Charging control method, charging control device, storage medium and electronic device

Abstract

The present disclosure provides a charging control method, a charging control device, a computer-readable storage medium and an electronic device, and relates to the field of charging technology. The charging control method comprises: in response to an electronic device meeting a charging prediction trigger condition, predicting charging willingness based on current state information of the electronic device to obtain a prediction result; and determining charging control information according to the prediction result. The present disclosure can provide personalized charging control services according to different users.

Description

Background Art

[0002] At present, electronic devices such as smart phones, portable computers, and wearable devices play an increasingly important role in people's daily lives and are widely used in various scenarios such as office and travel. While electronic devices bring convenience to people, they also occupy most of their daily activities, making people more and more dependent on them. However, due to the limitations of the hardware structure of electronic devices themselves, their battery life is limited, forcing users to charge them in time.

[0003] In order to ensure that users can charge their electronic devices in time, the prior art usually triggers a reminder for users to charge when the power level of the electronic device is below a certain level. However, this charging reminder mechanism is often relatively simple and lacks pertinence, and it is difficult to provide personalized charging suggestions based on the usage habits of different users. Summary of the invention

[0004] The present disclosure provides a charging control method, a charging control device, a computer-readable storage medium and an electronic device, thereby at least to a certain extent improving the problem in the prior art that it is difficult to provide personalized charging suggestions for different users.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to a first aspect of the present disclosure, a charging control method is provided, comprising: in response to an electronic device satisfying a charging prediction trigger condition, predicting charging willingness based on current state information of the electronic device to obtain a prediction result; and determining charging control information according to the prediction result.

[0007] According to a second aspect of the present disclosure, a charging control device is provided, comprising: a charging willingness prediction module, for predicting the charging willingness based on current status information of the electronic device in response to an electronic device satisfying a charging prediction trigger condition, and obtaining a prediction result; and a control information determination module, for determining charging control information according to the prediction result.

[0008] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the charging control method of the first aspect and possible implementation methods thereof are implemented.

[0009] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the charging control method of the first aspect and possible implementation thereof by executing the executable instructions.

[0010] The technical solution disclosed in this disclosure has the following beneficial effects:

[0011] In response to the electronic device satisfying the charging prediction trigger condition, the charging willingness is predicted based on the current state information of the electronic device to obtain a prediction result; and the charging control information is determined according to the prediction result. On the one hand, this exemplary embodiment provides a new charging control method. Different from the prior art method of setting a fixed power threshold for the electronic device to remind the user of the charging, this exemplary embodiment can predict the charging willingness of the user of the electronic device based on the current state information of the electronic device to meet the charging needs of users with different electronic device usage habits, and has strong pertinence and flexibility; on the other hand, this exemplary embodiment predicts the charging willingness based on the current state information of the electronic device, combined with the current actual usage state of the electronic device, which can further ensure the accuracy and effectiveness of the prediction results, provide users with more accurate charging control information, and has a wide range of applicable scenarios.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0014] Figure 1 A schematic diagram showing a system architecture in this exemplary embodiment;

[0015] Figure 2 A flow chart showing a charging control method in this exemplary embodiment;

[0016] Figure 3 A flow chart showing another charging control method in this exemplary embodiment;

[0017] Figure 4 A sub-flow chart showing a charging control method in this exemplary embodiment;

[0018] Figure 5 Another sub-flowchart of a charging control method in this exemplary embodiment is shown;

[0019] Figure 6 A schematic diagram of a decision process of a decision tree in this exemplary embodiment is shown;

[0020] Figure 7 A flowchart showing another charging control method in this exemplary embodiment is shown;

[0021] Figure 8 A structural block diagram of a charging control device in this exemplary embodiment is shown;

[0022] Fig. 9 A structural diagram of an electronic device in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0023] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0024] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0025] In view of one or more of the above problems, an exemplary embodiment of the present disclosure provides a charging control method. Figure 1 1 shows a system architecture diagram of the operating environment of this exemplary embodiment. Figure 1 As shown, the system architecture 100 may include an electronic device 110 and a server 120, which form a communication interaction through a network. For example, the electronic device 110 may send current status information to the server 120, and the server 120 predicts the charging willingness based on the current status information of the electronic device. Among them, the electronic device 110 may include but is not limited to a smart phone, a tablet computer, a game console, a wearable device, etc.; the server 120 refers to a background server that provides Internet services, which may also be a cloud or platform that can predict the charging willingness.

[0026] It should be understood that Figure 1 The number of each device is only exemplary. According to the implementation requirements, any number of electronic devices can be set, or the server can be a cluster formed by multiple servers.

[0027] The charging control method provided in the embodiments of the present disclosure may be executed by the electronic device 110, for example, the electronic device directly predicts the charging intention after obtaining the current status information; it may also be executed by the server 120, for example, the electronic device sends the current status information to the server after obtaining it, and the server predicts the charging intention and obtains the prediction result, etc. The present disclosure does not limit this.

[0028] Figure 2 An exemplary process of the charging control method is shown, including the following steps S210 to S220:

[0029] Step S210, in response to the electronic device satisfying the charging prediction trigger condition, a charging willingness prediction is performed based on the current state information of the electronic device to obtain a prediction result.

[0030] Among them, the charging prediction trigger condition refers to the trigger condition used to determine whether the current electronic device needs to perform charging prediction control. The charging prediction trigger condition can be set according to the state of the electronic device. For example, the charging prediction trigger condition can be that the power of the electronic device is lower than the average starting charge, the use time of the electronic device reaches a preset time, or the current time corresponding to the electronic device reaches a preset time or a preset time period, such as reaching 8 o'clock every night, and the charging prediction trigger condition is met; the charging prediction trigger condition can also be set according to the user's operation, for example, the charging prediction trigger condition can be that the user opens or slides to a specific display interface when using the electronic device, such as sliding to the negative one screen interface of the electronic device display interface; using a certain application, such as setting a commonly used application as a trigger application, when the user uses or opens the application, it is considered that the charging prediction trigger condition is met; performing specific interactive operations, such as sliding the screen with two or three fingers, lighting the screen in the off state or long pressing the screen, etc.; or other operations, such as checking the current power of the electronic device or checking the battery status, etc. The charging prediction trigger condition can also be a combination of the above multiple conditions, for example, the charging prediction trigger condition can be that the user performs a specific interactive operation, and the power of the electronic device is lower than the average starting charge, etc., and the present disclosure does not make specific limitations on this.

[0031] When an electronic device meets the charging prediction trigger conditions, the current status information of the electronic device can be obtained or collected. Among them, the current status information refers to the information generated or determined by the electronic device during use, which can reflect its usage status, and can specifically include time-related information, such as the current time, the date or week number corresponding to the current time, etc.; information related to applications, such as the number of applications used, the length of time the applications are used, etc.; or information related to power, such as the power corresponding to the current time, the power consumption rate, etc. In actual applications, the current status information can be one or more of the above information, which can be expanded or deleted according to actual needs.

[0032] Furthermore, this exemplary embodiment can predict the user's willingness to charge based on the current state information of the electronic device to obtain a prediction result. Charging willingness prediction refers to the process of predicting whether the user currently wants to charge or whether he or she will charge. The prediction result may include the result of whether the current electronic device is charged, such as charging or not charging; it may also include the probability result of whether charging; it may also include the result of when the current electronic device may be charged, etc. The specific prediction result can be customized according to the specific prediction method or prediction algorithm.

[0033] In this exemplary embodiment, the prediction of charging willingness based on the current status information of the electronic device can be achieved by training a machine learning model or establishing a rule engine. For example, a classification model for predicting charging willingness can be pre-trained. After obtaining the current status information of the electronic device, the current status information is converted into a feature vector or matrix as an input to the classification model to predict charging willingness, thereby obtaining a prediction result of whether the electronic device is charged.

[0034] In addition, in order to ensure the accuracy of the prediction of the user's charging willingness, this exemplary embodiment can also screen and filter users based on their historical usage data of electronic devices, and perform a charging willingness prediction process for users whose charging usage habits are obvious or whose stability meets certain conditions, such as predicting the charging willingness of users whose historical charging time meets certain rules or whose historical charging amount is within a certain fixed range, etc.

[0035] In an exemplary embodiment, the electronic device meets the charging prediction trigger condition, which may include:

[0036] The electronic device enters a preset interface, and the current power of the electronic device is lower than the average starting charge.

[0037] In actual applications, electronic devices can usually include multiple interfaces, such as the corresponding menu option interface when the user swipes down; the corresponding setting interface opened when the user performs a setting operation; the display interface created or set by the user; or the screen display interface of the electronic device itself, etc. Among them, different screen display interfaces can be customized to place different applications or components according to the user's usage habits. For example, a display device can usually include a main screen display interface, a second screen display interface, a third screen display interface, etc. Different screen interfaces can be switched according to the user's specific operation behavior. For example, in the main screen display interface, the user can swipe left to switch to the second screen display interface; in the second screen display interface, swipe left again to switch to the third screen display interface, etc. In addition, the screen display interface may also include a negative one screen interface. For example, when the user slides to the right on the main screen display interface, the user may switch to a multifunctional interface at the negative one screen position. The interface may include user-common applications, multiple components and applications added by system settings, component modules such as scenario recognition or smart applications, as well as news information, weather forecast, code scanning, notes or search and other quick functions, etc. The user may also adjust the content in the negative one screen interface according to their needs. The preset interface in this exemplary embodiment may be one or more of the above-mentioned multiple interfaces. For example, the preset interface may be a menu option interface, a menu option interface or a negative one screen interface, etc. Specifically, it may be customized as needed, and the present disclosure does not specifically limit this.

[0038] In this exemplary embodiment, it is taken into account that users often visit multiple interfaces when using electronic devices, for example, users often visit the negative one-screen interface with multiple shortcut functions. Therefore, the relevant engine or module of charging prediction can be configured in one or more preset interfaces as needed to use the user's access to the preset interface as one of the charging prediction trigger conditions. Since the user does not need to predict the willingness to charge every time he accesses the preset interface. Therefore, in order to improve the effectiveness and accuracy of triggering the prediction of charging willingness and save computing resources, this exemplary embodiment can be set to meet the charging prediction trigger condition when the electronic device enters the preset interface and the current power of the electronic device is lower than the average starting charge. Among them, the average starting charge refers to the average power of the electronic device when it starts charging in the historical charging behavior, and the average starting charge can be obtained by obtaining historical data statistics of the electronic device.

[0039] Step S220: determining charging control information according to the prediction result.

[0040] The charging control information may be information generated according to the charging intention prediction result for providing charging suggestions or reminders to the user. For example, when the prediction result is charging, the charging control information may be information suggesting or reminding the user that the electronic device currently needs to be charged, or information suggesting the user to close background applications, adjust screen brightness, or enter power saving mode, etc.; when the prediction result is not charging, the charging control information may be information suggesting that the electronic device does not need to be charged. In this exemplary embodiment, the charging control information may be presented to the user in the form of text or voice to inform the user of the result of the current prediction of the charging intention of the electronic device. The user may perform specific interactive operations according to the charging control information to perform charging control. For example, when the charging control information suggests that the user charge the electronic device, the charging control information may be sent directly to the user to remind the user that the current electronic device needs to be charged, and the user may perform charging operations on the electronic device; or perform operations such as closing background applications, adjusting screen brightness, or entering power saving mode. When the charging control information does not require charging of the electronic device, according to actual needs, the charging control information may be sent to the user to inform the user that the current electronic device has completed the charging intention prediction and does not need to be charged at present; or no reminder may be made.

[0041] The charging control information may also be information generated based on the charging intention prediction result for making charging control decisions for the electronic device. The electronic device may directly perform corresponding charging control based on the charging control information. For example, when the prediction result is charging, the charging control information may be information that can actively send a charging warning to the user; or control information that directly executes operations such as closing background applications, adjusting screen brightness, or entering power saving mode; or, if the user still does not charge the electronic device within a preset time (such as 10 minutes) after receiving a reminder that charging is required, control information that executes operations such as closing background applications or automatically adjusting screen brightness, etc.

[0042] In summary, in this exemplary embodiment, in response to the electronic device satisfying the charging prediction trigger condition, the charging willingness is predicted based on the current state information of the electronic device to obtain a prediction result; and the charging control information is determined according to the prediction result. On the one hand, this exemplary embodiment provides a new charging control method, which is different from the method of setting a fixed power threshold for the electronic device to provide charging reminders in the prior art. This exemplary embodiment can predict the charging willingness of the user using the electronic device based on the current state information of the electronic device to meet the charging needs of users with different electronic device usage habits, and has strong pertinence and flexibility; on the other hand, this exemplary embodiment predicts the charging willingness based on the current state information of the electronic device, combined with the current actual usage state of the electronic device, which can further ensure the accuracy and effectiveness of the prediction results, provide users with more accurate charging control information, and has a wide range of applicable scenarios.

[0043] Figure 3 A flow chart of another charging control method in this exemplary embodiment is shown, which may specifically include the following steps:

[0044] Step S310, determining whether the electronic device meets the charging prediction trigger condition;

[0045] The charging prediction trigger condition may be that the electronic device enters the negative one screen and the power of the electronic device is lower than the average starting charging power;

[0046] When the electronic device does not meet the charging prediction trigger condition, the process ends;

[0047] When the electronic device meets the charging prediction trigger conditions, execute

[0048] Step S320, obtaining current status information of the electronic device;

[0049] Step S330, performing data preprocessing and feature extraction processing on the current state information;

[0050] Among them, data preprocessing may include data cleaning processing such as deduplication, filling or correction of data; feature extraction processing may be to extract feature data related to charging willingness prediction from current state information, so as to facilitate subsequent prediction processing;

[0051] Step S340, predicting charging willingness based on the processed current state information and determining a prediction result;

[0052] Step S350, determining charging control information according to the prediction result.

[0053] In an exemplary embodiment, if Figure 4As shown, in the above step S210, the charging intention is predicted based on the current state information of the electronic device to obtain the prediction result, which may include the following steps:

[0054] Step S410, obtaining a target model for predicting charging willingness;

[0055] Step S420: Process the current state information of the electronic device using the target model to obtain a prediction result.

[0056] This exemplary embodiment can obtain a target model for predicting charging willingness by training a machine learning model, and the target model is a trained machine learning model. Based on the processing of the current state information of the electronic device by the target model, the classification prediction result of whether the electronic device is charged can be directly output, and the probability result of whether it is charged can also be obtained, and the classification result is determined and output according to the probability result. In this exemplary embodiment, the target model can be a classification model, for example, it can be a decision tree model, a naive Bayes model, a random forest model, or a gradient boosting decision tree model. Before using the target model to process the current state information of the electronic device, the current state information can be processed first, and the current state information can be converted into a feature vector or a feature matrix to generate input data of the target model, and then input into the target model for processing to obtain the final prediction result.

[0057] In addition, in order to ensure that the target model can conform to the user's charging and usage habits of electronic devices as much as possible and improve the accuracy of predicting the user's charging willingness, this exemplary embodiment can set a preset period, such as one week or one month, to regularly update the target model.

[0058] In an exemplary embodiment, if Figure 5 As shown, the charging control method may further include the following steps:

[0059] Step S510, collecting usage information of electronic devices as a sample data set;

[0060] Step S520: In response to the sample data set satisfying the training trigger condition, the target model is trained using the sample data set.

[0061] Among them, the usage information may include a variety of usage data when the user uses the electronic device, for example, the usage information may include the usage time of the electronic device, the usage time of the electronic device, the number of applications used in the electronic device, the usage time of each application in the electronic device, the power or power consumption rate corresponding to different times when the electronic device is used, etc. This exemplary embodiment can collect the usage information of the electronic device in any time period or a specific time period as a sample data set for training the target model. For example, when the user performs the electronic device power-on operation, it can trigger the collection of the usage information of the electronic device, or from 0:00 on Sunday to 24:00 on Saturday, the usage information of the electronic device for one week is collected as a sample data set, etc. This exemplary embodiment can also collect usage information according to the user's specific operations or actual needs. For example, when the user sets the charging willingness prediction function to be turned on, the collection of the usage information of the electronic device as a sample data set can be triggered when the electronic device is used normally.

[0062] In order to improve the effectiveness, timeliness and reliability of the sample data set and further ensure the accuracy of the target model prediction, this exemplary embodiment can be set to periodically update the sample data set to optimize and update the target model. For example, it can be set to re-collect the usage information of the electronic device once a week or every two weeks, use the newly collected usage information to train the target model again, and use the new target model to update the old target model, and so on.

[0063] Considering that the effectiveness of target model training depends greatly on the quality of the sample data set, if the quality of the sample data set is not good, it will further affect the prediction accuracy of the target model and generate unnecessary computing workload. Therefore, after acquiring the sample data set, this exemplary embodiment can set a training trigger condition, and only when the sample data set meets certain conditions, will the training of the target model be triggered. Based on this, the effectiveness of the sample data set is improved, thereby further ensuring the accuracy of model training. Among them, the training trigger condition can be considered from multiple aspects such as the scale, comprehensiveness and balance of the sample data set. For example, the training trigger condition can be a combination of one or more conditions such as the amount of data in the sample data set reaches a preset number, or the time corresponding to each sample data in the sample data set meets the preset coverage time range, or the data type in the sample data set reaches a preset number of types.

[0064] In an exemplary embodiment, the sample data set meeting the training trigger condition may include at least one of the following situations:

[0065] The data volume of the sample data set reaches the preset data volume;

[0066] The coverage time of the sample data set reaches the preset duration.

[0067] That is, the exemplary embodiment can determine the training trigger condition of the sample data set from at least one of the above two aspects. The training trigger condition can be that the amount of data in the sample data set reaches the preset data amount, and the preset data amount can be set as needed. For example, the preset data amount can be set to 1000, 1500 or 2000, etc., then when the amount of data in the sample data set is greater than 1000, 1500 or 2000, etc., it is considered that the currently collected sample data set can more comprehensively reflect the user's use habits of the electronic device in terms of quantity, and then, it is considered to meet the training trigger condition. The training trigger condition can also be that the coverage time of the sample data set reaches the preset duration, and the preset duration can also be customized as needed. For example, the preset duration can be set to 72 hours, 7 days or 14 days, etc., then when the coverage time of the data in the sample data set reaches 72 hours, 7 days or 14 days, etc., it is considered that the currently collected sample data set can more comprehensively reflect the user's use habits of the electronic device in terms of time range, and then, it can be considered that the collected sample data set meets the training trigger condition, and the training process of the target model is executed. The training trigger condition can also be jointly determined by the above two aspects, that is, when the amount of data in the sample data set reaches the preset data amount, and the coverage time of the sample data set reaches the preset duration, for example, when the amount of data in the sample data set is greater than 1,000, and the coverage time of the sample data set reaches 14 days, it is considered that the training trigger condition is met, etc. Based on the joint constraints of the above two aspects, the validity and comprehensiveness of the sample data set data can be further guaranteed, thereby improving the accuracy of the target model training, etc.

[0068] After the training trigger condition is met, in order to facilitate the training of the target model, the exemplary embodiment can also perform data preprocessing and feature data extraction processing on the sample data in the sample data set, and use the processed sample data to train the target model. Among them, data preprocessing can include data cleaning, such as performing corresponding deduplication, correction or supplementation on duplicate data, abnormal data or empty data in the data collection process; feature data extraction can include extracting feature data from the sample data, wherein the feature data can be the collected original sample data, such as the usage time of the electronic device or the corresponding power when the electronic device is used, etc. The feature data can also be the statistical data of the collected original sample data, such as the statistics of the electronic device screen on / off and the power on / off data, determining the corresponding timestamps of each application entering and exiting the electronic device, and further extracting the feature data of the usage time of each application, etc.

[0069] In an exemplary embodiment, the above step S510 may include:

[0070] In units of time slices, the state information of the electronic device in each time slice is collected as training data in the sample data set, and the charging information of the electronic device in each time slice is collected as label data in the sample data set;

[0071] The status information includes at least one of the following: power information within the current time slice; the distance between the power within the current time slice and the average starting charge; the distance between the current time slice and the last charging time; the number of applications used in the previous time slice; the application usage time in the previous time slice; the power consumption rate in the previous time slice.

[0072] In order to better represent and manage the status information, this exemplary embodiment can collect the status information of the electronic device in each time slice in units of time slices as training data in the sample data set. The time slice refers to a sub-time period divided from a time period according to a preset time unit. For example, if 30 minutes is a preset time unit and the division starts from midnight every day, 24 hours a day can be divided into 48 time slices. If 60 minutes is a preset time unit and the division starts from midnight every day, 24 hours a day can be divided into 24 time slices, etc. The value range of the preset time unit t can be [30, 60], in minutes. After the division of each time slice is completed, the status information in each time slice can be collected. In addition, the charging information of the electronic device in each time slice can also be collected as the label data c corresponding to each training data in the sample data set. c , the label data can be a classification label of charged or uncharged.

[0073] In this exemplary embodiment, each time slice may be used as the current time slice to collect status information. c The status information in the current time slice may include: c ; The distance a between the current time slice's power and the average starting charge c ; The distance d between the current time slice and the last charging time c ; The number of applications used in the previous time slice app p ; Application usage time in the previous time slice at p ; Power consumption rate c in the previous time slice p .

[0074] Specifically, the power information b in the current time slice c, whose value range can be defined as [0, 100], with a total of 101 values. If no charging behavior occurs in the current time slice, the power closest to the starting point of the current time slice is selected as the power information of the time slice; if charging behavior occurs in the current time slice, the starting charge at the beginning of the charging behavior can be used as the power information of the time slice. When charging behavior occurs in both the previous time slice and the current time slice, or both are in the charging state, the power information of the current time slice should be the same as the power information corresponding to the previous time slice.

[0075] The distance a between the current time slice's power and the average starting charge c , its value range can be defined as [0, 100], with a total of 101 values, where the average starting charge capacity can be calculated from the starting charge capacity of data of a preset percentage (such as 80%) of the total data volume.

[0076] The distance d between the current time slice and the last charging time c , the last charging time can also be represented by the time slice where the last charging behavior is located, then the distance between the current time slice and the last charging time is the number of time slices that differ between the current time slice and the time slice corresponding to the last charging behavior. In this exemplary embodiment, the total time corresponding to the number of time slices that differ can be set to no more than 1 day, that is, the maximum distance is 24 hours.

[0077] The preceding time slice refers to one or more time slices that are arranged in time sequence and are located before the current time slice.

[0078] The number of applications used in the previous time slice app p , which can be the number of applications used in the previous time slice of the current time slice. Its value range can be defined as [0, 20], with a total of 21 values, that is, the default maximum number of applications used is 20. For example, when the previous time slice is from 12 noon to 12:30, when the user uses 15 applications, the number of applications used can be determined to be 15; when the user uses 30 applications, the number of applications used can be determined to be 20, and so on.

[0079] The application usage time in the previous time slice at p , which can be the duration of using the application in the time slice before the current time slice, and its value range can be defined as [0, t], with a total of t+1 values.

[0080] The power consumption rate c in the previous time slice p , which can be the power consumption rate of the previous multiple time slices of the current time slice, for example, the power consumption rate of the previous four time slices, which can be expressed as c in chronological order.p1 、c p2 、c p3 、c p4 . Its value range can be defined as [0, 100], with a total of 101 values. The power consumption rate can be calculated by subtracting the starting charge of the previous time slice from the starting charge of the current time slice as the power consumption rate of the previous time slice. When both time slices generate charging behavior or are in a charging state, since the power information of the two time slices is the same, the power consumption rate is considered to be 0.

[0081] Furthermore, in an exemplary embodiment, the above step S510 may also include:

[0082] Add time-slicing information to the training data;

[0083] The time slice information includes at least one of the following: the length of the time slice; the ordinal number of the time slice; and the date information to which the time slice belongs.

[0084] In addition to the above-mentioned status information of the electronic device in each time slice, the exemplary embodiment may also add the information of the time slice to the training data. The information of the time slice may include: the length t of the time slice, which is used to divide the time slice of fixed time length from the time period. For example, when the length t of the time slice is 60 minutes, the time period of a day can be divided into 24 time slices; the ordinal number of the time slice, which is used to identify different time slices t; c , to distinguish which time slice it is currently in; the date information w to which the time slice belongs, which can reflect the date attribute of the time slice and is used to determine the time characteristics of the time slice. For example, the day of the week that the current time slice is in can be determined based on the date information of the current time slice. The value range of the day of the week can be defined as [0, 6], with a total of 7 values, corresponding to Monday to Sunday respectively.

[0085] In this exemplary embodiment, various types of data involved in the training data are summarized in Table 1 below:

[0086] Table 1

[0087]

[0088]

[0089] This exemplary embodiment can be based on the above: the ordinal number t of the current time slice c , the power information in the current time slice b c , the distance a between the current time slice’s power and the average starting charge c , the distance d between the current time slice and the last charging time c、The number of applications used in the previous time slice app p , the application usage time in the previous time slice at p , the power consumption rate c of the first four time slices p1 、c p2 、c p3 、c p4 , the date information w of the current time slice, these 11 dimensions of information, construct the feature data for target model training, defined as S = {t c 、b c 、a c d c 、w、app p , at p 、c p1 、c p2 、c p3 、c p4}, the label of the feature data can be defined as c c , the value range is [charging, not charging], where charging can be represented by "1" and not charging can be represented by "0". Further, the above feature data and labels can be abstractly represented as x1, x2, ..., x 12 , where x 12 That is, label data, through feature data, and label data to train the target model.

[0090] When extracting the above-mentioned characteristic data for characterization, this exemplary embodiment can perform data normalization on the continuous data in the above-mentioned characteristic data to ensure data standardization, wherein the normalization method includes but is not limited to Z-score 0 (Z-score) mean normalization, Min-Max (minimum-maximum) linear function normalization, etc. For example, the power information b in the current time slice c Normalization is performed to convert the value range from [0, 100] to [0, 1], etc. In addition, for discrete data, a specific encoding method can be used, such as One-Hot encoding, to convert the label c of the feature data c The value range of is [charging, not charging], and is encoded as [1, 0], etc. Through the above processing method, the extracted feature data and the corresponding label data can be converted into a feature vector or a feature matrix to execute the training process of the target model.

[0091] In an exemplary embodiment, the above step S410 may include:

[0092] The optimal model among multiple charging intention prediction models is taken as the target model.

[0093] In this example, the obtained sample data set can be used to train multiple charging willingness prediction models, such as decision tree models, naive Bayes models, etc., and further evaluate different charging willingness prediction models, select the best model as the target model, and predict charging willingness. Among them, the best model can be a model with higher accuracy or faster calculation speed among multiple models, and the specific best standard can be determined according to actual needs.

[0094] Specifically, after obtaining the sample data set, the data therein can be divided into a training data set and a prediction data set according to a certain ratio. For example, according to the generation order of the data in the data set, the first 80% of the data is added to the training data set in a ratio of 8:2 to train the charging intention prediction model, and the remaining 20% ​​of the data is added to the prediction data set to evaluate the trained charging intention prediction model.

[0095] In this exemplary embodiment, the target model can be determined by calculating the F1 scores (an indicator used in statistics to measure the accuracy of a binary classification model) of different charging willingness prediction models. For example, the charging willingness prediction model can be a random forest model and a naive Bayes model. Using the sample data in the prediction data set, the F1 scores of the random forest model and the naive Bayes model can be calculated respectively. According to the F1 score results, the model with the highest score is determined as the optimal model as the target model. The F1 score can be calculated by the following formula:

[0096]

[0097] Among them, the evaluation indicators involved in precision and recall are shown in Table 2 below:

[0098] Table 2

[0099] Evaluation indicators meaning TP (True Positive) The predicted result is charging, and the actual result is also charging FP (False Positive) The predicted result is charging, but the actual result is not charging FN (false negative) The predicted result is not charged, the actual result is charged TN (True Negative) The predicted result is not charged, and the actual result is also not charged

[0100] The above evaluation indicators are expressed by the number of samples that meet the requirements, and precision represents the accuracy, which can be expressed by the formula Calculated, (TP+FP) includes the number of samples that are charged and not charged, TP is the number of samples that are predicted to be charged and are actually charged, and precision can reflect the accuracy of the model. Recall is the recall rate, which can be calculated by the formula It is calculated as follows: (TP+FN) represents the number of samples that are actually charged, that is, the denominator is the sum of the cases that are actually true, TP is the number of samples that are predicted to be charged and are actually charged, and the recall rate recall is more concerned with whether the user charges, which can reflect the effectiveness of the model.

[0101] In an exemplary embodiment, when the charging willingness prediction model is a random forest, its construction and prediction process may include the following steps:

[0102] Determine a sample data set for model training. The sample data in the sample data set can be the 11-dimensional feature data D = [x1, x2, ..., x 11 ] T , the label data of the feature data y = x 12 , y = [0, 1];

[0103] Select n sample data from N sample data in the sample data set by simulated random resampling, i.e., sampling with replacement, as the training data set of the CART (classification and regression tree) tree, construct the CART tree, and repeat this step to obtain multiple CART trees for generating random forests; wherein the selected sample data may have features of k dimensions, and specifically, one or more features of the dimensions may be selected from the above-mentioned power information, power consumption rate, average initial charge capacity, date information, and application usage, and the value range is [1, 11];

[0104] In this exemplary embodiment, the construction process of each decision tree (i.e., CART tree) can be achieved by the following process:

[0105] 1. Input the training data set D for training CART tree train , the threshold of the Gini coefficient and the threshold of the number of sample data; starting from the root node, using the training data set, recursively establish the CART tree.

[0106] 2. The training data set for the current node is D train , if the number of samples is less than the threshold or there is no feature, the decision subtree is returned and the recursion of the current node stops.

[0107] 3. Calculate the training data set D train If the Gini coefficient is less than the threshold, the decision tree subtree is returned and the recursion of the current node stops.

[0108] This is a two-class classification problem, that is, the current state S of the electronic device is judged as charging or not charging. Assuming that the output probability of charging is p, the probability of not charging can be expressed by 1-p. At this time, the Gini coefficient expression is:

[0109] Gini(p)=2p(1-p)

[0110] 4. For each dimension of features, calculate the feature values ​​of each feature of the current node for the training data set D trainThe Gini coefficient is the probability that a randomly selected sample in the sample set is misclassified. The smaller the Gini coefficient, the smaller the probability that the selected sample in the set is misclassified, that is, the higher the purity of the set.

[0111] In this exemplary embodiment, for the processing of discrete feature data, a method of continuously binary discrete features can be adopted; and for continuous feature data, a method of continuous feature discretization can be adopted. For example, among M sample data, there are m continuous features A. After arranging from small to large, the average of two adjacent samples is taken, and a total of m-1 division points are obtained, among which the i-th division point T i It can be expressed as For these m-1 division points, calculate the Gini coefficient when each division point is used as a binary classification point, and select the point with the smallest Gini coefficient as the binary discrete classification point of the continuous feature data. For example, the point with the smallest Gini coefficient is a t , then it is less than a t The value of is category 1, which is greater than a t The value of is category 2; for the training data set D train , if according to a certain value a of feature A, the training data set D train Divided into two parts, D1 and D2, then under the condition of feature A, D train The Gini coefficient expression can be expressed by the following formula:

[0112]

[0113] 5. The calculated feature values ​​of each feature are used for the training data set D train Among the Gini coefficients, select the feature with the smallest Gini coefficient, such as feature A and the corresponding eigenvalue a. Based on this optimal feature and optimal eigenvalue, divide the data set into two parts, D1 and D2, and establish the left and right nodes of the current node. The training data set D train D1, the data set of the right node D train is D2.

[0114] 6. Recursively call steps 1 to 4 above for the left and right child nodes to generate a decision tree, where the optimal features and optimal feature values ​​saved in each decision tree are obtained through training.

[0115] When making predictions for the generated decision tree, if a piece of data d in the test set falls into a leaf node, and there are multiple training samples in this node, the category prediction for the current data d is the category with the highest probability in this leaf node. Figure 6The diagram shows the decision-making process of a CART tree when k=3. When data falls on the leaf node 610, its path can be determined by judging whether its power information is less than or equal to 80 grids of power. When the power information is greater than 80 grids of power, it is predicted that it will not be charged. When the power information is less than or equal to 80 grids of power, it falls to the leaf node 620 for judgment. When the distance between the current time slice and the last charging time is less than 5 time slices, it is predicted that it will not be charged. When the distance between the current time slice and the last charging time is greater than or equal to 5 time slices, it falls to the leaf node 630 for judgment. When the distance between the power in the current time slice and the average starting charging power is greater than 30 grids of power, it is predicted that it will be charged. When the distance between the power in the current time slice and the average starting charging power is less than 30 grids of power, it is predicted that it will not be charged, etc.

[0116] Furthermore, a random forest model can be generated based on the obtained multiple CART trees.

[0117] Finally, when applied, each CART tree can get a corresponding prediction result. The voting results of the decision tree constructed based on different features in the random forest model can determine the final prediction result of whether to charge or not.

[0118] In an exemplary embodiment, the charging willingness prediction model may also be a Naive Bayes model.

[0119] The Naive Bayes model is a classification algorithm based on the Bayesian theorem and assumes that the feature conditions are independent of each other, and that the continuous data follows a Gaussian distribution, and uses Laplace to smooth the data. First, through a given training data set, with independence between features as the premise assumption, learn the joint probability distribution from input to output, and then based on the learned model, input X to find the output result Y that maximizes the posterior probability.

[0120] The distribution of the charging state in this exemplary embodiment belongs to the prior probability, P(Y) may include the probability distribution of charging and uncharging, and the prior probability may be expressed as:

[0121] P prior =P(Y)

[0122] The posterior probability is calculated based on each feature and is expressed as:

[0123] P po2t =P(Y|X)

[0124] Naive Bayes is based on the independence of each feature. Given a category y, according to the prior probability P prior and the posterior probability P post , we can get:

[0125]

[0126] Furthermore, the posterior probability can be calculated as:

[0127]

[0128] Where d represents the training data set D train The size of c i It represents the category of the label data, and its value range is [0, 1], which means no charging or charging respectively. Since the size of P(X) is fixed, when comparing the posterior probability, only the numerator of the above formula needs to be compared.

[0129] Therefore, for the current classification problem, we can get a sample data belonging to category y i The naive Bayes calculation formula of , whose label data category value range is [0, 1], is expressed as:

[0130]

[0131] Based on the above process, the training of the Naive Bayes model can be completed.

[0132] In this exemplary embodiment, after the training of the random forest model and the naive Bayes model is completed using the training data set, the prediction data set can be used to calculate the F1 scores of the random forest model and the naive Bayes model respectively, and the model with a higher F1 score is used as the target model to predict the charging intention. This exemplary embodiment trains multiple models and evaluates and determines the target model, which can determine a charging prediction method that is more suitable for the current user and improve the accuracy of the charging prediction.

[0133] Figure 7 A flow chart of another charging control method in this exemplary embodiment is shown, which may specifically include the following steps:

[0134] Step S710, obtaining usage information of the electronic device as a sample data set;

[0135] The usage information of the electronic device may include power information, application information, power on / off, screen on / off and other related data of the electronic device; the sample data set may be divided into a training data set and a prediction data set according to a ratio of 8:2;

[0136] Step S720, determining whether the data volume of the sample data set reaches a preset data volume, and whether the coverage time of the sample data set reaches a preset duration;

[0137] If the data volume of the sample data set does not reach the preset data volume, and the coverage time of the sample data set reaches the preset duration, the process ends;

[0138] If the amount of data in the sample data set reaches the preset amount of data, and the coverage time of the sample data set reaches the preset duration, execute

[0139] Step S730, extracting feature data from the sample data set;

[0140] Step S740, training a random forest model and a naive Bayes model based on the sample data set respectively;

[0141] Step S750, determining whether the electronic device meets the charging prediction trigger condition;

[0142] For example, determining whether the electronic device has entered a negative one screen state, and the current power level is lower than the historical average charge level, and is not currently being charged;

[0143] If the electronic device does not meet the charging prediction triggering conditions, no charging intention prediction is performed;

[0144] If the electronic device meets the charging prediction trigger conditions, it executes

[0145] Step S760, obtaining current status information of the electronic device;

[0146] Step S770, determining a target model for predicting charging intention from the random forest model and the naive Bayes model;

[0147] For example, the F1 scores of the random forest model and the naive Bayes model can be calculated using the prediction data set, and the model with the higher F1 score can be used as the target model;

[0148] Step S780: Process the current state information of the electronic device using the target model to obtain a prediction result.

[0149] Among them, the above-mentioned step S760 and step S770 can be executed simultaneously or at different times. When they are not executed at different times, their order is not specifically limited. In addition, the selection of the target model in step S770 can be executed before step S750, that is, the target model can be determined after the model training is completed, or it can be executed after step S750, that is, when the electronic device enters the charging prediction state, the target model for charging prediction is determined, etc. This disclosure does not make specific limitations on this.

[0150] The exemplary embodiment of the present disclosure also provides a charging control device. Figure 8 As shown, the charging control device 800 may include: a charging willingness prediction module 810, which is used to predict the charging willingness based on the current status information of the electronic device in response to the electronic device satisfying the charging prediction trigger condition to obtain a prediction result; and a control information determination module 820, which is used to determine the charging control information according to the prediction result.

[0151] In an exemplary embodiment, the charging willingness prediction module includes: a target model acquisition unit, used to acquire a target model for charging willingness prediction; an information processing unit, used to process current state information of the electronic device using the target model to obtain a prediction result.

[0152] In an exemplary embodiment, the charging control device also includes: a usage information collection module for collecting usage information of the electronic device as a sample data set; and a target model training module for training a target model using the sample data set in response to the sample data set satisfying a training trigger condition.

[0153] In an exemplary embodiment, the usage information collection module includes: a first collection unit, which is used to collect status information of the electronic device in each time slice as training data in a sample data set, and collect charging information of the electronic device in each time slice as label data in the sample data set; the status information includes at least one of the following: power information in the current time slice; the distance between the power in the current time slice and the average charging amount; the distance between the current time slice and the last charging time; the number of applications used in the previous time slice; the application usage time in the previous time slice; the power consumption rate in the previous time slice.

[0154] In an exemplary embodiment, the usage information collection module also includes: a second collection unit, used to add time slice information to the training data; the time slice information includes at least one of the following: the length of the time slice; the ordinal number of the time slice; the date information to which the time slice belongs.

[0155] In an exemplary embodiment, the target model training module includes: a training condition triggering unit, the training condition triggering unit includes at least one of the following situations: the data volume of the sample data set reaches a preset data volume; the coverage time of the sample data set reaches a preset duration.

[0156] In an exemplary embodiment, the charging willingness prediction module includes: a prediction condition triggering unit, which is used when the electronic device enters a preset interface and the current power of the electronic device is lower than the average starting charging power.

[0157] The specific details of each part of the above device have been described in detail in the implementation method part, so they will not be repeated here.

[0158] The exemplary embodiments of the present disclosure further provide a computer-readable storage medium, which can be implemented in the form of a program product, including program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification, for example, to execute Figure 2 , Figure 3 , Figure 4 , Figure 5 or Figure 7 The program product may be in the form of a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0159] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory, a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0160] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0162] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0163] The exemplary embodiment of the present disclosure also provides an electronic device. Generally, the electronic device may include a processor and a memory, the memory is used to store executable instructions of the processor, and the processor is configured to execute the above charging control method by executing the executable instructions.

[0164] Below Fig. 9 The mobile terminal 900 in FIG. 1 is taken as an example to exemplify the structure of the electronic device. It should be understood by those skilled in the art that, in addition to the components specifically used for mobile purposes, Fig. 9 The construction in can also be applied to fixed type equipment.

[0165] like Fig. 9 As shown, the mobile terminal 900 may specifically include: a processor 901, a memory 902, a bus 903, a mobile communication module 904, an antenna 1, a wireless communication module 905, an antenna 2, a display screen 906, a camera module 907, an audio module 908, a power module 909 and a sensor module 910.

[0166] The processor 901 may include one or more processing units, for example, the processor 901 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc. The charging control method in this exemplary embodiment may be performed by an AP, a GPU, or a DSP.

[0167] The encoder can encode (i.e. compress) an image or video to reduce the data size for storage or transmission. The decoder can decode (i.e. decompress) the encoded data of an image or video to restore the image or video data.

[0168] The processor 901 may be connected to the memory 902 or other components via a bus 903 .

[0169] The memory 902 may be used to store computer executable program codes, which may include instructions. The processor 901 executes various functional applications and data processing of the mobile terminal 900 by running the instructions stored in the memory 902. The memory 902 may also store application data, such as images, videos, and other files.

[0170] The communication function of the mobile terminal 900 can be implemented by the mobile communication module 904, antenna 1, wireless communication module 905, antenna 2, modulation and demodulation processor and baseband processor. Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 904 can provide 3G, 4G, 5G and other mobile communication solutions applied to the mobile terminal 900. The wireless communication module 905 can provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. applied to the mobile terminal 900.

[0171] The display screen 906 is used to implement display functions, such as displaying user interfaces, images, videos, etc. The camera module 907 is used to implement shooting functions, such as shooting images, videos, etc. The audio module 908 is used to implement audio functions, such as playing audio, collecting voice, etc. The power module 909 is used to implement power management functions, such as charging the battery, powering the device, monitoring the battery status, etc. The sensor module 910 may include one or more sensors to implement corresponding sensing detection functions.

[0172] It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or implementations combining hardware and software aspects, which may be collectively referred to herein as "circuit", "module" or "system". Those skilled in the art will readily think of other implementations of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and implementation are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0173] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A charging control method, characterized in that: include: In response to the electronic device satisfying a charging prediction trigger condition, a charging intention prediction is performed based on the current state information of the electronic device to obtain a prediction result; the charging prediction trigger condition refers to a trigger condition for determining whether the current electronic device needs to perform charging prediction control; the charging prediction trigger condition is set according to a combination of one or more of the state of the electronic device, the user's operation, whether a trigger application is used or opened, and whether a specific interactive operation is performed; Determining charging control information according to the prediction result; The electronic device meets the charging prediction trigger condition, further comprising: The electronic device enters a preset interface, and the current power of the electronic device is lower than the average starting charge; The preset interface includes a multi-function interface.

2. The method according to claim 1, characterized in that The predicting of charging willingness based on the current state information of the electronic device to obtain a prediction result includes: Obtaining a target model for predicting charging intention; The target model is used to process the current state information of the electronic device to obtain the prediction result.

3. The method according to claim 2, characterized in that The method further comprises: Collecting usage information of the electronic device as a sample data set; In response to the sample data set satisfying a training trigger condition, the target model is trained using the sample data set.

4. The method according to claim 3, characterized in that The collecting of the usage information of the electronic device as a sample data set includes: In units of time slices, state information of the electronic device in each time slice is collected as training data in the sample data set, and charging information of the electronic device in each time slice is collected as label data in the sample data set; The status information includes at least one of the following: power information in the current time slice; the distance between the power in the current time slice and the average starting charge; the distance between the current time slice and the last charging time; the number of applications used in the previous time slice; the application usage time in the previous time slice; the power consumption rate in the previous time slice.

5. The method according to claim 4, characterized in that The collecting the usage information of the electronic device as a sample data set further includes: Adding the time slice information to the training data; The information of the time slice includes at least one of the following: the length of the time slice; the ordinal number of the time slice; and the date information to which the time slice belongs.

6. The method according to claim 3, characterized in that The sample data set meets the training trigger condition, including at least one of the following situations: The data volume of the sample data set reaches a preset data volume; The coverage time of the sample data set reaches a preset time length.

7. A charging control device, characterized in that: include: A charging willingness prediction module, for predicting the charging willingness of the electronic device based on the current state information of the electronic device in response to the electronic device satisfying the charging prediction trigger condition, and obtaining a prediction result; the charging prediction trigger condition refers to a trigger condition for determining whether the current electronic device needs to perform charging prediction control; the charging prediction trigger condition is set according to a combination of one or more of the state of the electronic device, the user's operation, whether a trigger application is used or opened, and whether a specific interactive operation is performed; A control information determination module, used to determine charging control information according to the prediction result; The electronic device meets the charging prediction trigger condition and is further configured to: The electronic device enters a preset interface, and the current power of the electronic device is lower than the average starting charge; the preset interface includes a multi-function interface.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 6 by executing the executable instructions.

Images