KR102650678B1 - Device control apparatus and method for controlling an inactive mode of a device - Google Patents

Abstract

Measure the charging point at which the device's charging state begins, measure the charging time interval from the charging point to the interruption point at which the charging state ceases, assign a charging weight when the charging time interval exceeds a threshold, and determine different Provided is a device control device that creates an inactivity period model by learning a plurality of charging weights assigned at a point in time, and sets the device to an inactivity mode based on the inactivity period model.

Description

DEVICE CONTROL APPARATUS AND METHOD FOR CONTROLLING AN INACTIVE MODE OF A DEVICE}

The present invention relates to a device control apparatus and method for controlling an inactive mode of a device, and more specifically, to a device control apparatus and method for controlling an inactive mode of a device according to an activity pattern of the device.

In addition to regular computers used in fixed locations, easily portable mobile smart devices are being widely used. Unlike regular computers, smart devices such as smartphones are limited by memory size. To compensate for these limitations, much research has been conducted on memory management techniques for smartphones. However, existing studies only used simple information such as the number of times an application was used as a variable in the memory management algorithm.

However, moving data from memory to a secondary storage device and reloading data from the secondary storage device to memory takes a considerable amount of time. These times have a significant impact on the responsiveness of the device to the user. Therefore, when memory is insufficient, it is very important to decide which part of the memory to move to a secondary storage device to secure free memory space.

The technical problem to be solved by the present invention is to provide a device control device and method for controlling the inactive mode of a device by learning a period during which the device is in an inactive state and controlling the device to be in an inactive mode during the learned period.

One aspect of the present invention provides a device control device for controlling an inactive mode of a device, comprising: a detection unit for detecting a charging state of the device; a timer unit that measures a charging point in time when the charging state begins and measures a charging time interval from the charging point to an interruption point in which the charging state is discontinued; When the charging time interval exceeds a threshold, a charging weight is assigned to the period from the charging time to the charging time interval, and learning of a plurality of charging weights assigned at different time points creates an inactivity period model. wealth; and a control unit that sets the device to an inactive mode based on the inactive period model.

In addition, the learning unit assigns different charging weights depending on the length of the charging time interval. The longer the charging time interval, the larger the charging weight, and the shorter the charging time interval, the smaller the charging weight. It can be granted.

In addition, the detection unit detects the memory activity state of the device, and the timer unit measures an idle point in time at which the memory activity state is detected to be below the threshold, and from the idle point in time, detects the memory activity state to be above the threshold. You can measure the idle time interval up to the point where it becomes active.

In addition, when the idle time interval exceeds the threshold, the learning unit assigns an idle weight to the period from the idle time to the idle time interval, and further learns a plurality of idle weights assigned at different time points to You can create a model of periods of inactivity.

Additionally, the learning unit may generate the inactive period model so that control of the inactive mode is repeated according to a first time period and a second time period that is longer than the first time period.

Another aspect of the present invention is a device control method in a device control apparatus for controlling an inactive mode of a device, comprising: a detection unit detecting a charging state of the device; A timer unit measuring a charging point at which the charging state begins, and measuring a charging time interval from the charging point to an interruption point at which the charging state is stopped; When the charging time interval exceeds the threshold, the learning unit assigns a charging weight to the period from the charging time to the charging time interval, and generates an inactivity period model by learning a plurality of charging weights assigned at different time points. steps; and setting the device to an inactive mode by the control unit based on the inactive period model.

In addition, the learning unit assigns different charging weights depending on the length of the charging time interval. The longer the charging time interval, the larger the charging weight, and the shorter the charging time interval, the smaller the charging weight. It can be granted.

In addition, the detection unit detects the memory activity state of the device, and the timer unit measures an idle point in time at which the memory activity state is detected to be below the threshold, and from the idle point in time, detects the memory activity state to be above the threshold. You can measure the idle time interval up to the point where it becomes active.

In addition, when the idle time interval exceeds the threshold, the learning unit assigns an idle weight to the period from the idle time to the idle time interval, and further learns a plurality of idle weights assigned at different time points to You can create a model of periods of inactivity.

Additionally, the learning unit may generate the inactive period model so that control of the inactive mode is repeated according to a first time period and a second time period that is longer than the first time period.

According to one aspect of the present invention described above, by providing a device control apparatus and method for controlling an inactive mode of a device, it is possible to learn a period in which the device is in an inactive state and control the device in an inactive mode during the learned period. there is.

1 is a schematic diagram of a device control system including a device control device according to an embodiment of the present invention.
Figure 2 is a control block diagram of a device control device according to an embodiment of the present invention.
Figures 3 to 5 are block diagrams showing a process for measuring time intervals in the timer unit of Figure 2.
Figure 6 is a block diagram showing the process of generating an inactivity period model in the learning unit of Figure 2.
Figure 7 is a block diagram showing a process in which the control unit of Figure 2 controls the device in an inactive mode.
Figure 8 is a flowchart of a device control method according to an embodiment of the present invention.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented in one embodiment without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

1 is a schematic diagram of a device control system including a device control device according to an embodiment of the present invention.

The device control system 1 may be configured so that the device control apparatus 100 learns the state of the device 200 and sets the device 200 to an inactive mode.

Here, the device 200 may refer to a user terminal device such as a smartphone, tablet, or laptop. Accordingly, the state of the device 200 is the charging state of the device 200 by the charging device 203, the device It may mean the memory activity state of 200, input from the user through the input device 201, etc.

At this time, the charging device 203 may be provided to charge the battery of the device 200, and the input device 201 may be provided to allow the device 200, such as a keyboard, mouse, or touch pad, to receive commands from the user. It may be possible.

Accordingly, the device control apparatus 100 may detect the state of the device 200 and set the device 200 to an inactive mode when the state of the device 200 is in an inactive state.

Here, the inactive state may mean an idle state of the device 200. In other words, the inactive state may mean a state in which the user does not operate the device 200.

Accordingly, the inactive mode may mean a control mode that can be performed while the device 200 is inactive. For example, the inactive mode is a power saving mode that reduces the power consumption of the device 200, and the device 200 ) may mean a firmware update mode, an update mode such as an application installed on the device 200, a memory organization mode provided in the device 200, etc.

In one embodiment, the inactive mode may mean a mode such as learning cache memory collected while the device 200 is in an active mode.

Hereinafter, the device control apparatus 100 according to an embodiment of the present invention will be described in detail.

Figure 2 is a control block diagram of a device control device according to an embodiment of the present invention.

The device control apparatus 100 may include a detection unit 110, a timer unit 120, a learning unit 130, and a control unit 140.

Additionally, the device control apparatus 100 may be implemented with more components than those shown in FIG. 2 or may be implemented with fewer components. Alternatively, the device control apparatus 100 may integrate at least two components provided in the device control apparatus 100 into one component, so that one component may perform a complex function. Hereinafter, the above-described components will be described in detail.

The detection unit 110 can detect the state of the device 200. For example, the detector 110 may detect the charging state of the device 200, and the detector 110 may also detect the memory activity state of the device 200.

Here, the memory activity state may mean the memory usage of the device 200.

The timer unit 120 may extract time information indicating an arbitrary point in time. In this case, the timer unit 120 may extract time information based on the current time.

Here, the current time may include time in units of hours, minutes, and seconds, and the current time may also include time in units of years, months, and days.

Additionally, the timer unit 120 can measure the time interval from an arbitrary point in time to another arbitrary point in time.

Accordingly, the timer unit 120 can measure the charging point when the charging state begins, and the timer unit 120 can measure the charging time interval from the charging point to the interruption point when the charging state is stopped.

The learning unit 130 may generate an inactivity period model using artificial intelligence (AI) techniques such as machine learning.

Here, machine learning can be understood as a technique for generating a learning model based on a plurality of information to classify the plurality of information into one or more groups, and classifying arbitrary information based on the generated learning model. Likewise, machine learning is supervised learning, which creates a learning model so that arbitrary information can be classified according to a plurality of information classified by an administrator, analyzes the plurality of information itself, or performs a clustering process to create a learning model. Unsupervised learning that generates, semi-supervised learning that creates a learning model by mixing supervised learning and unsupervised learning, and compensation generated in the process of performing random actions on a plurality of pieces of information. It may include reinforcement learning, which creates a learning model depending on the method.

Accordingly, a period of inactivity model may be created to represent a period of time during which the device 200 is in an inactive state, in other words, the period of inactivity model may be created to represent a time period during which the device 200 is set to an inactive state. It can be.

In one embodiment, the learning unit 130 may generate an inactivity period model based on unsupervised learning. To this end, the learning unit 130 clusters charging points and charging time intervals generated at different times. This allows you to create a model for periods of inactivity.

As such, the inactivity period model can be created by continuously clustering time information and time intervals extracted or measured while the user operates the device 200.

At this time, the inactivity period model may be created adaptively to the user's device 200 operation pattern by assigning a lower weight to information generated in the past and a higher weight to information generated more recently.

Additionally, the inactivity period model may be created by weighting the time information extracted or measured by the timer unit 120 and the importance of the time interval.

In this regard, in one embodiment, the learning unit 130 may assign a charging weight to the period from the charging point to the charging time interval when the charging time interval exceeds the threshold, and the learning unit 130 may An inactivity period model can be created by learning multiple charging weights assigned at different points in time.

At this time, the learning unit 130 may assign different charging weights depending on the length of the charging time interval. For example, the learning unit 130 may assign a larger charging weight as the length of the charging time interval is longer. , the learning unit 130 may assign a smaller charging weight as the length of the charging time interval is shorter.

The control unit 140 may set the device 200 to an inactive mode based on the inactivity period model. At this time, the control unit 140 may extract the time zone set to the inactive state from the inactivity period model, and if the current time corresponds to the extracted time zone, the control unit 140 may set the device 200 to the inactive mode. It can be set to .

Figures 3 to 5 are block diagrams showing a process for measuring time intervals in the timer unit of Figure 2.

Referring to Figure 3, the detection unit 110 can detect the charging state of the device 200. At this time, the detection unit 110 may detect the charging state of the device 200 by detecting the charging power input to the charging module 210 of the device 200.

Alternatively, the detection unit 110 may be provided to receive a signal indicating the charging state from the charging module 210 of the device 200.

Accordingly, the timer unit 120 can measure the charging point when the charging state begins, and the timer unit 120 can measure the charging time interval from the charging point to the interruption point when the charging state is stopped.

Meanwhile, referring to Figure 4, the detection unit 110 can detect the memory activity state of the device 200. At this time, the detection unit 110 may detect the memory activity state by measuring the memory usage of the memory module 220 of the device 200.

Alternatively, the detection unit 110 may be configured to receive information indicating memory usage from the memory module 220 and detect the memory activity state.

Accordingly, the timer unit 120 can measure the idle time when the memory activity state is detected as less than the threshold, and the timer unit 120 can measure the idle time interval from the idle time to the time when the memory activity state is detected as more than the threshold. can be measured.

For example, the timer unit 120 may extract the time interval at which the memory activity state is detected as less than 10 percent as the idle time, and the timer unit 120 may extract the time interval at which the memory activity state is detected as less than 10 percent as the idle time point. It can be measured at time intervals.

Meanwhile, referring to Figure 5, the detection unit 110 can detect a command input to the device 200 from the user. At this time, the detection unit 110 may detect a command of the device 200 by detecting a signal input to the input module 230 of the device 200.

Accordingly, the timer unit 120 can measure the input waiting time interval from the time when the last command was input to the time when a new command is input. Accordingly, the timer unit 120 can measure the input waiting time interval. If the preset threshold time interval is exceeded, the first input point of the corresponding input waiting time interval can be extracted.

Meanwhile, the detection unit 110 may detect signals such as sleep mode and flight mode provided from the device 200. Accordingly, when the detection unit 110 detects signals such as sleep mode or flight mode provided from the device 200, the timer unit 120 can measure the time interval at which each mode is set.

Figure 6 is a block diagram showing the process of generating an inactivity period model in the learning unit of Figure 2.

Referring to Figure 6, the learning unit 130 may assign a charging weight to the period from the charging time to the charging time interval when the charging time interval exceeds the threshold, and the learning unit 130 may assign charging weights to the period from the charging time interval to the charging time interval. An inactivity period model can be created by learning a plurality of assigned charging weights.

At this time, the learning unit 130 may assign different charging weights depending on the length of the charging time interval. For example, the learning unit 130 may assign a larger charging weight as the length of the charging time interval is longer. , the learning unit 130 may assign a smaller charging weight as the length of the charging time interval is shorter.

Accordingly, the learning unit 130 may generate an inactive period model based on charging weights assigned to different periods.

For example, the learning unit 130 may extract a period in which the size of the charging weight assigned to each period exceeds a preset threshold ratio based on the largest charging weight among the charging weights assigned to different periods. there is. In this case, the learning unit 130 may create an inactivity period model to represent the extracted period.

In addition, when the idle time interval exceeds the threshold, the learning unit 130 may assign an idle weight to the period from the idle time to the idle time interval, and the learning unit 130 may assign an idle weight to the period from the idle time interval to the idle time interval. By further learning the idle weights, a model for periods of inactivity can be created.

At this time, the learning unit 130 may assign different idle weights depending on the length of the idle time interval. For example, the learning unit 130 may assign a larger idle weight as the length of the idle time interval is longer. , the learning unit 130 may assign a smaller idle weight as the length of the idle time interval is shorter.

Accordingly, the learning unit 130 may generate an inactive period model based on the idle weights assigned to different periods.

For example, the learning unit 130 may extract a period in which the size of the idle weight assigned to each period exceeds a preset threshold ratio based on the largest idle weight among the idle weights assigned to different periods. there is. In this case, the learning unit 130 may create an inactivity period model to represent the extracted period.

Additionally, if the input waiting time interval exceeds the threshold, the learning unit 130 may assign an input waiting weight to the period from the initial input time to the input waiting time interval, and the learning unit 130 may assign an input waiting weight to the period from the initial input time to the input waiting time interval. An inactivity period model can be created by further learning the plurality of assigned input waiting weights.

At this time, the learning unit 130 may assign different input waiting weights depending on the length of the input waiting time interval. For example, the learning unit 130 may assign a larger input waiting weight as the length of the input waiting time interval is longer. The learning unit 130 can assign a smaller input waiting weight as the length of the input waiting time interval is shorter.

Accordingly, the learning unit 130 may generate an inactive period model based on the input waiting weights assigned to different periods.

For example, the learning unit 130 determines a period in which the size of the input waiting weight assigned to each period exceeds a preset threshold ratio, based on the largest input waiting weight among the input waiting weights assigned to different periods. It can be extracted. In this case, the learning unit 130 may create an inactivity period model to represent the extracted period.

Meanwhile, the learning unit 130 may generate an inactivity period model by complexly considering at least one of the charging weight, the idle weight, and the input waiting weight.

In this regard, in one embodiment, the learning unit 130 may generate a comprehensive weight based on the charging weight, idle weight, and input waiting weight assigned to each period, and in this case, the learning unit 130 Based on the largest overall weight among the overall weights assigned to different periods, the period in which the size of the overall weight assigned to each period exceeds a preset threshold ratio can be extracted. In this case, the learning unit 130 may create an inactivity period model to represent the extracted period.

At this time, the learning unit 130 may generate a comprehensive weight by multiplying the charging weight, the idle weight, and the input standby weight assigned to each period, or the learning unit 130 may generate a comprehensive weight by multiplying the charging weight and the idle weight assigned to each period. A composite weight can also be created by adding the weight and the input waiting weight.

In this regard, the learning unit 130 may set the charging weight, the idle weight, and the input waiting weight to different weights. For example, the learning unit 130 may set the charging weight, the input waiting weight, and the charging weight in that order. The weight value can be set large.

In addition, when the learning unit 130 detects signals such as sleep mode and flight mode provided from the device 200 in the timer unit 120, and when the time interval for setting each mode is measured, each mode You can also create an inactivity period model by setting weights according to .

Meanwhile, the learning unit 130 may generate an inactive period model to be repeated according to a preset time period. In this case, the learning unit 130 may create an inactive period model to be repeated according to a plurality of different time periods. can be created.

Specifically, the learning unit 130 may generate an inactivity period model so that control of the inactivity mode is repeated according to a first time period and a second time period that is longer than the first time period.

In one embodiment, the learning unit 130 may generate an inactivity period model such that control of the inactivity mode is repeated according to a first time period of 24 hour intervals and a second time period of a week interval.

In this case, the learning unit 130 may generate an inactivity period model based on one or more weights generated during a 24-hour period, and the learning unit 130 may divide the one or more weights generated during a week into 24-hour intervals. You can compare the patterns of one or more divided weights. Accordingly, the learning unit 130 can generate the same inactivity period model when the similarity of the weight pattern is within the critical range, and the learning unit 130 can generate the same inactivity period model when the similarity of the weight pattern is outside the critical range. Based on those weights, different inactivity period models can be created.

Figure 7 is a block diagram showing a process in which the control unit of Figure 2 controls the device in an inactive mode.

Referring to Figure 7, the learning unit 130 may generate an inactivity period model to indicate a period during which the device 200 is in an inactive state, and accordingly, the control unit 140 may generate an inactivity period model based on the inactivity period model. The device 200 may be set to an inactive mode.

At this time, the control unit 140 may extract the time zone set to the inactive state from the inactivity period model, and if the current time corresponds to the extracted time zone, the control unit 140 may set the device 200 to the inactive mode. It can be set to .

In one embodiment, the control unit 140 performs tasks such as removing cache accumulated in the cache memory of the memory module 220 of the device 200 or extracting a cache whose usage frequency is more than a threshold frequency in an inactive mode. The device 200 may be controlled to do so.

Figure 8 is a flowchart of a device control method according to an embodiment of the present invention.

Since the device control method according to an embodiment of the present invention is carried out on substantially the same configuration as the device control apparatus 100 shown in FIG. 1, the same reference numerals refer to the same components as the device control apparatus 100 shown in FIG. 1. will be given, and repeated explanations will be omitted.

The device control method includes detecting the charging state of the device (800), measuring the charging point and measuring the charging time interval (810), assigning a charging weight to the period up to the charging time interval, and learning the charging weight. This may include generating an inactivity period model (820) and setting the device to an inactivity mode based on the inactivity period model (830).

The step 800 of detecting the charging state of the device may be a step in which the detection unit 110 detects the charging state of the device 200.

In the step 810 of measuring the charging point and measuring the charging time interval, the timer unit 120 measures the charging point when the charging state begins, and measures the charging time interval from the charging point to the stopping point when the charging state is stopped. This may be a measurement step.

In the step 820 of assigning a charging weight to the period up to the charging time interval and learning the charging weight to create an inactivity period model, the learning unit 130 performs charging from the charging point when the charging time interval exceeds the threshold. This may be a step of assigning a charging weight to the period up to the time interval and learning a plurality of charging weights assigned at different points in time to create an inactivity period model.

Step 830 of setting the device to the inactive mode based on the inactive period model may be a step in which the control unit 140 sets the device 200 to the inactive mode based on the inactive period model.

Such a device control method may be implemented as an application or in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination.

The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention, or may be known and usable by those skilled in the computer software field.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc.

Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

Although the above has been described with reference to embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the following patent claims. You will be able to.

1: Device control system
100: device control device
200: device
201: input device
203: Charging device

Claims (10)

In the device control device for controlling the inactivity mode of the device,
A detection unit that detects the charging state of the device;
a timer unit that measures a charging point in time when the charging state begins and measures a charging time interval from the charging point to an interruption point in which the charging state is discontinued;
When the charging time interval exceeds the threshold, a charging weight is assigned to the period from the charging point to the charging time interval, and different charging weights are assigned depending on the length of the charging time interval. A learning unit that assigns a larger charging weight as the length is longer, assigns a smaller charging weight as the length of the charging time interval is shorter, and generates an inactivity period model by learning a plurality of charging weights assigned at different points in time;
It includes a control unit that sets the device to an inactive mode based on the inactivity period model,
The sensing unit,
Detect the memory activity state of the device,
The timer unit,
Measuring an idle point in time when the memory activity state is detected as being below a threshold, and measuring an idle time interval from the idle point in time to a point in time when the memory activity state is detected as being above the threshold,
The learning department,
If the idle time interval exceeds a threshold, an idle weight is assigned to the period from the idle time to the idle time interval,
Different idle weights are given depending on the length of the idle time interval, where a larger idle weight is given as the length of the idle time interval is longer, and a smaller idle weight is given as the length of the idle time interval is shorter, and at different times. A device control device that generates the inactivity period model by further learning a plurality of idle weights assigned from .
delete delete delete The method of claim 1, wherein the learning unit,
A device control apparatus that generates the inactive period model so that control of the inactive mode is repeated respectively according to a first time period and a second time period longer than the first time period.
In a device control method in a device control apparatus for controlling an inactive mode of a device,
A detection unit detecting the charging state of the device;
A timer unit measuring a charging point at which the charging state begins, and measuring a charging time interval from the charging point to an interruption point at which the charging state is stopped;
When the charging time interval exceeds a threshold, the learning unit assigns a charging weight to the period from the charging point to the charging time interval, and assigns different charging weights depending on the length of the charging time interval, assigning a larger charging weight as the length of the interval is longer, assigning a smaller charging weight as the length of the charging time interval is shorter, and generating an inactivity period model by learning a plurality of charging weights assigned at different time points;
A control unit setting the device to an inactivity mode based on the inactivity period model,
The sensing unit,
Detect the memory activity state of the device,
The timer unit,
Measuring an idle point in time when the memory activity state is detected as being below a threshold, and measuring an idle time interval from the idle point in time to a point in time when the memory activity state is detected as being above the threshold,
The learning department,
When the idle time interval exceeds the threshold, an idle weight is assigned to the period from the idle time to the idle time interval, and different idle weights are assigned depending on the length of the idle time interval. A device that assigns a larger idle weight as the length is longer, assigns a smaller idle weight as the length of the idle time interval is shorter, and generates the inactivity period model by further learning a plurality of idle weights assigned at different time points. Control method.
delete delete delete The method of claim 6, wherein the learning unit,
A device control method for generating the inactive period model so that control of the inactive mode is repeated respectively according to a first time period and a second time period longer than the first time period.

Images