Model training; Specifically, in the specific training process, the parameters need to be initialized first; then, the sample data is enhanced; in the data enhancement process, Gaussian noise can be added to the sample data (the specific parameters used are: μ = 0, σ = 0.05), and the ellipse of the contact area can be randomly rotated (the rotation angle range can be selected within ±15°); further, in the process of configuring the false touch label, it can be achieved in the following way: first, the contact ellipticity and area gradient are calculated every 8ms; second, when 5 consecutive frames meet: ellipticity>0.7 and area gradient<0.05px 2 / ms, it is determined to be a palm false touch; further, false touch events can be divided into mild false touch and severe false touch; for example, if the pressure value is less than 0.2, it is determined to be a mild false touch and the current touch event can be discarded; otherwise, it is determined to be a severe false touch; in the scenario of severe false touch, the effective touch area can be dynamically shrunk; the specific shrinking process is: active_area = original_area × (1-false touch confidence).

[0085] In step S120, the interactive control to be touched is determined based on the current touch intention prediction result, and the original control position of the interactive control to be touched is dynamically adjusted to obtain the target control position.

[0086] Specifically, the specific process of determining the target control position is as follows: if the current touch intention prediction result is that the probability of continuous sliding is greater than the first preset threshold or the probability of a click operation is greater than the second preset threshold, then the event occurrence position of the current interface touch event on the current interactive interface is obtained; the interactive control to be touched and the control type of the interactive control to be touched are determined according to the event occurrence position, and the original control position is dynamically adjusted according to the control type of the interactive control to be touched to obtain the target control position. That is, if it is determined that the user has the intention of continuous sliding or the intention of a click operation, dynamic adjustment of the interactive interface is required; otherwise, the touch event can be ignored; at the same time, the first preset threshold and the second preset threshold recorded here can be set according to actual needs, and this example does not impose special restrictions on this.

[0087] In an exemplary embodiment, dynamically adjusting the original control position according to the control type of the interactive control to be touched to obtain the target control position can be achieved as follows: determining a position compensation rule required for dynamically adjusting the original control position according to the control type of the interactive control to be touched; wherein the control type includes any one of an interactive operation type, an information display type, and an immersive display type, and the position compensation rule includes any one of a first position compensation rule corresponding to the interactive operation type, a second position compensation rule corresponding to the information display type, and a third position compensation rule corresponding to the immersive display type; based on the first position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the interactive operation type to obtain the target control position; or based on the second position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the information display type to obtain the target control position; or based on the third position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the immersive display type to obtain the target control position. That is, in actual application, different compensation rules can be set according to different touch areas and different control types to achieve the purpose of dynamic interface adjustment. At the same time, the first position compensation rule recorded here can be a reverse compensation rule, which can be specifically used to compensate for the position of skill interaction controls (such as virtual joysticks, etc.); the second position compensation rule recorded here can be, for example, a delay damping compensation rule, which can be specifically used to compensate for the position of interactive controls such as minimaps and task tracking; the third position compensation rule recorded here can be, for example, a scene freezing rule, which can be specifically used to compensate for the position of cutscene subtitles.

[0088] In an example embodiment, based on the first position compensation rule, the original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted to obtain the target control position, which can be achieved in the following way: first, the current anchor point area of the interactive control to be touched in the current interactive interface is determined, and the event offset threshold and the current damping coefficient are determined based on the current anchor point area; secondly, the real-time sliding screen speed and the maximum tracking speed of the device of the current interface touch event on the current interactive interface are determined, and the first position compensation result is determined based on the event offset threshold, the current damping coefficient, the real-time sliding screen speed and the maximum tracking speed of the device; then, the original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted based on the first position compensation result to obtain the target control position.

[0089] The following further explains and illustrates the dynamic adjustment process of the original control position of the interactive control to be touched in the interactive operation type. Specifically, in the actual dynamic adjustment process, it is first necessary to calculate the first position compensation result; wherein, the specific calculation process of the first position compensation result can be shown in the following formula (6):

[0090]

[0091] Among them, ΔUI pos1 is the first position compensation result, k is the current damping coefficient, ΔTouch offset is the event offset threshold. In actual application, if the current anchor point area is the upper left or lower right area of the nine-square grid, the event offset threshold can be 0.3 (a larger offset threshold can also be set); otherwise, the event offset threshold can be 0.8. In actual application, it can also be set according to actual needs. This example does not impose any special restrictions on this. v is the real-time sliding speed, v max is the maximum tracking speed of the device; under this premise, the specific calculation process of the current damping coefficient can be shown in the following formula (7):

[0092] k=k base *α device *β region ; Formula (7)

[0093] Among them, k base is the basic damping coefficient, k base =0.8;α device Equipment performance factor, β region is the regional weight factor; the specific values of the device performance factor and the regional weight factor can be referred to as shown in Table 3 and Table 4:

[0094] Table 3

[0095] Device Type α_device value Judgment conditions high-end equipment 1.2 GPU frame time ≤ 8ms, touch sampling rate ≥ 240Hz mid-range devices 1.0 8ms < GPU frame time ≤ 16ms Low-end devices 0.6 GPU frame time > 16ms

[0096] Table 4

[0097] Nine-square grid area β_region Applicable control examples Core operating area 1.2 Skill button, shooting button Middle functional area 0.9 Minimap, backpack icon Marginal information area 0.5 Health bar, task prompts

[0098] It should be noted that when the player is detected in combat, the core area coefficient is automatically increased to 1.5; the game status detection process can be obtained through the game event bus.

[0099] Furthermore, the specific calculation process of the real-time sliding screen speed can be shown as the following formula (8):

[0100]

[0101] Among them, v is the real-time sliding speed, Δx is the horizontal moving distance, Δy is the vertical moving distance, t current is the start timestamp, t current Current timestamp. In practical applications, we first need to use a sliding window with a window width of 5 (corresponding to 40ms data) to eliminate jitter noise, and then convert the pixel speed into physical speed (unit: mm / s). The specific conversion process can be shown in the following formula (9):

[0102]

[0103] Among them, v phy is the converted real-time sliding screen speed, DPI is the number of pixels per inch; v pixel is the speed calculated by formula (8). Taking a certain brand of mobile phone as an example, the specific value of DPI is 450 and the specific value of refresh rate is 120Hz, then the real-time sliding speed is 318mm / s.

[0104] Furthermore, the specific calculation process of the maximum tracking speed of the device recorded above can be shown as the following formula (10):

[0105] v max =min(touch sampling rate*0.8, GPU rendering capability threshold); Formula (10)

[0106] Among them, v max is the maximum tracking speed of the device; at the same time, the touch sampling rate needs to meet the following conditions: max_touch = sampling rate (Hz) * maximum single-frame displacement (px); for example, a 240Hz touch screen allows a maximum single-frame displacement of 6px, so v_max_touch = 1440px / s. Furthermore, the GPU rendering capability threshold needs to meet the following conditions: For example, if the device frame time is 10ms, then v_max_gpu = 70px / ms = 70000px / s. In actual applications, the maximum tracking speed of a device can also be determined by the device level; for example, e-sports-level devices can use a value of 2000px / s; flagship-level devices can use a value of 1500px / s; and general-level devices can use a value of 1000px / s.

[0107] Furthermore, after obtaining the first position compensation result, the original position of the interactive control to be touched for the interactive operation type can be dynamically adjusted based on the first position compensation result to obtain the target control position. Specifically, for skill-based interactive controls, the specific adjustment process can be implemented as follows: First, capture the original control position (x_raw, y_raw) and record the contact pressure value P∈[0,1]; second, perform dynamic adjustment; specifically, x_calib = x_raw + ΔUI_x × alpha; y_calib = y_raw + ΔUI_y × alpha; the specific value of alpha is alpha = log2(460 / 326) + 1 ≈ 1.48. Furthermore, if the contact pressure value is less than 0.3, pressure compensation is required; the specific compensation process is: x_final = x_calib × (1 + 0.5 * (0.3-P)); based on this method, the anti-false touch mechanism can be triggered; further, if the coordinates exceed the button hot zone after calibration, they are mapped to the nearest edge; the specific mapping process is: if x_final>button_right, then x_final = button_right-5px, in order to retain a 5px trigger buffer. Among them, the specific dynamic adjustment scene example diagram can be referred to Figure 6 shown.

[0108] In an example embodiment, based on the second position compensation rule, the original control position of the interactive control to be touched of the information display type is dynamically adjusted to obtain the target control position, which can be achieved as follows: first, a second-order damping system differential equation is constructed, and the first event displacement and the second event displacement of the current interface touch event at two adjacent time points are determined according to the second-order damping system differential equation; secondly, the delay coefficient and the critical damping ratio of the current interface touch event are determined, and the second position compensation result is determined according to the first event displacement, the second event displacement, the delay coefficient and the critical damping ratio; then, the original control position of the interactive control to be touched of the information display type is dynamically adjusted according to the second position compensation result to obtain the target control position.

[0109] The following further explains and illustrates the dynamic adjustment process of the original control position of the interactive control to be touched of the information display type. Specifically, first, a second-order damping system differential equation is constructed; wherein, the second-order damping system differential equation can be specifically shown as the following formula (11):

[0110]

[0111] Where F(t) is the external force; m is the normalized mass, which is set to 1.0; c is the damping coefficient, k' is the stiffness coefficient, τ is the delay coefficient, with a specific value of 0.3. It should be noted that the delay coefficient can also be dynamically adjusted according to the control type. For example, for map controls in large map dragging scenarios, the delay coefficient can be 0.5s; for backpack controls in fast item switching scenarios, the delay coefficient can be 0.2ss; for controls in skill control bars in high-frequency skill release scenarios, the delay coefficient can be 0.15s; ξ is the critical damping ratio, with a specific value of 0.7. Under this premise, it can be calculated that c = 9.33, k' = 11.111. Based on the known formula, the first event displacement Δx(t) and the second event displacement Δx(t-1) at two adjacent time points can be obtained.

[0112] Secondly, the second position compensation result is determined. Specifically, the specific determination process of the second position compensation result can be shown in the following formula (12):

[0113]

[0114] Among them, w n is the natural frequency, and its specific value is w d is the damped oscillation frequency, the specific value is Δt is the refresh frequency, and the specific value is Δt=0.0167s.

[0115] Finally, after obtaining the second position compensation result, the target control position can be determined based on the corresponding position compensation result. Specifically, x_calib = x_raw + ΔUI_x × alpha; y_calib = y_raw + ΔUI_y × alpha; the specific value of alpha is alpha = log2(460 / 326) + 1 ≈ 1.48.

[0116] In an example embodiment, based on the third position compensation rule, the original control position of the interactive control to be touched of the immersive display type is dynamically adjusted to obtain the target control position, which can be achieved in the following way: first, the virtual camera parameters of the virtual camera in the current interactive interface and the movement vector of the virtual camera in the current interactive interface are determined; secondly, the third position compensation result is determined according to the virtual camera parameters, the movement vector and the anchor point weight of the current anchor point area where the interactive control to be touched is located in the current interactive interface; then, the original control position of the interactive control to be touched of the immersive display type is dynamically adjusted according to the third position compensation result to obtain the target control position.

[0117] The following will explain and illustrate the dynamic adjustment process of the original control position of the interactive control to be touched in the immersive display type. Specifically, first, the third position compensation result is determined; wherein the specific determination process of the third position compensation result can be shown in the following formula (13):

[0118] ΔUI pos3 =-k camera *(camera movement vector*UI anchor weight); Formula (13)

[0119] Among them, ΔUI pos3 is the third position compensation result; k camera are virtual camera parameters, and there are: The specific value of the UI anchor weight is consistent with the specific value of the anchor weight recorded above, and no further details will be given here. The specific calculation process of the camera movement vector is: ∫[camera speed*(-k freeze )]dt; where k freeze is the freezing coefficient, and there is: k freeze = camera speed threshold * screen size coefficient; camera speed threshold v_threshold = max(30px / s, 0.1×screen width / second); for example, the threshold for a 1080p screen (1080px width) is 108px / s.

[0120] Finally, after obtaining the third position compensation result, the target control position can be determined based on the corresponding position compensation result. Specifically, x_calib = x_raw + ΔUI_x × alpha; y_calib = y_raw + ΔUI_y × alpha; the specific value of alpha is alpha = log2(460 / 326) + 1 ≈ 1.48.

[0121] In step S130, the current interactive interface is redrawn based on the target control position to obtain a target interactive interface, and the current interactive interface is replaced and displayed based on the target interactive interface.

[0122] In this example embodiment, first, the current interactive interface is redrawn based on the target control position to obtain the target interactive interface; specifically, this can be achieved in the following manner: according to the real-time sliding speed of the current interface touch event on the current interactive interface and the device type of the terminal device, the screen redrawing mode required for redrawing the current interactive interface is determined; wherein, the screen redrawing mode includes a high frame rate mode or a dirty rectangle mode; based on the screen redrawing mode, the current interactive interface is redrawn according to the target control position to obtain the target interactive interface. Specifically, in actual application, when the sliding speed is greater than 800px / s, the number of instances of the particle system is limited to ≤50, and the font texture is downsampled to 1 / 4 of the original size; if the sliding speed is less than 800px / s, the number of instances of the particle system is determined according to the actual situation and the original size of the font texture is used; under this premise, the device type also needs to be determined; for example, if it is a high-end device, the high frame rate mode is used (that is, all areas are updated); otherwise, the dirty rectangle mode is used (that is, only the changed area is updated). Secondly, the current interactive interface can be replaced based on the target interactive interface.

[0123] At this point, the interactive interface adjustment method described in the exemplary embodiments of this disclosure has been fully implemented. Based on the aforementioned content, it can be seen that the interactive interface adjustment method described in the exemplary embodiments of this disclosure can reduce the GPU load rate while improving operational accuracy, thereby achieving the purpose of enhancing the user's gaming experience.

[0124] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0125] The exemplary embodiment of the present disclosure also provides an adjustment device for an interactive interface. Figure 7 As shown, the interactive interface adjustment device may include a current touch intention prediction module 710, a target control position determination module 720, and an interactive interface adjustment module 730. Among them:

[0126] The current touch intention prediction module 710 may be configured to determine current touch acceleration data in response to a current interface touch event on a current interactive interface, and input the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result;

[0127] The target control position determination module 720 may be configured to determine the interactive control to be touched based on the current touch intention prediction result, and dynamically adjust the original control position of the interactive control to be touched to obtain the target control position;

[0128] The interactive interface adjustment module 730 can be used to redraw the current interactive interface based on the target control position to obtain a target interactive interface, and replace the current interactive interface with the target interactive interface.

[0129] In an exemplary embodiment of the present disclosure, in response to a current interface touch event for a current interactive interface, current touch acceleration data is determined, including: in response to the current interface touch event for the current interactive interface, a start timestamp of the current interface touch event is determined, and an end timestamp is determined based on the start timestamp and a preset time interval; a current event stream generated by the current interface touch event in a time period consisting of the start timestamp to the end timestamp is obtained, and a current touch point sequence is determined based on the current event stream; instantaneous touch speeds at different time points are determined based on the current touch point sequence, and current touch acceleration data of the current interface touch event is determined based on the instantaneous touch speeds at different time points.

[0130] In an exemplary embodiment of the present disclosure, current touch acceleration data of a current interface touch event is determined according to instantaneous touch speeds at different time points, including: determining original acceleration components at different time points according to the instantaneous touch speeds at different time points, and smoothing the original acceleration components at different time points to obtain target acceleration components at different time points; determining a maximum acceleration according to device screen parameters of a terminal device, and normalizing the target acceleration components at different time points according to the maximum acceleration to obtain current touch acceleration data at different time points.

[0131] In an exemplary embodiment of the present disclosure, the preset intention prediction model includes multiple fully connected layers and a long short-term memory network; wherein, the current touch acceleration data is input into the preset intention prediction model to obtain a current touch intention prediction result, including: determining the current pressure value of the current interface touch event, the current contact area between the current interactive interface and the current game state according to the current event stream generated by the current interface touch event in the time period consisting of a start timestamp to an end timestamp; using multiple fully connected layers to perform feature sorting on the current touch acceleration data, the current pressure value, the current contact area and the current game state to obtain a current event feature corresponding to the current interface touch event; inputting the current event feature into the long short-term memory network to obtain a current touch intention prediction result; wherein, the current touch intention prediction result includes any one of continuous sliding, stopping sliding after a preset time period, and performing a click operation after sliding to a preset position.

[0132] In an exemplary embodiment of the present disclosure, the preset intention prediction model is trained in the following manner: obtaining a historical event stream generated by a historical interface touch event within a time period consisting of a start timestamp to an end timestamp, and determining a historical coordinate sequence and a historical event result of the historical interface touch event based on the historical event stream; determining historical touch acceleration data based on the historical coordinate sequence, and inputting the historical touch acceleration data, historical pressure value, historical contact area and historical game state into the network model to be trained to obtain a predicted event result; constructing a loss function based on the historical event results and the predicted event results, and adjusting the parameters of the network model to be trained based on the loss function to obtain a preset intention prediction model.

[0133] In an exemplary embodiment of the present disclosure, the adjustment device for the interactive interface further includes:

[0134] an event feature determination module, configured to determine a current contact region between the current interface touch event and the current interactive interface, a current contact area of the current contact region, and a current pressure value;

[0135] a false touch event prediction module, configured to input the current contact region, the current contact area, and the current pressure value into a preset false touch event prediction model to obtain a false touch event prediction result;

[0136] The false touch event determination module is used to determine whether the current interface touch event is a false touch event based on the false touch event prediction result, and when it is determined that the current interface touch event is a normal event, determine the current touch acceleration data of the current interface touch event.

[0137] In an exemplary embodiment of the present disclosure, the current contact area, the current contact area and the current pressure value are input into a preset false touch event prediction model to obtain a false touch event prediction result, including: determining the touch shape regularity between the current interface touch event and the current interactive interface according to the current contact area, and determining the touch area change speed between the current interface touch event and the current interactive interface according to the current contact area; determining the pressing stability between the current interface touch event and the current interactive interface according to the current pressure value, and splicing the touch shape regularity, touch area change speed and pressing stability to obtain an event feature splicing result; inputting the event feature splicing result into the preset false touch event prediction model to obtain the false touch event prediction result.

[0138] In an exemplary embodiment of the present disclosure, the interactive control to be touched is determined based on the current touch intention prediction result, and the original control position of the interactive control to be touched is dynamically adjusted to obtain the target control position, including: if the current touch intention prediction result is that the probability of continuous sliding is greater than a first preset threshold or the probability of a click operation is greater than a second preset threshold, then obtaining the event occurrence position of the current interface touch event on the current interactive interface; determining the interactive control to be touched and the control type of the interactive control to be touched according to the event occurrence position, and dynamically adjusting the original control position according to the control type of the interactive control to be touched to obtain the target control position.

[0139] In an exemplary embodiment of the present disclosure, the original control position is dynamically adjusted according to the control type of the interactive control to be touched to obtain the target control position, including: determining the position compensation rule required for dynamically adjusting the original control position according to the control type of the interactive control to be touched; wherein the control type includes any one of an interactive operation type, an information display type and an immersive display type, and the position compensation rule includes any one of a first position compensation rule corresponding to the interactive operation type, a second position compensation rule corresponding to the information display type and a third position compensation rule corresponding to the immersive display type; based on the first position compensation rule, the original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted to obtain the target control position; or based on the second position compensation rule, the original control position of the interactive control to be touched of the information display type is dynamically adjusted to obtain the target control position; or based on the third position compensation rule, the original control position of the interactive control to be touched of the immersive display type is dynamically adjusted to obtain the target control position.

[0140] In an exemplary embodiment of the present disclosure, based on the first position compensation rule, the original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted to obtain the target control position, including: determining the current anchor point area where the interactive control to be touched is located in the current interactive interface, and determining the event offset threshold and the current damping coefficient based on the current anchor point area; determining the real-time sliding speed of the current interface touch event on the current interactive interface and the maximum tracking speed of the device, and determining the first position compensation result based on the event offset threshold, the current damping coefficient, the real-time sliding speed and the maximum tracking speed of the device; based on the first position compensation result, the original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted to obtain the target control position.

[0141] In an exemplary embodiment of the present disclosure, based on the second position compensation rule, the original control position of the interactive control to be touched of the information display type is dynamically adjusted to obtain the target control position, including: constructing a second-order damping system differential equation, and determining the first event displacement and the second event displacement of the current interface touch event at two adjacent time points according to the second-order damping system differential equation; determining the delay coefficient and the critical damping ratio of the current interface touch event, and determining the second position compensation result according to the first event displacement, the second event displacement, the delay coefficient and the critical damping ratio; dynamically adjusting the original control position of the interactive control to be touched of the information display type according to the second position compensation result to obtain the target control position.

[0142] In an exemplary embodiment of the present disclosure, based on the third position compensation rule, the original control position of the interactive control to be touched of the immersive display type is dynamically adjusted to obtain the target control position, including: determining the virtual camera parameters of the virtual camera in the current interactive interface and the movement vector of the virtual camera in the current interactive interface; determining the third position compensation result according to the virtual camera parameters, the movement vector and the anchor point weight of the current anchor point area where the interactive control to be touched is located in the current interactive interface; dynamically adjusting the original control position of the interactive control to be touched of the immersive display type according to the third position compensation result to obtain the target control position.

[0143] In an exemplary embodiment of the present disclosure, the target interactive interface is obtained by redrawing the current interactive interface based on the target control position, including: determining the screen redrawing mode required for redrawing the current interactive interface according to the real-time sliding speed of the current interface touch event on the current interactive interface and the device type of the terminal device; wherein the screen redrawing mode includes a high frame rate mode or a dirty rectangle mode; based on the screen redrawing mode, the current interactive interface is redrawn according to the target control position to obtain the target interactive interface.

[0144] The specific details of each module in the above-mentioned interactive interface adjustment device have been described in detail in the corresponding interactive interface adjustment method, so they will not be repeated here.

[0145] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0146] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0147] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. Those skilled in the art will appreciate that various aspects of the present disclosure can be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as a circuit, module, or system.

[0148] Refer to the following Figure 8 800 according to this embodiment of the present disclosure will be described. Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0149] like Figure 8 As shown, electronic device 800 is implemented as a general-purpose computing device. Components of electronic device 800 may include, but are not limited to, the aforementioned at least one processing unit 810, the aforementioned at least one storage unit 820, a bus 830 connecting various system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0150] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps described in the "Exemplary Method" section of the present disclosure according to various exemplary embodiments. For example, the processing unit 810 can perform the following steps: Figure 1 Step S110 shown in: in response to the current interface touch event for the current interactive interface, determine the current touch acceleration data, and input the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result; step S120: determine the interactive control to be touched based on the current touch intention prediction result, and dynamically adjust the original control position of the interactive control to be touched to obtain a target control position; step S130: redraw the current interactive interface based on the target control position to obtain a target interactive interface, and replace the current interactive interface based on the target interactive interface.

[0151] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0152] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0153] Bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0154] The electronic device 800 can also communicate with one or more external devices 900 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 850. Furthermore, the electronic device 800 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0155] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0156] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present disclosure.

[0157] According to an embodiment of the present disclosure, a program product for implementing the above-mentioned method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0158] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0159] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0161] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0162] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0163] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not invented herein. The specification and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A method for adjusting an interactive interface, characterized in that: include: In response to a current interface touch event on a current interactive interface, determining current touch acceleration data, and inputting the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result; Determining an interactive control to be touched based on the current touch intention prediction result, and dynamically adjusting an original control position of the interactive control to be touched to obtain a target control position; The current interactive interface is redrawn based on the target control position to obtain a target interactive interface, and the current interactive interface is replaced and displayed based on the target interactive interface.

2. The method for adjusting the interactive interface according to claim 1, characterized in that: In response to a current interface touch event on a current interactive interface, current touch acceleration data is determined, including: In response to a current interface touch event for a current interactive interface, determining a start timestamp of the current interface touch event, and determining an end timestamp based on the start timestamp and a preset time interval; Acquire a current event stream generated by the current interface touch event within a time period consisting of the start timestamp to the end timestamp, and determine a current touch point sequence according to the current event stream; Instantaneous touch speeds at different time points are determined according to the current touch point sequence, and current touch acceleration data of the current interface touch event is determined according to the instantaneous touch speeds at different time points.

3. The method for adjusting the interactive interface according to claim 2, wherein: Determine the current touch acceleration data of the current interface touch event based on the instantaneous touch speed at different time points, including: determining original acceleration components at different time points according to the instantaneous touch speeds at different time points, and performing smoothing on the original acceleration components at different time points to obtain target acceleration components at different time points; The maximum acceleration is determined according to the device screen parameters of the terminal device, and the target acceleration components at different time points are normalized according to the maximum acceleration to obtain current touch acceleration data at different time points.

4. The method for adjusting the interactive interface according to claim 1, wherein: The preset intention prediction model includes multiple fully connected layers and a long short-term memory network; Inputting the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result, including: Determining, based on a current event stream generated by the current interface touch event within a time period consisting of a start timestamp and an end timestamp, a current pressure value of the current interface touch event, a current contact area with the current interactive interface, and a current game state; Using multiple fully connected layers to perform feature sorting on the current touch acceleration data, the current pressure value, the current contact area, and the current game state, to obtain a current event feature corresponding to the current interface touch event; The current event feature is input into a long short-term memory network to obtain a current touch intention prediction result; wherein the current touch intention prediction result includes any one of continuous sliding and clicking.

5. The method for adjusting the interactive interface according to claim 1 or 4, characterized in that: The preset intention prediction model is trained in the following way: Acquire a historical event stream generated by a historical interface touch event within a time period consisting of a start timestamp to an end timestamp, and determine a historical coordinate sequence and a historical event result of the historical interface touch event based on the historical event stream; Determining historical touch acceleration data according to the historical coordinate sequence, and inputting the historical touch acceleration data, historical pressure values, historical contact areas, and historical game states into a network model to be trained to obtain a predicted event result; A loss function is constructed according to the historical event results and the predicted event results, and the parameters of the network model to be trained are adjusted based on the loss function to obtain a preset intention prediction model.

6. The method for adjusting the interactive interface according to claim 1, wherein: Before determining the current touch acceleration data, the method for adjusting the interactive interface further includes: Determine a current contact region between the current interface touch event and the current interactive interface, a current contact area of the current contact region, and a current pressure value; Inputting the current contact region, the current contact area, and the current pressure value into a preset false touch event prediction model to obtain a false touch event prediction result; It is determined whether the current interface touch event is a false touch event according to the false touch event prediction result, and when it is determined that the current interface touch event is a normal event, current touch acceleration data of the current interface touch event is determined.

7. The method for adjusting the interactive interface according to claim 6, characterized in that: Inputting the current contact region, current contact area, and current pressure value into a preset false touch event prediction model to obtain a false touch event prediction result, including: Determining a touch shape regularity between the current interface touch event and the current interactive interface according to the current contact area, and determining a touch area change speed between the current interface touch event and the current interactive interface according to the current contact area; Determining the pressing stability between the current interface touch event and the current interactive interface according to the current pressure value, and splicing the touch shape regularity, touch area change speed, and pressing stability to obtain an event feature splicing result; The event feature splicing result is input into a preset false touch event prediction model to obtain the false touch event prediction result.

8. The method for adjusting the interactive interface according to claim 1, wherein: Determining the interactive control to be touched based on the current touch intention prediction result, and dynamically adjusting the original control position of the interactive control to be touched to obtain a target control position, including: If the current touch intention prediction result is that the probability of continuous sliding is greater than a first preset threshold or the probability of a click operation is greater than a second preset threshold, then obtaining the event occurrence position of the current interface touch event on the current interactive interface; The interactive control to be touched and the control type of the interactive control to be touched are determined according to the event occurrence position, and the original control position is dynamically adjusted according to the control type of the interactive control to be touched to obtain a target control position.

9. The method for adjusting the interactive interface according to claim 8, characterized in that: Dynamically adjusting the original control position according to the control type of the interactive control to be touched to obtain a target control position includes: Determining, according to the control type of the interactive control to be touched, a position compensation rule required for dynamically adjusting the position of the original control; wherein the control type includes any one of an interactive operation type, an information display type, and an immersive display type, and the position compensation rule includes any one of a first position compensation rule corresponding to the interactive operation type, a second position compensation rule corresponding to the information display type, and a third position compensation rule corresponding to the immersive display type; Based on the first position compensation rule, dynamically adjust the original control position of the interactive control to be touched of the interactive operation type to obtain the target control position; or Based on the second position compensation rule, dynamically adjust the original control position of the interactive control to be touched of the information display type to obtain the target control position; or Based on the third position compensation rule, the original control position of the interactive control to be touched of the immersive display type is dynamically adjusted to obtain the target control position.

10. The method for adjusting the interactive interface according to claim 9, characterized in that: Based on the first position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the interactive operation type to obtain the target control position includes: Determining a current anchor point area where the interactive control to be touched is located on the current interactive interface, and determining an event offset threshold and a current damping coefficient according to the current anchor point area; Determining a real-time sliding speed of the current interface touch event on the current interactive interface and a maximum tracking speed of the device, and determining a first position compensation result according to the event offset threshold, the current damping coefficient, the real-time sliding speed, and the maximum tracking speed of the device; The original control position of the interactive control to be touched of the interactive operation type is dynamically adjusted based on the first position compensation result to obtain a target control position.

11. The method for adjusting the interactive interface according to claim 9, characterized in that: Based on the second position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the information display type to obtain the target control position includes: Constructing a second-order damping system differential equation, and determining a first event displacement and a second event displacement of a current interface touch event at two adjacent time points according to the second-order damping system differential equation; Determining a delay coefficient and a critical damping ratio of a current interface touch event, and determining a second position compensation result according to the first event displacement, the second event displacement, the delay coefficient, and the critical damping ratio; The original control position of the interactive control to be touched of the information display type is dynamically adjusted according to the second position compensation result to obtain a target control position.

12. The method for adjusting the interactive interface according to claim 9, wherein: Based on the third position compensation rule, dynamically adjusting the original control position of the interactive control to be touched of the immersive display type to obtain the target control position includes: Determining virtual camera parameters of a virtual camera in the current interactive interface and a movement vector of the virtual camera in the current interactive interface; Determining a third position compensation result according to the virtual camera parameters, the movement vector, and the anchor point weight of the interactive control to be touched in the current anchor point area where the current interactive interface is located; The original control position of the interactive control to be touched of the immersive display type is dynamically adjusted according to the third position compensation result to obtain a target control position.

13. The method for adjusting the interactive interface according to claim 1, characterized in that: Redraw the current interactive interface based on the target control position to obtain the target interactive interface, including: Determining a screen redrawing mode required for redrawing the current interactive interface based on a real-time sliding speed of the current interface touch event on the current interactive interface and a device type of the terminal device; wherein the screen redrawing mode includes a high frame rate mode or a dirty rectangle mode; Based on the screen redrawing mode, the current interactive interface is redrawn according to the target control position to obtain the target interactive interface.

14. A device for adjusting an interactive interface, characterized in that: include: a current touch intention prediction module, configured to determine current touch acceleration data in response to a current interface touch event on a current interactive interface, and input the current touch acceleration data into a preset intention prediction model to obtain a current touch intention prediction result; a target control position determination module, configured to determine an interactive control to be touched based on the current touch intention prediction result, and dynamically adjust an original control position of the interactive control to be touched to obtain a target control position; The interactive interface adjustment module is used to redraw the current interactive interface based on the target control position to obtain a target interactive interface, and replace the current interactive interface with the target interactive interface.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for adjusting the interactive interface according to any one of claims 1 to 13 is implemented.

16. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the method for adjusting the interactive interface according to any one of claims 1 to 13 by executing the executable instructions.

Images