KR102446901B1 - Apparatus and method for power analysis of home appliances - Google Patents

Abstract

The present invention provides a power analysis method of a home appliance, the method comprising the steps of: obtaining power data sets for a plurality of home appliances; Predicting individual power usage results of the plurality of home appliances by inputting the acquired power data set into the model, and on/off of the plurality of home appliances determined based on the individual power usage results of the plurality of home appliances and providing a power monitoring interface comprising status data.

Description

Apparatus and method for home appliance power analysis

The present invention relates to a home appliance power analysis apparatus and method.

In general, a power management system may monitor the operating state of various power devices used in industries or houses. Based on the monitoring information, the power management system may detect whether abnormal situations that may cause power accidents such as blackouts, overcurrents, wire overloads, and fires occur during power usage, or may provide a service for monitoring power usage. Accordingly, users can take quick action when an abnormal situation occurs, and they can prevent excessive power use by recognizing the increase in power consumption through power usage monitoring. .

On the other hand, in order to monitor the operating state and power usage of power devices (hereinafter referred to as electrical devices), a technique for installing individual energy measuring devices/sensors for each home appliance has been conventionally used, but the limitation of the installation space and the increased investment in facilities there is

The description underlying the invention has been prepared to facilitate understanding of the invention. It should not be construed as an admission that the matters described in the background technology of the invention exist as prior art.

Accordingly, a method of installing a power measuring device at the power entry point and collecting and analyzing it by the server was used, but only in this way, the characteristics of home appliances (eg, power consumption according to the release year of refrigerators of a specific manufacturer) and home appliances were used. In order to reflect the characteristics of device consumers (eg, changes in power consumption depending on the presence or absence of unusual home appliances), there is a cumbersome aspect of continuously acquiring power usage data of various individual home appliances.

Accordingly, there is a need for a new method for predicting individual power consumption of a plurality of home appliances without a sensor (measuring device) connected to the home appliance.

As a result, the inventors of the present invention predict individual power usage results of a plurality of home appliances through a machine-learning model on one power data set in which the usage of a plurality of home appliances is combined, and analyze the predicted results. An attempt was made to develop a method and an apparatus for performing the same.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the problems as described above, there is provided a power analysis method of a home appliance according to an embodiment of the present invention. The method includes the steps of: obtaining a power data set for a plurality of home appliances; inputting the obtained power data set to a power amount prediction model trained to predict a power usage result for each home appliance by inputting the power data set as an input; Predicting individual power usage results of a plurality of home appliances, providing a power monitoring interface including individual power usage results of the plurality of home appliances and on/off state data of the plurality of home appliances determined based on the results is configured to include

According to a feature of the present invention, the power monitoring interface may include an area in which a graph of power usage over time of the home appliance is displayed in relation to the individual power usage result.

According to another feature of the present invention, the step of providing the power monitoring interface may further include determining an on/off time point in the individual power usage results of the plurality of home appliances based on a preset threshold value. .

According to another feature of the present invention, the power monitoring interface may include an area in which at least one of an on/off time point of the plurality of home appliances, an operation time for each function, and a power usage prediction result for a preset period is displayed. can

According to another feature of the present invention, by inputting the individual power usage results of the plurality of home appliances to the inspection model learned to predict the abnormal results of the home appliances by inputting the power usage results as input, any one of the plurality of home appliances The method may further include predicting an abnormal result for one home appliance.

According to another feature of the present invention, the power monitoring interface may be configured to display abnormal results for any one of the plurality of home appliances on the power usage graph.

According to another feature of the present invention, the abnormal result may include whether the usage of each of the plurality of home appliances is exceeded or whether there is a failure.

According to another feature of the present invention, the power amount prediction model may be configured to extract individual features of the plurality of home appliances from the power data set through a convolutional layer.

According to another feature of the present invention, the power amount prediction model further includes a sub-layer consisting of a recurrent layer and a recurrent-skip layer, the recurrent layer and the recurrent layer - The skip layer may be configured to determine a time interval related to an off state in at least one home appliance among the plurality of home appliances based on the extracted feature.

According to another feature of the present invention, the obtaining of the power data set may include obtaining a filtered power data set based on a preset minimum value or a noise feature for each household appliance.

In order to solve the problems as described above, a power analysis apparatus according to another embodiment of the present invention is provided. The apparatus includes a communication interface, a memory, and a processor operatively coupled to the communication interface and the memory, the processor to obtain power data sets for a plurality of home appliances and receive the power data sets as inputs to the home appliances. By inputting the acquired power data set into the power amount prediction model trained to predict the power usage result for each device, the individual power usage result of the plurality of home appliances is predicted, and the individual power usage result of the plurality of home appliances and the result based on it and provide a power monitoring interface including the determined on/off state data of the plurality of home appliances.

The details of other embodiments are included in the detailed description and drawings.

The present invention can predict the current power usage and future power usage of the home appliance without a sensor (measuring device) individually connected to the home appliance through a machine-learning power consumption prediction model of the power usage of various home appliances. In particular, the present invention can reduce the cost and time for installing a sensor (measuring device) at home and further in the city to predict the power usage, and for maintenance.

In addition, the present invention extracts a feature of a home appliance according to a preset time unit from a power data set and calculates it through an RNN-based GRU model, so that it is possible to quickly and accurately predict the power usage result of a plurality of home appliances.

In addition, the present invention provides the current operating state, future operating state (eg, on/off time, operation time for each function) of home appliances based on the results predicted through the wattage prediction model, and abnormal signs (eg, abnormal usage, excessive, malfunction) ) can be predicted.

In addition, the present invention provides a monitoring interface that can check the power consumption of home appliances at a glance, so that each home and power consumer can use power more efficiently.

In addition, the present invention can reduce the load of a device for processing a large amount of power data set by removing micro-current and noise from the power data set.

The effect according to the present invention is not limited by the contents exemplified above, and more various effects are included in the present invention.

1 is a schematic diagram of a home appliance power analysis system according to an embodiment of the present invention.
2 is a block diagram illustrating a configuration of a user device according to an embodiment of the present invention.
3 is a block diagram showing the configuration of a power analysis apparatus according to an embodiment of the present invention.
4 is a flowchart of a method for analyzing power of a home appliance according to an embodiment of the present invention.
5 is a schematic diagram for explaining a pre-processing of a power data set according to an embodiment of the present invention.
6 is a schematic diagram illustrating a power amount prediction model according to an embodiment of the present invention.
7 is a schematic diagram for explaining a hierarchical structure of a power amount prediction model according to an embodiment of the present invention.
8 is a schematic diagram illustrating a power monitoring interface screen provided to a user device according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be embodied in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, like reference numerals may be used for like components.

In this document, expressions such as "has," "may have," "includes," or "may include" refer to the presence of a corresponding characteristic (eg, a numerical value, function, operation, or component such as a part). and does not exclude the presence of additional features.

In this document, expressions such as "A or B," "at least one of A or/and B," or "one or more of A or/and B" may include all possible combinations of the items listed together. . For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) includes at least one A, (2) includes at least one B; Or (3) it may refer to all cases including both at least one A and at least one B.

As used herein, expressions such as "first," "second," "first," or "second," may modify various elements, regardless of order and/or importance, and refer to one element. It is used only to distinguish it from other components, and does not limit the components. For example, the first user equipment and the second user equipment may represent different user equipment regardless of order or importance. For example, without departing from the scope of the rights described in this document, the first component may be named as the second component, and similarly, the second component may also be renamed as the first component.

A component (eg, a first component) is "coupled with/to (operatively or communicatively)" to another component (eg, a second component) When referring to "connected to", it should be understood that the certain element may be directly connected to the other element or may be connected through another element (eg, a third element). On the other hand, when it is said that a component (eg, a first component) is "directly connected" or "directly connected" to another component (eg, a second component), the component and the It may be understood that other components (eg, a third component) do not exist between other components.

As used herein, the expression "configured to (or configured to)" depends on the context, for example, "suitable for," "having the capacity to ," "designed to," "adapted to," "made to," or "capable of." The term “configured (or configured to)” may not necessarily mean only “specifically designed to” in hardware. Instead, in some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts. For example, the phrase "a processor configured (or configured to perform) A, B, and C" refers to a dedicated processor (eg, an embedded processor) for performing the operations, or by executing one or more software programs stored in a memory device. , may mean a generic-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

Terms used in this document are only used to describe specific embodiments, and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meanings as commonly understood by one of ordinary skill in the art described in this document. Among the terms used in this document, terms defined in a general dictionary may be interpreted with the same or similar meaning to the meaning in the context of the related art, and unless explicitly defined in this document, ideal or excessively formal meanings is not interpreted as In some cases, even terms defined in this document cannot be construed to exclude embodiments of the present document.

Each feature of the various embodiments of the present invention may be partially or wholly combined or combined with each other, and as those skilled in the art will fully understand, technically various interlocking and driving are possible, and each embodiment may be independently implemented with respect to each other. It may be possible to implement together in a related relationship.

For clarity of interpretation of the present specification, terms used herein will be defined below.

1 is a schematic diagram of a home appliance power analysis system according to an embodiment of the present invention.

Referring to FIG. 1 , a home appliance power analysis system 1000 (hereinafter, a power analysis system) may include a user device 100 , a plurality of home appliances 200 , and a power analysis apparatus 300 .

The user device 100 is a device of a user who uses and manages a plurality of home appliances 200 , and may include various electronic devices such as a smart phone, a tablet PC, and a PC.

A web/app application provided by the power analysis apparatus 300 may be installed or executed on the user device 100 , and power monitoring for monitoring the power consumption of the plurality of home appliances 200 through the web/app application The interface screen can be displayed.

The user device 100 provides user identification information or identification information of a power consumer to the power analysis apparatus 300 , and turns on/off the plurality of home appliances 200 through the power monitoring interface provided from the power analysis apparatus 300 . It is possible to control off, check whether the home appliance 200 is abnormal, future power usage, and the like.

In various embodiments, the user device 100 provides a photographed image of the central power measurement device 250 in which the total power usage can be checked according to a photographing guideline provided by the power monitoring interface, or is measured by the central power measurement apparatus 250 . It is possible to obtain and provide the total amount of power used.

The plurality of home appliances 200 may include various types of home appliances installed and usable at home, such as an air conditioner 201 , a refrigerator 202 , a TV 203 , a computer 204 , and an induction 205 . Specifically, the user device 100 may add or exclude the home appliance 200 for monitoring power usage in addition to the home appliance 200 illustrated in FIG. 1 .

In various embodiments, the plurality of home appliances 200 may be connected to the central power measuring device 250 , wherein the central power measuring device 250 may be a meter installed in all power consumers consuming electricity.

The central power measuring device 250 may be connected to the power entry point of the plurality of home appliances 200 to obtain all power data (power waveform and power usage) consumed by the plurality of home appliances 200 . Specifically, the central power measuring device 250 measures the total power usage of the power consumer in units of hours, days, weeks, and months, and provides it to the power analysis device 300 or calculates the total power usage consumed in real time. It may be provided to the analysis device 300 .

In various embodiments, the central power measurement device 250 directly transmits the power data set for the plurality of home appliances 200 to the power analysis device 300 , that is, the power waveform and the total power usage, or the user device 100 . may be transmitted to the power analysis device 300 through

That is, the central power measuring apparatus 250 may provide the power waveform and the total power usage together with the identification information of the user device 100 or the identification information of the consumer to the power analysis apparatus 300 .

In the present invention, it has been described that the central power measuring device 250 is preferably a meter, but according to an embodiment, the central power measuring device 250 may be a power consumption measuring device having a current/voltage sensor. However, in this case, the power analysis device 300 may perform a process of refining the data received from the central power measuring device 250, which will be described later.

The power analysis device 300 is a device that manages the power consumption of the plurality of home appliances 200 , and may include various electronic devices such as a PC, a tablet PC, and a data server. The power analysis apparatus 300 may monitor individual power usage and failure of the plurality of home appliances 200 for stable and smooth operation of the plurality of home appliances 200 disposed in the home or power consumer.

The power analysis apparatus 300 does not acquire individual power data through a sensor installed from a plurality of home appliances 200 or through a home appliance 200 capable of measuring its own power usage, but rather the user device 100 . Alternatively, a power data set (power waveform and total power usage) may be acquired from the central power measuring device 250, and the power usage and failure of each home appliance 200 may be determined through pre-learned features for each home appliance 200. can be monitored.

That is, the power analysis device 300 does not analyze the power usage of the individual home appliances 200 possessed by the user based on the identification information of the home appliance 200 , but only uses the power data set through the pre-learned power amount prediction model. Individual power usage of the device 200 may be predicted.

In various embodiments, the power analysis apparatus 300 may provide a power monitoring interface to the user device 100 in order to provide an analysis result, and accordingly, direct or indirect control of the home appliance 200 is performed by the user device 100 ) can be done through

So far, the power analysis system 1000 according to an embodiment of the present invention has been described. According to the present invention, the power analysis system 1000 includes a home appliance 200 capable of measuring individual power consumption without installing a sensor (measuring device) in each of a plurality of home appliances 200 or having a sensor on its own. Without it, individual power usage results of the plurality of home appliances 200 can be predicted through the entire power data set consumed at home.

Hereinafter, the user device 100 for monitoring and managing the power consumption of the plurality of home appliances 200 will be described.

2 is a block diagram illustrating a configuration of a user device according to an embodiment of the present invention.

Referring to FIG. 2 , the user device 100 may include a memory interface 110 , one or more processors 120 , and a peripheral interface 130 . The various components within user device 100 may be connected by one or more communication buses or signal lines.

The memory interface 110 may be connected to the memory 150 to transmit various data to the processor 120 . Here, the memory 150 is a flash memory type, hard disk type, multimedia card micro type, card type memory (eg, SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage storage, cloud , it may include a storage medium of at least one type of the block chain database.

In various embodiments, memory 150 includes operating system 151 , communication module 152 , graphical user interface module (GUI) 153 , sensor processing module 154 , phone module 155 , and application 156 . At least one of them may be stored. Specifically, the operating system 151 may include instructions for processing basic system services and instructions for performing hardware tasks. The communication module 152 may communicate with at least one of other one or more devices, computers, and servers. A graphical user interface module (GUI) 153 may process a graphical user interface. The sensor processing module 154 may process a sensor-related function (eg, processing a received voice input using one or more microphones 192 ). The phone module 155 may process a phone-related function. The application module 156 may perform various functions of the user application, such as electronic messaging, web browsing, media processing, navigation, imaging, and other processing functions. In addition, the user device 100 may store one or more software applications 156 - 1 and 156 - 2 (eg, a power monitoring application) associated with one type of service in the memory 150 .

In various embodiments, memory 150 may store digital assistant client module 157 (hereinafter, DA client module), such as instructions for performing the functions of the client side of the digital assistant and various user data 158 . (eg, user-customized vocabulary data, preference data, and other data such as the user's electronic address book, to-do list, shopping list, etc.).

On the other hand, the DA client module 157 receives the user's voice input, text input, touch input, and/or gesture input through various user interfaces (eg, I/O subsystem 140 ) provided in the user device 100 . can be obtained

Also, the DA client module 157 may output audio-visual and tactile data. For example, the DA client module 157 may output data including a combination of at least two or more of voice, sound, notification, text message, menu, graphic, video, animation, and vibration. In addition, the DA client module 157 may communicate with a digital assistant server (not shown) using the communication subsystem 180 .

In various embodiments, the DA client module 157 may collect additional information about the surrounding environment of the user device 100 from various sensors, subsystems, and peripheral devices to construct a context associated with the user input. . For example, the DA client module 157 may infer the user's intention by providing context information together with the user input to the digital assistant server. Here, the context information that may accompany the user input may include sensor information, for example, lighting, ambient noise, ambient temperature, an image of the surrounding environment, a video, and the like. For another example, the context information may include the physical state of the user device 100 (eg, device orientation, device location, device temperature, power level, speed, acceleration, motion pattern, cellular signal strength, etc.). For another example, the context information may include information related to the software state of the user device 100 (eg, processes running in the user device 100 , installed programs, past and current network activity, background services, error logs, resource usage). etc.) may be included.

In various embodiments, the memory 150 may include added or deleted commands, and further, the user device 100 may include additional components in addition to the components shown in FIG. 2 , or may exclude some components.

The processor 120 may control the overall operation of the user device 100 , and may execute various commands for implementing a power monitoring interface by driving an application or program stored in the memory 150 .

The processor 120 may correspond to a computing device such as a central processing unit (CPU) or an application processor (AP). Also, the processor 120 may be implemented in the form of an integrated chip (IC) such as a system on chip (SoC) in which various computing devices such as a neural processing unit (NPU) are integrated.

In various embodiments, the processor 120 may monitor the power usage, on, off state, function operation time, etc. of the plurality of home appliances 200 through the power monitoring interface provided from the power analysis device 300 , Furthermore, it is possible to control the on/off of the plurality of home appliances 200 . In this case, the processor 120 may output a home appliance 200 maintenance notification when an abnormal result exists in the home appliance 200 according to the monitoring result.

In various embodiments, the processor 120 is the total power usage obtained from the user through the touch screen 143 or the camera subsystem 170 or the power received from the central power measurement device 250 through the communication module 152 The data set (power waveform and total power usage) may be transmitted to the power analysis device 300 . Here, when the total power usage is obtained through the camera subsystem 170 , the processor 120 may analyze the image to obtain characters and text corresponding to the power usage.

The peripheral interface 130 may be connected to various sensors, subsystems, and peripheral devices to provide data so that the user device 100 may perform various functions. Here, it may be understood that the user device 100 performs a certain function as being performed by the processor 120 .

Peripheral interface 130 may receive data from motion sensor 160 , light sensor (light sensor) 161 , and proximity sensor 162 , through which user device 100 provides orientation, light, and proximity A detection function and the like may be performed. As another example, the peripheral interface 130 may receive data from the other sensors 163 (positioning system-GPS receiver, temperature sensor, biometric sensor), through which the user device 100 may receive data from other sensors. Functions related to (163) may be performed.

In various embodiments, the user device 100 may include a camera subsystem 170 coupled with a peripheral interface 130 and an optical sensor 171 coupled thereto, through which the user device 100 may take pictures and video Various shooting functions such as clip recording can be performed.

In various embodiments, the user device 100 may include a communication subsystem 180 coupled to the peripheral interface 130 . The communication subsystem 180 is composed of one or more wired/wireless networks, and may include various communication ports, radio frequency transceivers, and optical transceivers.

In various embodiments, the user device 100 includes an audio subsystem 190 coupled with a peripheral interface 130 , which includes one or more speakers 191 and one or more microphones 192 . By including, the user device 100 may perform voice-activated functions, such as voice recognition, voice replication, digital recording, and telephony functions, and the like.

In various embodiments, the user device 100 may include an I/O subsystem 140 coupled with a peripheral interface 130 . For example, the I/O subsystem 140 may control the touch screen 143 included in the user device 100 via the touch screen controller 141 . As an example, the touch screen controller 141 may use any one of a plurality of touch sensing technologies such as capacitive type, resistive type, infrared type, surface acoustic wave technology, proximity sensor array, and the like to touch and move or touch the user. and cessation of movement. For another example, I/O subsystem 140 may control other input/control devices 144 included in user device 100 via other input controller(s) 142 . As an example, the other input controller(s) 142 may control one or more buttons, rocker switches, thumb-wheels, an infrared port, a USB port, and a pointer device such as a stylus.

So far, the user device 100 according to an embodiment of the present invention has been described, and in the following, the data is provided so that the user device 100 can monitor the power consumption of a plurality of home appliances 200 . The power analysis device 300 will be described.

3 is a block diagram showing the configuration of a power analysis apparatus according to an embodiment of the present invention.

Referring to FIG. 3 , the power analysis device 300 may include a communication interface 310 , a memory 320 , an I/O interface 330 and a processor 340 , and each configuration includes one or more communication buses or They can communicate with each other via signal lines.

The communication interface 310 may be connected to the user device 100 and the central power measuring apparatus 250 through a wired/wireless communication network to exchange data. For example, the communication interface 310 may receive a power data set in units of hours/days/weeks/months along with user or power consumer identification information from the user device 100 or the central power measurement device 250, The individual power usage result of the home appliance 200 analyzed based on the power data set may be transmitted to the user device 100 .

On the other hand, the communication interface 310 that enables transmission and reception of such data includes a communication port 311 and a wireless circuit 312, wherein the wired communication port 311 is one or more wired interfaces, for example, Ethernet, Universal Serial Bus (USB), FireWire, and the like. Also, the wireless circuit 312 may transmit/receive data to and from an external device through an RF signal or an optical signal. In addition, the wireless communication may use at least one of a plurality of communication standards, protocols and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

The memory 320 may store various data used in the power analysis apparatus 300 . For example, the memory 320 may store the configuration data of the power monitoring interface, the power amount prediction model trained to predict the power usage result for each home appliance by inputting the power data set as an input, and the home appliance by inputting the power usage result as an input It is possible to store, for example, an inspection model trained to predict abnormal results of the device.

In various embodiments, memory 320 may store data sets and preprocessed power data sets. Here, the pre-processing process may include a data processing process, such as filtering out an obvious measurement error value such as negative power usage, or synchronizing the power usage consumption time of a plurality of home appliances 200 , and the processor 340 can be performed by

In various embodiments, memory 320 may include a volatile or non-volatile recording medium capable of storing various data, commands, and information. For example, the memory 320 may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg, SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage storage. , cloud, and may include at least one type of storage medium of a blockchain database.

In various embodiments, the memory 320 may store a configuration of at least one of the operating system 321 , the communication module 322 , the user interface module 323 , and one or more applications 324 .

Operating system 321 (eg embedded operating systems such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) includes various software for controlling and managing general system operations (eg memory management, storage device control, power management, etc.) It may include components and drivers, and may support communication between various hardware, firmware, and software components.

The communication module 323 may support communication with other devices through the communication interface 310 . The communication module 320 may include various software components for processing data received by the wired communication port 311 or the wireless circuit 312 of the communication interface 310 .

The user interface module 323 may receive a user's request or input from a keyboard, a touch screen, a microphone, etc. through the I/O interface 330 , and may provide a user interface on a display.

Applications 324 may include programs or modules configured to be executed by one or more processors 330 . Here, an application for providing a power monitoring service may be implemented on a server farm.

The I/O interface 330 may connect an input/output device (not shown) of the power analysis apparatus 300 , for example, at least one of a display, a keyboard, a touch screen, and a microphone to the user interface module 323 . The I/O interface 330 may receive a user input (eg, a voice input, a keyboard input, a touch input, etc.) together with the user interface module 323 and process a command according to the received input.

The processor 340 is connected to the communication interface 310 , the memory 320 and the I/O interface 330 to control the overall operation of the power analysis device 300 , and an application or program stored in the memory 320 . Through this, it is possible to predict individual power usage results of the home appliance 200 and perform various commands for predicting abnormal results.

The processor 340 may correspond to a computing device such as a central processing unit (CPU) or an application processor (AP). In addition, the processor 340 may be implemented in the form of an integrated chip (IC) such as a system on chip (SoC) in which various computing devices are integrated. Alternatively, the processor 340 may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

In various embodiments, the processor 340 may predict individual power consumption results of the plurality of home appliances 200 only with one power data set, which will be described below with reference to FIGS. 4 to 7 .

4 is a flowchart of a method for analyzing power of a home appliance according to an embodiment of the present invention.

Referring to FIG. 4 , the processor 340 may acquire power data sets for a plurality of home appliances ( S110 ). Here, the power data set may mean a power waveform and total power usage. The processor 340 may receive the total power usage of the individual/power consumer measured from the user device 100 or the central power measuring device 250 through the communication interface 310 , and from the central power measuring device 250 . A power waveform can be received.

In various embodiments, the processor 340 may obtain an image of the central power measurement apparatus 250 from the user device 100 , and may obtain a total power usage through image analysis.

In various embodiments, the processor 340 may pre-process the acquired power data set before predicting individual power usage.

5 is a schematic diagram for explaining a pre-processing of a power data set according to an embodiment of the present invention.

Referring to FIG. 5 , the processor 340 may perform a pre-processing process of refining raw-data obtained through the central power measurement device 250 into data that can be input to the power amount prediction model. Specifically, the processor 340 may remove error data such as negative power usage from raw-data and classify valid power data (data cleaning).

In addition, the processor 340 may classify data within an allowable error range and perform normalization for reducing the scale of a frequency in the power waveform (feature scaling). Specifically, the processor 340 may filter the power data set according to a preset minimum value or a noise feature for each household appliance 200 .

In this way, by pre-processing the power data set, data in a form that can be input to the power amount prediction model can be obtained, and unnecessary microcurrents not used for predicting power usage can be cut off. For example, in the case of the home appliance 200, a current of 0.1W to 0.01W is measured finely and quickly regardless of whether it is used or not, but unnecessary power data is removed through a preprocessing process, and accordingly, the load of the processor 340 is It is possible to reduce energy consumption and obtain power consumption results more quickly and accurately.

After step S110, the processor 340 inputs the acquired power data set to the power amount prediction model learned to predict the power usage result for each home appliance by inputting the power data set as an input, and results in individual power usage of the plurality of home appliances. can be predicted

In relation to this, FIG. 6 is a schematic diagram for explaining a wattage prediction model according to an embodiment of the present invention, and FIG. 7 is a schematic diagram for explaining a hierarchical structure of an wattage prediction model according to an embodiment of the present invention.

Referring to FIG. 6 , the power amount prediction model 350 may input a power data set for a power waveform and total power usage from a central power measurement device 250 such as a meter in the user's home, and finally, a home appliance ( 200) of individual power usage results (graph) can be output.

Referring to FIG. 7 , the wattage prediction model 350 includes an input layer 351 that receives a power waveform image, a convolutional layer 353 that extracts features of home appliances 200 , home appliances A sub-layer including a recurrent layer and a recurrent-skip layer 355 for determining an on/off state of the device 200, and finally a home appliance ( 200 ) and may include a fully connected layer 357 .

Specifically, the wattage prediction model 350 may properly extract individual features of the plurality of home appliances 200 from the wattage data set through the convolutional layer 353 . In addition, the wattage prediction model 350 may extract features of the home appliance 200 according to a preset time unit.

The wattage prediction model 350 may input the extracted features to the recurrent layer and the recurrent-skip layer 355, and the recurrent layer and the recurrent-skip layer 355 are used in the features of the power data set for home appliances ( 200) may determine a time interval related to the off state, and skip the power data value of the corresponding interval to 0.

The power amount prediction model 350 may finally output the power usage result 359 subdivided for each of the plurality of home appliances 200 . That is, the power amount prediction model 350 may more quickly and accurately predict the power usage result by processing the extracted features using the RNN-based GRU model. For example, the power consumption prediction model 350 may output the power usage results of the refrigerator, air conditioner, induction, and TV in the form of a graph of power usage change over time.

Meanwhile, although it has been described that the power amount prediction model 350 has a hierarchical structure as shown in FIG. 7 , the structure of the power amount prediction model 350 may not be limited thereto. Accordingly, the wattage prediction model 350 may have an artificial neural network hierarchical structure of various known structures capable of image analysis.

Referring back to FIG. 4 , after step S120 , the processor 340 monitors the individual power usage results of the plurality of home appliances 200 and power monitoring including the on/off state data of the plurality of home appliances 200 determined based on the results. An interface may be provided (S130). Specifically, the processor 340 may determine the on/off timing of the individual electric devices 200 based on a preset threshold value from the power usage result obtained through the power amount prediction model 350 .

In various embodiments, the processor 340 receives the power usage result as an input and the individual power usage result of the plurality of home appliances 200 obtained in step S120 in the inspection model trained to predict the abnormal result of the home appliance 200 . By inputting , it is possible to predict an abnormal result for any one of the plurality of home appliances 200 . Specifically, the processor 340 may predict an abnormal result of whether the power consumption of each of the plurality of home appliances 200 is exceeded or whether each of the plurality of home appliances 200 fails through the inspection model.

In relation to this, FIG. 8 is a schematic diagram for explaining a power monitoring interface screen provided to a user device according to an embodiment of the present invention.

Referring to FIG. 8 , the processor 340 may provide the following power monitoring interface to the user device 100 . Specifically, the power monitoring interface may include an area in which a graph of power usage over time of the home appliance 200 is displayed in relation to individual power usage results.

In addition, the power monitoring interface may include an area in which at least one of the on/off timing of the plurality of home appliances 200 , the operation timing for each function, and the power usage prediction result for a preset period is displayed. Such information may be displayed on the power usage graph, and in the case of on/off time and operation time, specific time information (eg, 12:34 pm on September 1) may be provided in the form of a pop-up window.

In addition, the power monitoring interface may highlight and display an abnormal result in the power usage graph. For example, a “consumption caution section” and a “failure prediction section” may be displayed on the power usage result of the air conditioner, and at the same time, an audiovisual alarm or a vibration alarm may be provided to the user device 100 together.

So far, the power analysis apparatus 300 according to an embodiment of the present invention has been described. According to the present invention, the power analysis device 300 through the power consumption prediction model 350 machine-learning the power consumption of various home appliances 200, without a sensor (measuring device) individually connected to the home appliance 200, Current power usage and future power usage of the home appliance 200 may be predicted.

Although one embodiment of the present invention has been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be made within the scope without departing from the technical spirit of the present invention. have. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

1000: power analysis system
100: user device
110: memory interface 120: processor
130: peripheral interface 140: I/O subsystem
141: touch screen controller 142: other input controller
143: touch screen
144: other input control device
150: memory 151: operating system
152: communication module 153: GUI module
154: sensor processing module 155: phone module
156: application module
156-1, 156-2: Applications
157: digital assistant client module
158: user data
160: motion sensor 161: light sensor
162: proximity sensor 163: other sensor
170: camera subsystem 171: optical sensor
180: communication subsystem
190: audio subsystem
191: speaker 192: microphone
200: home appliances
250: central power measuring device
300: power analysis device
310: communication interface
311: wired communication port 312: wireless circuit
320: memory
321: operating system 322: communication module
323: user interface module 324: application
330: I/O interface 340: processor

Claims (11)

acquiring power data sets for a plurality of home appliances;
Predicting individual power usage results of the plurality of home appliances by inputting the acquired power data set into a power amount prediction model trained to predict the power usage results for each home appliance by inputting the power data set as an input;
providing a power monitoring interface including individual power usage results of the plurality of home appliances and on/off state data of the plurality of home appliances determined based on the individual power usage results; including,
the power data set includes a power waveform and total power usage;
The power amount prediction model is,
A method for analyzing power of a home appliance, configured to extract individual features of the plurality of home appliances from the power data set through a convolutional layer. According to claim 1,
The power monitoring interface,
and an area in which a graph of power usage over time of the home appliance is displayed in relation to the individual power usage result. According to claim 1,
The step of providing the power monitoring interface comprises:
Determining an on/off time point in the individual power usage results of the plurality of home appliances based on a preset threshold value, further comprising a power analysis method of a home appliance. According to claim 1,
The power monitoring interface,
The method for analyzing power of home appliances, comprising an area in which at least one of on/off timings of the plurality of home appliances, operation times for each function, and power usage prediction results for a preset period are displayed. 3. The method of claim 2,
By inputting the individual power usage results of the plurality of home appliances to the inspection model trained to predict the abnormal results of the home appliances by inputting the power usage results as input, the abnormal results for any one of the plurality of home appliances are displayed. Predicting, power analysis method of home appliances further comprising a. 6. The method of claim 5,
The power monitoring interface,
The power analysis method of home appliances, configured to display abnormal results for any one of the plurality of home appliances on the power usage graph. 6. The method of claim 5,
The above result is,
A power analysis method of home appliances, including whether each of the plurality of home appliances is used in excess or malfunctions. delete According to claim 1,
The wattage prediction model is,
Further comprising a sub-layer consisting of a recurrent layer (recurrent layer) and a recurrent-skip layer (recurrent-skip layer),
The recurrent layer and the recurrent-skip layer are
and determine a time interval associated with an off state in at least one of the plurality of home appliances based on the extracted features. According to claim 1,
Obtaining the power data set comprises:
The step of obtaining a filtered power data set based on a preset minimum value or a noise feature for each household appliance, the power analysis method of the home appliance. communication interface;
Memory; and
a processor operatively coupled to the communication interface and the memory; including,
The processor is
Acquire power data sets for a plurality of home appliances,
By inputting the power data set obtained to the power amount prediction model trained to predict the power usage result for each home appliance by inputting the power data set as an input, predicting the individual power usage result of the plurality of home appliances,
configured to provide a power monitoring interface including individual power usage results of the plurality of home appliances and on/off state data of the plurality of home appliances determined based on the individual power usage results,
the power data set includes a power waveform and total power usage;
The electric energy prediction model is
and extract individual features of the plurality of household appliances from the power data set via a convolutional layer.

Images