Freezing Screen Detection Method and Electronic Device

Abstract

Embodiments of the present application disclose a frozen screen detection method and an electronic device. The method may include: in response to the frozen screen detection function being in an enabled state, determining a first feature set based on touch data and operating parameters of touch events within a first time period. The first feature set includes touch statistical features corresponding to each time window in at least one time window within the first time period, and the touch statistical features indicate time-dependent covariates and non-time-dependent covariates within the corresponding time window; generating a prediction feature set corresponding to the first feature set based on the first feature set; the prediction feature set includes prediction features corresponding to each time window; generating a frozen screen detection result based on loss parameters corresponding to the prediction features corresponding to each time window; the frozen screen detection result indicates whether there is a frozen screen in the electronic device within the first time period. In this way, it can be detected whether there is a frozen screen in the electronic device during a certain time period, which helps to improve the accuracy and efficiency of frozen screen detection.

Description

Technical Field

[0001] This application relates to the technical field of electronic devices, and particularly to a method for detecting frozen screen and an electronic device. Background Art

[0002] With the rapid development of electronic technology, touch technology is widely used in various electronic devices. For example, touch panels are integrated in the display screens of electronic devices such as mobile phones, tablet computers, wearable devices, and teaching all-in-one machines, enabling the electronic devices to have touch functions while displaying.

[0003] After detecting a touch event, these electronic devices with touch functions may experience frozen screen. Frozen screen means that the electronic device can detect a touch event but cannot jump to the user interface corresponding to the touch event. For example, the electronic device detects a click operation on the application icon of a certain application, but fails to display the corresponding interface of the application. The occurrence of frozen screen in the electronic device will result in poor user experience. Therefore, detecting whether the electronic device has a frozen screen is a very necessary technology. Summary of the Invention

[0004] Embodiments of this application provide a method for detecting frozen screen and an electronic device, which can detect whether the electronic device has a frozen screen and helps to improve the accuracy and efficiency of frozen screen detection.

[0005] In a first aspect, embodiments of this application provide a method for detecting frozen screen, which can be applied to an electronic device. The method includes: in response to the frozen screen detection function being in an enabled state, obtaining touch data and operation parameters of touch events within a first time period; determining a first feature set based on the touch data and operation parameters of the touch events, where the first feature set includes touch statistical features corresponding to each time window in at least one time window, and the touch statistical features indicate time-dependent covariates and non-time-dependent covariates within the corresponding time window; the first time period includes at least one time window; generating a prediction feature set corresponding to the first feature set based on the first feature set; the prediction feature set includes prediction features corresponding to each time window; generating a frozen screen detection result based on loss parameters corresponding to the prediction features corresponding to each time window; the frozen screen detection result indicates whether the electronic device has a frozen screen within the first time period.

[0006] It can be seen that when the frozen screen detection function of the electronic device is enabled, the electronic device can determine the first feature set based on the touch data and operation parameters of the touch events, and then generate a frozen screen detection result based on the prediction feature set corresponding to the first feature set, which can detect whether the electronic device has a frozen screen and helps to improve the accuracy and efficiency of frozen screen detection.

[0007] In combination with the first aspect, in a possible manner, the time-dependent covariates include one or more of the following: touch frequency, average touch movement distance, average CPU (Central Processing Unit) usage rate, memory growth rate, screen refresh rate change value; the non-time-dependent covariates include one or more of the following: screen touch sensitivity, application type, network status.

[0008] In combination with the first aspect, in a possible manner, the touch data includes one or more of the following: event end time, event type, touch start coordinate, touch end coordinate; the running parameters include one or more of the following: CPU usage rate, memory usage rate, screen refresh rate, screen touch sensitivity, network status, application type.

[0009] In combination with the first aspect, in a possible manner, generating a prediction feature set corresponding to the first feature set based on the first feature set includes: determining a first input feature set based on the time-dependent covariates corresponding to each time window, and determining a second input feature set based on the non-time-dependent covariates corresponding to each time window; determining the prediction feature set corresponding to the first feature set based on the first input feature set and the second input features.

[0010] It can be seen that the present application can determine the first input feature set based on the time-dependent covariates corresponding to each time window, determine the second input feature set based on the non-time-dependent covariates corresponding to each time window, determine the prediction feature set based on the first input feature set and the second input feature set, distinguish the time-dependent covariates and the non-time-dependent covariates based on whether the covariates change over time, and perform differential processing on the time-dependent covariates and the non-time-dependent covariates to ensure the accuracy of determining the prediction feature set, thereby improving the accuracy of freeze screen detection.

[0011] In combination with the first aspect, in a possible manner, generating a freeze screen detection result based on the loss parameters corresponding to the prediction features of each time window includes: comparing the prediction features corresponding to each time window with the reference features respectively to obtain the abnormality score corresponding to each time window, where the abnormality score indicates the degree of difference between the prediction feature and the reference feature within the corresponding time window; generating a freeze screen detection result based on the abnormality scores corresponding to each time window.

[0012] It can be seen that by comparing the prediction feature corresponding to the time window with the reference feature to determine the abnormality score corresponding to the time window, the degree of difference between the prediction feature and the reference feature within the time window can be quantified, which can further improve the accuracy of generating the freeze screen detection result.

[0013] In combination with the first aspect, in a possible manner, a frozen screen detection result is generated based on the anomaly score values corresponding to each time window, including: in response to the existence of an anomaly score value greater than a threshold, a frozen screen detection result is generated, and the frozen screen detection result indicates that the electronic device has a frozen screen within a first time period; or, in response to the non-existence of an anomaly score value greater than the threshold, a frozen screen detection result is generated, and the frozen screen detection result indicates that the electronic device does not have a frozen screen within the first time period.

[0014] It can be seen that by introducing a threshold and generating a frozen screen detection result based on the comparison result between the anomaly score value corresponding to each time window and the threshold, the convenience of generating the frozen screen detection result can be improved, thereby improving the efficiency of frozen screen detection.

[0015] In combination with the first aspect, in a possible manner, a prediction feature set corresponding to the first feature set is generated based on the first feature set, including: inputting the first feature set into a feature processing module in the frozen screen detection model to obtain the prediction feature set corresponding to the first feature set output by the feature processing module.

[0016] It can be seen that the present application can determine the prediction feature set corresponding to the first feature set through the feature processing module in the frozen screen detection model to improve the accuracy of the prediction feature set.

[0017] In combination with the first aspect, in a possible manner, a frozen screen detection result is generated based on the loss parameters corresponding to the prediction features corresponding to each time window, including: inputting the prediction features corresponding to each time window into a prediction module in the frozen screen detection model to obtain the loss parameters corresponding to the prediction features corresponding to each time window output by the prediction module; inputting the loss parameters corresponding to the prediction features corresponding to each time window into a frozen screen analysis module in the frozen screen detection model to obtain the frozen screen detection result output by the frozen screen analysis module.

[0018] It can be seen that the present application can output the loss parameters corresponding to the prediction features corresponding to each time window through the prediction module in the frozen screen detection model to improve the accuracy of the loss parameters corresponding to the prediction features corresponding to each time window, and output the frozen screen detection result through the frozen screen analysis module in the frozen screen detection model to further improve the accuracy of the frozen screen detection result.

[0019] In combination with the first aspect, in a possible manner, the method further includes: in response to the electronic device having a frozen screen within the first time period and the system mode of the electronic device being the simple mode, restarting the target application or restarting the electronic device; wherein, the target application is the application running in the foreground on the electronic device within the first time period.

[0020] It can be seen that when the electronic device has a frozen screen within the first time period and the system mode of the electronic device is a simple mode, the electronic device can automatically restart the target application or restart the electronic device to unfreeze the frozen screen, thereby improving the intelligence of the electronic device and further improving the user experience.

[0021] In combination with the first aspect, in one possible manner, the method also includes: in response to the electronic device having a frozen screen within a first time period and the system mode of the electronic device is not a simple mode, displaying a first window; wherein the first window includes a first prompt message, the first prompt message prompting the electronic device that the screen is frozen and whether to unfreeze the screen; in response to receiving a confirmation to unfreeze the screen operation, restarting the target application or restarting the electronic device; wherein the target application is the application running in the foreground on the electronic device within the first time period.

[0022] It can be seen that the electronic device can, when the screen of the electronic device is frozen within the first time period and the system mode of the electronic device is not the simple mode, remind the user that the screen of the electronic device is frozen and ask whether to unfreeze the screen. Based on the user's confirmation, the user can restart the target application or restart the electronic device to unfreeze the screen, thereby improving the user's human-computer interaction experience and the flexibility of unfreezing the screen.

[0023] In a second aspect, the present application provides an electronic device, which includes: one or more processors, a display screen and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute: in response to the frozen screen detection function being in an on state, obtaining touch data and operating parameters of touch events within a first time period; based on the touch data and operating parameters of the touch events, determining a first feature set, the first feature set includes touch statistical features corresponding to each time window in at least one time window, the touch statistical features indicate time-dependent covariates and non-time-dependent covariates within the corresponding time window; the first time period includes at least one time window; based on the first feature set, generating a predicted feature set corresponding to the first feature set; the predicted feature set includes predicted features corresponding to each time window; based on the loss parameters corresponding to the predicted features corresponding to each time window, generating a frozen screen detection result; the frozen screen detection result indicates whether the electronic device has a frozen screen within the first time period.

[0024] In combination with the second aspect, in one possible manner, the time-dependent covariates include one or more of the following: touch frequency, average touch movement distance, average CPU usage, memory growth rate, and screen refresh rate change; the non-time-dependent covariates include one or more of the following: screen touch sensitivity, application type, and network status.

[0025] In combination with the second aspect, in a possible manner, the touch data includes one or more of the following: timestamp, event type, touch start coordinate, touch end coordinate, touch movement distance; the operating parameters include one or more of the following: CPU usage rate, memory usage rate, screen refresh rate, screen touch sensitivity, network status, application type.

[0026] In combination with the second aspect, in a possible manner, the one or more processors call the computer instructions to cause the electronic device to perform: determining a first input feature set based on the time-dependent covariates corresponding to each time window, and determining a second input feature set based on the non-time-dependent covariates corresponding to each time window; determining a prediction feature set corresponding to the first feature set based on the first input feature set and the second input feature set.

[0027] In combination with the second aspect, in a possible manner, the one or more processors call the computer instructions to cause the electronic device to perform: comparing the prediction features corresponding to each time window with the reference features respectively to obtain the anomaly score corresponding to each time window, where the anomaly score indicates the degree of difference between the prediction feature and the reference feature within the corresponding time window; generating a frozen screen detection result based on the anomaly scores corresponding to each time window.

[0028] In combination with the second aspect, in a possible manner, the one or more processors call the computer instructions to cause the electronic device to perform: generating a frozen screen detection result in response to the existence of an anomaly score greater than the threshold, where the frozen screen detection result indicates that the electronic device has a frozen screen within the first time period; or generating a frozen screen detection result in response to the non-existence of an anomaly score greater than the threshold, where the frozen screen detection result indicates that the electronic device does not have a frozen screen within the first time period.

[0029] In combination with the second aspect, in a possible manner, the one or more processors call the computer instructions to cause the electronic device to perform: inputting the first feature set into the feature processing module in the frozen screen detection model to obtain the prediction feature set corresponding to the first feature set output by the feature processing module.

[0030] In combination with the second aspect, in a possible manner, the one or more processors call the computer instructions to cause the electronic device to perform: inputting the prediction features corresponding to each time window into the prediction module in the frozen screen detection model to obtain the loss parameters corresponding to the prediction features corresponding to each time window output by the prediction module; inputting the loss parameters corresponding to the prediction features corresponding to each time window into the frozen screen analysis module in the frozen screen detection model to obtain the frozen screen detection result output by the frozen screen analysis module.

[0031] In combination with the second aspect, in one possible manner, the one or more processors call the computer instructions to cause the electronic device to execute: in response to the electronic device having a frozen screen within a first time period and the system mode of the electronic device being a simple mode, restarting the target application or restarting the electronic device; wherein the target application is the application running in the foreground on the electronic device within the first time period.

[0032] In combination with the second aspect, in one possible manner, the one or more processors call the computer instructions to cause the electronic device to execute: in response to the electronic device having a frozen screen within a first time period and the system mode of the electronic device being a non-simple mode, displaying a first window; wherein the first window includes a first prompt message, and the first prompt message prompts the electronic device that the screen is frozen and whether to unfreeze the screen; in response to receiving a confirmation to unfreeze the screen operation, restarting the target application or restarting the electronic device; wherein the target application is the application running in the foreground on the electronic device within the first time period.

[0033] In a third aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect above.

[0034] In a fourth aspect, the present application provides a chip system, which is coupled to a memory, and the chip system is used to read and execute a computer program stored in the memory to implement the method described in the first aspect above.

[0035] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a frozen screen provided in an embodiment of the present application;

[0037] Figures 2A - 2D A schematic diagram of an interface for enabling a frozen screen detection function provided in an embodiment of the present application;

[0038] Figures 2E - 2G A schematic diagram of an interface for opening a simple mode provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of a frozen screen detection method provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of an interface for performing a frozen screen release reminder in a simple mode provided in an embodiment of the present application;

[0041] Figure 5A schematic diagram of an interface for unfreezing the screen in a first non-simple mode provided in an embodiment of the present application;

[0042] Figure 6 A schematic diagram of an interface for unfreezing the screen in a second non-simple mode provided in an embodiment of the present application;

[0043] Figure 7 A schematic diagram of an interface for unfreezing the screen in a third non-simple mode provided in an embodiment of the present application;

[0044] Figure 8 A schematic diagram of an interface for unfreezing the screen in a fourth non-simple mode provided in an embodiment of the present application;

[0045] Figure 9 A schematic diagram of a flow chart of another frozen screen detection method provided in an embodiment of the present application;

[0046] Figure 10 A schematic diagram of the software structure of an electronic device provided in an embodiment of the present application;

[0047] Figure 11 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The terms "first", "second", "third", etc. in the embodiments of the present application are distinguished from different objects, rather than being used to describe a specific order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions. For example, a series of steps or units are included, or alternatively, steps or units not listed are also included, or other steps or units inherent to these processes, methods, products or devices are optionally included. The terms "one embodiment" or "some embodiments", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment are included in one or more embodiments of the present application. Thus, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in the differences in the embodiments of the present application are not necessarily all with reference to the same embodiment, but mean "one or more but not all embodiments", unless otherwise particularly emphasized.

[0050] In the embodiments of the present application, words such as "for example" or "such as" are used to give examples, illustrations or explanations. Any embodiment or design described as "for example" or "such as" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or designs. Rather, the use of words such as "for example" or "such as" is intended to present relevant concepts in a specific manner.

[0051] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B may be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item)" or similar expressions refer to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, and c may represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c, where a, b, and c may be single or multiple.

[0052] In the following embodiments of the present application, terms such as "component", "module", "system", etc. are used to represent computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, an application running on a computing device and the computing device can both be components. One or more components may reside in a process and / or an execution thread, and the components may be located on one computer and / or distributed between two or more computers. In addition, these components may execute from various computer-readable media on which various data structures are stored. The components may communicate, for example, through local and / or remote processes according to signals having one or more data packets (such as data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems through signals).

[0053] Next, some terms in the present application are explained to facilitate understanding by those skilled in the art.

[0054] 1. Touch screen and touch data

[0055] A touch panel (TP), also known as a touch screen or touch control panel, is a display device capable of receiving input information. For example, on electronic devices such as mobile phones and tablet computers, the touch screen of the electronic device can receive touch operations such as clicks, swipes, zooms, and drags by the user on graphic elements such as icons and text displayed on the touch screen.

[0056] The touch screen detects whether there is a touch operation by scanning. The touch screen can generate corresponding electrical signals based on the detected touch operation and transmit the electrical signals to the corresponding touch control device of the touch screen. The touch control device can generate initial touch data according to the change of the electrical signal. The initial touch data includes touch position data, pressing force data, touch time, etc. The corresponding touch drive module of the touch screen can identify the touch event occurring on the touch screen based on the initial touch data and collect the touch data of the touch event. In the embodiments of the present application, the touch data of the touch event may include data such as the event end time, event type, touch start coordinate, and touch end coordinate of the touch event. The event type may include, but is not limited to, click events, swipe events, drag events, etc.

[0057] 2. Frozen screen

[0058] A frozen screen means that the electronic device can detect a touch event but cannot jump to the user interface corresponding to the touch event.

[0059] As Figure 1 shown, the electronic device can display the interface 101 of the main screen, which includes multiple application icons, such as the live application icon 1011, weather application icon, stock application icon, calculator application icon, settings application icon, mail application icon, gallery application icon, Facebook application icon, browser application icon, music application icon, video application icon, app store icon, etc. A page indicator is also included below the multiple application icons to indicate the positional relationship between the currently displayed page and other pages. The electronic device can detect the selection operation 1012 (such as a click operation) of the user on the live application icon 1011. If the electronic device does not have a frozen screen, the electronic device can respond to the selection operation 1012 and display the user interface 102 of the live application. If the electronic device has a frozen screen, it cannot respond to the selection operation 1012. In this case, the electronic device cannot display the user interface 102 of the live application and may, for example, remain on the interface 101 of the main screen.

[0060] When the electronic device has a frozen screen, it will result in a poor user experience. Therefore, the frozen screen detection method provided in the embodiments of the present application can be used to accurately and quickly determine whether the electronic device has a frozen screen.

[0061] In the embodiments of the present application, an electronic device such as a smart phone can provide a frozen screen detection function. Among them, the frozen screen detection function can detect a frozen screen, that is, detect whether the electronic device has a frozen screen, or it can be described as detecting whether there is a risk of a frozen screen on the electronic device.

[0062] It can be understood that the frozen screen detection can also be called other names such as screen freeze detection and screen status detection. The embodiments of the present application do not limit this.

[0063] 3. Opening process of the frozen screen detection function

[0064] In practical applications, the user can decide whether to enable the frozen screen detection function according to their own needs. The following will introduce the opening process of the frozen screen detection function in combination with Figures 2A - 2D to introduce the opening process of the frozen screen detection function.

[0065] As Figure 2A shown, the electronic device can display the interface of the main screen, which includes multiple application icons, such as the settings application icon 2011, the live application icon, the gallery application icon, the weather application icon, the stock application icon, the calculator application icon, the email application icon, the Facebook application icon, the browser application icon, the music application icon, the app store icon, the video application icon, etc. Below the multiple application icons, there is also a page indicator to indicate the position relationship between the currently displayed page and other pages. The electronic device can detect the user's selection operation 2012 (click operation) on the settings application icon 2011. In response to the selection operation 2012, it displays Figure 2B the user interface 202 of the settings application shown.

[0066] As Figure 2B shown, the user interface 202 can include multiple general function icons of the electronic device, such as the frozen screen detection function identifier 2021, the system and update function identifier 2022, the flight mode function identifier, the Wi-Fi function identifier, the Bluetooth function identifier, the personal hotspot function identifier, the mobile network function identifier, the Honor account function identifier, etc.

[0067] As Figure 2C shown, the electronic device can detect the user's selection operation 2023 (such as a click operation) on the frozen screen detection function identifier 2021 in Figure 2B . In response to the selection operation 2023, it displays Figure 2D the user interface 203 of the frozen screen detection function shown.

[0068] As Figure 2DAs shown, the user interface 203 includes a confirmation enabling item 2031 for the frozen screen detection function. The electronic device can detect a confirmation enabling operation 2032 (such as a click operation) by the user on the confirmation enabling item 2031. In response to the confirmation enabling operation 2032, the frozen screen detection function is enabled. The user interface 203 may further include a function introduction of the frozen screen detection function to facilitate the user's understanding of the frozen screen detection function.

[0069] 4. Simple mode and non-simple mode

[0070] The simple mode is a mode that simplifies complex functions and interfaces, aiming to provide a simple and easy-to-operate user experience. By reducing the operation steps and configuration options, it enables users to quickly get started and perform basic operations. The simple mode is achieved by simplifying the interface layout, hiding advanced functions, providing intuitive guidance and help, etc. In the embodiments of the present application, after the simple mode is enabled, when the electronic device detects that it has a frozen screen, it can automatically restart the applications running in the foreground on the electronic device when the frozen screen occurs or restart the electronic device, and the frozen screen can be lifted without the need for user participation.

[0071] The non-simple mode corresponds to the simple mode. When the simple mode of the electronic device is not enabled, the system mode of the electronic device is the non-simple mode. In the embodiments of the present application, in the non-simple mode, when the electronic device detects that it has a frozen screen, it will prompt the user that the electronic device has a frozen screen and ask whether to lift the frozen screen. After the user confirms to lift the frozen screen, it will restart the applications running in the foreground on the electronic device when the frozen screen occurs or restart the electronic device.

[0072] 5. Opening process of the simple mode

[0073] In practical applications, the user can decide whether to enable the simple mode according to their own needs. The following will Figures 2E - 2G introduce the opening process of the simple mode in detail.

[0074] As Figure 2E shown, the electronic device can detect a selection operation 2024 (such as a click operation) by the user on the system and update function identifier 2022 in the user interface 202. In response to the selection operation 2024, the user interface 204 of the system and update function as shown in Figure 2F is displayed. The display path and interface content of the user interface 202 have been introduced in detail in the foregoing part regarding the opening process of the frozen screen detection function. Please refer to the description of the relevant content for Figures 2A to 2B in that part, and details will not be repeated here.

[0075] As Figure 2FAs shown, the user interface 204 includes multiple sub - function identifiers under the system and update functions. For example, the simple mode function identifier 2041, software update function identifier, system navigation mode function identifier, language and input method function identifier, date and time function identifier, device - to - device cloning function identifier, reset function identifier, user experience improvement plan function identifier, etc. The electronic device can detect a selection operation 2042 (such as a click operation) of the user on the simple mode function identifier 2041. In response to the selection operation 2042, it displays Figure 2G the user interface 205 of the simple mode function as shown.

[0076] As Figure 2G shown, the user interface 205 includes a confirmation and enable item 2051 for the simple mode. The electronic device can detect a confirmation and enable operation 2052 (such as a click operation) of the user on the confirmation and enable item 2051. In response to the confirmation and enable operation 2052, the simple mode is enabled. This user interface 205 can also include an introduction (i.e., function description) of the simple mode. For example, the function description includes text information such as "Larger display", "Simpler desktop layout, larger text and icons, automatically unfreeze the screen when the screen freezes", so as to facilitate the user to understand the simple mode.

[0077] Based on the above description, the following combines Figure 3 to introduce the screen freeze detection method provided by the embodiments of this application. Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a screen freeze detection method provided by the embodiments of this application.

[0078] This screen freeze detection method can be applied to an electronic device, and can be executed by the electronic device, or by a processor in the electronic device, or by a chip or chip system with processor functions, etc. As Figure 3 shown, this screen freeze detection method may include but is not limited to the following steps:

[0079] S301, in response to the screen freeze detection function being in an on state, obtain the touch data and operating parameters of touch events within a first time period.

[0080] Among them, the first time period refers to the duration between one moment and another moment. The length of the first time period can be 1 minute, 5 minutes, 10 minutes, etc. The embodiments of this application do not make a specific limitation on the length of the first time period. The touch events within the first time period refer to the touch events that occur on the touch screen of the electronic device within the first time period. The touch events include at least one of the following process events: touch start (Touchstart), touch move (Touchmove), touch end (Ttouchend), etc. Touch start corresponds to a finger touching the screen, touch move corresponds to a finger moving on the screen, and touch end corresponds to a finger leaving the screen.

[0081] In the embodiments of the present application, the touch data of a touch event may include, but is not limited to, one or more of the following: timestamp, event type, touch start coordinate, touch end coordinate, and touch movement distance. Among them, the content recorded by the timestamp includes the event occurrence time of the touch event, and the event occurrence time may be the event end time, or the event start time, or any time between the event end time and the event start time. The event type may include, but is not limited to, click event (Click), swipe event (Swipe), drag event (Drag), etc. The touch start coordinate refers to the screen coordinate corresponding to the start of the touch in the touch event, and the touch start coordinate is also referred to as the touch start position. The touch end coordinate refers to the screen coordinate corresponding to the end of the touch in the touch event, and the touch end coordinate is the touch end position. Optionally, the screen coordinate can be represented by a rectangular coordinate system, such as (x, y), and the unit can be pixels. Optionally, the touch movement distance may be the actual movement distance of the finger from the touch start coordinate to the touch end coordinate in the touch event. In this case, the touch movement distance can be obtained during the touch movement process. Optionally, the touch movement distance may be the straight-line distance from the touch start position to the touch end position in the touch event. In this case, the touch movement distance can be calculated from the touch start position and the touch end position.

[0082] In the embodiments of the present application, the operating parameters of a touch event may include, but are not limited to, one or more of the following: Central Processing Unit (CPU) usage rate, memory usage rate, screen refresh rate, screen touch sensitivity, network status, and application type. The CPU usage rate refers to the amount of processing time consumed by the CPU of an electronic device, which indicates how much CPU capacity is utilized at any given time, measured as a percentage, with 100% representing full utilization of the CPU processing capacity. The CPU usage rate of a touch event is the CPU usage rate at the end moment of the touch event. The memory usage rate refers to the proportion of physical memory being used by an electronic device at a certain moment to the total available memory, which is one of the indicators for measuring the utilization of the memory resources of an electronic device. The memory usage rate is the ratio of the used memory of the electronic device to the total memory of the electronic device. The memory usage rate of a touch event is the memory usage rate at the end moment of the touch event. The screen refresh rate refers to the number of times the display of an electronic device updates images per second, with the unit of Hertz (Hz). The screen refresh rate of a touch event is the average screen refresh rate within a second time period after the end moment of the touch event. The time length of the second time period can be 2s, 3s, etc., and no specific limitation is imposed on the length of the second time period. The screen touch sensitivity refers to the response speed and accuracy of the screen to touch operations when a user uses the device. The screen touch sensitivity is related to the hardware configuration of the electronic device and can be obtained through touch tests. The network status includes the network being in a connected state (Connected) and the network being in a non-connected state (NoConnection). Optionally, Connected can be used to indicate that the network status is the network being in a connected state, and NoConnection can be used to indicate that the network status is the network being in a non-connected state. Optionally, a network status number can be used to indicate the corresponding network status. For example, Connected is indicated by 1 and No Connection is indicated by 0. The application type is used to distinguish applications, and the application type may include game applications, video applications, social applications, office applications, etc. Optionally, a type number can be used to indicate the corresponding application type. For example, a game application is indicated by 1, a video application is indicated by 2, and a social application is indicated by 3.

[0083] In the embodiments of the present application, obtaining the touch data and operating parameters of a touch event within a first time period means obtaining the touch data and operating parameters of each touch event in at least one touch event within the first time period.

[0084] Next, take the touch data of a touch event including a timestamp, event type, touch start coordinates, touch end coordinates, and the running parameters of the touch event including CPU usage rate, memory usage rate, screen refresh rate, network status, and application type as an example. Arrange the touch data and running parameters of the touch event in the following order: timestamp, event type, touch start coordinates, touch end coordinates, CPU usage rate, memory usage rate, screen refresh rate, network status, application type. Take the touch event TE1 as an example to illustrate the touch data and running parameters of the touch event.

[0085] For example, the touch data and running parameters corresponding to the touch event TE1 are: 2024-01-01 10:00:00.123, Click, (320, 480), (320, 480), 45%, 60%, 60Hz, Connected, 1. Among them, the first data 2024-01-01 10:00:00.123 represents the timestamp of the touch event TE1, the second data Click represents that the event type of the touch event TE1 is a click event, the third data (320, 480) refers to the touch start coordinates of the touch event TE1, the fourth data (320, 480) refers to the touch start coordinates of the touch event TE1, the fifth data 45% refers to the CPU usage rate of the touch event TE1, the sixth data 60% refers to the screen refresh rate of the touch event TE1, the seventh data Connected means that the network status of the touch event TE1 is in a connected state, and the eighth data 1 means that the application type of the touch event TE1 is a game application.

[0086] Optionally, the electronic device can provide a frozen screen detection setting option, which can be added to the system function list of the electronic device (for example, the user interface shown above can be referred to), or can be added to the function list of any application program (such as a video playback application program). Correspondingly, the frozen screen detection setting option can include an enable button. By clicking the enable button, the user can trigger the electronic device to enable the frozen screen detection function. The opening process of the frozen screen detection function has been described before and will not be elaborated here. Figure 2B

[0087] S302, Determine the first feature set based on the touch data and running parameters of the touch event.

[0088] ​Among them, the first time period may include at least one time window. A time window refers to the time range used to determine whether the electronic device has a frozen screen. When the first time period includes one time window, the time window can be any time period on the first time period (including the first time period itself). When the first time period includes multiple time windows, the multiple time windows can be consecutive and equal-length time windows on the first time period, or non-consecutive time windows on the first time period. The multiple time windows on the first time period can also be defined in other ways, and the corresponding relationship between the time period and the time window is not specifically limited. For example, if the time of the first time period is ten minutes and the first time period is evenly divided into 10 sub-time periods, and these 10 sub-time periods are all used as time windows, obviously, the first time period includes 10 time windows, and the duration of each time window is 1 minute. The multiple time windows can also be non-consecutive time windows on the first time period. For example, if the first time period is 6 minutes, it can be determined that the first minute, the third minute, and the fifth minute on the first time period are the 3 time windows of the first time period. The time windows within the first time period can be indicated by the unique encoding (Identity document, Id) of the time window. For example, the first time window within the first time period is indicated by W001, the second time window is indicated by W002, the third time window is indicated by W003, and so on.

[0089] In the embodiments of the present application, when the network state of the electronic device changes and / or the application type of the foreground-running application on the electronic device changes, starting from the moment of the change, the time window is re-divided.

[0090] Among them, the first feature set includes the touch statistical features corresponding to each time window in at least one time window, and the touch statistical features indicate the time-dependent covariates and non-time-dependent covariates within the corresponding time window. A time-dependent covariate refers to a covariate that changes with time, and a time-dependent covariate is also called a time-dependent covariate or an intrinsic time-dependent covariate or a time-varying covariate. A non-time-dependent covariate refers to a covariate that does not change with time.

[0091] In the embodiments of the present application, the time-dependent covariates may include, but are not limited to, one or more of the following: touch frequency, average touch moving distance, average CPU usage rate of the central processing unit CPU, memory growth rate, and screen refresh rate change value. The touch frequency within the time window refers to the number of touch events occurring per second on average within the time window. The average touch moving distance within the time window refers to the average value of the touch moving distances of the touch events within the time window. The average CPU usage rate within the time window refers to the average value of the CPU usage rates of the touch events within the time window.

[0092] Among them, the memory growth rate within the time window can be obtained by the following formula (1):

[0093] (y) / y Formula (1)

[0094] In Formula (1), is the memory growth rate of the i-th time window, is the average memory utilization rate within the i-th time window, and y is the average memory utilization rate within the (i - 1)-th time window.

[0095] Among them, the change value of the screen refresh rate within the time window can be obtained by the following formula (2):

[0096] Formula (2)

[0097] In Formula (2), is the change value of the screen refresh rate within the time window, r is the average screen refresh rate within the time window, and s is the reference refresh rate within the time window.

[0098] In Formula (2), the reference refresh rate refers to the lowest refresh rate required for a monitor or screen in a normal working state to ensure stable image display and avoid flickering. The reference refresh rate can be determined according to specific application scenarios and user requirements. For example, in daily office work and web browsing scenarios (such as daily text reading, document processing, or surfing the Internet), the reference refresh rate can be 60Hz; since most movie and video content is recorded at 24 frames or 30 frames per second, the reference refresh rate in movie and video viewing scenarios can be 60Hz to provide a smooth and flicker-free viewing experience; e-sports and first-person shooting games (FPS) require a higher refresh rate to reduce latency and make actions look more natural and smooth, so their reference refresh rate can be 144Hz and above. Based on this, the application type can be used to indicate the application scenario, and then the reference refresh rate within the time window can be determined by the application type within that time window. Obviously, the reference refresh rates of different application types can be the same or different. For example, the reference refresh rates of office applications, web applications, and video applications are all 60Hz, and the reference refresh rate of game applications is 144Hz. Further, the application scenario can also be indicated in the form of a combination of application type and application function to subdivide the application scenario.

[0099] In specific implementation, the application types can be classified according to user requirements, and the corresponding reference refresh rates for different application types can be determined. The corresponding relationship set between the application types and the reference refresh rates can also be obtained in advance. When it is necessary to determine the reference refresh rate of a time window, the corresponding relationship set can be found based on the application type of the time window.

[0100] In the embodiments of the present application, the time-independent covariates may include, but are not limited to, one or more of the following: screen touch sensitivity, application type, and network status.

[0101] In the embodiments of the present application, taking the time-dependent covariates including touch frequency, average touch movement distance, average CPU (Central Processing Unit) usage rate, memory growth rate, and screen refresh rate change value, and the time-independent covariates including application type and network status as examples, the touch statistical features (including time-dependent covariates and time-independent covariates) of each time window are arranged in the following order: touch frequency, average touch movement distance, average CPU usage rate, memory growth rate, screen refresh rate change value, network status, application type. Next, taking the time window W001 as an example, the touch statistical features within the time window are described.

[0102] Touch statistical features of time window W001: 2.5, 150, 47%, 2%, -0.1, 1, 1. Among them, the first data 2.5 represents the touch frequency within time window W001, the second data 150 represents the average touch movement distance within time window W001, the third data 47% refers to the average CPU usage rate within time window W001, the fourth data 2% refers to the memory growth rate within time window W001, the fifth data -0.1 refers to the screen refresh rate change value within time window W001, the sixth data 1 indicates that the network status within time window W001 is the connected state, and the seventh data 1 indicates that the application type within time window W001 is a game application.

[0103] In some embodiments, after obtaining the touch data and running parameters of the touch event, the obtained data can be preprocessed to obtain preprocessed data, and then feature extraction is performed on the preprocessed data to obtain a first feature set. The preprocessing process may include the following steps:

[0104] Step A1, data cleaning. The data can be cleaned in the following ways: 1) Remove / fill in missing data: It can be filled by calculation, filled by experience or business, filled by other fields, and filled with unified indicators. For example, the missing values of touch frequency are filled with the mean, median, mode, etc. of the touch frequency; 2) Remove / modify data with format and content errors (i.e., invalid data): For example, remove line breaks, spaces, data before touch events, etc.; 3) Remove / modify data with logical errors: That is, remove unreasonable values. For example, remove abnormal values of screen refresh rate or touch frequency, and correct contradictory content; 4) Remove unnecessary data: For example, delete unnecessary fields. For example, when the touch moving distance is the straight-line distance between the touch start coordinate and the touch end coordinate, after having the touch moving distance, the touch start coordinate and the touch end coordinate can be deleted.

[0105] Step A2, time alignment. Align the touch data of the touch event and the operating parameters to the same time axis.

[0106] S303, generate a prediction feature set corresponding to the first feature set based on the first feature set.

[0107] Among them, the prediction feature set includes prediction features corresponding to each time window.

[0108] In some embodiments, after the electronic device obtains the first feature set, it can determine the first input feature set based on the time-dependent covariates corresponding to each time window in the first feature set, and determine the second input feature set based on the non-time-dependent covariates corresponding to each time window in the first feature set; based on the first input feature set and the second input feature set, determine the prediction feature set corresponding to the first feature set. In this application, based on whether the covariates change with time, the time-dependent covariates and the non-time-dependent covariates are distinguished, and the time-dependent covariates and the non-time-dependent covariates are processed differently to ensure the accuracy of the determination of the prediction feature set, thereby improving the accuracy of the frozen screen detection.

[0109] Among them, the first input feature set includes input vectors corresponding to each time window. The input vector is obtained by splicing the time-dependent covariates of the corresponding time window. For example, if the window end time of the i-th time window is t, the input vector of the i-th time window is denoted as X_t, and the window end time of the i-1-th time window is t-1, then the input vector of the i-1-th time window is denoted as X_t-1.

[0110] X_t =

[0111] Touch frequency, / / x1: range [0 - 10], unit: times / second

[0112] Average touch movement distance, / / x2: range [0-1000], unit: pixel

[0113] Average CPU usage, / / x3: range [0-100]%

[0114] Memory growth rate, / / x4: range [-1,1]

[0115] Screen refresh rate change value / / x5: range [-1,1] ]

[0117] Among them, the second input feature set includes the control vectors corresponding to each time window, and the control vectors are obtained by splicing the non-time-dependent covariates of the corresponding time windows. Similarly, the window end time of the i-th time window is t, then the control vector of the i-th time window is expressed as u_t, the window end time of the i-1-th time window is t-1, then the control vector of the i-1-th time window is expressed as u_t-1.

[0118] u_t = [

[0119] Application type, / / u1: value [1-5], application type represents different types of applications (games, videos, social networking, etc.)

[0120] Touch sensitivity, / / u2: value [0-1], touch sensitivity is related to the device hardware configuration and can be obtained through touch testing;

[0121] Network status / / u3: value [0,1], 1 means the network is connected, 0 means the network is not connected ]

[0123] When X_t-1 and u_t are determined, Y_t can be determined based on X_t-1, u_t and the first corresponding relationship, where the first corresponding relationship refers to the corresponding relationship between Y_t and X_t-1, u_t. For example, the first corresponding relationship can be:

[0124] X_t = A * X_t-1+ B * u_t + w_t

[0125] Y_t = H * X_t + v_t

[0126] Where A is the state transfer matrix, which is defined as follows:

[0127] A = [

[0128] [0.8, 0.1, 0.0, 0.0, 0.1],

[0129] [0.1, 0.7, 0.1, 0.0, 0.1],

[0130] [0.0, 0.1, 0.8, 0.1, 0.0],

[0131] [0.0, 0.0, 0.1, 0.8, 0.1],

[0132] [0.1, 0.1, 0.0, 0.1, 0.7]

[0134] B is the control input matrix and is defined as follows:

[0135] B =

[0136] [0.1, 0.0, 0.0], / / Influence of application type on touch frequency

[0137] [0.0, 0.2, 0.0], / / Influence of touch sensitivity on average touch movement distance

[0138] [0.0, 0.0, 0.1], / / Influence of network status on average CPU usage

[0139] [0.1, 0.0, 0.1], / / Influence of application type and network status on memory growth rate

[0140] [0.1, 0.1, 0.0] / / Influence of application type and touch sensitivity on screen refresh rate change value

[0142] H is the observation matrix and is defined as follows:

[0143] H =

[0144] [1.0, 0.0, 0.0, 0.0, 0.0],

[0145] [0.0, 1.0, 0.0, 0.0, 0.0],

[0146] [0.0, 0.0, 1.0, 0.0, 0.0],

[0147] [0.0, 0.0, 0.0, 1.0, 0.0],

[0148] [0.0, 0.0, 0.0, 0.0, 1.0]

[0150] ​​​$w_t \sim N(0, Q)$ / / $Q$ is the process noise covariance matrix. Generally, the influence of $w_t$ can be ignored, i.e., $w_t = 0$.

[0151] $v_t \sim N(0, R)$ / / $R$ is the observation noise covariance matrix. Generally, the influence of $v_t$ can be ignored, i.e., $v_t = 0$.

[0152] In some embodiments, after obtaining the first feature set, the electronic device can process the obtained first feature set through the feature processing module in the frozen screen detection model to obtain the predicted feature set corresponding to the first feature set. The frozen screen detection model including the feature processing module can be, for example, a model pre-stored locally in the electronic device. After inputting the first feature set into the feature processing module, the feature processing module can output the predicted feature set corresponding to the first feature set based on the first feature set. By determining the predicted feature set corresponding to the first feature set through the feature processing module in the frozen screen detection model in the embodiments of the present application, the accuracy of the predicted feature set can be improved.

[0153] In some embodiments, the electronic device can send a processing request including the first feature set to the cloud server to request the cloud server to generate the predicted feature set corresponding to the first feature set based on the first feature set. Similarly, the cloud server can store a frozen screen detection model that has been trained. The trained frozen screen detection model includes a feature processing module. By inputting the first feature set into the feature processing module, the feature processing module can output the predicted feature set corresponding to the first feature set based on the first feature set. In this way, the electronic device does not need to pre-store the frozen screen detection model of the feature processing module, which helps to save storage space.

[0154] The frozen screen detection model including the feature processing module is obtained by comparative learning based on positive samples, negative samples and frozen screen labels in the training sample set. The frozen screen label is used to characterize whether the electronic device has a frozen screen. The touch data and operating parameters of the touch operation within a period of time (for example, one minute) before the frozen screen occurs can be obtained from the operation log of the existing frozen screen problem (referred to as data 1), and the first feature set determined based on data 1 is used as a negative sample. The touch data and operating parameters of the touch operation within a period of time (for example, one minute) after the frozen screen occurs are obtained from the reporting log of the existing frozen screen problem (referred to as data 2), and the first feature set determined based on data 2) is used as a positive sample, thereby obtaining a positive and negative sample pair. The initial model is supervised and learned using multiple positive and negative samples, and the generalization ability and detection accuracy of the initial model are improved through multiple rounds of iterative optimization. The initial model is optimized with the goal of minimizing the loss function until the loss function of the model converges (for example, the loss value change amplitude is less than the set amplitude threshold) or the preset training round is reached, and the feature processing module is obtained. The model structure of the feature processing module can be a state space model network, and the basic equation of the state space model is the same as the first corresponding relationship mentioned above. Please refer to the description of the first corresponding relationship above, which will not be repeated here. In some embodiments, the feature processing module is a frozen screen detection model.

[0155] S304: Generate a frozen screen detection result based on the loss parameters corresponding to the prediction features corresponding to each time window.

[0156] The loss parameter may be an abnormality score. The frozen screen detection result indicates whether the electronic device has a frozen screen within the first time period.

[0157] In order to generate the frozen screen detection result, the predicted features corresponding to each time window can be compared with the reference features respectively to obtain the abnormality scores corresponding to each time window. The abnormality score indicates the degree of difference between the predicted features and the reference features in the corresponding time window. The larger the abnormality score, the greater the degree of difference between the predicted features and the reference features, and the smaller the abnormality score, the smaller the degree of difference between the predicted features and the reference features. Then, the frozen screen detection result can be generated based on the abnormality scores corresponding to each time window.

[0158] Specifically, in order to obtain the abnormality scores corresponding to each time window, the following operations may be performed on the prediction features corresponding to each time window in turn:

[0159] Step B1: Obtain the Euclidean distance between the prediction feature and the reference feature corresponding to the current processing time window using the following formula (3).

[0160] Formula (3)

[0161] In formula (3), D is the and Euclidean distance between them. The Euclidean distance can also be called the distance score. y_t is the predicted feature corresponding to the currently processed time window, y_expected is the reference feature, ^2 means to square, sum() is for summation, and sqrt() is for square root. The reference feature refers to the clustering center of the m predicted features corresponding to m time windows when the electronic device is in the normal state (i.e., the non-frozen screen state). m is a positive integer, and the larger m is, the better. The larger m is, the more predicted features there are, and the closer the clustering center corresponding to the sample is to the true value, that is, the smaller the error between it and the true value.

[0162] Step B2: Obtain the Euclidean distance and the reference distance corresponding to the currently processed time window through the following formula (4), and perform normalization processing to obtain the anomaly score corresponding to the currently processed time window.

[0163] Formula (4)

[0164] In formula (4), the anomaly score, D is the and Euclidean distance between them, which is calculated by formula (1), represents the reference distance, () is to take the minimum value. The reference distance refers to the clustering center (such as the average value, median, mode, etc.) of the n Euclidean distances of n time windows when the electronic device is in the normal state (non-frozen screen state). n is a positive integer. n can be the same as or different from the aforementioned m. The larger n is, the better. The larger n is, the more Euclidean distances there are, and the closer the obtained clustering center is to the true value, that is, the smaller the error between it and the true value.

[0165] It can be seen that by comparing the predicted feature corresponding to the time window with the reference feature to determine the anomaly score corresponding to the time window, the difference degree between the predicted feature and the reference feature within the time window can be quantified, and the accuracy of generating the frozen screen detection result can be further improved.

[0166] In some embodiments, after obtaining the anomaly scores corresponding to each time window, the anomaly scores corresponding to each time window can be respectively compared with a threshold to obtain the frozen screen detection result. The threshold is used to distinguish whether the electronic device does not have a frozen screen or the electronic device has a frozen screen.

[0167] Optionally, in response to the existence of an anomaly score greater than the threshold, a frozen screen detection result can be generated, and the frozen screen detection result indicates that within the first time period, the electronic device has a frozen screen.

[0168] For example, the time period T1 includes four time windows, namely time window W001, time window W002, time window W003, and time window W004. The anomaly score of time window W001 is 49, the anomaly score of time window W002 is 30, the anomaly score of time window W003 is 55, and the anomaly score of time window W004 is 80. Since both 80 and 55 are greater than 50, at this time, the generated frozen screen detection result indicates that the electronic device has a frozen screen within the time period T1.

[0169] Optionally, in response to the absence of an anomaly score greater than the threshold, a frozen screen detection result can be generated, and this frozen screen detection result indicates that the electronic device does not have a frozen screen within the first time period.

[0170] For example, the time period T2 includes three time windows, namely time window W001, time window W002, and time window W003. The anomaly score of time window W004 is 49, the anomaly score of time window W005 is 30, and the anomaly score of time window W006 is 21. Since 49, 30, and 21 are all less than 50, at this time, the generated frozen screen detection result indicates that the electronic device does not have a frozen screen within the time period T2.

[0171] It can be seen that by introducing a threshold and generating a frozen screen detection result based on the comparison result between the anomaly score corresponding to each time window and the threshold, the present application can improve the convenience of generating the frozen screen detection result, and further improve the efficiency of frozen screen detection.

[0172] For the sake of easy understanding, for the case where a time period includes one time window, taking the prediction feature corresponding to this time window as the processing object, the implementation process of generating the frozen screen detection result for this time period is illustrated by way of example.

[0173] Suppose the time period T3 includes the time window W001, and the prediction feature P1 corresponding to the time window W001 is: [0.5, 50, 85%, 0.08, -0.4]; the reference feature P2 is: [2.3, 120, 45%, 0.02, -0.1]; based on the above formulas (1) and (2), the anomaly score between the prediction feature P1 and the reference feature P2 can be calculated to be 70; if the current threshold is 50; since 70>50, it can be determined that the electronic device has a frozen screen within the time window W001 (that is, the time period T3).

[0174] For a situation where a time period includes multiple time windows, the implementation process of generating the frozen screen detection result for this time period is as follows. The anomaly score for each time window in the multiple time windows can be obtained separately to get multiple anomaly scores. If there is an anomaly score greater than the threshold among these multiple anomaly scores, a frozen screen detection result indicating that the electronic device has a frozen screen during this time period is generated. If there is no anomaly score greater than the threshold among these multiple anomaly scores, a frozen screen detection result indicating that the electronic device does not have a frozen screen during this time period is generated. In addition, in this case, the process of obtaining the anomaly score for a time window refers to the process of obtaining the anomaly score in the case where a time period includes one time window as described above, which will not be elaborated here.

[0175] In some embodiments, after obtaining the prediction features corresponding to each time window, the electronic device can, through the prediction module in the frozen screen detection model, output the loss parameters corresponding to the prediction features corresponding to each time window based on the prediction features corresponding to each time window. The frozen screen detection model including the feature processing module can be, for example, a model pre-stored locally by the electronic device. After inputting the prediction features corresponding to each time window into the prediction module, the prediction module can output the loss parameters corresponding to the prediction features corresponding to each time window based on the prediction features corresponding to each time window. By outputting the loss parameters corresponding to the prediction features corresponding to each time window through the prediction module in the frozen screen detection model in the embodiments of the present application, the accuracy of the loss parameters corresponding to the prediction features corresponding to each time window can be improved.

[0176] Optionally, the electronic device can send a processing request including the prediction features corresponding to each time window to the cloud server to request the cloud server to determine the loss parameters corresponding to the prediction features corresponding to each time window based on the prediction features corresponding to each time window. Similarly, the cloud server can store a trained frozen screen detection model, and the frozen screen detection model includes a prediction module. After inputting the prediction features corresponding to each time window into the prediction module, the prediction module can output the loss parameters corresponding to the prediction features corresponding to each time window. Based on the loss parameters corresponding to the prediction features corresponding to each time window, the frozen screen detection result can be determined. In this way, the electronic device does not need to pre-store a frozen screen detection model including a prediction module, which is beneficial to saving storage space.

[0177] In some embodiments, the frozen screen detection model may include a frozen screen analysis module. After obtaining the loss parameters corresponding to the predicted features corresponding to the various time windows, they may be input into the frozen screen analysis module to obtain the frozen screen detection results output by the frozen screen analysis module. It can be seen that by outputting the frozen screen detection results through the frozen screen analysis module in the frozen screen detection model, the accuracy of the frozen screen detection results is further improved. The frozen screen detection model including the frozen screen analysis module may be, for example, a module pre-stored locally by the electronic device. The loss parameters corresponding to the predicted features corresponding to the various time windows are input into the frozen screen analysis module to obtain the frozen screen detection results output by the frozen screen analysis module. In this way, it is helpful to improve the accuracy of the frozen screen detection results.

[0178] Optionally, the electronic device may send a processing request including loss parameters corresponding to the prediction features corresponding to the respective time windows to the cloud-side server, so as to request the cloud-side server to output a frozen screen detection result based on the loss parameters corresponding to the prediction features corresponding to the respective time windows. Similarly, the cloud-side server may store a frozen screen detection model that has been trained, and the frozen screen detection model includes a frozen screen analysis module. After the loss parameters corresponding to the prediction features corresponding to the respective time windows are processed, the prediction module may output a frozen screen detection result. In this way, the electronic device may not need to pre-store a frozen screen detection model including a frozen screen analysis module, which is beneficial for saving storage space.

[0179] The aforementioned frozen screen detection model including the feature processing module, the frozen screen detection model including the prediction module, and the frozen screen detection model including the frozen screen analysis module can be the same frozen screen detection model, or can be three different frozen screen detection models, or two of them can be the same frozen screen detection model and the other one can be another frozen screen detection model, and the embodiments of the present application do not make specific limitations on this.

[0180] After the frozen screen detection result is generated, if the electronic device has a frozen screen within the first time period, the following processing methods can be used to present the value of the frozen screen detection result.

[0181] Mode 1: Output frozen screen reminder information to remind the user that the current device has frozen screen. The frozen screen reminder information can be broadcast in the form of voice, for example, playing "no response" in the form of voice; or it can be displayed in the user interface in the form of text or animation, for example, displaying the text message "no response" in the user interface, or displaying an animation effect in the user interface to indicate that the user device has frozen screen. In this mode, the user can find a way to unfreeze the screen based on the frozen screen reminder information.

[0182] Method 2: defrost the screen. Since the system modes of the electronic device include a simple mode and a non-simple mode, the defrost screen methods are different in different system modes. Based on the system mode of the electronic device, the defrost screen methods in the corresponding system modes are introduced.

[0183] Next, we will introduce how to release the frozen screen in simple mode.

[0184] In some embodiments, in response to the electronic device having a frozen screen in a first time period and the system mode of the electronic device being a simple mode, the electronic device can restart the target application or restart the electronic device to unfreeze the screen, thereby improving the intelligence of the electronic device and further improving the user experience. In the embodiment of the present application, the target application is the application running in the foreground on the electronic device in the first time period.

[0185] In some embodiments, the electronic device may first restart the target application, and if the restart of the target application fails, restart the electronic device. Specifically, the electronic device may obtain the application restart result after restarting the target application, and the application restart result includes the failure to restart the target application and the success to restart the target application; in response to the failure to restart the target application, restart the electronic device. In actual applications, the number of times the target application is restarted can be set as needed, and the present application does not specifically limit the number of times the target application is restarted. Optionally, the number of times the target application is restarted is once, that is, after a target application fails to restart once, the electronic device is restarted. Optionally, the number of times the target application is restarted can be at least twice. For example, if the number of times the target application is restarted is 3 times, the electronic device will restart the target application 3 times. If all 3 restarts fail, the electronic device is restarted.

[0186] In some embodiments, the electronic device may display a second window in response to the electronic device having a frozen screen and the system mode of the electronic device being a simple mode. The second window may include a second prompt message and a third prompt message. The second prompt message is used to prompt that the electronic device has a frozen screen, and the third prompt message is used to prompt an upcoming frozen screen release operation. If the display time of the second window exceeds a certain time (first time), the target application may be restarted or the electronic device may be restarted to release the frozen screen. The first time may be, for example, 3 seconds, 5 seconds, etc., and there is no specific limitation on the first time. This method is beneficial for users to learn that the electronic device has a frozen screen, and to learn that the electronic device will restart the target application or restart the electronic device, further improving the intelligence of the electronic device and improving the user experience.

[0187] For example, the second window can be Figure 4 The window 401 shown may include a text prompt message 402 (second prompt message) of "the electronic device has a frozen screen" and a text prompt message 403 (third prompt message) of "an upcoming frozen screen release operation". After displaying the window 401, the electronic device may obtain the display duration of the window 401, and restart the target application or restart the electronic device if the display duration of the window 401 exceeds 5 seconds.

[0188] Next, we will introduce how to release the frozen screen in non-simple mode.

[0189] In some embodiments, the electronic device may display a first window in response to the electronic device having a frozen screen in the first time period and the system mode of the electronic device being a non-simple mode. The first window may include a first prompt message, which prompts the electronic device whether to unfreeze the screen. After displaying the first window, the electronic device may receive a confirmation unfreeze screen operation. If the confirmation unfreeze screen operation is received, the target application may be restarted or the electronic device may be restarted. The target application is an application running in the foreground of the electronic device in the first time period. Optionally, after displaying the first window, the electronic device may also receive a confirmation unfreeze screen operation. If the confirmation unfreeze screen operation is received, the first window will no longer be displayed. It can be seen that the electronic device may remind the user that the electronic device has a frozen screen in the first time period and the system mode of the electronic device is a non-simple mode, whether to unfreeze the screen, and based on the user's confirmation unfreeze screen operation, restart the target application or restart the electronic device to unfreeze the screen, thereby improving the user's human-computer interaction experience and improving the flexibility of unfreezing the screen.

[0190] Optionally, the first window may further include a confirmation control for confirming to unfreeze the screen and a cancel control for confirming not to unfreeze the screen. The operation of confirming to unfreeze the screen may be a click operation on the confirmation control, and the operation of confirming not to unfreeze the screen may be a click operation on the cancel control.

[0191] Optionally, the electronic device may display an interactive area while displaying the first window. The interactive area may include a text input box and a voice input box. The text input box is used to obtain text instructions, and the voice input box is used to obtain voice instructions. The interactive area may be set independently of the first window, and the interactive area may also be set in the first window. The embodiments of the present application do not specifically limit this. To confirm the unfreeze screen operation, a text instruction for confirming unfreeze screen may be entered in the text input box. To confirm the non-unfreeze screen operation, a voice instruction for confirming non-unfreeze screen may be entered in the voice input box. If both the first window and the interactive area are displayed, the first window and the interactive area will no longer be displayed after the confirmation of the unfreeze screen operation is detected.

[0192] For example, the first window can be Figure 5 As shown in the window 501, the interactive area can be Figure 5The interactive area 504 shown. The window 501 may include a prompt message 502 (the first prompt message) of "The electronic device has a frozen screen. Do you want to unfreeze it?", a confirmation control 503 for confirming to unfreeze the screen, and a cancel control 507 for confirming not to unfreeze the screen. The interactive area 504 includes a text input box 505 and a voice input box 506. After the prompt message 502 is output, if a click operation on the confirmation control 503 is obtained, or a text instruction similar to "yes" is input in the text input box 505, or a voice instruction similar to "yes" is input in the voice input box 506, the target application or the electronic device will be restarted. If a click operation on the cancel control 507 is obtained, or a text instruction similar to "no" is input in the text input box 505, or a voice instruction similar to "no" is input in the voice input box 506, the window 501 and the interactive area 504 will no longer be displayed.

[0193] Optionally, the first window may also be the window 601 as Figure 6 shown. The window 601 includes a prompt message 602 of "Not responding. Do you want to restart the application?", a control 603 for confirming to restart the application, and a control 604 for waiting for the application to respond. In response to receiving a click operation on the control 603, the target application is restarted. In response to receiving a click operation on the control 604, the display of the first window ends. Optionally, the first window may also be the following window A. The window A includes a prompt message of "Not responding. Do you want to restart the device?", a control 1 for confirming to restart the device, and a control 2 for waiting for the application to respond. If a click operation on the control 1 is received, the electronic device is restarted. If in response to receiving a click operation on the control 2, the first window is no longer displayed.

[0194] In some embodiments, after restarting the target application, the electronic device may obtain the application restart result. The application restart result includes that the restart of the target application fails and the restart of the target application is successful. In response to the failure of restarting the target application, a third window is displayed. Among them, the third window includes a fourth prompt message, and the fourth prompt message prompts that the restart of the target application by the electronic device fails. Do you want to restart the device? In response to receiving an operation of confirming to restart the electronic device, the electronic device is restarted. The third window may be the Figure 7 window 701 shown. The window 701 includes a prompt message 702 of "The restart of the application fails. Do you want to restart the device?", a control 703 for confirming to restart the device, and a control 704 for waiting for the application to respond. In response to receiving a click operation on the control 703, the electronic device is restarted. In response to receiving a click operation on the control 704, the display of the third window ends.

[0195] In some embodiments, if the electronic device has a frozen screen during the first time period, and the system mode of the electronic device is not the simple mode, it can be determined whether the electronic device meets the setting conditions of the frozen screen release function. The frozen screen release function is used to trigger restarting the target application or restarting the electronic device when a frozen screen is detected. After the frozen screen release function is turned on, if the electronic device is subsequently monitored to have a frozen screen, the target application can be restarted or the electronic device can be restarted even if the system mode of the electronic device is not the simple mode. If the electronic device meets the setting conditions of the frozen screen release function, it can be displayed as follows Figure 8 The freeze screen release function setting window 801 includes prompt information 802 indicating whether the electronic device has a freeze screen release function and whether to turn on the freeze screen release function, a confirmation control 803, and a cancel control 804. At the same time, it can detect and confirm the operation of turning on the freeze screen release function (for example, for Figure 8 In the case of detecting a click operation of the confirmation control 803 in the middle, the freeze screen release function is enabled, and the target application is restarted or the electronic device is restarted. The operation of enabling the freeze screen release function can be detected and confirmed (for example, for Figure 8 Cancel the click operation of control 804 in the control), and when the operation of confirming the start of the frozen screen release function is detected, the frozen screen release function is turned on, and the target application or the electronic device is restarted. The setting condition of the frozen screen release function can be, for example, one of the following: (1) the first time that the electronic device is detected to have a frozen screen; (2) the time interval between the current system time and the first reference time exceeds the first time interval, the first time interval can be, for example, 10 days, 15 days, 30 days, etc., and the first time interval is not specifically limited. The first reference time is the time when the frozen screen release function was last turned off from the current system time; (3) the time interval between the current system time and the second reference time exceeds the second time interval, the second time interval can be, for example, seven days, 15 days, 30 days, etc., and the second time interval is not specifically limited. The second reference time is the time when the frozen screen release function was last turned on from the current time; (4) the number of frozen screen detections from the time when the frozen screen release function was last turned on or off to the current system time exceeds a preset number of times, for example, the preset number of times can be 3 times, 4 times, 6 times, etc., and the preset number of times is not specifically limited.

[0196] See also Figure 9 , Figure 9 is a flow chart of another frozen screen detection method provided in an embodiment of the present application, from Figure 9 It can be seen that the frozen screen detection method provided in the embodiment of the present application can be summarized into three parts: the first part is how to start frozen screen detection; the second part is how to detect frozen screen; and the third part is how to unfreeze the screen.

[0197] Starting the frozen screen detection function Electronic devices can add the frozen screen detection setting option to the system function list of the electronic device. When the user needs to use the frozen screen detection function, he can turn it on in the system function list. The process of turning on the frozen screen detection function has been described in detail in the terminology description section. Please refer to the contents of that section and will not be repeated here.

[0198] 2) Perform a frozen screen test

[0199] When the frozen screen detection function is turned on, the electronic device can collect and process data. Specifically, the touch data and operating parameters of the touch events within the first time period can be collected, and then the acquired data can be preprocessed to obtain preprocessed data, and the comparison algorithm can be started to extract features of the preprocessed data to obtain a first feature set, and then based on the first feature set, a prediction feature set corresponding to the first feature set is generated, and then the prediction features corresponding to each time window in the prediction feature set are compared with the reference features to obtain the abnormality scores corresponding to each time window. If there is an abnormality score greater than the threshold, that is, the frozen screen is detected, the frozen screen will be unfrozen.

[0200] 3) Unfreeze the screen

[0201] The process of unfreezing the screen is to first determine whether the simple mode is turned on. If the simple mode is turned on, the target application is restarted. If the simple mode is not turned on (non-simple mode), the user will be prompted that the electronic device has a frozen screen and whether to unfreeze the screen. After receiving confirmation of the unfreezing screen operation, the target application will be restarted. Regardless of whether the simple mode is turned on or not, after restarting the target application, it can be determined whether the restart of the target application is successful. If the restart of the target application is successful, the current process ends. If the restart of the target application fails, the electronic device is restarted.

[0202] Figure 10 It is a software structure diagram of an electronic device. The software structure adopts a layered architecture, which divides the software into several layers, and each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. Taking the Android system, the Android system running on the AP as an example, in some embodiments, the Android system is divided into five layers, from top to bottom, namely the application layer, the application framework layer (framework), the system runtime layer, the hardware abstract layer (hard abstract layer, HAL) and the kernel layer (kernel).

[0203] Among them, the application layer may include a series of application packages. The application packages may include apps such as live broadcast, camera, gallery, calendar, call, map, news, Bluetooth, music, video, settings, etc. In the embodiment of the present application, the electronic device provides an entrance for setting the frozen screen detection function and an entrance for setting the simple mode through the settings program, facilitating the user to enable the frozen screen detection function and the simple mode in the settings program.

[0204] The application layer may also include a system user interface (system UI), and the system UI is used to display the interface of the electronic device, such as displaying the signal icon corresponding to the SIM card, displaying the call interface, etc. In the embodiment of the present application, the system UI is used to display the user interface as Figures 2A - 2G shown. Figures 4 - 8 shown.

[0205] The application framework layer provides application programming interfaces (APIs) and programming frameworks for the applications in the application layer. The application framework layer includes some predefined functions. For example, the application framework layer may include a window manager, a content provider, a view system, a telephony manager, a resource manager, a notification manager, etc. The telephony manager is used to provide the call function of the electronic device, such as the management of call states (including answering, hanging up, etc.).

[0206] The system runtime library layer is divided into two parts, namely the C / C++ library and the Android runtime library. The C / C++ library mainly includes a multimedia library (media framework), a surface manager, a 3D image processing library, a 2D graphics engine, etc. The Android runtime library mainly includes a runtime environment (Android runtime, ART), etc.

[0207] The hardware abstraction layer is used to isolate the application framework layer from the kernel layer, avoiding the Android system's excessive dependence on the kernel layer, so that the development of the application framework layer can be carried out without considering the driver. The hardware abstraction layer may include multiple functional modules. For example, modules such as a display HAL, a camera HAL, an audio HAL, a sensor HAL, etc.

[0208] The kernel layer is the layer between the hardware and the software. The kernel layer at least includes a display driver, a camera driver, an audio driver, a sensor driver, and a shared memory driver. In the embodiment of the present application, the display driver can be used to drive the system UI to display the user interface as Figures 2A - 2G shown. Figures 4 - 8For the user interface shown, sensor driving can be used to obtain touch data and operating parameters of touch events.

[0209] In addition, some embodiments of the present application provide an electronic device, which includes: one or more processors and a memory; the memory is used to store computer program code, and the computer program code includes computer instructions. When the one or more processors execute the computer instructions, the electronic device executes the above-mentioned image processing method.

[0210] Some embodiments of the present application provide a chip system, which is applied to an electronic device. The chip system includes at least one processor and an interface. The interface is used to receive instructions and transmit them to the at least one processor; the at least one processor runs the instructions to make the electronic device execute the above-mentioned image processing method. Among them, the chip system can be a modulation and demodulation processor, or a system on chip (SOC) including a modulation and demodulation processor. The above-mentioned image processing method can be implemented by a modulation and demodulation processor.

[0211] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0212] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps may be adopted in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0213] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned unit division is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0214] The units described as separate components above may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0215] In addition, each functional unit in the embodiments of the present application may be integrated into a processing unit, may exist physically alone for each unit, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0216] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc., specifically, the processor in the computer device) to execute all or part of the steps of the above methods in the various embodiments of the present application. Among them, the aforementioned storage medium may include: USB flash drives, mobile hard disks, magnetic disks, optical disks, read-only memory (ROM), or random access memory (RAM), etc., various media that can store program codes.

[0217] As described above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

[0218] Such as Figure 11As shown in the figure, the electronic device may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. Among them, the sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0219] The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0220] The NPU is a neural network computing processor. By learning from the biological neural network structure, for example, learning from the transmission mode between human brain neurons, it can quickly process the input information and can also continuously self-learn. Through the NPU, applications such as intelligent cognition of electronic devices can be realized. For example: image recognition, face recognition, speech recognition, text understanding, etc. In this application, the NPU can be used to build a frozen screen detection model.

[0221] A memory can also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store the instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can directly call it from the said memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0222] The electronic device realizes the display function through the GPU, the display screen 194, and the application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to execute mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or change the display information.

[0223] The wireless communication function of the electronic device can be realized through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, and the baseband processor, etc.

[0224] The antenna 1 and the antenna 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in the electronic device can be used to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization rate of the antennas. For example: the antenna 1 can be multiplexed as the diversity antenna of the wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0225] The mobile communication module 150 can provide solutions for wireless communications such as 2G / 3G / 4G / 5G applied to the electronic device. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves by the antenna 1, filter, amplify, etc. the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor and convert it into electromagnetic waves through the antenna 1 for radiation. In some embodiments, at least some functional modules of the mobile communication module 150 can be provided in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 can be provided in the same device.

[0226] The wireless communication module 160 may provide wireless communication solutions applied to an electronic device, including wireless local area networks (WLANs) (such as Wi-Fi networks), Bluetooth (BT), BLE broadcasts, global navigation satellite systems (GNSSs), frequency modulation (FM), near field communication (NFC), infrared technology (IR), and the like. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, performs frequency modulation and filtering processing on the electromagnetic wave signals, and sends the processed signals to the processor 110. The wireless communication module 160 may also receive signals to be sent from the processor 110, perform frequency modulation and amplification on them, and convert them into electromagnetic waves through the antenna 2 for radiation.

[0227] The electronic device realizes the display function through the GPU, the display screen 194, the application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to execute mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or change display information.

[0228] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel may adopt a liquid crystal display (LCD), an organic light emitting diode (OLED), an active matrix organic light emitting diode (AMOLED), a flexible light emitting diode (FLED), a MiniLED, a MicroLED, a MicrooLED, a quantum dot light emitting diode (QLED), etc. In some embodiments, the electronic device may include 1 or N display screens 194, where N is a positive integer greater than 1. In the embodiments of the present application, the display screen 194 may be used to display a user interface as Figures 2A - 2G shown, Figures 4 - 8 the shown user interface.

[0229] The touch sensor 180K, also known as the "touch panel". The touch sensor 180K can be disposed on the display screen 194. The touch sensor 180K and the display screen 194 together form a touch screen, also known as the "touch screen". Visual output related to touch operations can be provided through the display screen 194. In some other embodiments, the touch sensor 180K can also be disposed on the surface of the electronic device, at a different position from where the display screen 194 is located. In the embodiments of the present application, the touch sensor 180K is used to detect touch events acting thereon or in its vicinity. The touch sensor 180K can transmit the detected touch events to the application processor to determine the type of touch event, touch frequency, touch movement distance, etc.

[0230] It can be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device. In some other embodiments, the electronic device may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0231] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk).

[0232] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0233] The steps in the method embodiments of this application can be adjusted, combined, and deleted according to actual needs.

[0234] The modules in the device embodiments of this application can be combined, divided, and deleted according to actual needs.

[0235] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The readable storage medium can include: flash drive, ROM, RAM, magnetic disk, or optical disc, etc.

[0236] What is disclosed above is only a preferred embodiment of this application, and it is only a part of the embodiments of this application. It cannot be used to limit the scope of rights of this application.

Claims

1. A method for detecting frozen screen, characterized in that, The method is applied to an electronic device, and the method includes: In response to the freezing screen detection function being in an enabled state, obtaining touch data and operating parameters of touch events within a first time period; the operating parameters include one or more of the following: CPU usage rate, memory usage rate, screen refresh rate, screen touch sensitivity, network status, application type; the network status includes the network being in a connected state and the network being in a non-connected state; Based on the touch data and operating parameters of the touch events, determining a first feature set, the first feature set including touch statistical features corresponding to each time window in at least one time window, the touch statistical features indicating time-dependent covariates and non-time-dependent covariates within the corresponding time window; the first time period includes the at least one time window; the time-dependent covariates include one or more of the following: touch frequency, average touch moving distance, average CPU usage rate of the central processing unit (CPU), memory growth rate, screen refresh rate change value; the non-time-dependent covariates include one or more of the following: the screen touch sensitivity, the application type, the network status; Based on the first feature set, generating a prediction feature set corresponding to the first feature set; the prediction feature set includes prediction features corresponding to each time window; Based on loss parameters corresponding to the prediction features corresponding to each time window, generating a freezing screen detection result; the freezing screen detection result indicates whether the electronic device has a frozen screen within the first time period.

2. The method according to claim 1, characterized in that, The touch data includes one or more of the following: timestamp, event type, touch start coordinate, touch end coordinate, touch moving distance.

3. The method according to claim 1, wherein The generating the prediction feature set corresponding to the first feature set based on the first feature set includes: Based on the time-dependent covariates corresponding to each time window, determining a first input feature set, and based on the non-time-dependent covariates corresponding to each time window, determining a second input feature set; Based on the first input feature set and the second input feature set, determining the prediction feature set corresponding to the first feature set.

4. The method according to claim 1, characterized in that, The generating the freezing screen detection result based on the loss parameters corresponding to the prediction features corresponding to each time window includes: Comparing the prediction features corresponding to each time window with reference features respectively to obtain anomaly score values corresponding to each time window, the anomaly score values indicating the degree of difference between the prediction features and the reference features within the corresponding time window; Based on the anomaly score values corresponding to each time window, generating a freezing screen detection result.

5. The method according to claim 4, characterized in that The generating the freezing screen detection result based on the anomaly score values corresponding to each time window includes: In response to there being an anomaly score value greater than a threshold, generating a freezing screen detection result, the freezing screen detection result indicating that the electronic device has a frozen screen within the first time period; or, In response to there being no anomaly score value greater than a threshold, generating a freezing screen detection result, the freezing screen detection result indicating that the electronic device does not have a frozen screen within the first time period.

6. The method according to claim 1, wherein The generating the prediction feature set corresponding to the first feature set based on the first feature set includes: The first feature set is input into a feature processing module in a frozen screen detection model to obtain a prediction feature set corresponding to the first feature set output by the feature processing module.

7. The method according to claim 1, wherein The generating the frozen screen detection result based on the loss parameter corresponding to the prediction feature corresponding to each time window includes: Inputting the prediction features corresponding to the respective time windows into a prediction module in the freezing screen detection model, and obtaining loss parameters corresponding to the prediction features corresponding to the respective time windows output by the prediction module; The loss parameters corresponding to the prediction features corresponding to the respective time windows are input into the frozen screen analysis module in the frozen screen detection model to obtain the frozen screen detection result output by the frozen screen analysis module.

8. The method according to any one of claims 1-7, characterized in that, The method further comprises: In response to the screen being frozen on the electronic device within the first time period and the system mode of the electronic device being the simple mode, restarting the target application or restarting the electronic device; wherein the target application is the application running in the foreground on the electronic device within the first time period.

9. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: In response to the electronic device having a frozen screen within the first time period and the system mode of the electronic device being a non-simple mode, displaying a first window; wherein the first window includes a first prompt message, the first prompt message prompting the electronic device having a frozen screen and whether to unfreeze the screen; In response to receiving a confirmation to unfreeze the screen, restarting the target application or restarting the electronic device; wherein the target application is an application running in the foreground on the electronic device during the first time period.

10. An electronic device includes a memory, one or more processors, a plurality of applications, and one or more programs; wherein, The one or more programs are stored in the memory; it is characterized in that when the one or more processors execute the one or more programs, the electronic device implements the method as described in any one of claims 1-9.

11. A chip system, characterized in that, The chip system includes at least one processor, a memory and an interface circuit, the memory, the interface circuit and the at least one processor are interconnected by lines, and program instructions are stored in the memory; when the program instructions are executed by the processor, the chip system executes the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images