CN116795628B

CN116795628B - Power consumption processing method of terminal equipment, terminal equipment and readable storage medium

Info

Publication number: CN116795628B
Application number: CN202310598030.6A
Authority: CN
Inventors: 林俊宏; 黄桂武; 谢泽雄; 温兆恒
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-05-24
Filing date: 2023-05-24
Publication date: 2024-05-14
Anticipated expiration: 2043-05-24
Also published as: CN116795628A

Abstract

The embodiment of the application provides a power consumption processing method of terminal equipment, the terminal equipment and a readable storage medium. The method comprises the following steps: the terminal equipment acquires power consumption data of the terminal equipment, wherein the power consumption data comprises power consumption data of a first application; determining a user group to which a user corresponding to the terminal equipment belongs and a threshold value of a main feature corresponding to the user group according to the power consumption model of the first application; detecting whether the power consumption of the first application is abnormal or not according to the threshold value of the main characteristic and the numerical value of the main characteristic in the power consumption data of the first application, and obtaining a power consumption detection result of the first application; and executing corresponding operation according to the power consumption detection result of the first application. Therefore, the terminal equipment can determine the group to which the user belongs according to the habit of using the terminal equipment by the user, and further adopts the threshold value of the corresponding main characteristic to detect the power consumption, so that the flexibility is high.

Description

Power consumption processing method of terminal equipment, terminal equipment and readable storage medium

Technical Field

The present application relates to the field of terminal technologies, and in particular, to a power consumption processing method of a terminal device, and a readable storage medium.

Background

With the rapid development of terminal devices, applications installed on the terminal devices are increasing. The user can open a plurality of applications at the same time, and the running of the applications increases the power consumption of the terminal device, so that it is necessary to detect and manage the power consumption of the applications to extend the endurance of the terminal device.

Currently, a power consumption threshold may be set, and the terminal device may detect the power consumption of an application running in the background. When the power consumption of the application running in the background is greater than the power consumption threshold, the terminal device may kill the application to reduce the power consumption of the terminal device.

The current processing method of the power consumption of the terminal equipment can reduce the power consumption of the terminal equipment, but the using habits of different user groups on the terminal equipment are different, and the power consumption of the terminal equipment is processed by adopting the same method aiming at all the user groups, so that the flexibility is poor.

Disclosure of Invention

The embodiment of the application provides a power consumption processing method of terminal equipment, the terminal equipment and a readable storage medium, which are applied to the technical field of terminals, can adaptively process the power consumption of the terminal equipment according to the use habit of a user on the terminal equipment, and have high flexibility.

In a first aspect, an embodiment of the present application provides a method for processing power consumption of a terminal device, where an execution body for executing the method may be the terminal device or a chip in the terminal device, and the following description will take the terminal device as an example. The method comprises the following steps: the terminal device may collect power consumption data of the terminal device, where the power consumption data includes power consumption data of the first application. And when the power consumption data of the first application is the running of the first application, using the power consumption of each device in the terminal equipment.

The terminal equipment can store a power consumption model of a first application, and can determine a user group to which a user corresponding to the terminal equipment belongs and a threshold value of a main feature corresponding to the user group according to the power consumption model of the first application. The terminal equipment can detect whether the power consumption of the first application is abnormal according to the threshold value of the main characteristic and the numerical value of the main characteristic in the power consumption data of the first application, and a power consumption detection result of the first application is obtained. The terminal device may perform a corresponding operation, such as reducing power consumption of the first application, according to the power consumption detection result of the first application.

In the embodiment of the application, different applications can correspond to different power consumption models, and the accuracy of the power consumption models is high. In addition, in the embodiment of the application, the user group to which the user belongs can be determined according to the power consumption data, namely, whether the power consumption of the first application is abnormal or not can be detected according to the habit or the characteristic of the user using the terminal equipment and the threshold value of the main characteristic corresponding to the user. In the embodiment of the application, aiming at different user groups, different thresholds of main features can be used to detect whether the power consumption of the first application is abnormal or not, the flexibility is high, the habit or the feature of the user is matched more, and the user experience can be improved.

In one possible implementation, the power consumption model of the first application includes: the system comprises an auxiliary feature condition and a threshold value of a main feature corresponding to at least one user group, wherein the auxiliary feature condition is used for determining the user group to which a user belongs, and the at least one user group is determined based on the auxiliary feature condition.

The terminal equipment can determine the user group to which the user corresponding to the terminal equipment belongs according to the auxiliary characteristic condition and the numerical value of the auxiliary characteristic in the power consumption data of the first application. The terminal equipment can determine the threshold value of the main characteristic corresponding to the user group corresponding to the terminal equipment according to the threshold value of the main characteristic corresponding to the at least one user group and the user group corresponding to the user corresponding to the terminal equipment.

In this implementation manner, the terminal device may determine, according to the power consumption model of the first application, a user group to which the user belongs and a threshold value of a main feature corresponding to the user group, so that the threshold value of the main feature adapted to the user group may be adopted to detect whether the power consumption of the first application is abnormal.

In a possible implementation manner, the power consumption model of the first application is specifically a power consumption model of a first application of a first product family, and the terminal device belongs to the first product family.

In this implementation manner, the terminal device may determine, according to a power consumption model of the first application of the first product series, a user group to which a user corresponding to the terminal device belongs and a threshold value of a main feature corresponding to the user group, and further detect whether power consumption of the first application is abnormal based on the threshold value of the main feature corresponding to the user group.

In the implementation manner, because the used devices are different in the terminal equipment of different product series, when the first application runs in the same time, the power consumption of the devices is different.

In one possible implementation manner, when the value of the main feature is greater than or equal to the threshold value of the main feature, the terminal device determines that the power consumption of the first application is abnormal, and the power consumption detection result of the first application is used for indicating that the power consumption of the first application is abnormal. When the value of the main feature is smaller than the threshold value of the main feature, the terminal equipment determines that the power consumption of the first application is normal, and the power consumption detection result of the first application is used for indicating that the power consumption of the first application is normal.

In one possible implementation manner, the terminal device may determine not only whether the power consumption of the first application is abnormal, but also an abnormality level when the power consumption of the first application is abnormal. Illustratively, the threshold value of the primary feature includes: a first threshold, a second threshold, and a third threshold, the first threshold being less than the second threshold and the second threshold being less than the third threshold.

And when the value of the main feature is larger than or equal to the first threshold value and smaller than the second threshold value, determining that the power consumption abnormality of the first application is a first abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the first abnormality level. And when the value of the main characteristic is larger than or equal to the second threshold value and smaller than the third threshold value, determining that the power consumption abnormality of the first application is a second abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the second abnormality level. And when the value of the main characteristic is larger than or equal to the third threshold value, determining that the power consumption abnormality of the first application is a third abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the third abnormality level. And when the value of the main characteristic is smaller than the first threshold value, determining that the power consumption of the first application is normal, wherein the power consumption detection result of the first application is used for indicating that the power consumption of the first application is normal.

In one possible implementation manner, the power consumption abnormality levels of the first applications are different, and the corresponding operations performed by the terminal devices are different.

In the implementation manner, the terminal equipment can adopt the operation corresponding to the abnormal level to process based on the abnormal level of the power consumption of the first application, so that the flexibility is high.

In one possible implementation manner, a terminal device may send a power consumption model acquisition request to a cloud end to receive a power consumption model of the first application from the cloud end.

In some embodiments, the terminal device may receive a power consumption model of at least one application from the cloud, the at least one application may include a first application. Or the terminal device may receive a power consumption model of at least one application from at least one series of cloud, the at least one application may include a first application.

In a possible implementation manner, the terminal device may further send the power consumption data of the terminal device to the data platform, so that the cloud end may train to obtain the power consumption model based on the power consumption data of the terminal device, which may be described with reference to the second aspect.

In a second aspect, an embodiment of the present application provides a power consumption processing method of a terminal device, where an execution body for executing the method may be a cloud or a chip in the cloud, and the cloud is taken as an example for illustration. The method comprises the following steps: the cloud end can acquire the power consumption data of at least one terminal device from the data platform, and trains to obtain a power consumption model according to the power consumption data of the at least one terminal device. When the cloud receives a power consumption model acquisition request from the terminal equipment, the power consumption model can be sent to the terminal equipment.

The power consumption model may include a power consumption model of at least one application, the first application being included in the at least one application. Accordingly, the power consumption data of each terminal device may include power consumption data of the at least one application. In the embodiment of the application, the cloud training of the power consumption model may include cloud training to obtain the power consumption model of the first application. Taking a power consumption model of the first application trained by the cloud as an example, the process of training the power consumption model by the cloud is described below. The cloud end can train to obtain the power consumption data of the first application according to the power consumption data of the first application in a preset time period.

In one possible implementation manner, the power consumption model of the first application is specifically a power consumption model of a first application of a first product family, where the power consumption model of the first application of the first product family is obtained by training based on power consumption data of the first application of a terminal device of the first product family in the preset time period.

The following specifically describes a training process of training a power consumption model of a first application of a first product series according to power consumption data of the first application of the terminal device of the first product series in a preset time period by using a cloud as an example:

The cloud may obtain a correlation coefficient between the main feature and each other feature according to the power consumption data of the first application of the terminal device of the first product series in the preset time period, and determine an auxiliary feature according to the correlation coefficient between the main feature and each other feature. After the cloud determines the auxiliary characteristic, the cloud may acquire an auxiliary characteristic condition according to the power consumption data of the first application of the terminal device of the first product series in the preset period and the auxiliary characteristic, where the auxiliary characteristic condition is used for determining a user group to which the user belongs. The cloud may divide the users corresponding to the at least one terminal device into at least two user groups according to the auxiliary feature condition and the power consumption data of the first application of the terminal device of the first product series in the preset time period.

The cloud end can determine a threshold value of a main characteristic corresponding to each user group according to power consumption data of a first application of terminal equipment of a first product series in preset time of each user group, wherein the threshold value of the main characteristic is used for detecting whether power consumption of the first application is abnormal or not. And the cloud terminal generates a power consumption model of the first application of the first product series according to the auxiliary characteristic conditions and the threshold value of the main characteristic corresponding to each user group. Wherein the power consumption model of the first application of the first product family may comprise: the auxiliary feature condition and a threshold value of a main feature corresponding to at least one user group.

In one possible implementation, the correlation coefficient of the main feature with each of the other features includes Pearson correlation coefficient and Spearman correlation coefficient. And determining auxiliary features according to the correlation coefficient of the main feature and each other feature, wherein the method comprises the following steps: taking the features which are larger than or equal to the Pearson correlation coefficient threshold and larger than or equal to the Spearman correlation coefficient threshold as first candidate auxiliary features; and determining the auxiliary feature according to the first candidate auxiliary feature.

In one possible implementation, the first candidate auxiliary feature may be used as the auxiliary feature.

In a possible implementation manner, the determining the auxiliary feature according to the first candidate auxiliary feature includes:

Step A, obtaining a variance expansion coefficient VIF of each first candidate auxiliary feature and other first candidate auxiliary features;

Step B, aiming at a first candidate auxiliary feature corresponding to the maximum VIF, if the maximum VIF is larger than a VIF threshold value and the number of the first candidate auxiliary features is larger than a number threshold value, executing the step C; if the maximum VIF is greater than a VIF threshold and the number of first candidate auxiliary features is less than or equal to the number threshold, or if the maximum VIF is less than or equal to the VIF threshold, taking all the first candidate auxiliary features as second candidate auxiliary features, and determining the auxiliary features according to the second candidate auxiliary features;

And C, deleting the first candidate auxiliary feature corresponding to the maximum VIF, and returning to the step A-step B until the maximum VIF is smaller than or equal to the VIF threshold, or the number of the remaining first candidate auxiliary features is smaller than or equal to the number threshold, taking the remaining first candidate auxiliary features as second candidate auxiliary features, and determining the auxiliary features according to the second candidate auxiliary features.

In one possible implementation, the second candidate auxiliary feature may be used as the auxiliary feature.

In a possible implementation manner, the determining the auxiliary feature according to the second candidate auxiliary feature includes: obtaining an importance value of each second candidate auxiliary feature according to the minimum absolute shrinkage and the selection model; and taking the second candidate auxiliary feature ranked in the top N as the auxiliary feature, wherein the N is equal to the quantity threshold value.

In a possible implementation manner, the obtaining the auxiliary feature condition according to the power consumption data of the first application of the terminal device of the first product family in the preset time period and the auxiliary feature includes: training a classification and regression tree CART according to the auxiliary characteristics and the power consumption data of the first application of the terminal equipment of the first product series in the preset time period; and taking the leaf nodes in the CART as the auxiliary characteristic conditions.

In one possible implementation manner, the determining the threshold value of the main feature corresponding to each user group according to the power consumption data of the first application of the terminal device of the first product family within the preset time of each user group includes: and determining the threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and the first preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group.

In one possible implementation manner, the threshold value of the main feature corresponding to each user group determined based on the first preset proportion is a first threshold value. The method further comprises the steps of: determining a second threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and a second preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group; and determining a third threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and a third preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group, wherein the first preset proportion is smaller than the second preset proportion, the second preset proportion is smaller than the third preset proportion, and the first threshold value, the second threshold value and the third threshold value are used for determining the level of power consumption abnormality of the first application.

In a third aspect, an embodiment of the present application provides a terminal device, which may also be referred to as a terminal (terminal), a User Equipment (UE), a Mobile Station (MS), a Mobile Terminal (MT), or the like. The terminal device may be a mobile phone, a smart television, a wearable device, a tablet (Pad), a computer with wireless transceiving function, a Virtual Reality (VR) terminal device, an augmented reality (augmented reality, AR) terminal device, a wireless terminal in industrial control (industrial control), a wireless terminal in unmanned driving (self-driving), a wireless terminal in teleoperation (remote medical surgery), a wireless terminal in smart grid (SMART GRID), a wireless terminal in transportation security (transportation safety), a wireless terminal in smart city (SMART CITY), a wireless terminal in smart home (smart home), or the like.

The terminal device includes: a processor and a memory; the memory stores computer-executable instructions; the processor executes computer-executable instructions stored in the memory to cause the terminal device to perform a method as in the first aspect.

In a fourth aspect, an embodiment of the present application provides an electronic device, where the electronic device may be the cloud end of the second aspect. The electronic device includes: a processor and a memory; the memory stores computer-executable instructions; the processor executes computer-executable instructions stored in the memory to cause the electronic device to perform a method as in the second aspect.

In a fifth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program. The computer program, when executed by a processor, implements the method as in the first and second aspects.

In a sixth aspect, embodiments of the present application provide a computer program product comprising a computer program which, when run, causes a computer to perform the methods as in the first and second aspects.

In a seventh aspect, an embodiment of the present application provides a chip, the chip including a processor for invoking a computer program in a memory to perform the method according to the first and second aspects.

It should be understood that, the third aspect to the seventh aspect of the present application correspond to the technical solutions of the first aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding possible embodiments are similar, and are not repeated.

Drawings

Fig. 1 is a schematic diagram of a system architecture to which a power consumption processing method of a terminal device according to an embodiment of the present application is applicable;

Fig. 2A is another schematic diagram of a system architecture to which the power consumption processing method of a terminal device according to the embodiment of the present application is applicable;

Fig. 2B is a schematic flow chart of a power consumption processing method of a terminal device according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an acquisition flow of a power consumption model according to an embodiment of the present application;

Fig. 4 is a schematic diagram of CART according to an embodiment of the present application;

FIG. 5A is a schematic diagram of screening auxiliary features according to an embodiment of the present application;

FIG. 5B is a schematic diagram of determining a threshold value of a main feature according to an embodiment of the present application;

Fig. 6 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application;

fig. 7 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application;

Fig. 8 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "exemplary" or "such as" are used to denote examples, illustrations or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural. In addition, it should be understood that in the description of the present application, the words "first," "second," and the like are used merely for distinguishing between the descriptions and not for indicating or implying any relative importance or order.

It should be noted that "at … …" or "at … …" in the embodiments of the present application may be an instant when a certain situation occurs, or may be a period of time after a certain situation occurs, which is not particularly limited in the embodiments of the present application. In addition, the display interface provided by the embodiment of the application is only used as an example, and the display interface can also comprise more or less contents.

In some embodiments, the user's attention to the background running application is low compared to the foreground running application in the terminal device. Thus, a power consumption threshold may be currently set, for example, the power consumption threshold may be a threshold of background power consumption of a central processing unit (central processing unit, CPU) of the application, and the threshold of background power consumption of the CPU may be understood as power consumption generated by the application using the CPU in background running. The terminal device may detect the CPU power consumption of the application running in the background, and when the CPU power consumption of the application running in the background is greater than the power consumption threshold, the terminal device may kill (kill) the application to reduce the power consumption of the terminal device. Or the terminal device outputs prompt information to prompt the user that the power consumption of the background application is high. When the CPU power consumption of the application running in the background is less than or equal to the power consumption threshold, the application may continue to run in the background, e.g., the terminal device may not perform processing.

The current processing method of the power consumption of the terminal equipment can reduce the power consumption of the terminal equipment, but the using habits of different user groups on the terminal equipment are different, and the power consumption of the terminal equipment is processed by adopting the same method (such as adopting the same power consumption threshold) aiming at all the user groups, so that the flexibility is poor.

For example, user a likes to listen to music for a longer period of time each day, user B dislikes to listen to music, and hardly listens to music each day, but when both user a and user B open the audio playback class application and return the audio playback class application to background operation, the audio playback class application may play music. For the user A and the user B, if the terminal equipment is according to the same processing logic, when the CPU background power consumption of the audio playing application is larger than the power consumption threshold, the terminal equipment outputs prompt information to prompt the user that the power consumption of the application is large, and the user A who likes music can receive the prompt information as soon as the audio playing application is returned to the background, even the prompt information is continuously received, the user is disturbed too much, and the user experience is poor.

Based on the current problems, the embodiment of the application provides a power consumption processing method of terminal equipment, which can determine the user group to which a user belongs according to the habit or the characteristic of using an application by the user, and different user groups can correspond to different power consumption processing logics so as to adaptively adjust the power consumption processing method of the terminal equipment according to different users.

By way of example, taking an audio playing application as an example and taking the power consumption of the background of the CPU as a detection condition, for example, user a likes to listen to music, and the duration of listening to music per day is long, user B dislikes to listen to music, and hardly listens to music per day. The power consumption threshold corresponding to the user a may be a first power consumption threshold, and the power consumption threshold corresponding to the user B may be a second power consumption threshold, where the first power consumption threshold is greater than the second power consumption threshold. If both the user a and the user B open the audio playing application and return the audio playing application to the background running, the terminal device of the user a may compare the CPU background power consumption of the audio playing application with the first power consumption threshold, and if the CPU background power consumption of the audio playing application is greater than the first power consumption threshold, the terminal device of the user a may output the prompt message. The terminal device of the user B may compare the CPU background power consumption of the audio playback class application with a second power consumption threshold, e.g., when the CPU background power consumption of the audio playback class application is greater than the second power consumption threshold, the terminal device of the user B may output the prompt message.

Thus, for the user a who likes music, after the audio playing application falls back to the background, the user a will not receive the prompt information frequently because the first power consumption threshold is larger. For the user B dislike music, after the audio playing application is returned to the background, the terminal equipment of the user B can prompt the user B that the audio playing application is larger in time because the second power consumption threshold is smaller, so that the user B can know the power consumption of the application in the terminal equipment in time.

Before introducing the power consumption processing method of the terminal device provided by the embodiment of the present application, a system architecture applicable to the power consumption processing method of the terminal device provided by the embodiment of the present application is first described. Fig. 1 is a schematic diagram of a system architecture to which a power consumption processing method of a terminal device according to an embodiment of the present application is applicable. Referring to fig. 1, the system architecture may include: the system comprises at least one terminal device, a cloud end and a data platform. In fig. 1, a cloud end and a data platform are represented by servers, and the embodiments of the present application do not limit the forms of the cloud end and the data platform. It should be understood that 1 terminal device is taken as an example in fig. 1.

And the terminal equipment can report the power consumption data of the terminal equipment to the data platform. In some embodiments, the terminal device may periodically report the power consumption data of the terminal device to the data platform, e.g., the terminal device may report the power consumption data of the terminal device to the data platform once every three days. In some embodiments, the terminal device may report the power consumption data of the terminal device to the data platform at regular time, e.g. the terminal device may report the power consumption data of the terminal device to the data platform at 6 points per day.

The power consumption data of the terminal device may include: power consumption data of each application of the terminal device. Each application running uses a different device in the terminal equipment, and the device used in the application running can be called as the device corresponding to the application. The power consumption data of each application may include: and power consumption data of the corresponding device of each application.

Devices may include, but are not limited to: a CPU, a graphics processor (graphics processing unit, GPU), a Global navigation satellite System (global navigation SATELLITE SYSTEM GNSS), a screen, sensors, cameras, flash, an audio module, a Bluetooth module, a modem, a Wi-Fi module. The Bluetooth module may be, for example, a Bluetooth chip, and the Wi-Fi module may be, for example, a Wi-Fi chip, which is not shown in the embodiment of the present application. The terminal equipment can realize Bluetooth communication through the Bluetooth module, and the terminal equipment can realize Wi-Fi communication through the Wi-Fi module.

The sensors in the terminal device may include, but are not limited to: pressure sensor, gyroscope sensor, barometric sensor, magnetic sensor, acceleration sensor, distance sensor, proximity sensor, fingerprint sensor, temperature sensor, touch sensor, ambient light sensor, bone conduction sensor.

The audio modules in the terminal device may include, but are not limited to: speakers, receivers, microphones, etc. By way of example, the terminal device may play music, collect sound, etc. through the audio module.

In the embodiment of the application, the devices included in the terminal equipment are not limited, and the division mode of the devices in the terminal equipment is not limited. For example, in some embodiments, the Bluetooth module, modem, and Wi-Fi module may be divided into one module, which may be referred to as a communication module. In some embodiments, the devices may be further divided into finer or coarser granularity devices, as the embodiments of the application are not limited in this respect.

The terminal device may periodically count power consumption data of each application of the terminal device, and periodically report the power consumption data of the terminal device to the data platform.

By way of example, taking the power consumption data of "one-time-of-day" statistics, the power consumption data of each application in a day may include at least one of the following: the foreground use duration, the foreground power consumption, the background use duration, the background power consumption, the foreground total flow and the background total flow of the corresponding devices are applied.

It should be appreciated that the power consumption data corresponding to different devices may be different. For example, if the communication module, such as the terminal device, implements communication through the modem and the Wi-Fi module, traffic of the terminal device may be used, so the power consumption data of the modem and the Wi-Fi module may include: foreground total flow, and background total flow. For example, if the status of the screen includes bright screen and off screen, the screen will not run in the background, so the power consumption data of the screen may include: screen lighting power consumption, screen lighting use duration, screen foreground power consumption and screen foreground use duration. For example, an application, whether running in the foreground or in the background, may use the resources of the CPU, and thus the power consumption data of the CPU may include: CPU foreground power consumption, CPU foreground use duration, CPU background power consumption and CPU background use duration.

The power consumption data of the terminal device is reported to the data platform once a week by the terminal device. The terminal device may report the power consumption data of the terminal device to the data platform once every one week, where the power consumption data may include 7 days of power consumption data of the terminal device.

Table one is an example diagram of contents included in power consumption data of a terminal device, and meanings of the contents. It should be understood that the data power consumption of the terminal device may be reported to the data platform in a text form, a table form, or the like, and the embodiment of the present application does not limit the data form of the power consumption data.

List one

In Table one, FG characterizes the foreground (foreground), BG characterizes the background (background), trfc characterizes the flow (traffic).

In some embodiments, because the power consumption data of the terminal device may include power consumption data of each application of the terminal device, the power consumption data of the terminal device may further include application information in order to facilitate the power consumption data of different applications of the regional terminal device. For example, the application information may include an application name and an application version. In some embodiments, the application name may also be replaced with application number, application icon, etc. that can distinguish between different applications.

In some embodiments, the power consumption data of the terminal device may further include: device information. For example, the device information may include a name (product name) of the terminal device, a model number (product version) of the terminal device, and a Serial Number (SN), for example. In some embodiments, the product name may also be replaced with information such as a product number that can distinguish between different products.

In some embodiments, the power consumption data of the terminal device may further include: a time stamp. The time stamp represents the time when the terminal device reported the power consumption data of the terminal device to the data platform.

It should be noted that, in table one, the power consumption data of the terminal device is also classified, and features corresponding to the power consumption data are shown. For example, the device information may characterize product-related features, the application information may characterize application features, and the screen-on power consumption, the screen-on use duration, the screen-off power consumption, and the screen-off use duration may characterize screen-related features. Other relevant features of the terminal device may be as shown in table one.

It should be appreciated that because the at least one terminal device may report the power consumption data of the terminal device to the data platform, the data platform may store the power consumption data of the at least one terminal device.

For example, table two shows the power consumption data of application 1 of a plurality of terminal devices received by the data platform in one day. It should be understood that the power consumption data of the application 1 is taken as an example in the table two, and the foreground power consumption of the device corresponding to the application 1 is included.

Watch II

By way of example, embodiments of the present application relate to power consumption in milliamp-hours (mAh).

It will be appreciated that in table 1, terminal devices of different serial numbers of product 1 are shown, and that the foreground power consumption of the device corresponding to application 1 of the terminal device on the same day (2023/5/15) is shown. It should be understood that the terminal devices may be different, and the product names of the terminal devices may be the same or different. Illustratively, the product names of the terminal devices are the same when the terminal devices belong to the same product family, and the product names of the terminal devices are different when the terminal devices do not belong to the same product family. Different terminal devices, different SN of the terminal devices, different terminal devices can be distinguished by the SN.

The cloud end can acquire the power consumption data of the terminal equipment from the data platform, and train the power consumption model based on the power consumption data of the terminal equipment. In some embodiments, the cloud may periodically obtain the power consumption data of the terminal device from the data platform, or the cloud may periodically obtain the power consumption data of the terminal device from the data platform. The power consumption model may be used to determine a user group to which a user corresponding to the terminal device belongs, and power consumption processing logic corresponding to the user group.

It should be noted that the cloud may periodically update the power consumption model. For example, taking 1 day as an example, the cloud end can update the power consumption model every 1 day according to the power consumption data of the terminal device acquired from the data platform on the previous day, so as to ensure the accuracy and instantaneity of the power consumption model.

The cloud trains to obtain the power consumption model, or after the cloud updates the power consumption model, the power consumption model can be issued to the terminal equipment.

The terminal device may store the power consumption model. In the running process of the terminal equipment, the power consumption data of the terminal equipment can be acquired in real time, and based on the power consumption model, the user group to which the user corresponding to the terminal equipment belongs and the power consumption processing logic corresponding to the user group are obtained. The terminal device may process the power consumption of the terminal device according to the power consumption processing logic corresponding to the user group, and the processing logic of the terminal device may be described with reference to fig. 6 and fig. 7.

In some embodiments, referring to fig. 2A, a terminal device may include a computing engine and a power consumption processing module.

The power consumption processing module is used for collecting the power consumption data of the terminal equipment in real time and sending the power consumption data of the terminal equipment to the calculation engine.

The computing engine is used for storing the power consumption model, inputting the power consumption data of the terminal equipment from the power consumption processing module into the power consumption model, and obtaining a user group to which the user corresponding to the terminal equipment belongs and power consumption processing logic corresponding to the user group. The computing engine may process the power consumption of the terminal device according to the power consumption processing logic corresponding to the user group.

In some embodiments, the computing engine may detect whether the power consumption of the terminal device is abnormal according to the power consumption processing logic corresponding to the user group, specifically may detect whether the power consumption of the application of the terminal device is abnormal, and send the power consumption detection result to the power consumption processing module. The power consumption detection result may include, but is not limited to: normal power consumption and abnormal power consumption.

Accordingly, the power consumption processing module, in response to the power consumption detection result from the computing engine, may perform a corresponding operation based on the power consumption detection result to manage power consumption of the application of the terminal device.

In some embodiments, the computing engine may include a power consumption business module. The power consumption service module may include: the system comprises a power consumption interface, a power consumption model calling unit and a power consumption model storage unit.

The power consumption interface is used for transmitting power consumption data of the terminal equipment from the power consumption processing module and a power consumption detection result.

And the power consumption model storage unit is used for storing the power consumption model. The power consumption model calling unit is used for calling the power consumption model in the power consumption model storage unit so as to detect whether the power consumption of the terminal equipment is abnormal or not.

In some embodiments, the power consumption processing module may include: a power consumption processing process and a power consumption response unit. In some embodiments, the power consumption processing process and the power consumption corresponding unit may be separately provided, e.g., the terminal device may include a computing engine, a power consumption processing process, and a power consumption responding unit. In some embodiments, the power consumption processing process and the power consumption corresponding unit may be integrally provided, and fig. 2A illustrates that the power consumption processing process and the power consumption response unit are included in the power consumption processing module.

The power consumption processing process is used for collecting power consumption data of the terminal equipment and reporting the power consumption data of the terminal equipment to the data platform. And the power consumption processing process is also used for collecting the power consumption data of the terminal equipment in real time, sending the power consumption data of the terminal equipment to the computing engine through the power consumption interface and receiving the power consumption detection result from the computing engine.

And the power consumption processing process can instruct the power consumption response unit to execute corresponding operation based on the power consumption detection result so as to control the power consumption of the application.

Fig. 2B is a schematic flow chart of a power consumption processing method of a terminal device according to an embodiment of the present application. In fig. 2B, a terminal device is taken as an example, and an interaction process between the terminal device and a cloud end and a data platform is illustrated. Referring to fig. 2B, the method for processing power consumption of a terminal device according to the embodiment of the present application may include:

S201, the power consumption processing process collects power consumption data of the terminal equipment.

For example, the power consumption processing process may collect power consumption data of the terminal device once every 10 minutes.

S202, the power consumption processing process reports the power consumption data of the terminal equipment to the data platform.

For example, taking the power consumption data of the terminal device reported once a day as an example, after the power consumption processing process collects the power consumption data of the terminal device once every 10 minutes, the power consumption data of the terminal device collected in the day can be counted every day, and the power consumption data of the terminal device is reported once a day to the data platform.

S203, the data platform stores power consumption data of at least one terminal device.

S204, the cloud acquires power consumption data of at least one terminal device from the data platform.

S205, the cloud end trains a power consumption model according to the power consumption data of at least one terminal device.

In some embodiments, the power consumption data for different applications may be different, and each application may correspond to a power consumption model. For a power consumption model of an application, the cloud end can train to obtain the power consumption model of the application according to the power consumption data of the application of at least one terminal device. In this embodiment, the cloud may train to obtain a power consumption model corresponding to each application.

In this embodiment, the power consumption model obtained by cloud training may include: the identity of the application, and the power consumption model of the application.

In some embodiments, the end devices of different product families, in which the model of the device laid out is different, so that the power consumption of the same device varies when the same device is used by the same application at the same time. For example, the terminal device of the product family 1 uses the bluetooth chip 1, the terminal device of the product family 2 uses the bluetooth chip 2, and the same application in the terminal device of the product family 1 and the terminal device of the product family 2 respectively uses respective bluetooth chips for communication in the same time, and the power consumption of the bluetooth chip 1 and the power consumption of the bluetooth chip 2 are different. In this embodiment, for different product series, the cloud end may train to obtain a power consumption model of the terminal device of each product series according to the power consumption data of the terminal device of the different product series.

It is understood that in the same product series, the cloud end can train to obtain a power consumption model of each application in the product series according to power consumption data of different applications in the product series. In this embodiment, the power consumption model obtained by cloud training may include: identification of product families, identification of applications, and power consumption models of applications under the product families.

The specific training process of S205 may be described with reference to fig. 3.

S206, the computing engine acquires a power consumption model from the cloud.

In some embodiments, the computing engine may periodically or periodically obtain the power consumption model from the cloud. For example, the computing engine may send a power consumption model acquisition request to the cloud once a day, the power consumption model acquisition request requesting the latest power consumption model.

When the terminal equipment is started for the first time, the power consumption model is not stored in the computing engine. The computing engine may send a power consumption model acquisition request to the cloud, and the cloud may send the latest power consumption model in the cloud to the computing engine in response to the power consumption model acquisition request.

Because the cloud can update the power consumption model, in the embodiment of the application, in order to facilitate distinguishing the power consumption models of different versions, version identification or number identification can be performed on the power consumption model. Taking the version identifier as an example, when the terminal device is started for the first time, because the power consumption model is not stored in the computing engine, the power consumption model acquisition request sent by the computing engine may not include the version identifier of the power consumption model, or the power consumption model acquisition request may include an identifier for indicating that the computing engine has not requested the power consumption model.

In some embodiments, when the computing engine sends a power consumption model acquisition request to the cloud, the power consumption model acquisition request may include a version identification of the power consumption model stored in the computing engine. Thus, in response to a power consumption model acquisition request from the computing engine, the cloud end can determine the version of the stored power consumption model in the computing engine, and when the latest power consumption model is stored in the cloud end, the cloud end can send the latest power consumption model to the computing engine. When the version of the power consumption model stored in the cloud is the same as the version of the power consumption model of the computing engine, that is, the power consumption model is not updated by the cloud, the cloud can feed back a response message of 'not updated power consumption model' to the computing engine.

S207, the power consumption processing process sends the power consumption data of the terminal equipment to the computing engine through the power consumption interface.

It should be understood that S207 and S202 may be performed simultaneously, without distinction of the order.

For example, the power consumption processing process may collect the power consumption data of the terminal device once every 10 minutes, and the power consumption processing process may send the power consumption data of the terminal device to the computing engine through the power consumption interface once every 10 minutes.

S208, the calculation engine calls the power consumption model, and power consumption data of the terminal equipment are input into the power consumption model to obtain a power consumption detection result.

S209, the calculation engine sends a power consumption detection result to the power consumption processing process.

S210, the power consumption processing process indicates the power consumption response unit to execute corresponding operation according to the power consumption detection result.

S208 to S210 may be described with reference to fig. 6 and fig. 7.

Fig. 3 illustrates a process of obtaining a power consumption model by the cloud, taking an application of a terminal device of a product family as an example. It should be appreciated that for other product families, and other applications of the power consumption model acquisition process, reference may be made to the description in FIG. 3.

Fig. 3 is a schematic diagram of an acquisition flow of a power consumption model according to an embodiment of the present application. Referring to fig. 3, the method for processing power consumption of a terminal device according to an embodiment of the present application may include:

S301, determining a target application by the cloud, wherein the target application is an application of a power consumption model to be trained.

In some embodiments, S301 is an optional step. In some embodiments, the cloud may train a power consumption model for every other application for every application. Wherein the target application may comprise each application of the terminal device.

In some embodiments, the target application may be a preset application. In some embodiments, the target application may be a hot application. In some embodiments, the target application may be a developer-customized application.

In some embodiments, the cloud end may determine the target application according to the power consumption data of the at least one terminal device based on the data amount of the power consumption data of the application. Taking the power consumption data of the terminal equipment for counting 1 time a day as an example, referring to a second table, one row of data in the second table can be used as 1 piece of power consumption data of the application 1. The more users using the application, the more terminal devices report the power consumption data of the application, and the more the data volume of the power consumption data of the application.

For example, the cloud may sort the data amounts of the power consumption data of all the applications in the order from more to less, and the cloud may select the application of 150 before sorting as the target application. It should be understood that 150 is an illustration and that the values may be custom modified. In some embodiments, the pre-ranking 150 application may be referred to simply as a top150 application.

In some embodiments, because some applications of the terminal device are resident applications, the non-running of the resident applications may cause the terminal device to fail (bug). By way of example, the resident application may be a system application, which may include, but is not limited to: desktop applications, screen locking applications, etc.

In the embodiment of the application, the cloud can sort the data volume of the power consumption data of all the applications according to the sequence from more to less, delete the resident application and select the top150 application as the target application.

In some embodiments, the amount of power consumption data varies from product family to product family, as well as from application to application. By way of example, with applications such as social applications, entertainment applications, etc. having a large number of users, the amount of power consumption data for an application in a day may reach millions, while with some office applications, etc. having a small number of users, the amount of power consumption data for an application in a day is smaller.

In the embodiment of the application, in order to avoid the problem of waste of training resources caused by excessive data volume of power consumption data of a first application of terminal equipment of a first product series in a preset time period and to avoid the problem of low accuracy of a power consumption model caused by excessive data volume, a first data volume threshold and a second data volume threshold can be preset, wherein the first data volume threshold is larger than the second data volume threshold. Illustratively, the first number threshold may be 100 ten thousand, and the second number threshold may be 10 ten thousand.

When the data size of the power consumption data of the first application of the terminal device of the first product series in the preset time period is greater than 100 ten thousand (a first data size threshold), the cloud end can randomly extract 100 ten thousand power consumption data as training data in the data size of the power consumption data of the first application of the terminal device of the first product series in the preset time period. When the data size of the power consumption data of the first application of the terminal device of the first product series in the preset time period is less than or equal to 100 ten thousand (the first data size threshold value) and greater than or equal to 10 ten thousand (the second data size threshold value), the cloud end can take the power consumption data of the first application of the terminal device of the first product series in the preset time period as training data. When the data size of the power consumption data of the first application of the terminal device of the first product series in the preset time period is smaller than 10 ten thousand (the second data size threshold), the cloud end may not train the power consumption model, because the accuracy of the power consumption model is low due to the small data size.

S302, the cloud terminal preprocesses power consumption data of a first application of the terminal equipment of the first product series in a preset time period.

In some embodiments, S302 is an optional step. In some embodiments, the cloud end may not pre-process the power consumption data of the first application of the terminal device of the first product series in the preset period, but directly train according to the power consumption data of the first application of the terminal device of the first product series in the preset period, to obtain the power consumption model.

It should be appreciated that the first product family may represent each product family and the first application may represent each of the target applications. In the embodiment of the application, the cloud end can divide all the power consumption data according to the product series and the application to obtain the power consumption data of the first application of the terminal equipment of the first product series. It will be appreciated that multiple models of terminal devices may be included in the same product line.

In some embodiments, the preset time period may be, for example, one day, one week, one month, or the like, which is not limited by the embodiments of the present application. For example, taking a preset time period of 30 days as an example, the cloud may obtain power consumption data of the first application of the terminal device of the first product series in the last 30 days. In other words, the cloud may acquire the power consumption data of each application of the terminal device of each product series within the last 30 days to acquire the power consumption model of each application of the terminal device of each product series according to the power consumption data of each application of the terminal device of each product series, and may refer to the related description of "the first application of the terminal device of the first product series".

The pretreatment process is described below:

In some embodiments, the cloud may delete the power consumption data of the data with the missing features because of unstable network and other reasons. For example, referring to table two, if one piece of power consumption data lacks the data of the power consumption of the foreground of the screen, the cloud may delete the piece of power consumption data.

In some embodiments, the power consumption data reported to the data platform by the terminal device may also store a repeated problem, for example, there is a plurality of pieces of power consumption data in one application of the terminal device in one day, in this case, the cloud may perform deduplication processing, and one piece of power consumption data of one application of the terminal device is reserved. For example, the cloud may reserve the piece of power consumption data with the largest power consumption of the background of the CPU, which is not limited in the embodiment of the present application.

Secondly, because the devices used are different when different applications run, the magnitude of the power consumption values of the devices are different. For example, as shown in table two, in the terminal devices of product series 1 and SN1, the power consumption of the Wi-Fi module foreground of application 1 is only 0.29, but in the terminal devices of product series 1 and SN2, the power consumption of the screen foreground of application 1 is 780.33, the latter is 7000 times that of the former, and the magnitude difference of the power consumption values is larger. If the cloud directly uses the power consumption data with large magnitude difference, the features with large values can be more prominent and important in the power consumption model, and the features with small values can be insignificant in the power consumption model, so that the accuracy of the power consumption model is low.

Therefore, in order to unify the comparison standards and ensure the accuracy of the power consumption model, the cloud can perform standardized processing on the power consumption data so that the power consumption values of all devices in the first application of the terminal equipment of the first product series within the preset time period are in the same order of magnitude, and the influence caused by different factor magnitudes among different features is eliminated. For example, the cloud may perform Z-Score standardization processing on power consumption data of the first application of the terminal device of the first product series within a preset period. In some embodiments, the cloud may also use a method such as a standard deviation method or a linear proportion standard method to normalize the power consumption data.

In the embodiment of the application, after the cloud performs the Z-Score standardization processing on the power consumption data of the first application of the terminal device of the first product series in the preset time period, the average value between the power consumption data may be 0 and the standard deviation may be 1.

S303, the cloud side obtains the correlation coefficient of each feature and the main feature in the power consumption data according to the power consumption data of the first application of the terminal equipment of the first product series in the preset time period.

Note that the power consumption data used in S303 is power consumption data subjected to preprocessing.

The power consumption data of the first application of the terminal device of the first product series within the preset time period may include data of at least one feature. Referring to table one, as the at least one feature may include, but is not limited to: screen related features, CPU related features, GNSS related features, sensor related features, GPU related features, camera related features, flash related features, audio related features, bluetooth related features, modem related features, and Wi-Fi related features. The application feature, the time feature, and the product-related feature do not participate in the calculation of the correlation coefficient with the main feature in S303.

The main feature is used for detecting whether the power consumption of the first application is abnormal. In some embodiments, the main feature may be pre-set.

For example, the main feature may be CPU background power consumption. For example, taking main features as the background power consumption of the CPU as an example, for each piece of power consumption data, the cloud end may obtain a correlation coefficient between each feature and the background power consumption of the CPU in each piece of power consumption data. Referring to table one, for product 1 (first product series), and SN1 terminal device, in 2023/5/15, the cloud may obtain a correlation coefficient between the power consumption of the screen on screen and the power consumption of the CPU background, a correlation coefficient between the duration of the screen on screen use and the power consumption of the CPU background, a correlation coefficient between the power consumption of the screen foreground and the power consumption of the CPU background, … …, and a correlation coefficient between the total flow of the Wi-Fi module background and the power consumption of the CPU background.

In some embodiments, for each piece of power consumption data, the cloud may obtain Pearson correlation coefficients (Pearson correlation coefficient), abbreviated as Pearson correlation coefficients, for each feature and the main feature. The cloud may use the Pearson correlation coefficient as the correlation coefficient for each feature to the main feature. The Pearson correlation coefficient is used for describing the linear relation between the two features, and the value of the Pearson correlation coefficient can be between [ -1,1 ].

The stronger the linear relationship between the two features, the closer the Pearson correlation coefficient will be to-1 or 1, and the weaker the linear relationship between the two features, the closer the Pearson correlation coefficient will be to 0. The cloud may calculate Pearson correlation coefficients for each feature and the main feature using equations 1-4 as follows:

Where Y may represent a main feature, such as CPU background power consumption. X may represent each feature in the power consumption data, which may or may not include a main feature. Equation 1 is used for calculating the standard deviation σ _Y of the main feature in the power consumption data of the first application of the terminal device of the first product series in the preset time period, and equation 2 is used for calculating the standard deviation σ _X of each feature in the power consumption data of the first application of the terminal device of the first product series in the preset time period.

Wherein i represents any piece of power consumption data of a first application of the terminal device of the first product series in a preset time period, and n represents the data quantity of the power consumption data. Y _i represents the value of the main feature in any piece of power consumption data, and mu _Y represents the average value of the main feature in the power consumption data of the first application of the terminal equipment of the first product series in the preset time period. Similarly, taking an example that each feature includes the first feature, X _i represents a value of the first feature in the arbitrary piece of power consumption data, and μ _X represents a mean value of the first feature in power consumption data of the first application of the terminal device of the first product series in a preset period.

Wherein equation 3 is used to calculate covariance cov (X, Y) between each feature and the main feature.

Wherein equation 4 is used to calculate the Pearson correlation coefficient ρ (X, Y) between each feature and the main feature.

In some embodiments, for each piece of power consumption data, the cloud may obtain Spearman correlation coefficients for each feature and the main feature, and take Spearman correlation coefficients as correlation coefficients for each feature and the main feature. The Spearman correlation coefficient may represent a monotonic relationship between the two features, with the Spearman correlation coefficient also having a value between [ -1,1 ].

In some embodiments, for each piece of power consumption data, the cloud may obtain Pearson correlation coefficients for each feature and the main feature, and Spearman correlation coefficients for each feature and the main feature, and the correlation coefficients for each feature and the main feature may include: pearson correlation coefficient of each feature with the main feature, and Spearman correlation coefficient of each feature with the main feature.

S304, the cloud determines auxiliary features according to the correlation coefficient of each feature and the main feature.

In some embodiments, a Pearson correlation coefficient threshold and a Spearman correlation coefficient threshold may be preset. The Pearson correlation coefficient threshold and the Spearman correlation coefficient threshold may be equal or unequal. For example, the Pearson correlation coefficient threshold may be 0.3 and the spearman correlation coefficient threshold may be 0.3.

When the cloud acquires the Pearson correlation coefficient of each feature and the main feature, the cloud may use the feature greater than or equal to the Pearson correlation coefficient threshold as the auxiliary feature. When the cloud acquires the Spearman correlation coefficient of each feature and the main feature, the cloud can take the feature which is larger than or equal to the Spearman correlation coefficient threshold value as the auxiliary feature. When the cloud obtains Pearson correlation coefficients of each feature and the main feature and Spearman correlation coefficients of each feature and the main feature, the cloud may use the feature greater than or equal to the Pearson correlation coefficient threshold and greater than or equal to the Spearman correlation coefficient threshold as the auxiliary feature.

In some embodiments, taking the Pearson correlation coefficient of each feature and the main feature and the spearson correlation coefficient of each feature and the main feature as an example, the cloud may take a feature greater than or equal to the Pearson correlation coefficient threshold and greater than or equal to the spearson correlation coefficient threshold as the first candidate auxiliary feature. The cloud may filter among the first candidate auxiliary features to obtain auxiliary features.

In some embodiments, multiple collinearity may exist between some of the first candidate secondary features, i.e., the first candidate secondary features are not independent of each other, and one of the first candidate secondary features may be a linear combination of one or more other of the first candidate secondary features. For example, taking a navigation application as an example, when a user uses the navigation application, the screen may be in a bright screen state, and then there is multiple collinearity between the screen foreground use duration and the screen bright screen use duration, and the screen bright screen power consumption. In this case, if the power consumption model is trained by using the several first candidate auxiliary features with multiple collinearity as auxiliary features, the several first candidate auxiliary features will affect each other, which is not beneficial to the power consumption model to output a correct power consumption detection result.

In some embodiments, the coefficient of variance expansion (variance inflation factor, VIF) may measure the co-linearity between the first candidate secondary features, the larger the VIF value, the more pronounced the problem of co-linearity between features. In some embodiments, the first VIF threshold and the second VIF threshold may be preset. Illustratively, the first VIF threshold may be 100 and the second VIF threshold may be 10.

When the VIF between the first candidate auxiliary features is greater than or equal to 100, it indicates that there is serious multiple collinearity between the first candidate auxiliary features, when the VIF between the first candidate auxiliary features is less than 10, it indicates that there is no collinearity between the first candidate auxiliary features, and when the VIF between the first candidate auxiliary features is greater than or equal to 10 and less than 100, it indicates that there is strong multiple collinearity between the first candidate auxiliary features.

Therefore, in the embodiment of the present application, the cloud may execute the following steps:

step A, taking any one first candidate auxiliary feature as a dependent variable, taking each other first candidate auxiliary feature as an independent variable, and performing linear regression processing on the first candidate auxiliary feature and the other first candidate auxiliary features, wherein the following formula 5-1 can be referred to:

Wherein X represents first candidate auxiliary features, and the number of the first candidate auxiliary features is p. X _j represents any one of the first candidate auxiliary features, and β ₀,β₁,……,β_j represents the coefficient of the linear regression process. X _j is a value obtained by linear regression treatment.

The cloud may calculate the VIF between the first candidate secondary feature and the other first candidate secondary features using equations 5-2 and 6 as follows:

where i represents any one piece of power consumption data, and n represents the total number of pieces of power consumption data, i.e., the data amount of the power consumption data. X _ji represents the value of any one of the first candidate auxiliary features in any one piece of power consumption data, Representing the value of any one first candidate auxiliary feature in any piece of power consumption data after linear regression processingAnd representing the average value of any first candidate auxiliary feature in the n pieces of power consumption data. R _j ² represents the decision coefficient corresponding to the arbitrary first candidate auxiliary feature. VIF _j represents the VIF of the any one of the first candidate secondary features.

Wherein R _j ² is a decision coefficient in a linear regression processing model, and can measure how many independent variables can be interpreted by the independent variables, the larger R _j ² is, the larger VIF _j is, the better the model interpretation is, the stronger the linear relation between the independent variables and the dependent variables is, and the more probable multiple collinearity is.

Illustratively, assume that there are 10 first candidate auxiliary features, first candidate auxiliary feature 1, first candidate auxiliary features 2, … …, and first candidate auxiliary feature 10, respectively. The cloud may calculate the VIF for the first candidate assist feature 1 using equation 5-1, equation 5-2, and equation 6.

And B, repeating the step A, and sequentially taking each other first candidate auxiliary feature as a dependent variable to calculate the VIF of each other first candidate auxiliary feature.

Illustratively, the cloud may also calculate the VIF of the first candidate secondary feature 2, the VIF of the first candidate secondary feature 3, … …, and the VIF of the first candidate secondary feature 10.

In some embodiments, the step B and the step a may be combined into one step, that is, the cloud obtains the coefficient of expansion VIF of variance of each first candidate auxiliary feature and other first candidate auxiliary features.

And C, aiming at the first candidate auxiliary features corresponding to the maximum VIF, if the maximum VIF is larger than 10 and the first candidate auxiliary features are larger than 3, deleting the first candidate auxiliary features corresponding to the maximum VIF, and executing the step D. And if the VIFs of all the first candidate auxiliary features are smaller than or equal to 10, or the maximum VIFs are larger than 10 and the number of the first candidate auxiliary features is smaller than or equal to 3, taking all the first candidate auxiliary features as second candidate auxiliary features. It should be understood that 3 are exemplary, other values may be substituted, and 3 may be referred to as a quantity threshold. In some embodiments, 10 (the second VIF threshold) may be the VIF threshold.

For example, if the first candidate auxiliary feature corresponding to the maximum VIF is the first candidate auxiliary feature 1, the VIF of the first candidate auxiliary feature 1 is greater than 10, the number of the first candidate auxiliary features is 10, and the number of the first candidate auxiliary features is greater than 3, the first candidate auxiliary feature 1 is deleted. If the VIF (maximum VIF) of the first candidate auxiliary feature 1 is less than or equal to 10, the first candidate auxiliary feature 1, the first candidate auxiliary features 2, … …, and the first candidate auxiliary feature 10 are all used as the second candidate auxiliary features. Or the maximum VIF is greater than 10 and the number of the first candidate auxiliary features is less than or equal to 3, for example, if the VIF of the first candidate auxiliary feature 1 is greater than 10, but the first candidate auxiliary feature is only three of the first candidate auxiliary feature 1, the first candidate auxiliary feature 2 and the first candidate auxiliary feature 3, so the first candidate auxiliary feature 1, the first candidate auxiliary feature 2 and the first candidate auxiliary feature 3 can be used as the second candidate auxiliary feature.

And D, repeating the steps A-C for other first candidate auxiliary features after deleting the first candidate auxiliary features corresponding to the maximum VIF until the maximum VIF is less than or equal to 10 or the number of the remaining first candidate auxiliary features is less than or equal to a number threshold (e.g. 3), and taking the remaining first candidate auxiliary features as second candidate auxiliary features.

For example, after deleting the first candidate auxiliary feature corresponding to the maximum VIF as the first candidate auxiliary feature 1, there are still 9 first candidate auxiliary features, and for the 9 first candidate auxiliary features, the steps a-C may be re-performed until the maximum VIF is less than or equal to 10, or the number of the remaining first candidate auxiliary features is less than or equal to the number threshold, and the cloud may use the last remaining first candidate auxiliary feature as the second candidate auxiliary feature.

In some embodiments, the cloud may treat the second candidate secondary feature as a secondary feature.

In some embodiments, the cloud may also filter among the second candidate auxiliary features to obtain the auxiliary features. For example, the cloud may use a Least Absolute Shrinkage and Selection (LASSO) model to filter among the second candidate auxiliary features to obtain the auxiliary features.

The LASSO model is also a linear regression model in nature, but differs from the traditional linear model in that it incorporates a penalty function for L1 regularization, so the LASSO model is congested with two features:

1. some regression coefficients are compressed, i.e. the sum of the absolute values of the forcing coefficients is smaller than a certain fixed value.

2. And some regression coefficients are zero, so that sparse results are formed, and important features can be screened out.

In the power consumption data of the first application of the terminal equipment of the first product series in the preset time period, the cloud can acquire the values of the main features and the values of the second candidate auxiliary features, and the cloud can input the values of the main features and the values of the second candidate auxiliary features into the LASSO model to acquire the importance value of each second candidate auxiliary feature.

In the embodiment of the application, the cloud may use the second candidate auxiliary features corresponding to the maximum 3 importance values as the auxiliary features. The 3 are illustrative, and other values may be substituted.

In some embodiments, the LASSO model may be as shown in equation 7:

Where P represents the number of second auxiliary features and j represents any one of the second auxiliary features. Lambda is a super parameter and may be a preset value. Beta ₀ is a constant. Y _i denotes a value of a main feature in any one of the n pieces of power consumption data, and X _ji denotes a value of any second auxiliary feature in any one of the n pieces of power consumption data.

In the embodiment of the application, the cloud can input the numerical value of the main feature and the numerical value of the second candidate auxiliary feature into the LASSO model to obtain beta _j of any second auxiliary feature, the cloud takes an absolute value of beta _j, and the absolute value of beta _j can represent the importance of the second candidate auxiliary feature. The larger the absolute value of β _j, the larger the importance value of the second candidate auxiliary feature.

Fig. 5A is a schematic diagram of screening auxiliary features according to an embodiment of the present application. A in fig. 5A shows all features in the power consumption data. After calculation of the Pearson correlation coefficient and the Spearman correlation coefficient, the first candidate auxiliary feature is screened out. Referring to b in fig. 5A, as the first candidate secondary feature may include: camera front-end power consumption, camera front-end use time length, modem front-end power consumption, modem back-end power consumption, wi-Fi module front-end total flow, and Wi-Fi module back-end power consumption. After performing the VIF computational screening, a second candidate secondary feature may be obtained. Referring to c in fig. 5A, the second candidate secondary feature may include: the method comprises the steps of camera foreground use duration, modem background power consumption, wi-Fi module foreground total flow and Wi-Fi module background power consumption. After the LASSO model process, the secondary features can be obtained. Referring to d in fig. 5A, as auxiliary features may include: modem background power consumption, wi-Fi module foreground total traffic, and Wi-Fi module background power consumption.

S305, the cloud acquires auxiliary feature conditions, wherein the auxiliary feature conditions are used for determining a user group to which the user belongs.

In the embodiment of the application, the cloud terminal can also acquire the auxiliary characteristic condition after determining the auxiliary characteristic. The secondary feature condition is used to determine the user population to which the user belongs.

In some embodiments, the cloud may train a classification and regression tree (classification and regression tree, CART) based on Yu Fu features and power consumption data of the first application of the terminal device of the first product family in a preset period, and use leaf nodes in the CART as auxiliary feature conditions. It should be appreciated that the habits of the user population in each leaf node are similar. It is to be understood that the power consumption data of the first application of the terminal device of the first product series in the preset period of time used in S305 to S307 is data not subjected to the Z-Score normalization process.

In some embodiments, in order to prevent CART from over-fitting and ensure that each leaf node has a sufficient data size, in the embodiments of the present application, the following super-parameters may be set during CART training:

1. The loss function is the mean square error.

2. The maximum depth is 3. Wherein the root node may act as layer 0.

3. The maximum number of leaf nodes is 8.

4. The minimum data size of the leaf nodes is 5000.

Fig. 4 is a schematic diagram of CART according to an embodiment of the present application. Taking the example of 4 leaf nodes included in CART in fig. 4, referring to fig. 4, the auxiliary feature condition may include: "Wi-Fi module background power consumption is less than or equal to 5.732 and modem background power consumption is less than or equal to 0.942", and "Wi-Fi module background power consumption is less than or equal to 5.732 and modem background power consumption is greater than 0.942", and "Wi-Fi module background power consumption is greater than 5.732 and modem background power consumption is less than or equal to 24186.737", and "Wi-Fi module background power consumption is greater than 5.732 and modem background power consumption is greater than 24186.737".

S306, the cloud end divides the users corresponding to the terminal equipment into at least two user groups according to the auxiliary characteristic conditions and the power consumption data of the first application of the terminal equipment of the first product series in a preset time period.

Illustratively, using the secondary feature conditions in fig. 4, users may be divided into 4 types of user groups, user group 1, user group 2, user group 3, and user group 4, respectively. If the power consumption data of the terminal device corresponding to the user group 1 satisfies "Wi-Fi module background power consumption is less than or equal to 5.732 and the modem background power consumption is less than or equal to 0.942", the power consumption data of the terminal device corresponding to the user group 1 satisfies "Wi-Fi module background power consumption is less than or equal to 5.732 and the modem background power consumption is greater than 0.942", the power consumption data of the terminal device corresponding to the user group 3 satisfies "Wi-Fi module background power consumption is greater than 5.732 and the modem background power consumption is less than or equal to 24186.737", and the power consumption data of the terminal device corresponding to the user group 4 satisfies "Wi-Fi module background power consumption is greater than 5.732 and the modem background power consumption is greater than 24186.737".

S307, the cloud end determines a threshold value of a main characteristic corresponding to each user group according to the power consumption data of the first application of the terminal equipment of the first product series in the preset time of each user group, wherein the threshold value of the main characteristic is used for detecting whether the power consumption of the first application is abnormal or not.

After the cloud end divides the user groups based on the auxiliary feature conditions, the cloud end can determine a threshold value of the main feature corresponding to each user group according to power consumption data (simply called power consumption data) of the first application of the terminal equipment of the first product series within preset time of each user group. The threshold value of the main characteristic is used for detecting whether the power consumption of the first application is abnormal. For example, if the main characteristic is the CPU background power consumption, the cloud may determine, according to the power consumption data of each user group, a threshold value of the CPU background power consumption corresponding to each user group, where the threshold value of the CPU background power consumption corresponding to each user group is used to detect whether the CPU background power consumption in the power consumption data of the user group is abnormal, and the CPU background power consumption may represent that the power consumption of the first application is abnormal.

In some embodiments, a first preset ratio may be preset, the first preset ratio being used to determine a threshold value of the main feature. Taking the main characteristic as the CPU background power consumption as an example, aiming at the numerical value of the CPU background power consumption in the power consumption data of each user group, the cloud can sort according to the size sequence, and the first value of the numerical value of the CPU background power consumption which is more than or equal to 90% is used as the threshold value of the CPU background power consumption.

For example, taking the user group 1 as an example, for example, the first preset proportion is 90%, a in fig. 5B represents the size distribution of the values of the CPU background power consumption in the power consumption data corresponding to the user group 1 with a rectangular frame, and the cloud may use, as the threshold of the CPU background power consumption, a first value greater than or equal to 90% of the values of the CPU background power consumption in the power consumption data corresponding to the user group 1. For example, if 100 pieces of power consumption data corresponding to the user group 1 are arranged according to the order from small to large of the values of the background power consumption of the CPU, the first value of the values of the background power consumption of the CPU in the 90 th piece of power consumption data is used as the threshold value of the background power consumption of the CPU. For example, the value of the background power consumption of the CPU in the 90 th power consumption data is a, and the value of the background power consumption of the CPU in the 91 st power consumption data is B, either one of the value a and the value B may be used as the first value, or a or B may be used as the first value, that is, the threshold value of the background power consumption of the CPU.

And the threshold value of the background power consumption of the CPU is used for detecting whether the power consumption of the first application is abnormal. When the value of the background power consumption of the CPU in the power consumption data of the first application is larger than or equal to the threshold value of the background power consumption of the CPU, the abnormal power consumption of the first application can be determined, and when the value of the background power consumption of the CPU in the power consumption data of the first application is smaller than the threshold value of the background power consumption of the CPU, the normal power consumption of the first application can be determined.

In some embodiments, the cloud may also rank the anomalies. In the embodiment of the application, a second preset proportion and a third preset proportion can be preset. For example, the second preset ratio may be 98% and the third preset ratio may be 99.5%. Referring to B in fig. 5B, B in fig. 5B represents, with a rectangular frame, a numerical distribution of CPU background power consumption in the power consumption data corresponding to the user group 1, and the cloud may calculate a second value of the numerical value of CPU background power consumption greater than or equal to a second preset proportion (98%), and a third value of the numerical value of CPU background power consumption greater than or equal to a third preset proportion (99.5%).

In this embodiment, the cloud may use the first value as a first threshold of the CPU background power consumption at the time of abnormality, the second value as a second threshold of the CPU background power consumption at the time of superabnormality, and the third value as a third threshold of the CPU background power consumption at the time of extreme abnormality.

In some embodiments, the threshold for CPU background power consumption may include: a first threshold for detecting whether the power consumption of the first application is abnormal, a second threshold for detecting whether the power consumption of the first application exceeds the abnormal CPU background power consumption, and a third threshold for detecting whether the power consumption of the first application is extremely abnormal. When the value of the background power consumption of the CPU in the power consumption data of the first application is larger than or equal to a first threshold value and smaller than a second threshold value, the abnormal power consumption of the first application can be determined, when the value of the background power consumption of the CPU in the power consumption data of the first application is larger than or equal to the second threshold value and smaller than a third threshold value, the super abnormal power consumption of the first application can be determined, and when the value of the background power consumption of the CPU in the power consumption data of the first application is larger than or equal to the third threshold value, the extreme abnormal power consumption of the first application can be determined.

In some embodiments, "anomaly, superanomaly, and extreme anomaly" may be respectively taken as three anomaly levels of power consumption anomalies for the first application. The method includes that when the value of the background power consumption of the CPU in the power consumption data of the first application is greater than or equal to a first threshold and smaller than a second threshold, the power consumption abnormality of the first application belongs to a first abnormality level, when the value of the background power consumption of the CPU in the power consumption data of the first application is greater than or equal to the second threshold and smaller than a third threshold, the power consumption abnormality of the first application belongs to a second abnormality level, and when the value of the background power consumption of the CPU in the power consumption data of the first application is greater than or equal to the third threshold, the power consumption abnormality of the first application belongs to a third abnormality level. Wherein the degree of abnormality of the first abnormality level is smaller than the degree of abnormality of the second abnormality level, and the degree of abnormality of the second abnormality level is smaller than the degree of abnormality of the third abnormality level.

In some embodiments, for applications with a large data volume, the distribution of the values of the main features is dense, and the problem that the threshold values corresponding to different anomaly levels have smaller differences can occur. In the embodiment of the application, the cloud can adjust the second threshold and the third threshold so as to obviously distinguish the abnormal level of the first application based on the adjusted second threshold and the adjusted third threshold.

For the second threshold, the adjustment rule of the cloud is as follows:

The cloud may acquire a normal distribution Z value of the second threshold by using the following formula 8 to detect whether the second threshold needs to be adjusted:

Wherein Q _0.98 represents a second threshold value, μ represents a mean value of values of the CPU background power consumption corresponding to each user group, σ represents a standard deviation of values of the CPU background power consumption corresponding to each user group.

Based on formula 8, if the obtained normal distribution Z value is smaller than the preset Z value, the cloud end may increase the second threshold. And the cloud uses the increased second threshold value, and calculates by adopting the formula 8 again, wherein the obtained normal distribution Z value is equal to the preset Z value. For example, the preset Z value may be 3.

The adjusted second threshold may be the maximum value of the original second threshold and the increased second threshold, e.g., the adjusted second threshold may be max (Q _0.98, 3σ+μ).

For the third threshold, the adjustment rule of the cloud is as follows:

The cloud may acquire a normal distribution Z value of the third threshold by using the following formula 9 to detect whether the third threshold needs to be adjusted:

Wherein Q _0.995 represents a third threshold. Based on formula 9, if the obtained normal distribution Z value is smaller than the preset Z value, the cloud may increase the third threshold. And the cloud uses the increased third threshold value, and the formula 9 is adopted again to calculate, so that the obtained normal distribution Z value is equal to the preset Z value. For example, the increased third threshold may be referred to as a first candidate third threshold.

In addition, the adjusted third threshold value needs to be larger than the outlier of the bin graph, and the outlier of the bin graph can be calculated by the following formula 10:

outlier=q _0.75+1.5(Q_0.75-Q_0.25) equation 10

Wherein Q _0.75 represents a value of CPU background power consumption greater than or equal to 75% among values of CPU background power consumption in the power consumption data corresponding to the user group, and Q _0.25 represents a value of CPU background power consumption greater than or equal to 25% among values of CPU background power consumption in the power consumption data corresponding to the user group. For example, the adjusted third threshold, i.e., the third threshold greater than the outlier of the bin graph, may be referred to as a second candidate third threshold.

It may be appreciated that in the embodiment of the present application, the adjusted third threshold may be the maximum value of the original third threshold, the first candidate third threshold, and the second candidate third threshold. The third threshold, as adjusted, may be max (Q _0.995, 3σ+μ, outlier).

S308, the cloud end generates a power consumption model of a first application of the terminal equipment of the first product series according to the auxiliary characteristic conditions and the threshold value of the main characteristic corresponding to each user group.

In some embodiments, the power consumption model of the first application of the terminal device of the first product family may be simply referred to as the power consumption model of the first application of the first product family. The power consumption model of the first application of the first product family may include: and dividing the auxiliary characteristic conditions of the user groups and the threshold value of the main characteristic corresponding to each user group. In some embodiments, the threshold value of the primary feature may include a first threshold value. In some embodiments, the threshold of the primary feature may include: a first threshold, a second threshold, and a third threshold. In some embodiments, the second one of the thresholds of the primary feature may be an adjusted second threshold and the third one of the thresholds of the primary feature may be an adjusted third threshold.

And the threshold value of the main characteristic corresponding to each user group is used for detecting whether the power consumption of the first application is abnormal or not and detecting the abnormal level of the power consumption of the first application. In some embodiments, the threshold value of the primary feature for each user group may be referred to as processing logic of the power consumption of the first application.

In some embodiments, the cloud may store the power consumption model of the first application of the first product family in a form of a table, a text, or the like, and the embodiments of the present application do not limit the form of the power consumption model. The power consumption model of the first application storing the first product family is shown in table three in tabular form.

Watch III

Inf in Table three represents positive infinity (infinity).

In the embodiment of the application, the cloud can generate and update the power consumption model based on the latest power consumption data of the terminal equipment, and the real-time performance and the accuracy of the power consumption model are high. In addition, for different product series and for different applications, different product series and power consumption models for different applications can be respectively generated, so that granularity is finer and accuracy is higher.

After the cloud generates the power consumption model or updates the power consumption model, the power consumption model may be issued to the terminal device, and the issuing manner may refer to the related description in the foregoing embodiment. In some embodiments, the terminal device may use the power consumption model to detect whether the power consumption of the application of the terminal device is abnormal, and the abnormal level, and further execute a corresponding operation to reduce the power consumption of the application.

Fig. 6 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application. Referring to fig. 6, the method for processing power consumption of a terminal device according to an embodiment of the present application may include:

s601, terminal equipment collects power consumption data of the terminal equipment, wherein the power consumption data of the terminal equipment comprises power consumption data of a first application, and the terminal equipment belongs to a first product series.

It should be understood that, in the embodiment of the present application, the terminal device belongs to the first product series, and a process of obtaining the power consumption detection result of the first application by using the power consumption model of the first application of the first product series and the power consumption data of the first application by the terminal device is described as an example. In some embodiments, the first application may be an application running in the foreground of the terminal device and/or an application running in the background.

In the embodiment of the application, the terminal device can acquire the power consumption data of the terminal device, and the power consumption data of the terminal device can comprise the power consumption data of the first application.

It should be understood that, when the power consumption model issued by the cloud is a power consumption model of a different application and the product series is not distinguished, the terminal device may use the power consumption model of the first application to detect whether the power consumption of the first application is abnormal, and may refer to a related description of the power consumption model of the first application of the first product series.

S602, the terminal equipment determines a user group to which the user belongs and a threshold value of a main feature corresponding to the user group according to a power consumption model of a first application of the first product series and power consumption data of the first application.

The terminal equipment can determine a user group to which the user belongs and a threshold value of a main feature corresponding to the user group according to the power consumption data of the first application and the auxiliary feature condition in the power consumption model of the first application of the first product series. The user may be understood as the user to whom the terminal device corresponds.

In the power consumption data of the first application, the Wi-Fi module background power consumption is 6, and the modem background power consumption is 20, and the terminal device may determine that the user belongs to the user group 3 based on the power consumption model of the table three, where the threshold value of the main feature corresponding to the user group 3 includes: a first threshold (90.83), a second threshold (146.64), and a third threshold (203.57).

S603, the terminal equipment obtains a power consumption detection result of the first application according to the threshold value of the main characteristic corresponding to the user group and the power consumption data of the first application.

The power consumption data of the first application may comprise a value of the main feature. For example, if the main characteristic is the background power consumption of the CPU, the power consumption data of the first application may include a value of the background power consumption of the CPU. In some embodiments, the power consumption detection result of the first application is used to indicate whether the power consumption of the first application is abnormal. When the value of the main characteristic of the power consumption data of the first application is larger than or equal to the threshold value of the main characteristic corresponding to the user group, the abnormal power consumption of the first application can be determined, and when the value of the main characteristic of the power consumption data of the first application is smaller than the threshold value of the main characteristic corresponding to the user group, the normal power consumption of the first application can be determined.

In some embodiments, when the threshold value of the main feature in the power consumption model includes abnormal threshold values of different levels, the terminal device may detect whether the power consumption of the first application is abnormal according to the threshold value of the main feature corresponding to the user group and the power consumption data of the first application, and may determine the abnormal level of the power consumption of the first application. In this embodiment, the power consumption detection result of the first application is used to indicate whether the power consumption of the first application is abnormal or not, and the abnormality level of the power consumption of the first application.

For example, if the user belongs to the user group 3, referring to table three, the threshold value of the main feature corresponding to the user group 3 includes: a first threshold (90.83), a second threshold (146.64), and a third threshold (203.57). If the power consumption data of the first application is 100, the cloud end can determine that the power consumption of the first application is abnormal and the power consumption abnormality of the first application is a first abnormal level according to the threshold value of the main feature, wherein the value of the power consumption of the background of the CPU is larger than the first threshold value and smaller than the second threshold value.

S604, when the power consumption of the first application is abnormal, the terminal equipment executes corresponding operation.

In the embodiment of the application, when the power consumption of the first application is abnormal, the terminal equipment executes corresponding operation. For example, the terminal device may output a prompt message, where the prompt message is used to prompt that the power consumption of the first application is abnormal.

In some embodiments, when the power consumption of the first application is abnormal, and the terminal device may determine the abnormal level of the power consumption of the first application, the terminal device may perform the corresponding operation according to the abnormal level of the power consumption of the first application. Wherein, different exception grades, the operations performed by the terminal device may be different.

For example, when the abnormality level of the power consumption of the first application is the first abnormality level, the terminal device may decrease the frequency of the CPU used by the first application to the first frequency. When the abnormal level of the power consumption of the first application is the second abnormal level, the terminal device may decrease the frequency of the CPU used by the first application to the second frequency. When the abnormal level of the power consumption of the first application is the third abnormal level, the terminal device may decrease the frequency of the CPU used by the first application to the third frequency. Wherein the first frequency is greater than the second frequency and the second frequency is greater than the third frequency. That is, the more serious or higher the abnormality level of the power consumption of the first application, the more the CPU frequency drops.

In the embodiment of the application, the operation of the terminal equipment corresponding to different abnormal grades is not limited.

In the embodiment of the application, the terminal equipment does not manage the power consumption of all the terminal equipment based on a fixed power consumption threshold, but can determine the user group to which the user belongs aiming at different users, and the thresholds of the main features corresponding to the different user groups can be different. The terminal device can process the power consumption of the terminal device according to the threshold value of the main characteristic corresponding to the user group to which the user belongs, so that the terminal device can flexibly control the power consumption of the terminal device based on the characteristic or the use habit of the user. In addition, when the power consumption of the terminal equipment is abnormal, the terminal equipment can also determine the abnormal grade, and aiming at different abnormal grades, the terminal equipment can execute different response operations, so that the flexibility is high.

The power consumption processing method of the terminal device provided by the embodiment of the application is described below in terms of module interaction in the terminal device. Fig. 7 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application. Referring to fig. 7, the method for processing power consumption of a terminal device according to an embodiment of the present application may include:

S701, a power consumption processing process collects power consumption data of terminal equipment, wherein the power consumption data of the terminal equipment comprises power consumption data of a first application, and the terminal equipment belongs to a first product series.

S701 may refer to the description in S201 in fig. 2B.

S702, the power consumption processing process sends power consumption data of the terminal equipment to the computing engine through the power consumption interface.

S703, the computing engine calls a power consumption model of a first application of the first product series, and determines a user group to which the user belongs and a threshold value of a main feature corresponding to the user group according to power consumption data of the first application.

S704, the computing engine obtains a power consumption detection result of the first application according to the threshold value of the main feature corresponding to the user group and the power consumption data of the first application.

S703 to S704 may refer to the descriptions in S602 to S603.

S705, the computing engine sends the power consumption detection result of the first application to the power consumption processing process.

S706, the power consumption processing process sends a control instruction to the power consumption response unit according to the power consumption detection result of the first application, when the power consumption of the first application is determined to be abnormal, the control instruction is used for indicating the power consumption response unit to execute corresponding operation.

S707, the power consumption response unit performs a corresponding operation in response to the control instruction.

S707 may refer to the description in S604.

The power consumption processing method of the terminal device provided in the embodiment of the present application has the same technical principle and technical effect as the embodiment shown in fig. 6, and can be described with reference to the related description in the above embodiment.

Fig. 8 is a flowchart of another embodiment of a power consumption processing method of a terminal device according to an embodiment of the present application. Fig. 8 combines the steps of fig. 2B, 3, and fig. 6, 7. Referring to fig. 8, a method for processing power consumption of a terminal device according to an embodiment of the present application may include:

S801, the cloud end determines the top150 application as a target application according to the power consumption data of at least one terminal device.

S802, deleting the resident application by the cloud.

S803, the cloud acquires power consumption data of the top150 application of the terminal equipment of different product series in the last 30 days.

S804, the cloud end judges the data quantity of the power consumption data.

S801 to S804 can refer to the related description in S301.

S805, the cloud performs preprocessing on the power consumption data.

S805 may refer to the related description in S302.

S806, cloud screening auxiliary features.

S806 may refer to the descriptions in S303-S304.

S807, the cloud end performs data decomposition on the power consumption data based on the auxiliary features.

The cloud performs data decomposition on the power consumption data, which can be understood as: the cloud acquires the auxiliary feature condition, which can be described in S305.

S808, the cloud acquires the threshold value of the main feature corresponding to each user group.

S808 may refer to the descriptions in S306-S307.

In some embodiments, the cloud may further adjust a second threshold value and a third threshold value of the threshold values of the main features, which may refer to the related description in S307.

S809, the cloud outputs a power consumption model.

S810, the terminal equipment processes the power consumption of the terminal equipment according to the power consumption model.

S810 may refer to the description in the embodiment shown in fig. 6 and 7.

It should be understood that, in fig. 8, the steps of the cloud end and the steps of the terminal device are divided by solid lines, and the different steps performed by the cloud end are divided by dotted lines.

The power consumption processing method of the terminal device provided in the embodiment of the present application has the same technical principles and technical effects as those of the embodiments shown in fig. 2B, 3 and 6 and 7, and may be described with reference to the related descriptions in the above embodiments.

Those skilled in the art will understand that the system architecture and the power consumption processing method of the terminal device in the embodiment of the present application may be combined and cited, and the system architecture provided in the embodiment of the present application may execute the steps in the power consumption processing method of the terminal device.

It should be noted that, the power consumption data (including, but not limited to, data for analysis, stored data, displayed data, etc.) related to the present application are all information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

The power consumption processing method of the terminal equipment provided by the embodiment of the application can be applied to the electronic equipment with the communication function. The electronic device includes a terminal device, and specific device forms and the like of the terminal device may refer to the above related descriptions, which are not repeated herein.

The embodiment of the application provides a terminal device, which comprises: comprising the following steps: a processor and a memory; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to cause the terminal device to perform the method described above.

The embodiment of the application also provides electronic equipment, which can be the terminal equipment and the cloud terminal in the embodiment. Referring to fig. 9, the electronic device may include: a processor 901 (e.g., CPU), a memory 902. The memory 902 may include a random-access memory (RAM) and may also include a non-volatile memory (NVM), such as at least one magnetic disk memory, in which various instructions may be stored in the memory 902 for performing various processing functions and implementing method steps of the present application.

Optionally, the electronic device according to the present application may further include: a power supply 903, a communication bus 904, and a communication port 905. The communication ports 905 are used to enable connection communication between the electronic device and other peripheral devices. In an embodiment of the application, the memory 902 is used to store computer executable program code, the program code comprising instructions; when the processor 901 executes the instructions, the instructions cause the processor 901 of the electronic device to perform the actions in the above method embodiments, which achieve similar principles and technical effects, and are not described herein again.

The embodiment of the application provides a chip. The chip comprises a processor for invoking a computer program in a memory to perform the technical solutions in the above embodiments. The principle and technical effects of the present application are similar to those of the above-described related embodiments, and will not be described in detail herein.

The embodiment of the application also provides a computer readable storage medium. The computer-readable storage medium stores a computer program. The computer program realizes the above method when being executed by a processor. The methods described in the above embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer readable media can include computer storage media and communication media and can include any medium that can transfer a computer program from one place to another. The storage media may be any target media that is accessible by a computer.

In one possible implementation, the computer readable medium may include RAM, ROM, a compact disk-read only memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium targeted for carrying or storing the desired program code in the form of instructions or data structures and accessible by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (Digital Subscriber Line, DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk and disc, as used herein, includes optical disc, laser disc, optical disc, digital versatile disc (DIGITAL VERSATILE DISC, DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

Embodiments of the present application provide a computer program product comprising a computer program which, when executed, causes a computer to perform the above-described method.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the foregoing is by way of illustration and description only, and is not intended to limit the scope of the invention.

Claims

1. A power consumption processing method of a terminal device, applied to the terminal device, the method comprising:

Collecting power consumption data of the terminal equipment, wherein the power consumption data comprises power consumption data of a first application;

determining a user group to which a user corresponding to the terminal equipment belongs and a threshold value of a main feature corresponding to the user group according to the power consumption model of the first application;

Detecting whether the power consumption of the first application is abnormal or not according to the threshold value of the main characteristic and the numerical value of the main characteristic in the power consumption data of the first application, and obtaining a power consumption detection result of the first application;

executing corresponding operation according to the power consumption detection result of the first application;

The power consumption model of the first application includes: the method comprises the steps of determining an auxiliary characteristic condition and a threshold value of a main characteristic corresponding to at least one user group, wherein the auxiliary characteristic condition is used for determining the user group to which a user belongs;

the determining, according to the power consumption model of the first application, a user group to which the user corresponding to the terminal device belongs and a threshold value of a main feature corresponding to the user group includes:

Determining a user group to which a user corresponding to the terminal equipment belongs according to the auxiliary characteristic condition and the value of the auxiliary characteristic in the power consumption data of the first application;

And determining the threshold value of the main characteristic corresponding to the user group corresponding to the terminal equipment according to the threshold value of the main characteristic corresponding to the at least one user group and the user group corresponding to the user corresponding to the terminal equipment.

2. The method according to claim 1, characterized in that the power consumption model of the first application is in particular a power consumption model of a first application of a first product family to which the terminal device belongs.

3. The method according to claim 1, wherein detecting whether the power consumption of the first application is abnormal according to the threshold value of the main feature and the value of the main feature in the power consumption data of the first application, to obtain the power consumption detection result of the first application, includes:

when the value of the main characteristic is larger than or equal to the threshold value of the main characteristic, determining that the power consumption of the first application is abnormal, wherein the power consumption detection result of the first application is used for indicating that the power consumption of the first application is abnormal;

And when the value of the main characteristic is smaller than the threshold value of the main characteristic, determining that the power consumption of the first application is normal, wherein the power consumption detection result of the first application is used for indicating that the power consumption of the first application is normal.

4. The method of claim 1, wherein the threshold of the primary feature comprises: a first threshold, a second threshold, and a third threshold, the first threshold being less than the second threshold and the second threshold being less than the third threshold;

and detecting whether the power consumption of the first application is abnormal according to the threshold value of the main characteristic and the numerical value of the main characteristic in the power consumption data of the first application to obtain a power consumption detection result of the first application, wherein the power consumption detection result comprises:

when the value of the main feature is larger than or equal to the first threshold value and smaller than the second threshold value, determining that the power consumption abnormality of the first application is a first abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the first abnormality level;

When the value of the main feature is larger than or equal to the second threshold value and smaller than the third threshold value, determining that the power consumption abnormality of the first application is a second abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the second abnormality level;

When the value of the main characteristic is larger than or equal to the third threshold value, determining that the power consumption abnormality of the first application is a third abnormality level, wherein the power consumption detection result of the first application is used for indicating that the level of the power consumption abnormality of the first application is the third abnormality level;

And when the value of the main characteristic is smaller than the first threshold value, determining that the power consumption of the first application is normal, wherein the power consumption detection result of the first application is used for indicating that the power consumption of the first application is normal.

5. The method of claim 4, wherein the first application has different levels of power consumption anomalies and the terminal device performs different corresponding operations.

6. The method according to any one of claims 1-5, further comprising:

Sending a power consumption model acquisition request to the cloud;

a power consumption model of the first application from the cloud is received.

7. The method according to any one of claims 1-5, wherein after the collecting the power consumption data of the terminal device, further comprising:

And sending the power consumption data of the terminal equipment to a data platform.

8. The power consumption processing method of the terminal equipment is characterized by being applied to a cloud end, and comprises the following steps:

Acquiring power consumption data of at least one terminal device from a data platform; the power consumption data comprise power consumption data of at least one application, a first application is contained in the at least one application, and the power consumption model comprises a power consumption model of the first application; the power consumption model of the first application is specifically a power consumption model of the first application of the first product series;

training to obtain a power consumption model according to the power consumption data of the at least one terminal device;

receiving a power consumption model acquisition request from a terminal device;

transmitting the power consumption model to the terminal equipment;

training a power consumption model of a first application resulting in the first product family, comprising:

Acquiring a correlation coefficient of a main feature and each other feature according to power consumption data of a first application of the terminal equipment of the first product series in a preset time period;

determining auxiliary features according to the correlation coefficients of the main features and each other feature;

Acquiring an auxiliary characteristic condition according to the power consumption data of the first application of the terminal equipment of the first product series in the preset time period and the auxiliary characteristic, wherein the auxiliary characteristic condition is used for determining a user group to which a user belongs;

dividing the users corresponding to the at least one terminal device into at least two user groups according to the auxiliary characteristic conditions and the power consumption data of the first application of the terminal device of the first product series in the preset time period;

determining a threshold value of a main characteristic corresponding to each user group according to power consumption data of a first application of terminal equipment of a first product series in preset time of each user group, wherein the threshold value of the main characteristic is used for detecting whether power consumption of the first application is abnormal or not;

And generating a power consumption model of the first application of the first product series according to the auxiliary characteristic conditions and the threshold value of the main characteristic corresponding to each user group.

9. The method of claim 8, wherein the correlation coefficient of the main feature with each of the other features comprises Pearson correlation coefficient and Spearman correlation coefficient;

and determining auxiliary features according to the correlation coefficient of the main feature and each other feature, wherein the method comprises the following steps:

Taking the features which are larger than or equal to the Pearson correlation coefficient threshold and larger than or equal to the Spearman correlation coefficient threshold as first candidate auxiliary features;

And determining the auxiliary feature according to the first candidate auxiliary feature.

10. The method of claim 9, wherein the determining the secondary feature from the first candidate secondary feature comprises:

11. The method of claim 10, wherein said determining said secondary feature from said second candidate secondary feature comprises:

Obtaining an importance value of each second candidate auxiliary feature according to the minimum absolute shrinkage and the selection model;

And taking the second candidate auxiliary feature ranked in the top N as the auxiliary feature, wherein the N is equal to the quantity threshold value.

12. The method according to any one of claims 8-11, wherein the obtaining the secondary feature condition according to the power consumption data of the first application of the terminal device of the first product family and the secondary feature in the preset period of time includes:

Training a classification and regression tree CART according to the auxiliary characteristics and the power consumption data of the first application of the terminal equipment of the first product series in the preset time period;

and taking the leaf nodes in the CART as the auxiliary characteristic conditions.

13. The method according to any one of claims 8-11, wherein determining the threshold value of the main feature corresponding to each user group according to the power consumption data of the first application of the terminal device of the first product line within the preset time of each user group comprises:

And determining the threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and the first preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group.

14. The method of claim 13, wherein the threshold of the main feature corresponding to each user group determined based on the first preset ratio is a first threshold; the method further comprises the steps of:

Determining a second threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and a second preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group;

And determining a third threshold value of the main characteristic corresponding to each user group according to the numerical value of the main characteristic and a third preset proportion in the power consumption data of the first application of the terminal equipment of the first product series within the preset time of each user group, wherein the first preset proportion is smaller than the second preset proportion, the second preset proportion is smaller than the third preset proportion, and the first threshold value, the second threshold value and the third threshold value are used for determining the level of power consumption abnormality of the first application.

15. A terminal device, comprising: a processor and a memory;

the memory stores computer-executable instructions;

the processor executing computer-executable instructions stored in the memory to cause the terminal device to perform the method of any one of claims 1-7.

16. An electronic device, comprising: a processor and a memory;

the memory stores computer-executable instructions;

the processor executing computer-executable instructions stored in the memory to cause the electronic device to perform the method of any one of claims 8-14.

17. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1-14.