Startup control method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a startup control method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of terminal equipment. The method comprises the steps that when the terminal equipment detects a startup request, at least one piece of startup decision information is obtained, startup decision result information corresponding to the startup decision information is determined through a decision model, and the startup decision result information is sent to the terminal equipment; the startup decision result information comprises at least one of startup execution, startup interception or popup confirmation, and performing startup control according to the startup decision result information to obtain a startup control result. According to the invention, one or more kinds of startup decision information can be utilized to carry out startup decision processing, which is helpful for improving the accuracy of startup decision and realizing accurate control on whether startup is carried out or not. Decisions are made through the decision-making model based on the startup decision-making information, so that the accuracy of startup control is further improved.

Description

Technical Field

[0001] This application relates to the field of terminal equipment technology, specifically to a power-on control method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] With the development of terminal devices, various technologies and controls have been integrated into them. Powering on is a fundamental function of terminal devices, but with the diversification of terminal device technology and control methods, power-on control also faces some user experience issues. For example, the variety of power-on methods makes accidental power-on a persistent problem in current terminal device power-on control.

[0003] Currently, designs incorporate user distance detection and behavioral habits to make power-on decisions or judgments to reduce accidental power-on. However, the accuracy of these decisions or judgments still needs further improvement. Summary of the Invention

[0004] This application provides a power-on control method, apparatus, electronic device, and computer-readable storage medium, which can further improve the accuracy of power-on control.

[0005] In a first aspect, embodiments of this application provide a power-on control method applied to a terminal device, the method comprising: Upon detecting a power-on request, acquire at least one power-on decision information; The boot decision result information corresponding to the boot decision information is determined by the decision model. The boot decision result information includes at least one of executing boot, blocking boot, or pop-up confirmation. Power-on control is performed based on the power-on decision result information to obtain the power-on control result.

[0006] Secondly, embodiments of this application also provide a power-on control device, applied to a terminal device, the device comprising: The acquisition module is used to acquire at least one power-on decision information when a power-on request is detected; The determination module is used to determine the power-on decision result information corresponding to the power-on decision information through a decision model. The power-on decision result information includes at least one of executing power-on, blocking power-on, or pop-up confirmation. The control module is used to perform power-on control according to the power-on decision result information to obtain the power-on control result.

[0007] Optionally, in some embodiments of this application, the power-on decision information includes current power-on characteristic information and historical power-on characteristic information; The step of determining the power-on decision result information corresponding to the power-on decision information through a decision model includes: Based on the current power-on feature information and the historical power-on feature information, the decision model extracts current decision feature information, historical decision feature information, and related decision feature information. By integrating the current decision feature information, the historical decision feature information, and the associated decision feature information, the target power-on decision feature information is obtained; The power-on decision result information is determined based on the target power-on decision feature information.

[0008] Optionally, in some embodiments of this application, the current power-on feature information includes at least one of the following: current power-on time information, current power-on method information, current power-on sensing information, or current power-on scenario information; The historical boot feature information includes at least one of historical boot time information, historical boot method information, or user profile information; The step of extracting current decision feature information, historical decision feature information, and related decision feature information through the decision model based on the current boot feature information and the historical boot feature information includes: Calculate the first similarity between the current boot time information and the historical boot time information, and fuse the first similarity, the current boot method information, the current boot sensing information, and the current boot scenario information to obtain the current decision feature information; The historical power-on time information is extracted to obtain historical time distribution feature information, and the historical time distribution feature information, the historical power-on method information, and the user profile information are fused to obtain historical decision feature information; Extract the peak feature information corresponding to the current boot time information and the historical boot time information, calculate the second similarity between the current boot method information and the historical boot method information, and fuse the peak feature information and the second similarity to obtain the associated decision feature information.

[0009] Optionally, in some embodiments of this application, the step of fusing the current decision feature information, the historical decision feature information, and the associated decision feature information to obtain the target power-on decision feature information includes: The first fusion weight is calculated based on the current boot time information and the previous boot time information; The second fusion weight is calculated based on the weight threshold and the first fusion weight; The first fusion weight and the second fusion weight are combined to obtain the third fusion weight; The current decision feature information, the historical decision feature information, and the associated decision feature information are fused according to the first fusion weight, the second fusion weight, and the third fusion weight to obtain the target power-on decision feature information.

[0010] Optionally, in some embodiments of this application, the decision model is constructed based on the cross-entropy loss function and decision difference information. The decision difference information includes the difference between the current power-on decision score and the historical power-on decision score during training. The current power-on decision score and the historical power-on decision score during training are calculated based on the current power-on decision feature information and the historical power-on decision feature information during training, respectively.

[0011] Optionally, in some embodiments of this application, determining the power-on decision result information based on the target power-on decision feature information includes: Determine the power-on decision score information corresponding to the target power-on decision feature information; The power-on decision result information is generated based on the power-on decision score information and the target score threshold. The steps for obtaining the target score threshold include: The target score threshold is obtained by adjusting the initial threshold based on the false activation rate, wherein the false activation rate includes the proportion of errors in the decision model.

[0012] Optionally, in some embodiments of this application, the step of performing power-on control according to the power-on decision result information to obtain the power-on control result includes: If the power-on decision result information includes executing power-on, then the power-on process is executed to obtain the power-on control result characterizing power-on; If the power-on decision result information includes blocking power-on, then the power-on blocking process is executed to obtain a power-on control result indicating that the power is not turned on; If the power-on decision result information includes a pop-up confirmation, then a power-on confirmation pop-up is generated based on the current power-on method information and the current usage environment information. In response to the selection operation for the power-on confirmation pop-up, the power-on control process corresponding to the selection operation is executed to obtain the power-on control result.

[0013] Thirdly, embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps in the above-described power-on control method.

[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-described power-on control method.

[0015] Fifthly, embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in embodiments of this application.

[0016] In summary, when the terminal device of this application embodiment detects a power-on request, it obtains at least one power-on decision information, determines the power-on decision result information corresponding to the power-on decision information through a decision model, and the power-on decision result information includes at least one of executing power-on, intercepting power-on, or pop-up confirmation, and performs power-on control according to the power-on decision result information to obtain a power-on control result.

[0017] In this embodiment of the application, one or a combination of multiple power-on decision information can be used for power-on decision processing, which helps to improve the accuracy of power-on decision and achieve accurate control over whether to power on.

[0018] The embodiments of this application make decisions based on power-on decision information through a decision model, which further improves the accuracy of power-on control. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of a scenario in which a terminal device, according to an embodiment of this application, executes the power-on control method; Figure 2 This is a flowchart illustrating the power-on control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the power-on control device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application.

[0021] Explanation of icon numbers: 101-Terminal device; 301-Acquisition module; 302-Determination module; 303-Control module; 401-Processor; 402-Memory; 403-Power supply; 404-Input unit. Detailed Implementation

[0022] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] In the description of the embodiments of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," "third," and "fourth" may explicitly or implicitly include one or more features. In the description of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0024] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0025] This application provides a power-on control method, apparatus, electronic device, and computer-readable storage medium. Specifically, this application provides a power-on control apparatus suitable for electronic devices, including terminal devices, which include, but are not limited to, power-on controllable devices such as televisions, air conditioners, and refrigerators.

[0026] For example, please see Figure 1 , Figure 1This is a schematic diagram illustrating a scenario where a terminal device, according to an embodiment of this application, executes the power-on control method. Specifically, the execution process of the power-on control method by the terminal device is as follows: When the terminal device 101 detects a power-on request, it acquires at least one power-on decision information, determines the power-on decision result information corresponding to the power-on decision information through a decision model, and the power-on decision result information includes at least one of executing power-on, intercepting power-on, or pop-up confirmation. Power-on control is performed according to the power-on decision result information to obtain a power-on control result.

[0027] In summary, in the embodiments of this application, one or a combination of multiple power-on decision information can be used for power-on decision processing, which helps to improve the accuracy of power-on decisions and achieve accurate control over whether to power on.

[0028] The embodiments of this application make decisions based on power-on decision information through a decision model, which further improves the accuracy of power-on control.

[0029] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0030] Please see Figure 2 , Figure 2 This is a flowchart illustrating the power-on control method provided in an embodiment of this application. Although the flowchart shows a logical order, in some cases, the steps shown or described can be executed in a different order than that shown in the flowchart. Specifically, this power-on control method is applied to a terminal device, and the specific flow of the power-on control method is as follows: S201. When a power-on request is detected, at least one power-on decision information is obtained.

[0031] A power-on request is a request to instruct the TV to be turned on. With the diversification of power-on methods for terminal devices, the ways in which this power-on request is generated are also varied. For example, it can be generated by triggering the power button on the terminal device itself, by the user clicking a button on the remote control, by voice activation, or by screen mirroring from another terminal device to this terminal device.

[0032] Understandably, with the diversification of power-on methods, the probability of accidental power-on increases. Users may unintentionally request to power on their devices in daily life. For example, sending screen mirroring information to the wrong device may cause it to power on incorrectly, or users may accidentally utter a voice similar to the power-on wake-up word during voice conversations, all of which can lead to accidental power-on. Therefore, this application aims to improve the accuracy of power-on control by making decisions regarding power-on behavior.

[0033] Among them, power-on decision information refers to information related to power-on that reflects the characteristics of power-on and is of reference value for judging whether the power-on behavior is effective. For example, this power-on decision information includes power-on time, power-on method, or power-on scenario.

[0034] It is understood that the embodiments of this application, by collecting one or more power-on decision information when a power-on request is detected, help to make decisions on power-on behavior through this power-on decision information, thereby controlling whether the device is powered on, and achieving the purpose or effect of power-on control.

[0035] S202. Determine the boot decision result information corresponding to the boot decision information through the decision model. The boot decision result information includes at least one of executing boot, blocking boot, or pop-up confirmation.

[0036] Understandably, a decision model is a model used to make decisions about power-on behavior. The decision model determines whether or not to power on the device. For example, the decision model may include trained models based on deep learning or machine learning.

[0037] The power-on decision result information is the output of the decision model, including options such as executing power-on, blocking power-on, or pop-up confirmation. Executing power-on means the decision result is to instruct power-on, allowing the terminal device to power on. Blocking power-on means the decision result is to stop power-on, preventing the power-on process and keeping the terminal device in a powered-off state. Pop-up confirmation means a pop-up window is displayed to confirm the user's intent. For example, when it's unclear whether to execute or block power-on, a pop-up confirmation prompts the user to confirm. Understandably, after the pop-up window appears, the user can manually choose to power on or not, or the user's intent can be determined to not power on based on a prolonged period of inactivity.

[0038] S203. Perform power-on control according to the power-on decision result information to obtain the power-on control result.

[0039] For example, the power-on process can be executed according to the power-on decision result information, or the power-on control terminal device can be interrupted and kept in a powered-off state.

[0040] The power-on control result refers to the result or state of controlling the terminal device to power on according to the power-on decision result information. For example, the power-on control result includes powering on, keeping the device off, displaying a pop-up window, powering on based on a pop-up window, or powering off based on a pop-up window.

[0041] In summary, in the embodiments of this application, one or a combination of multiple power-on decision information can be used for power-on decision processing, which helps to improve the accuracy of power-on decisions and achieve accurate control over whether to power on.

[0042] The embodiments of this application make decisions based on power-on decision information through a decision model, which further improves the accuracy of power-on control.

[0043] In this application embodiment, historical power-on data can be combined to assist in power-on decision-making and improve the accuracy of power-on control. Specifically, in some embodiments of this application, the power-on decision information includes current power-on characteristic information and historical power-on characteristic information. The step "determining the power-on decision result information corresponding to the power-on decision information through a decision model" includes: Based on the current power-on feature information and the historical power-on feature information, the decision model extracts current decision feature information, historical decision feature information, and related decision feature information. By integrating the current decision feature information, the historical decision feature information, and the associated decision feature information, the target power-on decision feature information is obtained; The power-on decision result information is determined based on the target power-on decision feature information.

[0044] Among them, the current decision feature information refers to the features extracted from the current power-on feature information using a decision model, which is used to characterize the decision reference or influence of the current power-on feature information on the current power-on decision.

[0045] Among them, historical decision feature information refers to the features extracted from historical power-on feature information using a decision model, which is used to characterize the decision reference or influence of historical power-on feature information on current power-on decisions. Among them, the associated decision feature information is a feature extracted by associating the current boot feature information and the historical boot feature information, which is used to reflect the correlation between the current boot feature information and the historical boot feature information.

[0046] It is understood that the embodiments of this application extract boot decision features from multiple perspectives, such as current boot feature information, historical boot feature information, and the relationship between the current and historical information, to improve the accuracy and comprehensiveness of the target boot decision feature information, thereby helping to improve the accuracy of the boot decision result information obtained after making a boot decision based on the target boot decision feature information.

[0047] Specifically, in this embodiment, the current boot-up feature information includes at least one of the following: current boot-up time information, current boot-up method information, current boot-up sensing information, or current boot-up scenario information; the historical boot-up feature information includes at least one of the following: historical boot-up time information, historical boot-up method information, or user profile information. The step "based on the current boot-up feature information and the historical boot-up feature information, extracting current decision feature information, historical decision feature information, and associated decision feature information through the decision model" includes: Calculate the first similarity between the current boot time information and the historical boot time information, and fuse the first similarity, the current boot method information, the current boot sensing information, and the current boot scenario information to obtain the current decision feature information; The historical power-on time information is extracted to obtain historical time distribution feature information, and the historical time distribution feature information, the historical power-on method information, and the user profile information are fused to obtain historical decision feature information; Extract the peak feature information corresponding to the current boot time information and the historical boot time information, calculate the second similarity between the current boot method information and the historical boot method information, and fuse the peak feature information and the second similarity to obtain the associated decision feature information.

[0048] For example, in this embodiment of the application, the current decision feature information f(L) is represented by the following relationship: f(L) = w1·cos(2π|t-h_t|) + w2·m + w3·||s|| + w4·c.

[0049] Where t represents the current boot time information, using a standardized format of 0-24 hours; Where m represents the current power-on method information, with a value from 0 to n, each corresponding to a different power-on method. For example, 0 corresponds to infrared remote control power-on method, 1 corresponds to Bluetooth remote control power-on method, 2 corresponds to panel button power-on method, 3 corresponds to CEC device power-on method, and 4 corresponds to application software power-on method, etc. Where s represents the current power-on sensing information, which includes, but is not limited to, data such as distance, angle, and brightness captured by millimeter-wave radar sensors, infrared distance sensors, light sensors, cameras, etc. Where 'c' represents the current power-on scenario information, which is represented by one-hot encoding for scenario classification. This current power-on scenario information includes the scenario in which the terminal device responds to the power-on request from which power-off state. Power-off states include cold power-off, STR power-off, speaker mode, or stand-alone listening mode, etc.

[0050] Where h_t represents the historical boot time information, cos(2π|t-h_t|) represents the similarity between the current boot time information and the historical boot time information (that is, the first similarity mentioned above).

[0051] The historical decision characteristic information g(R) is represented by the following relationship: g(R) = w5·KL(h_t||U) + w6·h_m + w7·h_p.

[0052] Here, h_t represents historical boot time information, which can also use a standardized encoding format of 0-24 hours.

[0053] Here, h_m represents the historical boot method information. Different values ​​represent different boot methods. The boot methods are as described above and will not be repeated here.

[0054] Here, h_p represents the user profile, which includes the frequency of the user's use of the terminal device, commonly used applications, and time period preferences, providing a reference for power-on decisions.

[0055] Where U represents a uniform distribution, KL divergence measures the regularity of time, and KL(h_t||U) is used to measure whether the power-on time is regular. The larger KL(h_t||U) is, the sharper the distribution and the stronger the regularity; the closer KL(h_t||U) is to 0, the more uniform it is and the less obvious the regularity.

[0056] The associated decision feature information h(L, R) is represented by the following relationship: h(L, R) = w8·I(t∈peak_hours) + w9·sim(m, h_m).

[0057] Where I(t∈peak_hours) means that if the current power-on time information t falls within the historical peak period (referring to peak_hours, the set of high-probability hours extracted by h_t), then a bonus is awarded.

[0058] Where sim(m, h_m) represents the similarity (i.e., the second similarity) between the current boot method information and the historical boot method information.

[0059] Among them, w1, w2, w3, w4, w5, w6, w7, w8 and w9 are all weight parameters obtained after training the decision model.

[0060] Understandably, this design integrates the "current context (time / method / sensor / scene)" with "historical habits (time distribution / method distribution / user profile)," adjusts the trust level in different contexts through dynamic weights, and explicitly encodes "whether the current method falls on the historical peak and whether the current method conforms to historical preferences" using cross-correlation features. The final output is target power-on decision feature information for more accurate evaluation of power-on decisions.

[0061] In some embodiments of this application, a dynamic weight can be designed to fuse current decision feature information, historical decision feature information, and associated decision feature information to further improve the accuracy of the target power-on decision feature information. Specifically, in some embodiments of this application, the step "fusing the current decision feature information, the historical decision feature information, and the associated decision feature information to obtain the target power-on decision feature information" includes: The first fusion weight is calculated based on the current boot time information and the previous boot time information; The second fusion weight is calculated based on the weight threshold and the first fusion weight; The first fusion weight and the second fusion weight are combined to obtain the third fusion weight; The current decision feature information, the historical decision feature information, and the associated decision feature information are fused according to the first fusion weight, the second fusion weight, and the third fusion weight to obtain the target power-on decision feature information.

[0062] For example, the first fusion weight α, the second fusion weight β, and the third fusion weight γ are represented by the following relationship: α= 1 / (1+e^(-|t-last_on|)); β= 1 -α; γ= 0.5*(α+β).

[0063] The target startup decision feature information can be represented as: α·f(L) +β·g(R) +γ·h(L,R).

[0064] Where last_on represents the previous power-on time information, that is, the last power-on time. The first fusion weight α increases with the increase of the "time difference from the last power-on", that is, the larger the time interval, the more it is biased towards the current decision feature information f(L).

[0065] Among them, the second fusion weight β is complementary to the first fusion weight α. That is, the larger the time interval between the current power-on time and the previous power-on time, the smaller the weight of the historical decision feature information g(R).

[0066] Among them, the associated decision feature information is synchronously and dynamically adjusted based on the first fusion weight and the second fusion weight, improving the rationality of the weight design and the accuracy and effectiveness of the target boot decision feature information.

[0067] In the embodiments of the present application, the boot decision score information can be generated based on the target boot decision feature information, and then the boot decision result information is generated in combination with the score threshold. That is, optionally, in some embodiments of the present application, the step of "determining the boot decision result information according to the target boot decision feature information" includes: Determine the boot decision score information corresponding to the target boot decision feature information; Generate the boot decision result information according to the boot decision score information and the target score threshold; The obtaining step of the target score threshold includes: Adjust the initial threshold according to the mis-boot rate to obtain the target score threshold, and the mis-boot rate includes the proportion of the decision errors of the decision model.

[0068] For example, the boot decision score information P is represented by the following formula: P = σ(α·f(L) + β·g(R) + γ·h(L, R)).

[0069] Among them, the target score threshold is a threshold set in advance for comparing and judging the boot decision score information to generate the boot decision result information.

[0070] In the embodiments of the present application, the mis-boot rate is the probability of decision errors statistically obtained during the training process of the decision model, and the mis-boot rate includes the proportion of data where normal boot behavior is decided as mis-boot or mis-boot is decided as normal boot behavior.

[0071] It can be understood that in the embodiments of the present application, by optimizing the initial threshold based on the mis-boot rate, a dynamic target score threshold is obtained, realizing the dynamic adjustment and control of the boot decision, and improving the accuracy of the boot decision result information.

[0072] For example, in the embodiments of the present application, taking the three boot decision result information of executing boot, intercepting boot, and pop-up window confirmation as an example, the target score threshold can include the maximum score threshold θ_max and the minimum score threshold. If P≥θ_max (default 0.8), the boot decision result information is to execute boot. If P≤θ_min (default 0.2), the boot decision result information is to intercept boot. If θ_min<P<θ_max, the boot decision result information is pop-up window confirmation.

[0073] Among them, in the embodiments of the present application, the maximum score threshold is dynamically adjusted, and the expression of θ_max is as follows: θ_max=0.8 d·error_rate.

[0074] Here, 0.8 is the initial threshold, also known as the default threshold, error_rate is the false activation rate, and d is the sensitivity coefficient, which is dynamically adjusted according to the false activation rate. The intuitive goal is to make the threshold for triggering the adjustment of the maximum score threshold automatically stricter or looser based on online performance (mainly with reference to the false activation rate).

[0075] In this embodiment, the decision model can be constructed based on the cross-entropy loss function and decision difference information. The decision difference information includes the difference between the current power-on decision score and the historical power-on decision score during training. The current power-on decision score and the historical power-on decision score during training are calculated based on the current power-on decision feature information and the historical power-on decision feature information during training, respectively.

[0076] For example, the loss function L used to train a decision model is expressed by the following formula: .

[0077] Where, p t This is the predicted probability of the decision model for the true class. In this formula, α is the class balance coefficient, which differs from the first fusion weight mentioned earlier. γ is the focusing parameter; the larger γ is, the better it affects the likelihood of easily manipulated samples (p...). t The stronger the suppression, the closer it is to 1), the more the model focuses on difficult samples.

[0078] Among them, P local P refers to the local or current boot decision score during training. cloud This refers to the cloud-based, previous, or historical boot decision scores. It's understandable that by introducing decision difference information, the model training encourages P... local With P cloud Proximity serves to constrain the model or facilitate knowledge transfer.

[0079] In this application embodiment, for cases where the boot decision result information is a pop-up confirmation, the pop-up can be differentiated based on the current boot method, current usage environment information, and user intent to reduce the impact of the pop-up confirmation prompt on the user's senses, reduce its deliberateness and rigidity, and reduce unnecessary disturbance to the user. That is, optionally, in some embodiments of this application, the step "perform boot control according to the boot decision result information to obtain a boot control result" includes: If the power-on decision result information includes executing power-on, then the power-on process is executed to obtain the power-on control result characterizing power-on. If the power-on decision result information includes blocking power-on, then the power-on blocking process is executed to obtain a power-on control result indicating that the power is not turned on; If the power-on decision result information includes a pop-up confirmation, then a power-on confirmation pop-up is generated based on the current power-on method information and the current usage environment information. In response to the selection operation for the power-on confirmation pop-up, the power-on control process corresponding to the selection operation is executed to obtain the power-on control result.

[0080] For example, in the case of a pop-up confirmation, if the device is powered on using Wake-on-LAN screen mirroring, a pop-up will prompt whether to play the screen mirroring content. After confirmation, the device will be redirected directly. If the user does not confirm for a long time, it indicates that the user does not intend to power on the device. In this case, the pop-up will be canceled or hidden, and the terminal device will remain powered off. For example, if voice power-on is used, and it is determined that the current scene is daytime, then a voice prompt will be used instead of a pop-up prompt; if the current environment is noisy, then the prompt volume will be increased; if it is nighttime and the surrounding light is dim, then the screen backlight will be dimmed to reduce the brightness when a pop-up appears.

[0081] In summary, in the embodiments of this application, one or a combination of multiple power-on decision information can be used for power-on decision processing, which helps to improve the accuracy of power-on decisions and achieve accurate control over whether to power on.

[0082] The embodiments of this application make decisions based on power-on decision information through a decision model, which further improves the accuracy of power-on control.

[0083] The system improves the accuracy of power-on decisions by incorporating multiple power-on information, including current power-on time, power-on method, proximity sensing, power-on scenario, and historical power-on time, power-on method, and user profile.

[0084] Among these methods, the accuracy of startup decisions is improved by extracting current decision feature information, historical decision feature information, and related decision feature information.

[0085] The rationality of feature fusion is improved by dynamically designing the first, second, and third fusion weights during the fusion process.

[0086] Among these measures, the rationality and accuracy of startup decisions are improved through the dynamic design of target score thresholds.

[0087] Among them, by generating and processing pop-ups based on boot method, usage environment and user intent, differentiated processing of pop-ups under different circumstances is achieved, which helps to meet user needs, reduce user interference and improve user experience.

[0088] To facilitate better implementation of the power-on control method of this application, this application also provides a power-on control device based on the above-described power-on control method. The meanings of the terms used are the same as in the power-on control method described above, and specific implementation details can be found in the descriptions of the method embodiments.

[0089] Please see Figure 3 , Figure 3 This is a schematic diagram of the power-on control device provided in an embodiment of this application. The power-on control device is applied to a terminal device, and the power-on control device can specifically be as follows: The acquisition module 301 is used to acquire at least one power-on decision information when a power-on request is detected; The determining module 302 is used to determine the power-on decision result information corresponding to the power-on decision information through a decision model. The power-on decision result information includes at least one of executing power-on, blocking power-on, or pop-up confirmation. The control module 303 is used to perform power-on control according to the power-on decision result information to obtain the power-on control result.

[0090] Optionally, in some embodiments of this application, the power-on decision information includes current power-on characteristic information and historical power-on characteristic information; The step of determining the power-on decision result information corresponding to the power-on decision information through a decision model includes: Based on the current power-on feature information and the historical power-on feature information, the decision model extracts current decision feature information, historical decision feature information, and related decision feature information. By integrating the current decision feature information, the historical decision feature information, and the associated decision feature information, the target power-on decision feature information is obtained; The power-on decision result information is determined based on the target power-on decision feature information.

[0091] Optionally, in some embodiments of this application, the current power-on feature information includes at least one of the following: current power-on time information, current power-on method information, current power-on sensing information, or current power-on scenario information; The historical boot feature information includes at least one of historical boot time information, historical boot method information, or user profile information; The step of extracting current decision feature information, historical decision feature information, and related decision feature information through the decision model based on the current boot feature information and the historical boot feature information includes: Calculate the first similarity between the current boot time information and the historical boot time information, and fuse the first similarity, the current boot method information, the current boot sensing information, and the current boot scenario information to obtain the current decision feature information; The historical power-on time information is extracted to obtain historical time distribution feature information, and the historical time distribution feature information, the historical power-on method information, and the user profile information are fused to obtain historical decision feature information; Extract the peak feature information corresponding to the current boot time information and the historical boot time information, calculate the second similarity between the current boot method information and the historical boot method information, and fuse the peak feature information and the second similarity to obtain the associated decision feature information.

[0092] Optionally, in some embodiments of this application, the step of fusing the current decision feature information, the historical decision feature information, and the associated decision feature information to obtain the target power-on decision feature information includes: The first fusion weight is calculated based on the current boot time information and the previous boot time information; The second fusion weight is calculated based on the weight threshold and the first fusion weight; The first fusion weight and the second fusion weight are combined to obtain the third fusion weight; The current decision feature information, the historical decision feature information, and the associated decision feature information are fused according to the first fusion weight, the second fusion weight, and the third fusion weight to obtain the target power-on decision feature information.

[0093] Optionally, in some embodiments of this application, the decision model is constructed based on the cross-entropy loss function and decision difference information. The decision difference information includes the difference between the current power-on decision score and the historical power-on decision score during training. The current power-on decision score and the historical power-on decision score during training are calculated based on the current power-on decision feature information and the historical power-on decision feature information during training, respectively.

[0094] Optionally, in some embodiments of this application, determining the power-on decision result information based on the target power-on decision feature information includes: Determine the power-on decision score information corresponding to the target power-on decision feature information; The power-on decision result information is generated based on the power-on decision score information and the target score threshold. The steps for obtaining the target score threshold include: The target score threshold is obtained by adjusting the initial threshold based on the false activation rate, wherein the false activation rate includes the proportion of errors in the decision model.

[0095] Optionally, in some embodiments of this application, the step of performing power-on control according to the power-on decision result information to obtain the power-on control result includes: If the power-on decision result information includes executing power-on, then the power-on process is executed to obtain the power-on control result characterizing power-on. If the power-on decision result information includes blocking power-on, then the power-on blocking process is executed to obtain a power-on control result indicating that the power is not turned on; If the power-on decision result information includes a pop-up confirmation, then a power-on confirmation pop-up is generated based on the current power-on method information and the current usage environment information. In response to the selection operation for the power-on confirmation pop-up, the power-on control process corresponding to the selection operation is executed to obtain the power-on control result.

[0096] In this embodiment of the application, when the acquisition module 301 detects a power-on request, it acquires at least one power-on decision information. The determination module 302 determines the power-on decision result information corresponding to the power-on decision information through a decision model. The power-on decision result information includes at least one of executing power-on, blocking power-on, or pop-up confirmation. The control module 303 performs power-on control according to the power-on decision result information to obtain the power-on control result.

[0097] In summary, the embodiments of this application use a decision model to make power-on decisions based on power-on decision information, which further improves the accuracy of power-on control.

[0098] In addition, this application also provides an electronic device, such as Figure 4 As shown, it illustrates a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically: The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 401 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0099] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0100] The electronic device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power equipment debugging circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0101] The electronic device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0102] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402, thereby implementing the steps in any of the power-on control methods provided in the embodiments of this application.

[0103] When the terminal device of this application embodiment detects a power-on request, it obtains at least one power-on decision information, determines the power-on decision result information corresponding to the power-on decision information through a decision model, and the power-on decision result information includes at least one of executing power-on, intercepting power-on, or pop-up confirmation. Power-on control is performed according to the power-on decision result information to obtain a power-on control result.

[0104] In this embodiment of the application, one or a combination of multiple power-on decision information can be used for power-on decision processing, which helps to improve the accuracy of power-on decision and achieve accurate control over whether to power on.

[0105] The embodiments of this application make decisions based on power-on decision information through a decision model, which further improves the accuracy of power-on control.

[0106] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0107] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0108] Therefore, this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor to execute the steps of any of the power-on control methods provided in this application.

[0109] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0110] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0111] Since the instructions stored in the computer-readable storage medium can execute the steps of any of the power-on control methods provided in this application, the beneficial effects that any of the power-on control methods provided in this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0112] The above provides a detailed description of a power-on control method, apparatus, electronic device, and computer-readable storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A power-on control method, characterized in that, Applied to a terminal device, the method includes: Upon detecting a power-on request, acquire at least one power-on decision information; The boot decision result information corresponding to the boot decision information is determined by the decision model. The boot decision result information includes at least one of executing boot, blocking boot, or pop-up confirmation. Power-on control is performed based on the power-on decision result information to obtain the power-on control result.

2. The power-on control method according to claim 1, characterized in that, The power-on decision information includes current power-on characteristic information and historical power-on characteristic information; The step of determining the power-on decision result information corresponding to the power-on decision information through a decision model includes: Based on the current power-on feature information and the historical power-on feature information, the decision model extracts current decision feature information, historical decision feature information, and related decision feature information. By integrating the current decision feature information, the historical decision feature information, and the associated decision feature information, the target power-on decision feature information is obtained; The power-on decision result information is determined based on the target power-on decision feature information.

3. The power-on control method according to claim 2, characterized in that, The current power-on characteristic information includes at least one of the following: current power-on time information, current power-on method information, current power-on sensing information, or current power-on scenario information; The historical boot feature information includes at least one of historical boot time information, historical boot method information, or user profile information; The step of extracting current decision feature information, historical decision feature information, and related decision feature information through the decision model based on the current boot feature information and the historical boot feature information includes: Calculate the first similarity between the current boot time information and the historical boot time information, and fuse the first similarity, the current boot method information, the current boot sensing information, and the current boot scenario information to obtain the current decision feature information; The historical power-on time information is extracted to obtain historical time distribution feature information, and the historical time distribution feature information, the historical power-on method information, and the user profile information are fused to obtain historical decision feature information; Extract the peak feature information corresponding to the current boot time information and the historical boot time information, calculate the second similarity between the current boot method information and the historical boot method information, and fuse the peak feature information and the second similarity to obtain the associated decision feature information.

4. The power-on control method according to claim 3, characterized in that, The process of fusing the current decision feature information, the historical decision feature information, and the associated decision feature information to obtain the target power-on decision feature information includes: The first fusion weight is calculated based on the current boot time information and the previous boot time information; The second fusion weight is calculated based on the weight threshold and the first fusion weight; The first fusion weight and the second fusion weight are combined to obtain the third fusion weight; The current decision feature information, the historical decision feature information, and the associated decision feature information are fused according to the first fusion weight, the second fusion weight, and the third fusion weight to obtain the target power-on decision feature information.

5. The power-on control method according to claim 1, characterized in that, The decision model is constructed based on the cross-entropy loss function and decision difference information. The decision difference information includes the difference between the current power-on decision score and the historical power-on decision score during training. The current power-on decision score and the historical power-on decision score during training are calculated based on the current power-on decision feature information and the historical power-on decision feature information during training, respectively.

6. The power-on control method according to claim 2, characterized in that, The step of determining the power-on decision result information based on the target power-on decision feature information includes: Determine the power-on decision score information corresponding to the target power-on decision feature information; The power-on decision result information is generated based on the power-on decision score information and the target score threshold. The steps for obtaining the target score threshold include: The target score threshold is obtained by adjusting the initial threshold based on the false activation rate, wherein the false activation rate includes the proportion of errors in the decision model.

7. The power-on control method according to claim 1, characterized in that, The step of performing power-on control according to the power-on decision result information to obtain the power-on control result includes: If the power-on decision result information includes executing power-on, then the power-on process is executed to obtain the power-on control result characterizing power-on; If the power-on decision result information includes blocking power-on, then the power-on blocking process is executed to obtain a power-on control result indicating that the power is not turned on; If the power-on decision result information includes a pop-up confirmation, then a power-on confirmation pop-up is generated based on the current power-on method information and the current usage environment information. In response to the selection operation for the power-on confirmation pop-up, the power-on control process corresponding to the selection operation is executed to obtain the power-on control result.

8. A power-on control device, characterized in that, Applied to a terminal device, the device includes: The acquisition module is used to acquire at least one power-on decision information when a power-on request is detected; The determination module is used to determine the power-on decision result information corresponding to the power-on decision information through a decision model. The power-on decision result information includes at least one of executing power-on, blocking power-on, or pop-up confirmation. The control module is used to perform power-on control according to the power-on decision result information to obtain the power-on control result.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the power-on control method as described in any one of claims 1-7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the power-on control method as described in any one of claims 1-7.

Images