Control method and apparatus for electronic device, device, and storage medium

Abstract

The present application relates to the field of electronic devices, and discloses a control method and apparatus for an electronic device, a device, and a storage medium. The method comprises: acquiring current device information of an electronic device at a first moment; on the basis of the current device information, predicting a predicted state corresponding to a first system of the electronic device, wherein a state of the first system is related to the power consumption of the first system; and at a second moment, controlling the first system to switch to the predicted state, wherein the second moment is later than the first moment. Since the current device information is related to a usage scenario in which a user uses the electronic device, and the usage scenario is also related to a performance requirement of the user for the electronic device, a state that the first system having higher performance currently needs to enter is predicted on the basis of the performance requirement of the user, so that the state of the first system can be rationally controlled on the basis of the requirement of the user, thereby rationally balancing the performance and power consumption of the electronic device.

Description

Control methods, devices, equipment and storage media for electronic devices

[0001] This application claims priority to Chinese Patent Application No. 202411999351.8, filed on December 31, 2024, entitled "Control Method, Apparatus, Device and Storage Medium for Electronic Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of electronic devices, and in particular to a control method, apparatus, device, and storage medium for electronic devices. Background Technology

[0003] Wearable electronic devices are easy to carry and use, but due to their size limitations, their battery life is usually poor.

[0004] In related technologies, to improve the battery life of electronic devices, a dual-system architecture is typically employed. A more powerful first processor runs a more complex first system, while a less powerful second processor runs a less complex second system. Through the cooperation of these two systems, the power consumption of the electronic device can be reduced. For example, a user can control the first system to be running to meet their performance requirements; conversely, a user can also control the first system to be powered off to meet their battery life requirements. Summary of the Invention

[0005] This application provides a control method, apparatus, device, and storage medium for an electronic device, which can achieve a reasonable balance between the performance and power consumption of the electronic device. The technical solution is as follows:

[0006] According to one aspect of this application, a method for controlling an electronic device is provided, the method being executed by the electronic device, the electronic device comprising at least two systems, the method comprising:

[0007] Obtain the current device information of the electronic device at a first moment;

[0008] Based on the current device information, predict the predicted state of the first system of the electronic device, where the state of the first system is related to the power consumption of the first system.

[0009] At a second time point, the first system is controlled to switch to the predicted state, which is later than the first time point.

[0010] According to another aspect of this application, a control device for an electronic device is provided, the device comprising at least two systems, the device comprising:

[0011] The acquisition module is used to acquire the current device information of the device at a first moment;

[0012] The prediction module is used to predict the predicted state of the first system of the device based on the current device information. The state of the first system is related to the power consumption of the first system.

[0013] A switching module is used to control the first system to switch to the predicted state at a second time point, which is later than the first time point.

[0014] According to another aspect of this application, an electronic device is provided, the electronic device including a processor and a memory, the memory storing at least one program, the at least one program being loaded and executed by the processor to implement the control method of the electronic device as described above.

[0015] According to another aspect of this application, a computer-readable storage medium is provided, wherein at least one program is stored therein, the at least one program being loaded and executed by a processor to implement the control method of the electronic device as described above.

[0016] According to another aspect of this application, a chip is provided, the chip including programmable logic circuitry and / or program instructions, which, when the chip is operated on an electronic device, are used to implement the control method of the electronic device as described above.

[0017] According to another aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the control method for the electronic device provided in the above aspect. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 is a schematic diagram of a process for controlling an electronic device provided in an exemplary embodiment of this application;

[0020] Figure 2 is a flowchart illustrating a control method for an electronic device provided in an exemplary embodiment of this application;

[0021] Figure 3 is a flowchart illustrating a control method for an electronic device provided in an exemplary embodiment of this application;

[0022] Figure 4 is a schematic diagram of a process for determining a state prediction model provided in an exemplary embodiment of this application;

[0023] Figure 5 is a schematic diagram of a process for determining a state prediction model provided in an exemplary embodiment of this application;

[0024] Figure 6 is a schematic diagram of user habit-related data provided in an exemplary embodiment of this application;

[0025] Figure 7 is a schematic diagram of a switching operation mode process provided in an exemplary embodiment of this application;

[0026] Figure 8 is a schematic diagram of switching a first system state provided in an exemplary embodiment of this application;

[0027] Figure 9 is a schematic diagram of a transition animation provided in an exemplary embodiment of this application;

[0028] Figure 10 is a schematic diagram of the battery life of an electronic device provided in an exemplary embodiment of this application;

[0029] Figure 11 is a schematic diagram of the structure of a control device for an electronic device provided in an exemplary embodiment of this application;

[0030] Figure 12 is a schematic diagram of the structure of a control device for an electronic device provided in an exemplary embodiment of this application;

[0031] Figure 13 is a schematic diagram of the structure of a control device for an electronic device provided in an exemplary embodiment of this application;

[0032] Figure 14 is a schematic diagram of the structure of a control device for an electronic device provided in an exemplary embodiment of this application;

[0033] Figure 15 is a schematic diagram of the structure of a terminal provided in an exemplary embodiment of this application.

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0036] First, let me introduce the terms used in this application:

[0037] Dual system: A single electronic device has two processors and two different operating systems. For example, an electronic device has a first processor and a second processor, where the first processor runs a first system and the second processor runs a second system. In some embodiments, the first and second processors may be two separately packaged chips; in some embodiments, the first and second processors may be packaged in the same chip. In some embodiments, the program running on the processor can be understood as a system, including but not limited to an operating system; in some embodiments, a dual system may be two operating systems.

[0038] Deep Sleep (DS) State: For chips, deep sleep is a state that electronic devices enter to conserve power. In some embodiments, deep sleep is a suspend-to-memory state, such as writing memory to an embedded multi-media card (EMMC). When an electronic device is in deep sleep, most of the central processing unit (CPU) and hardware processes are paused, device functionality is reduced, and network connections may be lost. Only critical hardware of the electronic device can interrupt the deep sleep state, such as receiving a phone call or pressing the device's power button to wake the device and exit deep sleep. Compared to standby mode, deep sleep reduces battery consumption (power consumption) significantly. For dual-system electronic devices, deep sleep is a state that one or more systems can enter. In some embodiments, when one system of a dual-system electronic device enters deep sleep, its corresponding processor and hardware processes are paused, overall device functionality is reduced, and network connections for that system may be lost. Different chips may have different deep sleep states due to design differences. Therefore, the modules that are turned off during deep sleep and the power consumption may vary. The above definition is only an example and is not intended to limit the scope.

[0039] Standby state: For chips, standby state is the state in which some electronic components of an electronic device are turned off. This state allows some modules to be shut down to save power, while also enabling faster wake-up to respond to business needs. The specific modules that are turned off and those that are kept may vary depending on the chip design, and this is not limited. In some embodiments, standby state can be a state entered when no business is being processed, in which case some background processes can continue to run. In some embodiments, standby state can also be understood as hibernation state and / or sleep state. In some embodiments, when in standby state, the screen of the electronic device may be off, and the network connection may be disconnected, allowing background tasks to run. In some embodiments, for dual-system electronic devices, standby state can be a state that one or more systems can enter. In some embodiments, when one system of a dual-system electronic device enters standby state, that system disconnects from the network and keeps background processes running. Compared to deep sleep state, standby state shuts down fewer modules, and / or the system consumes more power in standby state than in deep sleep state.

[0040] Wearable devices: Wearable devices are portable electronic devices worn directly on the user's body or integrated into the user's clothing or accessories. Wearable devices not only provide hardware, but also offer powerful functions through software (such as an operating system), combined with data interaction and cloud interaction. For example, wearable devices can monitor health indicators, make and receive phone calls, and provide information notifications.

[0041] Smartwatches: Smartwatches are wearable devices that combine the form factor of a watch with an intelligent system. Through built-in systems (such as an operating system), processors, and memory, smartwatches can perform functions such as data processing, information display, and interactive control. In addition to the basic function of telling time, smartwatches can synchronize calls, text messages, emails, photos, music, etc., from other electronic devices (such as mobile phones). They also collect activity and physiological data from the user through various sensors (such as accelerometers, gyroscopes, and heart rate sensors), and connect to mobile phones or other electronic devices via wireless communication technology to achieve functions such as message synchronization and health management.

[0042] This application provides a control method for an electronic device, the method being executed by the electronic device, the electronic device comprising at least two systems, the method comprising:

[0043] Obtain the current device information of the electronic device at a first moment; predict the predicted state of the first system of the electronic device based on the current device information, wherein the state of the first system is related to the power consumption of the first system; control the first system to switch to the predicted state at a second moment, wherein the second moment is later than the first moment.

[0044] In some embodiments, predicting the predicted state of the first system of the electronic device based on the current device information includes: predicting the predicted state of the first system based on the current device information and the historical device information of the electronic device at a historical time; wherein the historical time is before the first time.

[0045] In some embodiments, predicting the predicted state of the first system based on the current device information and the historical device information of the electronic device at a historical time includes: inputting the current device information into a state prediction model to obtain the predicted state output by the state prediction model; wherein the state prediction model includes an artificial intelligence (AI) model, and the state prediction model is trained using the historical device information and the historical state of the first system under the historical device information.

[0046] In some embodiments, the method further includes: training a local AI model of the electronic device using the historical device information and the historical state to obtain the state prediction model.

[0047] In some embodiments, the method further includes: sending the historical device information and the historical state to a server; receiving model parameters sent by the server, the model parameters being obtained by the server training a local AI model of the server using the historical device information and the historical state; and determining the state prediction model based on the model parameters and the local AI model of the electronic device.

[0048] In some embodiments, predicting the predicted state of the first system based on the current device information and the historical device information of the electronic device at a historical time includes: sending the current device information to a server; receiving the predicted state sent by the server; wherein the predicted state is predicted by the server based on the current device information using a state prediction model, the state prediction model including an AI model, and the state prediction model is trained using the historical device information and the historical state of the first system under the historical device information.

[0049] In some embodiments, predicting the predicted state of the first system of the electronic device based on the current device information includes: predicting whether the predicted state is an ultra-low power state based on the current device information; controlling the first system to switch to the predicted state at a second time includes: if the predicted state is the ultra-low power state, controlling the first system to switch to the ultra-low power state at the second time; wherein the power consumption of the first system in the ultra-low power state is lower than that in the standby state and higher than that in the power-off state, and / or the wake-up time of the first system in the ultra-low power state is greater than that in the standby state and less than that in the power-off state.

[0050] In some embodiments, the method further includes: predicting a third moment when the predicted state is the ultra-low power state; and controlling the first system to exit the ultra-low power state at the third moment.

[0051] In some embodiments, the current device information includes one or more of the following: the behavior type of the user identified by the electronic device, the air pressure value collected by the electronic device, the current time in the electronic device, notification messages in the electronic device, location information collected by the electronic device, and physiological information of the user collected by the electronic device.

[0052] In some embodiments, the electronic device has at least two operating modes; predicting the predicted state corresponding to the first system of the electronic device based on the current device information includes: predicting the predicted state corresponding to the first system based on the current device information when the electronic device is in the first mode of the at least two operating modes.

[0053] In some embodiments, the at least two operating modes include the first mode and the second mode; wherein the first mode is a mode that supports controlling the state of the first system by prediction, the second mode is a mode that does not support predicting the state of the first system; and / or, the power consumption of the first mode is lower than that of the second mode.

[0054] In some embodiments, the at least two systems include the first system and the second system; wherein the relationship between the first system and the second system includes one or more of the following: the first system is more complex than the second system; the first system has more functions than the second system; the power consumption of running the first system is higher than that of the second system.

[0055] Figure 1 is a schematic diagram of a process for controlling an electronic device provided in an exemplary embodiment of this application. As shown in Figure 1, the electronic device includes at least two systems, such as a first system 101 and a second system 102. The first system 101 and the second system 102 may be different operating systems. In some embodiments, the relationship between the first system 101 and the second system 102 includes one or more of the following relationships: the first system 101 is more complex than the second system 102; the first system 101 has more functions than the second system 102; and the power consumption of running the first system 101 is higher than that of the second system 102. Optionally, the first system 101 is run by a first processor, and the second system 102 is run by a second processor. The performance of the first processor is stronger than that of the second processor, for example, the ultimate performance of the first processor is stronger than that of the second processor, and / or the energy efficiency of the first processor is stronger than that of the second processor. In some embodiments, the electronic device has at least two operating modes, such as a first mode 103 and a second mode 104. The first mode 103 may be called a battery life mode, and the second mode 104 may be called a performance mode. In some embodiments, the first mode 103 is a mode that supports predictive control of the state of the first system 101, and the second mode 104 is a mode that does not support predictive control of the state of the first system 101; and / or, the power consumption of the first mode 103 is lower than that of the second mode 104. The electronic device can be controlled to switch between different operating modes via its user interface. When the electronic device is in the first mode 103, the state of the first system 101 can be intelligently controlled through the process shown in FIG1, and the state of the first system 101 is related to the power consumption of the first system 101.

[0056] When the electronic device is in a first mode 103, which has at least two operating modes, it acquires current device information 105 at a first moment. Optionally, the current device information 105 includes one or more of the following: the behavior type of the user identified by the electronic device, the air pressure value collected by the electronic device, the current time in the electronic device, notification messages in the electronic device, location information collected by the electronic device, and physiological information of the user collected by the electronic device. The electronic device then inputs the current device information 105 into a state prediction model to obtain a predicted state 106 corresponding to the first system 101 output by the state prediction model. The state prediction model includes an artificial intelligence (AI) model, such as a machine learning model built using deep neural networks (DNNs). The state prediction model is trained using historical device information of the electronic device at historical moments and the historical state of the first system 101 under historical device information, with the historical moments preceding the first moment. After predicting the predicted state 106 corresponding to the first system 101, the electronic device controls the first system 101 to switch to the predicted state 106 at a second moment, which is later than the first moment.

[0057] By predicting the predicted state of the first system of an electronic device based on its current device information, the system can control the first system to switch to the predicted state. Since the current device information is related to the user's usage scenario of the electronic device, and the usage scenario is related to the user's performance requirements for the electronic device, predicting the state that the more powerful first system should enter based on the user's performance requirements allows for reasonable control of the first system's state according to the user's needs, thereby reasonably balancing the performance and power consumption of the electronic device.

[0058] Figure 2 is a flowchart illustrating a control method for an electronic device provided in an exemplary embodiment of this application. This method can be used in electronic devices, such as wearable devices. As shown in Figure 2, the method includes:

[0059] Step 202: Obtain the current device information of the electronic device at the first moment.

[0060] Current device information includes the device information of the electronic device at a specific moment, such as the device information of the electronic device collected at that moment. The device information includes information related to the electronic device, which is relevant to the user and the usage scenario of the electronic device. The first moment can be any moment, such as the moment when the device information of the electronic device was most recently acquired, and / or the current moment.

[0061] In some embodiments, the current device information includes one or more of the following: the behavior type of the user identified by the electronic device, the air pressure value collected by the electronic device, the current time in the electronic device, the notification message in the electronic device, the location information collected by the electronic device, and the physiological information of the user collected by the electronic device.

[0062] The behavior type of the user reflects the behavior of the user of the electronic device during its use, such as walking, sitting, standing, lying down, sleeping, running, swimming, playing football, playing basketball, dancing, aerobics, weightlifting, and skiing, or one or more of these. The user of the electronic device includes the object using the device, such as the user of the electronic device. It should be noted that, in addition to the behavior types of the user mentioned in the examples above, the electronic device can also identify more behavior types of the user, and this application embodiment does not limit this. Optionally, the behavior type of the user is obtained by identifying data collected by sensors in the electronic device. The sensors in the electronic device include motion sensors and / or physiological characteristic sensors. Motion sensors include one or more of gravity sensors, acceleration sensors, and gyroscope sensors. Physiological characteristic sensors include one or more of heart rate sensors, blood oxygen sensors, and blood pressure sensors. The air pressure value collected by the electronic device is the air pressure value corresponding to the location of the electronic device at the first moment, collected by the air pressure sensor and / or positioning sensor. The current time in the electronic device is the current time in the electronic device at the first moment, which can be the same as the first moment or may have a certain error. Notification messages in the electronic device include notification messages sent by the system of the electronic device and / or notification messages sent by the application of the electronic device. Location information refers to the information acquired by the electronic device at a given moment, reflecting its location. This includes information collected by the electronic device via positioning sensors at that moment. The physiological information of the user reflects the physiological characteristics of the user at that moment, including one or more of the following: heart rate, blood oxygen saturation, pressure, blood pressure, blood sugar, sleep status, and calorie consumption. Optionally, the user's physiological information is collected by physiological characteristic sensors in the electronic device. It should be noted that the current device information may include other information related to the electronic device in addition to the information mentioned above; this application embodiment does not limit this.

[0063] Optionally, the electronic device may acquire current device information in real time, and / or periodically, and / or according to a preset time, and / or according to a triggering event triggered by the user. This application embodiment does not impose any limitations on this.

[0064] The electronic device includes at least two systems, where each system can refer to an operating system. In some embodiments, the electronic device supports dual systems, with a first system and a second system configured therein. Optionally, the relationship between the first system and the second system includes one or more of the following: the first system is more complex than the second system, the first system has more functions than the second system, and the power consumption of running the first system is higher than that of the second system. The first system can be a first operating system, and the second system can be a second operating system. In some embodiments, the first system is a non-embedded system, and the second system is an embedded system. For example, the first system is the Android system, and the second system is a Real-Time Operating System (RTOS). It should be noted that the electronic device can support systems other than the first and second systems, and this application embodiment does not impose any limitations on this.

[0065] In some embodiments, the electronic device includes a first processing core and a second processing core, which are used to process instructions generated during the operation of the electronic device. In some embodiments, the performance of the first processing core is stronger than that of the second processing core, for example, the ultimate performance of the first processing core is stronger than that of the second processing core, and / or the energy efficiency of the first processing core is stronger than that of the second processing core. In some embodiments, the first processing core and the second processing core are integrated on a single chip, or they can be integrated on two separate chips. For example, the first processing core and the second processing core can be packaged in the same chip, or they can be two independently packaged chips. In some embodiments, the first processing core is a first processor, and the second processing core is a second processor. For example, the first processing core is a CPU, and the second processing core is a microcontroller unit (MCU). In some embodiments, the first processing core is used to run a first system, and the second processing core is used to run a second system. The first system can be called a big-core system, and the second system can be called a small-core system. It should be noted that, in addition to having the first and second processing cores, the electronic device may also have processing cores other than the first and second processing cores, and this application embodiment does not limit this.

[0066] In some embodiments, the electronic device includes a wearable device, such as a smartwatch.

[0067] Step 204: Predict the predicted state of the first system of the electronic device based on the current device information.

[0068] The first system is one of at least two systems in an electronic device, and the state of the first system is related to the power consumption of the first system. Optionally, the state of the first system includes one or more of the following: operating state, standby state, ultra-low power state, and power-off state.

[0069] The following provides illustrative examples of different system states: In some embodiments, from an energy-saving perspective, the system's power consumption in the running state is higher than in the standby state, and the system's power consumption in the standby state is higher than in the ultra-low power state, and the system's power consumption in the ultra-low power state is higher than in the shutdown state. In some embodiments, the system's power consumption in the shutdown state is 0, but if a shutdown timer task is set, such as a shutdown alarm, the system's power consumption in the shutdown state is greater than 0. In some embodiments, in terms of the functions provided by the system, the system provides more functions in the running state than in the standby state, and the system provides more functions in the standby state than in the ultra-low power state, and the system provides more functions in the ultra-low power state than in the shutdown state. For example, in terms of the activation status of the corresponding electronic components in the system, the system has more electronic components activated in the running state than in the standby state, and the system has more electronic components activated in the standby state than in the ultra-low power state, and the system has more electronic components activated in the ultra-low power state than in the shutdown state. For example, in terms of the wake-up time to bring the system to a running state, the wake-up time from standby to running state is shorter than that from ultra-low power state, and the wake-up time from ultra-low power state to running state is shorter than that from shutdown state. In some embodiments, in the running state, the system-related hardware works normally; in the standby state, most of the system-related hardware is turned off; in the ultra-low power state, most of the system-related hardware is turned off, providing only the most basic system functions; in the shutdown state, all system-related hardware is turned off, or only the scheduled task function is provided. For example, in the shutdown state, the processor loses power. In some embodiments, standby state can also be understood as hibernation state and / or sleep state, ultra-low power state can also be understood as DS state, and shutdown state can also be understood as shutdown state.

[0070] A predicted state is a state that an electronic device needs to enter, predicted based on its current device information. Optionally, the predicted state can be one of the following: running state, standby state, ultra-low power state, or power-off state. The predicted state can be the same as or different from the state of the first system at the time the predicted state was determined. Since the device information of an electronic device is related to the usage scenario of the user, and the usage scenario is related to the user's performance requirements for the electronic device, the predicted state of the first system can be predicted based on the current device information. For example, if the user frequently needs to use applications in the first system under the current device information's usage scenario, the predicted state of the first system can be determined as running state; if the user frequently uses applications in the first system under the current device information's usage scenario, the predicted state can be determined as standby state; if the user does not frequently use applications in the first system under the current device information's usage scenario, the predicted state can be determined as ultra-low power state; and if the user does not use applications in the first system at all under the current device information's usage scenario, the predicted state can be determined as power-off state.

[0071] In some embodiments, the electronic device predicts the predicted state of the first system based on current device information and historical device information at a historical moment. Historical device information includes device information of the electronic device at a historical moment, such as device information collected at a historical moment prior to the current moment. Optionally, the type of information in the historical device information is the same as the current device information. Optionally, the electronic device can determine the historical device information with the highest similarity to the current device information from different historical device information, i.e., the historical device information most likely to correspond to the same usage scenario as the current device information, based on the current device information. Then, based on the state of the first system under that historical device information, the predicted state of the first system is determined. It should be noted that the process of determining the predicted state can also be executed by the server corresponding to the electronic device, and this embodiment does not limit this.

[0072] Step 206: At the second moment, control the first system to switch to the prediction state.

[0073] The second moment is later than the first moment. Optionally, the time difference between the second moment and the first moment is not greater than the processing time, which is the time consumed by the electronic device to predict the predicted state corresponding to the first system based on the current device information.

[0074] In some embodiments, if the predicted state differs from the current state of the electronic device, the electronic device will control the first system to switch from the current state to the predicted state at a second time; if the predicted state is the same as the current state of the electronic device, the electronic device will keep the first system in the current state. Here, the current state is the state of the first system when the electronic device determines the predicted state.

[0075] In summary, the method provided in this embodiment predicts the predicted state of the first system of the electronic device based on the current device information, and controls the first system to switch to the predicted state accordingly. Since the current device information is related to the user's usage scenario of the electronic device, and the usage scenario is related to the user's performance requirements for the electronic device, predicting the state that the more powerful first system needs to enter based on the user's performance requirements enables reasonable control of the first system's state according to the user's needs, thereby reasonably balancing the performance and power consumption of the electronic device.

[0076] Figure 3 is a flowchart illustrating a control method for an electronic device provided in an exemplary embodiment of this application. This method can be used in electronic devices, such as wearable devices. As shown in Figure 3, the method includes:

[0077] Step 302: Obtain the current device information of the electronic device at the first moment.

[0078] Current device information includes the device information of the electronic device at a specific moment, such as the device information collected at that moment. The device information includes information related to the electronic device, which is relevant to the user scenario of the electronic device. In some embodiments, current device information includes one or more of the following: the behavior type of the user identified by the electronic device, the air pressure value collected by the electronic device, the current time in the electronic device, notification messages in the electronic device, location information collected by the electronic device, and physiological information of the user collected by the electronic device.

[0079] The behavior type of the user reflects the behavior of the user during the use of the electronic device, such as walking, sitting, standing, lying down, sleeping, running, swimming, playing soccer, playing basketball, dancing, aerobics, weightlifting, and skiing, among one or more of these. The air pressure value collected by the electronic device is the air pressure value corresponding to the location of the electronic device at the first moment. The current time in the electronic device is the current time in the electronic device at the first moment. Notification messages in the electronic device include notification messages sent by the system of the electronic device and / or notification messages sent by the application in the electronic device. Location information is information obtained by the electronic device at the first moment to reflect the location of the electronic device. The physiological information of the user reflects the physiological characteristics of the user at the first moment, such as heart rate, blood oxygen, pressure, blood pressure, blood sugar, sleep state, and calorie consumption, among one or more of these.

[0080] The electronic device includes at least two systems, where each system can refer to an operating system. In some embodiments, the electronic device supports dual systems, with a first system and a second system configured within it. Optionally, the relationship between the first system and the second system includes one or more of the following: the first system is more complex than the second system, the first system has more functions than the second system, and the power consumption of running the first system is higher than that of the second system. The first system can be a first operating system, and the second system can be a second operating system. In some embodiments, the first system is a non-embedded system, and the second system is an embedded system. For example, the first system is an Android system, and the second system is an RTOS. In some embodiments, the electronic device includes a first processing core and a second processing core, which are used to process instructions generated during the operation of the electronic device. In some embodiments, the performance of the first processing core is stronger than that of the second processing core, for example, the ultimate performance of the first processing core is stronger than that of the second processing core, and / or the energy efficiency of the first processing core is stronger than that of the second processing core. In some embodiments, the first processing core and the second processing core are integrated on a single chip, or they can be integrated on two separate chips. In some embodiments, the first processing core is a first processor, and the second processing core is a second processor. For example, the first processing core is a CPU, and the second processing core is an MCU. In some embodiments, a first processing core is used to run a first system, and a second processing core is used to run a second system. The first system can be referred to as a big-core system, and the second system can be referred to as a small-core system.

[0081] In some embodiments, the electronic device includes a wearable device, such as a smartwatch.

[0082] Step 304: Based on the current device information and the historical device information of the electronic device at a historical moment, predict the predicted state corresponding to the first system of the electronic device.

[0083] The first system is one of at least two systems of the electronic device, and the state of the first system is related to the power consumption of the first system. Historical device information includes device information of the electronic device at historical moments, such as device information collected at historical moments prior to the first moment. Optionally, the type of information in the historical device information is the same as the current device information.

[0084] The predicted state is a state that the electronic device needs to enter, predicted based on its current and historical device information. Optionally, the states of the first system include one or more of the following: running state, standby state, ultra-low power state, and power-off state. The predicted state is one of these states. The different system states are illustrated below: In some embodiments, from an energy-saving perspective, the power consumption of the system in the running state is higher than that in the standby state, and the power consumption of the system in the standby state is higher than that in the ultra-low power state, and the power consumption of the system in the ultra-low power state is higher than that in the power-off state. In some embodiments, the power consumption of the system in the power-off state is 0, but if a power-off timed task is set, such as a power-off alarm, the power consumption of the system in the power-off state is greater than 0. In some embodiments, in terms of the functions provided by the system, the system provides more functions in the running state than in the standby state, and the system provides more functions in the standby state than in the ultra-low power state, and the system provides more functions in the ultra-low power state than in the power-off state. For example, in terms of the activation status of the corresponding electronic components in the system, more electronic components are activated in the running state than in the standby state, and more electronic components are activated in the standby state than in the ultra-low power state, and more electronic components are activated in the ultra-low power state than in the power-off state. For example, in terms of the wake-up time to bring the system to the running state, the wake-up time from standby to running state is shorter than that in the ultra-low power state, and the wake-up time from the ultra-low power state to running state is shorter than that in the power-off state. In some embodiments, in the running state, the system-related hardware works normally; in the standby state, most of the system-related hardware is turned off; in the ultra-low power state, most of the system-related hardware is turned off, providing only the most basic system functions; in the power-off state, all system-related hardware is turned off, or only timed task functions are provided. For example, the processor loses power in the power-off state. In some embodiments, the standby state can also be understood as a hibernation state and / or a sleep state, the ultra-low power state can also be understood as a DS state, and the power-off state can also be understood as a shutdown state.

[0085] Optionally, the electronic device can identify the historical device information with the highest similarity to the current device information from different historical device information, that is, the historical device information with the highest probability of corresponding to the same usage scenario as the current device information. Then, based on the state of the first system under the corresponding historical device information, the predicted state of the first system is determined. For example, the historical device information includes information 1, information 2, and information 3. The state of the first system under information 1 is running, the state of the first system under information 2 is standby, and the state of the first system under information 3 is powered off. The electronic device determines that information 1 has the highest similarity to the current device information, and thus determines the running state as the predicted state of the first system.

[0086] For situations where electronic devices use AI models to determine predicted states:

[0087] Optionally, the electronic device obtains the predicted state of the first system output by inputting current device information into the state prediction model. The state prediction model includes an AI model, such as a machine learning model built using a DNN. This application embodiment does not limit the type of state prediction model. The state prediction model is trained using historical device information and the historical state of the first system under that historical device information. The historical state is the state of the first system at the historical moment when the historical device information was collected. In some embodiments, the electronic device supports automatically adjusting the state of the first system according to how the user uses the electronic device. Therefore, the historical state of the first system under different historical device information can be the same or different. For example, when the screen-off time of the electronic device reaches a first duration, the electronic device controls the first system to enter standby mode; when the screen-off time of the electronic device reaches a second duration, the electronic device controls the first system to enter an ultra-low power state, where the second duration is longer than the first duration; when the electronic device detects that the user is asleep and the sleep duration reaches a third duration, the electronic device controls the first system to enter a power-off state. It should be noted that the above-mentioned rules for adjusting the state of the first system according to the user's way of using the electronic device are only used as examples, and the embodiments of this application do not limit the rules for adjusting the state of the first system according to the way of use.

[0088] In some embodiments, the state prediction model is set in the AI ​​subsystem of the electronic device, and the AI ​​subsystem of the electronic device is used to run the state prediction model to determine the predicted state corresponding to the first system. The AI ​​subsystem can be integrated into the first system of the electronic device or into the second system of the electronic device, and the embodiments of this application do not limit this.

[0089] Optionally, during the training of the state prediction model, historical device information is input into the model to obtain the predicted output state of the electronic device under the historical device information. Then, based on the difference between the output state and the historical state, the error loss of the state prediction model can be determined. By continuously optimizing the error loss of the state prediction model using different historical device information, the state prediction model can be trained to obtain a state prediction model used to output the predicted state.

[0090] In some embodiments, the electronic device trains its local AI model using historical device information and historical states to obtain a state prediction model. The local AI model of the electronic device includes AI models pre-set in the device by the device's developers and / or AI models downloaded to the device. The process of training the local AI model of the electronic device can be referred to the relevant content above, and will not be repeated here in the embodiments of this application.

[0091] In some embodiments, the electronic device sends historical device information and historical states to the server and receives model parameters sent by the server. Based on the model parameters and the electronic device's local AI model, it determines a state prediction model. A communication connection is established between the server and the electronic device, for example, the electronic device directly establishes a communication connection with the server, and / or the electronic device establishes a communication connection with the server through a connected computer device, which can be a terminal, such as a smartphone. The model parameters are obtained by the server training its local AI model using historical device information and historical states. For example, after training its local AI model using historical device information and historical states, the server determines the model parameters to send to the electronic device based on the model parameters of the trained local AI model. Optionally, the electronic device obtains the state prediction model by adjusting the original model parameters of its local AI model to the model parameters sent by the server. During the process of adjusting the original model parameters to the model parameters sent by the server, the electronic device can replace the original model parameters with the model parameters sent by the server, or modify the original model parameters based on the model parameters sent by the server. The process of training the server's local AI model can be referred to the relevant content above, and will not be repeated here in this embodiment.

[0092] For cases where the server determines the predicted state using an AI model:

[0093] Optionally, the electronic device sends its current device information to the server, thereby receiving the predicted state corresponding to the first system sent by the server. The predicted state is predicted by the server based on the current device information using a state prediction model. The state prediction model includes AI models, such as machine learning models built using DNNs. This application embodiment does not limit the type of state prediction model. The state prediction model is trained by the server using historical device information and the historical state of the first system under the historical device information. During the training of the state prediction model, the electronic device sends historical device information and the corresponding historical state to the server. A communication connection is established between the server and the electronic device, for example, the electronic device directly establishes a communication connection with the server, and / or the electronic device establishes a communication connection with the server through a connected computer device, which can be a terminal, such as a smartphone.

[0094] In some embodiments, each electronic device corresponds to a state prediction model in the server, and different electronic devices correspond to different state prediction models in the server. In this case, the state prediction model corresponding to an electronic device is trained using data collected by that electronic device and is only used to predict the predicted state corresponding to that electronic device. The process of training the state prediction model and determining the predicted state based on the state prediction model can be referred to the relevant content above, and will not be repeated here in the embodiments of this application. In some embodiments, different electronic devices correspond to the same state prediction model in the server. In this case, the state prediction model is trained using data collected by different electronic devices. In the process of training the state prediction model, in addition to the content mentioned above, it is also necessary to input the identifier corresponding to the electronic device into the state prediction model, such as the account of the user of the electronic device. In the process of determining the predicted state through the state prediction model, in addition to the content mentioned above, it is also necessary to input the identifier corresponding to the electronic device into the state prediction model so that the state prediction model outputs the corresponding predicted state for the electronic device corresponding to the identifier.

[0095] Optionally, the electronic device can predict whether the predicted state corresponding to the first system is an ultra-low power state based on the current device information. The power consumption of the first system in the ultra-low power state is lower than that in the standby state and higher than that in the power-off state, and / or, the wake-up time of the first system in the ultra-low power state is greater than that in the standby state and less than that in the power-off state. The electronic device can predict whether the predicted state corresponding to the first system is an ultra-low power state using the above-described state prediction model. The prediction process and training process of the state prediction model can be referred to the relevant content above, and will not be repeated here in the embodiments of this application.

[0096] In some embodiments, when the predicted state corresponding to the first system is an ultra-low power state, the electronic device can also predict a third moment when the first system exits the ultra-low power state. Optionally, the electronic device simultaneously determines that the predicted state is an ultra-low power state and predicts the third moment; or, when the predicted state corresponding to the first system is an ultra-low power state, the electronic device predicts the third moment after determining that the predicted state is an ultra-low power state.

[0097] Optionally, the electronic device simultaneously determines the predicted state as an ultra-low power state and the predicted third time step using the aforementioned state prediction model. In this case, the historical state corresponding to the historical device information used to train the state prediction model reflects whether the electronic device was in an ultra-low power state at a historical time step. If the historical state is an ultra-low power state, during the training process, the state prediction model also predicts the predicted exit time of the first system exiting the ultra-low power state under the historical device information. This predicted exit time is used to predict when the first system will exit the ultra-low power state after the historical time step. By determining the error loss based on the error between the predicted exit time and the actual exit time of the first system exiting the ultra-low power state after the historical time step, and combining this error loss determined based on the output state and the historical state, the state prediction model can be trained to predict whether the predicted state of the first system is an ultra-low power state and to predict the third time step.

[0098] Optionally, the electronic device determines whether the predicted state is an ultra-low power state using the aforementioned state prediction model, and then predicts the third moment using the same model after determining that the predicted state is an ultra-low power state. Optionally, when determining whether the predicted state is an ultra-low power state using the state prediction model, the electronic device inputs first indication information to the state prediction model, which instructs the model to output whether the predicted state is an ultra-low power state. When predicting the third moment using the state prediction model, the electronic device inputs second indication information to the model, which instructs the model to output the third moment. In this case, the training process of the state prediction model can refer to the previous description of the state prediction model used to simultaneously determine the predicted state as an ultra-low power state and predict the third moment; this embodiment will not repeat the details here. Optionally, the electronic device determines whether the predicted state is an ultra-low power state using the aforementioned state prediction model, and then predicts the third moment based on historical device information by exiting the prediction model. The exit prediction model includes AI models, such as machine learning models built using DNNs; this embodiment does not limit the type of exit prediction model. Electronic devices input historical device information, or device information from a point after a historical moment, into an exit prediction model, thereby outputting a third exit moment. During the training of the exit prediction model, the model predicts the exit moment when the first system exits the ultra-low power state based on the historical device information. Then, by determining the error loss between the predicted exit moment and the actual exit moment of the first system after the historical moment, the model can be trained to predict the third exit moment.

[0099] In some embodiments, the electronic device determines whether the predicted state is an ultra-low power state through a first system and / or a second system, and the electronic device predicts a third moment through the first system and / or the second system. For example, the electronic device determines whether the predicted state is an ultra-low power state through the second system, and predicts the third moment through the second system. In some embodiments, the electronic device controls / switches the state of the first system through the second system.

[0100] For example, Figure 4 is a schematic diagram of the process of determining a state prediction model provided in an exemplary embodiment of this application. Since historical device information and historical states are related to the user's habits of using electronic devices, historical device information and historical states can be referred to as user habit-related data. As shown in Figure 4, in step S1, the electronic device uploads user habit-related data to the server. In step S2, if the server determines that the user habit-related data has regularity, it will train a local AI model using the user habit-related data, thereby distributing the edge model parameters of the AI ​​model to the electronic device. In step S3, the electronic device determines a state prediction model based on the edge model parameters and executes edge code based on the state prediction model, thereby predicting the predicted state corresponding to the first system based on the current device information, to determine whether the first system is currently entering or exiting the DS state.

[0101] For example, Figure 5 is a schematic diagram of the process of determining a state prediction model provided in an exemplary embodiment of this application. Since historical device information and historical states are related to the user's habits of using electronic devices, historical device information and historical states can be referred to as user habit-related data. As shown in Figure 5, during the process of user 501 using electronic device 502, electronic device 502 acquires user habit-related data and uploads it to server 503. Server 503 trains a local AI model using the user habit-related data to obtain an edge model, i.e., a state prediction model. The edge model is then deployed to electronic device 502. Electronic device 502, based on the current device information using the edge model, can predict the predicted state corresponding to the first system to determine whether the first system is currently entering or exiting the DS state.

[0102] For example, Figure 6 is a schematic diagram of user habit-related data provided in an exemplary embodiment of this application. As shown in Figure 6, the solid line reflects whether the first system of the electronic device is active. If the solid line is above the horizontal axis, it indicates that the first system is active, i.e., in a running state. The dashed line reflects the number of times the user uses the electronic device, such as the number of times the application in the first system is used. The horizontal axis of the coordinate axis represents time, and the vertical axis represents the number of times. According to the user habits shown in Figure 6, the user will not use the application in the first system between 11:00 and 14:00. When the current device information is the current time in the electronic device, the state prediction model will predict the predicted state of the first system as DS state when the current time is between 11:00 and 14:00.

[0103] In some embodiments, the electronic device has at least two operating modes. For example, the at least two operating modes include a first mode and a second mode, where the first mode may be referred to as a battery life mode and the second mode may be referred to as a performance mode. Optionally, the first mode is a mode that supports predictive control of the state of the first system, and the second mode is a mode that does not support predicting the state of the first system; and / or, the power consumption of the first mode is lower than that of the second mode. In some embodiments, when the electronic device is in the first mode, the first system can switch between an operating state, a standby state, an ultra-low power state, and a power-off state. When the electronic device is in the second mode, the first system can switch between an operating state, a standby state, and an ultra-low power state. When the electronic device is in the first mode of at least two operating modes, the predicted state of the first system is predicted based on the current device information. That is, only when the electronic device is in the first mode will the current device information be obtained and the predicted state of the first system be predicted, thereby automatically controlling the state of the first system; when the electronic device is not in the first mode, for example, in the second mode, the current device information will not be obtained and the predicted state of the first system will not be predicted.

[0104] In some embodiments, in addition to the first and second modes described above, the operating mode of the electronic device may also include a third mode, which is a mode in which the first system remains powered off. That is, while the electronic device is in the third mode, the first system remains powered off. The third mode may be called a lightweight smart mode or a long battery life mode.

[0105] The following describes the process of switching the operating mode of electronic devices:

[0106] In some embodiments, the electronic device displays a mode switching interface, which includes a user interface for switching operating modes. The interface displays mode controls corresponding to at least two operating modes. The electronic device displays the mode switching interface based on triggering the controls displayed in the user interface and / or triggering physical buttons on the electronic device. In response to triggering a first control among the mode controls, the electronic device is switched to a first mode. The first control is the mode control corresponding to the first mode, and the triggering operation can be a touch operation on the first control. It should be noted that the electronic device can also switch to the first mode in other ways, such as by triggering a physical button on the electronic device; this embodiment does not limit this method.

[0107] In some embodiments, when the electronic device switches to the first mode, it triggers a switch of the first system to an ultra-low power state. In response to a trigger operation of the first control in the mode control, if an application is running on the first system, the electronic device displays an operation interface with a close control for closing the applications running on the first system. If all applications running on the first system are closed using the close control, the electronic device controls the first system to enter the ultra-low power state and switches the electronic device to the first mode. If all applications running on the first system are not closed using the close control, the electronic device switches to the first mode at a target time. The target time is the moment when the electronic device automatically controls the first system to enter the ultra-low power state. The target time can be set by an object, for example, the target time is the sleep time set by the object; when the sleep time is reached, the electronic device automatically controls the first system to enter the ultra-low power state; and / or, the electronic device is a smartwatch, and the target time is the moment the smartwatch is removed from the wrist; when the smartwatch is removed from the wrist, the electronic device automatically controls the first system to enter the ultra-low power state. It should be noted that the target time can also be a time other than those mentioned in the above examples, and this application embodiment does not limit this.

[0108] For example, Figure 7 is a schematic diagram of a switching operation mode process provided in an exemplary embodiment of this application. As shown in Figure 7, the electronic device displays a user interface 701, which is a drop-down menu of the electronic device, and displays a mode switching control 702. In response to a touch operation on the mode switching control 702, the electronic device displays a user interface 703, which is a mode switching interface, and displays mode controls 704 and 705. Mode control 704 corresponds to the first mode, and mode control 705 corresponds to the second mode. In response to a touch operation on mode control 704, if no application is running on the first system, the electronic device will directly switch to the first mode. If an application is running on the first system, the electronic device will display a user interface 706, which is an operation interface, and displays a close control 706 for closing applications running on the first system. When all applications running on the first system are closed by closing the close control 706, the electronic device will control the first system to enter an ultra-low power state and switch the electronic device to the first mode. If all applications running on the first system are not closed by closing control 706, the electronic device will control the first system to enter an ultra-low power state at a target time before the next day, thereby switching to the first mode on the next day.

[0109] In some embodiments, in response to a triggering operation of the second control in the mode control, when the first system is in a powered-off state, the electronic device controls the first system to exit the powered-off state and switches the electronic device to the second mode, for example, by waking up the first system in the background to enter a running state and switching the electronic device to the second mode. When the first system is not in a powered-off state, the electronic device maintains the state of the first system and switches the electronic device to the second mode. The second control is the mode control corresponding to the second mode, and the second mode is a different running mode from the first mode among at least two running modes.

[0110] It should be noted that the process of switching to the third mode can be referred to the relevant content above, and will not be described in detail in this embodiment.

[0111] In some embodiments, when the first system is in an ultra-low power state, in response to a program execution operation, the electronic device wakes up the first system to enter a running state and runs the application indicated by the program execution operation through the first system. The program execution operation is used to trigger the execution of the application in the first system. For example, FIG8 is a schematic diagram of switching the state of the first system provided in an exemplary embodiment of this application. As shown in FIG8, the first system 801 of the electronic device is in a DS state. Upon receiving a program execution operation, the electronic device controls the first system 801 to exit the DS state and enter a running state to run the application indicated by the program execution operation through the first system. During the process of the electronic device controlling the state of the first system 801, the state of the second system 802 can remain unchanged. For example, FIG9 is a schematic diagram of a transition animation provided in an exemplary embodiment of this application. As shown in FIG9, when the first system of the electronic device is in the DS state and the electronic device receives a program execution operation, during the process of waking up the first system to enter the running state, the electronic device displays a user interface 901 and displays a transition animation 902 in the user interface 901 until the wake-up of the first system to enter the running state is completed, and then displays the user interface corresponding to the application indicated by the program execution operation.

[0112] Step 306: At the second moment, control the first system to switch to the prediction state.

[0113] The second moment is later than the first moment. Optionally, the time difference between the second moment and the first moment is no greater than the processing time, which is the time consumed by the electronic device to predict the predicted state corresponding to the first system based on the current device information. For example, it could be the time consumed by the electronic device to determine the predicted state through a state prediction model, and / or the time consumed by the electronic device to obtain the predicted state through a server.

[0114] In some embodiments, if the electronic device predicts whether the predicted state of the first system is an ultra-low power state based on current device information, and the predicted state is indeed an ultra-low power state, the electronic device will control the first system to switch to the ultra-low power state at a second time. In some embodiments, if the electronic device predicts a third time, it will control the first system to exit the ultra-low power state at the third time. Controlling the first system to exit the ultra-low power state includes controlling the first system to enter the running state, and / or controlling the first system to enter the state before switching to the ultra-low power state. The process of predicting the third time can be referred to the relevant content above, and will not be repeated here in the embodiments of this application.

[0115] For example, Figure 10 is a schematic diagram of the battery life of an electronic device provided in an exemplary embodiment of this application. As shown in Figure 10, the hybrid mode of the electronic device is a mode in which both the first system and the second system can be in operation. In this mode, the display screen of the electronic device can be controlled by either the first system or the second system. The long battery life mode (light intelligent mode) of the electronic device is a mode in which the first system is in a powered-off state. In this mode, the display screen of the electronic device is controlled by the second system. In the second mode (performance mode) of the hybrid mode, i.e., without intelligently adjusting the state of the first system using the method provided in the embodiment of this application, the battery life is 5 days. In the long battery life mode, since the first system is always powered off, the battery life can reach 15 days. If the user switches the electronic device from the second mode of the hybrid mode to the first mode (battery life mode) of the hybrid mode on the first day, and the first mode takes effect on the second day, the electronic device will intelligently adjust the state of the first system using the method provided in the embodiment of this application to improve the battery life of the electronic device. In an extreme case, i.e., by predictively controlling the first system to always maintain the DS state, the battery life of the electronic device can be increased to 13 days. Furthermore, even if the first system for predictively controlling electronic devices only enters DS state for 1 hour per day, it can still enable electronic devices to last for more than 5 days, thus providing users with a better battery life experience.

[0116] In summary, the method provided in this embodiment predicts the predicted state of the first system of the electronic device based on the current device information, and controls the first system to switch to the predicted state accordingly. Since the current device information is related to the user's usage scenario of the electronic device, and the usage scenario is related to the user's performance requirements for the electronic device, predicting the state that the more powerful first system needs to enter based on the user's performance requirements enables reasonable control of the first system's state according to the user's needs, thereby reasonably balancing the performance and power consumption of the electronic device.

[0117] The method provided in this embodiment further predicts the predicted state of the first system based on current device information and historical device information. Since historical device information is related to the user's habits, the predicted state can conform to the user's habits, improving the accuracy of determining the predicted state. Determining the predicted state using an AI model based on current device information leverages the powerful learning capabilities of AI models to accurately determine the predicted state. Obtaining the state prediction model by training the local AI model of the electronic device ensures its real-time performance. Obtaining the state prediction model using model parameters distributed by the server reduces the power consumption of the electronic device because it eliminates the need for local training. By determining whether the predicted state is an ultra-low power state and the time to exit the ultra-low power state, the method enables reasonable control of the first system's entry and exit from the ultra-low power state based on the user's needs, thereby reasonably balancing the performance and power consumption of the electronic device. By predicting the predicted state of the first system only when the electronic device is in the first mode, the method automatically controls the state of the first system according to the user's wishes, contributing to an improved user experience.

[0118] It should be noted that this application may display a prompt interface, pop-up window, or output voice prompts before and during the collection of user data (such as current device information and historical device information in this application). These prompt interfaces, pop-ups, or voice prompts are used to inform the user that their data is being collected. This ensures that the application only begins the steps for collecting user data after receiving confirmation from the user regarding the prompt interface or pop-up window; otherwise (i.e., without receiving confirmation from the user), the steps for collecting user data end, meaning no user data is collected. In other words, all user data collected in this application is collected with the user's consent and authorization, and the collection, use, and processing of related user data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0119] It should be noted that the order of the method steps provided in the embodiments of this application can be appropriately adjusted, and the steps can also be added or removed as appropriate. Any method variations that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application, and therefore will not be elaborated further.

[0120] Figure 11 is a schematic diagram of the structure of a control device for an electronic device provided in an exemplary embodiment of this application. The device includes at least two systems. As shown in Figure 11, the device includes:

[0121] The acquisition module 1101 is used to acquire the current device information of the device at a first moment;

[0122] Prediction module 1102 is used to predict the predicted state of the first system of the device based on the current device information, wherein the state of the first system is related to the power consumption of the first system.

[0123] The switching module 1103 is used to control the first system to switch to the predicted state at a second time, which is later than the first time.

[0124] In an optional design, the prediction module 1102 is used to predict the predicted state corresponding to the first system based on the current device information and the historical device information of the device at a historical time; wherein the historical time is before the first time.

[0125] In an optional design, the prediction module 1102 is used to obtain the predicted state output by the state prediction model by inputting the current device information into the state prediction model; wherein, the state prediction model includes an AI model, and the state prediction model is trained by the historical device information and the historical state of the first system under the historical device information.

[0126] In an optional design, as shown in Figure 12, the device further includes a training module 1104, used to train the device's local AI model using the historical device information and the historical state to obtain the state prediction model.

[0127] In an optional design, as shown in Figure 13, the device further includes: a sending module 1105, used to send the historical device information and the historical state to the server; a receiving module 1106, used to receive model parameters sent by the server, the model parameters being obtained by the server training its local AI model using the historical device information and the historical state; and a determining module 1107, used to determine the state prediction model based on the model parameters and the device's local AI model.

[0128] In an optional design, the determining module 1107 is used to obtain the state prediction model by adjusting the original model parameters of the device's local AI model to the model parameters.

[0129] In an optional design, as shown in Figure 13, the device further includes: a sending module 1105 for sending the current device information to the server; and a receiving module 1106 for receiving the predicted state sent by the server; wherein the predicted state is predicted by the server based on the current device information using a state prediction model, the state prediction model including an AI model, and the state prediction model is trained using the historical device information and the historical state of the first system under the historical device information.

[0130] In an optional design, the prediction module 1102 is used to predict whether the predicted state is an ultra-low power state based on the current device information; the switching module 1103 is used to control the first system to switch to the ultra-low power state at a second time when the predicted state is the ultra-low power state; wherein, the power consumption of the first system in the ultra-low power state is lower than that in the standby state and higher than that in the power-off state, and / or, the wake-up time of the first system in the ultra-low power state is greater than that in the standby state and less than that in the power-off state.

[0131] In an optional design, the prediction module 1102 is used to predict a third moment when the predicted state is the ultra-low power state; the switching module 1103 is used to control the first system to exit the ultra-low power state at the third moment.

[0132] In an optional design, the current device information includes one or more of the following: the behavior type of the user identified by the device, the air pressure value collected by the device, the current time in the device, notification messages in the device, location information collected by the device, and physiological information of the user collected by the device.

[0133] In an optional design, the device has at least two operating modes; the prediction module 1102 is used to predict the prediction state corresponding to the first system based on the current device information when the device is in the first mode of the at least two operating modes.

[0134] In an optional design, the at least two operating modes include the first mode and the second mode; wherein the first mode is a mode that supports controlling the state of the first system through prediction, the second mode is a mode that does not support predicting the state of the first system; and / or, the power consumption of the first mode is lower than that of the second mode.

[0135] In an optional design, as shown in Figure 14, the device further includes: a display module 1108 for displaying a mode switching interface, wherein the mode switching interface displays mode controls corresponding to each of the at least two operating modes; and a switching module 1103 for switching the device to the first mode in response to a trigger operation on the first control in the mode controls; wherein the first control is the mode control corresponding to the first mode.

[0136] In an optional design, the display module 1108 is used to display an operation interface when an application is running on the first system, the operation interface displaying a close control for closing the application running on the first system; the switching module 1103 is used to control the first system to enter an ultra-low power state and switch the device to the first mode when all applications running on the first system are closed by the close control; and when all applications running on the first system are not closed by the close control, the device is switched to the first mode at a target time, the target time being the time when the first system is automatically controlled to enter the ultra-low power state.

[0137] In an optional design, the switching module 1103 is configured to respond to a trigger operation on the second control in the mode control, and when the first system is in a power-off state, control the first system to exit the power-off state and switch the device to the second mode; when the first system is not in the power-off state, maintain the state of the first system unchanged and switch the device to the second mode; wherein, the second control is a mode control corresponding to the second mode, and the second mode is an operating mode different from the first mode among the at least two operating modes.

[0138] In an optional design, the at least two systems include the first system and the second system; wherein the relationship between the first system and the second system includes one or more of the following: the first system is more complex than the second system; the first system has more functions than the second system; the power consumption of running the first system is higher than that of the second system.

[0139] It should be noted that the control device for the electronic device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the control device for the electronic device provided in the above embodiments and the control method embodiments for the electronic device belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0140] The embodiments of this application also provide an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the control method of the electronic device provided in the above-described method embodiments.

[0141] For example, Figure 15 is a schematic diagram of the structure of a terminal provided in an exemplary embodiment of this application. In some embodiments, the terminal described above is implemented as an electronic device, such as a wearable device.

[0142] Typically, terminal 1500 includes a processor 1501 and a memory 1502.

[0143] Processor 1501 may include one or more processing cores, such as a 4-core processor, a 15-core processor, etc. Processor 1501 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1501 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1501 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1501 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0144] The memory 1502 may include one or more computer-readable storage media, which may be non-transitory. The memory 1502 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1502 is used to store at least one instruction, which is executed by the processor 1501 to implement the control method of the electronic device provided in the method embodiments of this application.

[0145] In some embodiments, the terminal 1500 may also optionally include a peripheral device interface 1503 and at least one peripheral device. The processor 1501, memory 1502, and peripheral device interface 1503 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1503 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: radio frequency circuitry 1504, display screen 1505, camera assembly 1506, audio circuitry 1507, and power supply 1508.

[0146] Peripheral device interface 1503 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1501 and memory 1502. In some embodiments, processor 1501, memory 1502 and peripheral device interface 1503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1501, memory 1502 and peripheral device interface 1503 can be implemented on separate chips or circuit boards, and this application embodiment is not limited in this respect.

[0147] The radio frequency (RF) circuit 1504 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1504 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1504 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1504 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1504 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0148] Display screen 1505 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1505 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1501 for processing. In this case, display screen 1505 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1505, which serves as the front panel of terminal 1500; in other embodiments, there may be at least two display screens, respectively disposed on different surfaces of terminal 1500 or in a folded design; in still other embodiments, display screen 1505 may be a flexible display screen, disposed on a curved or folded surface of terminal 1500. Furthermore, display screen 1505 may also be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1505 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0149] The camera assembly 1506 is used to acquire images or videos. Optionally, the camera assembly 1506 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal 1500, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1506 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0150] The audio circuit 1507 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1501 for processing, or input to the radio frequency circuit 1504 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1500. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1501 or the radio frequency circuit 1504 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1507 may also include a headphone jack.

[0151] Power supply 1508 is used to power the various components in terminal 1500. Power supply 1508 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1508 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0152] In some embodiments, the terminal 1500 further includes one or more sensors 1509. The one or more sensors 1509 include, but are not limited to: an acceleration sensor 1510, a gyroscope sensor 1511, a pressure sensor 1512, an optical sensor 1513, and a proximity sensor 1514.

[0153] Accelerometer 1510 can detect the magnitude of acceleration along the three axes of a coordinate system established by terminal 1500. For example, accelerometer 1510 can be used to detect the components of gravitational acceleration along the three axes. Processor 1501 can control touchscreen 1505 to display the user interface in landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1510. Accelerometer 1510 can also be used for games or for acquiring user motion data.

[0154] The gyroscope sensor 1511 can detect the orientation and rotation angle of the terminal 1500. The gyroscope sensor 1511 can work in conjunction with the accelerometer sensor 1510 to collect 3D motion data from the user on the terminal 1500. Based on the data collected by the gyroscope sensor 1511, the processor 1501 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0155] The pressure sensor 1512 can be disposed on the side bezel of the terminal 1500 and / or on the lower layer of the touch display screen 1505. When the pressure sensor 1512 is disposed on the side bezel of the terminal 1500, it can detect the user's grip signal on the terminal 1500, and the processor 1501 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1512. When the pressure sensor 1512 is disposed on the lower layer of the touch display screen 1505, the processor 1501 can control the operable controls on the UI interface based on the user's pressure operation on the touch display screen 1505. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0156] An optical sensor 1513 is used to collect ambient light intensity. In one embodiment, the processor 1501 can control the display brightness of the touch screen 1505 based on the ambient light intensity collected by the optical sensor 1513. Specifically, when the ambient light intensity is high, the display brightness of the touch screen 1505 is increased; when the ambient light intensity is low, the display brightness of the touch screen 1505 is decreased. In another embodiment, the processor 1501 can also dynamically adjust the shooting parameters of the camera assembly 1506 based on the ambient light intensity collected by the optical sensor 1513.

[0157] The proximity sensor 1514, also known as a distance sensor, is typically located on the front panel of the terminal 1500. The proximity sensor 1514 is used to detect the distance between the user and the front of the terminal 1500. In one embodiment, when the proximity sensor 1514 detects that the distance between the user and the front of the terminal 1500 is gradually decreasing, the processor 1501 controls the touchscreen display 1505 to switch from a screen-on state to a screen-off state; when the proximity sensor 1514 detects that the distance between the user and the front of the terminal 1500 is gradually increasing, the processor 1501 controls the touchscreen display 1505 to switch from a screen-off state to a screen-on state.

[0158] Those skilled in the art will understand that the structure shown in FIG15 does not constitute a limitation on the terminal 1500, and may include more or fewer components than shown, or combine certain components, or employ different component arrangements.

[0159] This application also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set. When the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor of an electronic device, the control method of the electronic device provided in the above-described method embodiments is implemented.

[0160] This application also provides a chip, which includes programmable logic circuits and / or program instructions. When the chip is run on an electronic device, it is used to implement the control methods of the electronic device provided in the above-described method embodiments.

[0161] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the control methods for the electronic device provided in the above-described method embodiments.

[0162] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0163] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent switching, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for an electronic device, characterized in that, The method is performed by the electronic device, which includes at least two systems, and the method includes: Obtain the current device information of the electronic device at a first moment; Based on the current device information, predict the predicted state of the first system of the electronic device, where the state of the first system is related to the power consumption of the first system. At a second time point, the first system is controlled to switch to the predicted state, which is later than the first time point.

2. The method according to claim 1, characterized in that, The step of predicting the predicted state of the first system of the electronic device based on the current device information includes: Based on the current device information and the historical device information of the electronic device at a historical moment, predict the predicted state corresponding to the first system; The historical moment mentioned above is before the first moment.

3. The method according to claim 2, characterized in that, The step of predicting the predicted state of the first system based on the current device information and the historical device information of the electronic device at a historical time includes: By inputting the current device information into the state prediction model, the predicted state output by the state prediction model is obtained; The state prediction model includes an artificial intelligence (AI) model, which is trained using the historical device information and the historical state of the first system under the historical device information.

4. The method according to claim 3, characterized in that, The method further includes: The state prediction model is obtained by training the local AI model of the electronic device using the historical device information and the historical state.

5. The method according to claim 3, characterized in that, The method further includes: Send the historical device information and the historical status to the server; Receive model parameters sent by the server, wherein the model parameters are obtained by the server training the server's local AI model using the historical device information and the historical state; The state prediction model is determined based on the model parameters and the local AI model of the electronic device.

6. The method according to any one of claims 2 to 5, characterized in that, The step of predicting the predicted state of the first system based on the current device information and the historical device information of the electronic device at a historical time includes: Send the current device information to the server; Receive the predicted state sent by the server; The predicted state is predicted by the server based on the current device information using a state prediction model. The state prediction model includes an AI model, which is trained using the historical device information and the historical states of the first system under the historical device information.

7. The method according to any one of claims 1 to 5, characterized in that, The step of predicting the predicted state of the first system of the electronic device based on the current device information includes: Based on the current device information, predict whether the predicted state is an ultra-low power state; The step of controlling the first system to switch to the predicted state at the second moment includes: If the predicted state is the ultra-low power state, the first system is controlled to switch to the ultra-low power state at the second time. Wherein, the power consumption of the first system in the ultra-low power state is lower than that in the standby state and higher than that in the power-off state, and / or, the wake-up time of the first system in the ultra-low power state is greater than that in the standby state and less than that in the power-off state.

8. The method according to claim 7, characterized in that, The method further includes: If the predicted state is the ultra-low power state, predict the third moment when the ultra-low power state will be exited. At the third moment, the first system is controlled to exit the ultra-low power state.

9. The method according to any one of claims 1 to 5, characterized in that, The current device information includes one or more of the following: the behavior type of the user identified by the electronic device, the air pressure value collected by the electronic device, the current time in the electronic device, the notification messages in the electronic device, the location information collected by the electronic device, and the physiological information of the user collected by the electronic device.

10. The method according to any one of claims 1 to 5, characterized in that, The electronic device has at least two operating modes; the step of predicting the predicted state of the first system of the electronic device based on the current device information includes: When the electronic device is in the first of the at least two operating modes, the predicted state corresponding to the first system is predicted based on the current device information.

11. The method according to claim 10, characterized in that, The at least two operating modes include the first mode and the second mode; Wherein, the first mode is a mode that supports controlling the state of the first system through prediction, the second mode is a mode that does not support predicting the state of the first system; and / or, the power consumption of the first mode is lower than that of the second mode.

12. The method according to any one of claims 1 to 5, characterized in that, The at least two systems include the first system and the second system; The relationship between the first system and the second system includes one or more of the following: the first system is more complex than the second system; the first system has more functions than the second system; the power consumption of running the first system is higher than that of the second system.

13. A control device for an electronic device, characterized in that, The device includes at least two systems, the device comprising: The acquisition module is used to acquire the current device information of the device at a first moment; The prediction module is used to predict the predicted state of the first system of the device based on the current device information. The state of the first system is related to the power consumption of the first system. A switching module is used to control the first system to switch to the predicted state at a second time point, which is later than the first time point.

14. The apparatus according to claim 13, characterized in that, The prediction module is used to predict the predicted state corresponding to the first system based on the current device information and the historical device information of the device at a historical time; wherein the historical time is before the first time.

15. The apparatus according to claim 14, characterized in that, The prediction module is used to obtain the predicted state output by the state prediction model by inputting the current device information into the state prediction model; wherein, the state prediction model includes an AI model, and the state prediction model is trained by the historical device information and the historical state of the first system under the historical device information.

16. The apparatus according to claim 15, characterized in that, The device further includes a training module for training a local AI model of the device using the historical device information and the historical state to obtain the state prediction model.

17. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one program, which is loaded and executed by the processor to implement the control method of the electronic device as described in any one of claims 1 to 12.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one program, which is loaded and executed by a processor to implement the control method of the electronic device as claimed in any one of claims 1 to 12.

19. A chip, characterized in that, The chip includes programmable logic circuits and / or program instructions, and when the chip is run on an electronic device, it is used to implement the control method of the electronic device according to any one of claims 1 to 12.

20. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, wherein a processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the electronic device to perform the control method of the electronic device as described in any one of claims 1 to 12.

Images