KR20180071932A - Home network managing server and controlling method thereof - Google Patents

Abstract

Disclosed is a server for managing a home network. The server capable of automatically detecting an error comprises: a storage unit storing operation states of at least one electronic device in a home network and reference sensing data per sensor; a communication unit receiving the sensing data from the plurality of sensors; and a processor determining the operation states of at least one electronic device, comparing the stored reference sensing data corresponding to the determined operation states with the received sensing data, and determining whether there is an error in at least one electronic device.

Description

TECHNICAL FIELD [0001] The present invention relates to a home network management server and a control method thereof.

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a server for managing a home network and a control method thereof, and more particularly to a server capable of automatically detecting an error in a device in a home network and a control method thereof.

In addition, the present disclosure relates to a server that automatically detects an error in a device using an artificial intelligence (AI) system that simulates functions such as recognition and judgment of a human brain using a machine learning algorithm, and a control method thereof will be.

With the development of computer technology, communication technology, and home electronics technology, a home network management service in which devices and systems in the home are connected and managed as a home network has emerged and is attracting attention as a future-oriented technology.

All information appliances in the home connected to the home network can transmit data to each other and can communicate with various user terminal devices. For example, a user can control all home appliances connected to a home network regardless of time and place by using a user interface (UI) provided in a user terminal device such as a mobile phone.

However, there were difficulties in maintaining, managing, and repairing multiple devices in such an environment. For example, even if a specific sensor included in the home network fails, the failure of such a device is not a matter that can be visually confirmed, so that it is difficult for the user to recognize the failure.

In addition, the home network environment is not structured in a predetermined form, but the environments constituted by the devices are determined in various ways as desired by the user, so it is impossible to predict a device failure situation corresponding to the environment, assuming a specific environment .

Meanwhile, in recent years, artificial intelligence systems that implement human-level intelligence have been used in various fields. Artificial intelligence system is a system that the machine learns, judges, and becomes smarter, unlike the existing rule-based smart system. Artificial intelligence systems are becoming more and more recognizable as users use them, and existing rule-based smart systems are increasingly being replaced by deep-run-based artificial intelligence systems.

Artificial intelligence technology consists of elemental technologies that utilize machine learning (eg, deep learning) and machine learning.

Machine learning is an algorithm technology that classifies / learns the characteristics of input data by itself. Element technology is a technology that simulates functions such as recognition and judgment of human brain using machine learning algorithms such as deep learning. Understanding, reasoning / prediction, knowledge representation, and motion control.

The various fields in which artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing, applying, and processing human language / characters, including natural language processing, machine translation, dialogue system, query response, speech recognition / synthesis, and the like. Visual understanding is a technology for recognizing and processing objects as human vision, including object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, and image enhancement. Inference prediction is a technique for judging and logically inferring and predicting information, including knowledge / probability based reasoning, optimization prediction, preference base planning, and recommendation. Knowledge representation is a technology for automating human experience information into knowledge data, including knowledge building (data generation / classification) and knowledge management (data utilization). The motion control is a technique for controlling the autonomous travel of the vehicle and the motion of the robot, and includes motion control (navigation, collision, traveling), operation control (behavior control), and the like.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and it is an object of the present invention to provide a server and a control method thereof that can automatically detect an error of a device in a home network.

Another object of the present invention is to provide a server and a control method thereof that can automatically detect errors in devices in a home network using an artificial intelligence system.

According to an aspect of the present invention, there is provided a server for managing a home network, including a storage unit for storing operation states of at least one electronic device in the home network, A communication unit for receiving sensing data from the plurality of sensors, and a control unit for determining an operation state of the at least one electronic device, comparing the stored reference sensing data corresponding to the determined operation state with the received sensing data, And a processor for determining whether the sensor and the at least one electronic device are erroneous.

In this case, the processor may determine whether each of the sensing data received from the plurality of sensors is within a predetermined allowable range of a plurality of sensor-specific reference sensing data corresponding to the determined operating condition, An error of the plurality of sensors and the at least one electronic device can be determined.

In this case, the processor determines that the at least one electronic device is in an error state with respect to the determined operating condition if the sensor out of the predetermined allowable range of the plurality of sensors is equal to or greater than a predetermined ratio, The sensor that is out of the predetermined allowable range may be determined to be in an error state if the sensor out of the predetermined allowable range is less than the preset ratio.

Meanwhile, when it is determined that the operation state of the at least one electronic device is a new operation state, the processor may cause the sensing data received from each of the plurality of sensors at a time corresponding to the new operation state to correspond to the new operation state The reference sensing data may be stored in the storage unit.

Meanwhile, when it is determined that the operation state of the at least one electronic device is a new operation state, a change in sensing value at a time point corresponding to the new operation state among a plurality of sensing data items received from the plurality of sensors, May be stored in the storage unit as reference sensing data corresponding to the new operation state.

Meanwhile, when the operating state of the at least one electronic device is determined after the new sensor is registered in the home network, the processor may determine the sensing data received from the new sensor at the time corresponding to the determined operating state, And storing the reference sensing data of the new sensor in the storage unit.

On the other hand, the processor may receive status information from the at least one electronic device and determine an operational status of the at least one electronic device based on the received status information.

Meanwhile, the processor may control the communication unit to transmit, to the user terminal device, information about the device, which is determined to have an error, out of the at least one electronic device and the plurality of sensors.

Meanwhile, the processor may control the communication unit to transmit information on the determined operation state to the user terminal device together with information on the device, which is determined as an error among the at least one electronic device and the plurality of sensors have.

According to another aspect of the present invention, there is provided a method of controlling a server for managing a home network, the method comprising: storing operation conditions of at least one electronic device in the home network and reference sensor data for each of the plurality of sensors; Receiving the sensing data from the at least one electronic device, determining the operation status of the at least one electronic device, and comparing the stored reference sensing data corresponding to the determined operating condition with the received sensing data, Determining whether the at least one electronic device is erroneous.

In this case, the step of determining whether or not the error is determined may include determining whether each of the sensing data received from the plurality of sensors is within a predetermined allowable range of a plurality of sensor-specific reference sensing data corresponding to the determined operating condition, And determine whether the plurality of sensors and the at least one electronic device are in error based on the determination.

In this case, the determining of the error may include determining that the at least one electronic device is in an error state with respect to the determined operation state if a sensor out of the predetermined allowable range among the plurality of sensors is equal to or greater than a predetermined ratio And if the sensor out of the predetermined allowable range among the plurality of sensors is less than the preset ratio, it is possible to determine that the sensor that is out of the predetermined allowable range is in an error state.

Meanwhile, the storing step may include storing sensing data received from each of the plurality of sensors at a time corresponding to the new operation state as the new operation state, when the operation state of the at least one electronic device is determined as a new operation state, As reference sensing data corresponding to the reference sensing data.

Meanwhile, the storing may include a step of, when it is determined that the operation state of the at least one electronic device is a new operation state, a sensing value at a time point corresponding to the new operation state among a plurality of sensing data received from the plurality of sensors, May be stored as reference sensing data corresponding to the new operation state.

If the operation state of the at least one electronic device is determined after the new sensor is registered in the home network, the storing step may include storing sensing data received from the new sensor at a time corresponding to the determined operation state And storing the reference sensing data of the new sensor with respect to the determined operation state.

Meanwhile, the step of determining the operation status may include receiving status information from the at least one electronic device, and determining an operation status of the at least one electronic device based on the received status information.

The method of controlling a server according to the present disclosure may further include transmitting information on a device determined as an error among the at least one electronic device and a plurality of sensors to a user terminal device.

Meanwhile, in the server control method according to the present disclosure, information on the determined operation state is transmitted to the user terminal device together with information on the device that is judged as having an error among the at least one electronic device and the plurality of sensors Step < / RTI >

On the other hand, in a computer-readable recording medium including a program for executing a control method of a server for managing a home network according to an embodiment of the present disclosure, the control method includes the steps of: The method comprising: storing operating conditions and a plurality of sensor-specific reference sensing data; receiving sensing data from the plurality of sensors; determining an operating condition of the at least one electronic device; And comparing the stored reference sensing data with the received sensing data to determine whether the plurality of sensors and the at least one electronic device are erroneous.

1 is a diagram for explaining a home network system according to an embodiment of the present disclosure;
2 is a block diagram illustrating a configuration of a server according to an embodiment of the present disclosure for managing a home network,
FIGS. 3 to 5 are diagrams for explaining a method of determining an error of a server according to various embodiments of the present disclosure;
6 is a diagram for explaining reference sensing data for error determination according to an embodiment of the present disclosure stored in a lookup table form,
7 is a diagram for describing a method according to an embodiment of the present disclosure for determining an error of a sensor in a specific situation,
FIG. 8 is a flowchart for explaining an error determination method of a server according to an embodiment of the present disclosure; and
9 is a flowchart illustrating a method of controlling a server according to an embodiment of the present disclosure.
10 is a diagram for explaining an error judgment process according to an embodiment of the present disclosure.
11 to 13 show a data learning unit and a data recognition unit, which are generated in a processor of a server according to an embodiment of the present disclosure.

In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present disclosure rather unclear. The terms used below are defined in consideration of the functions in this disclosure, and this may vary depending on the intention of the user, the operator, or the like. Therefore, the definition should be based on the contents throughout this specification.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the rights. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprise", "comprising" and the like are used to specify that there is a stated feature, number, step, operation, element, component, or combination thereof, But do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof.

In the embodiment, 'module' or 'sub' performs at least one function or operation, and may be implemented in hardware or software, or a combination of hardware and software. In addition, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module except for 'module' or 'module' which needs to be implemented by specific hardware, and may be implemented by at least one processor.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. However, the present disclosure may be embodied in many different forms and is not limited to the embodiments described herein. In order that the present disclosure may be more fully understood, the same reference numbers are used throughout the specification to refer to the same or like parts.

Hereinafter, the present disclosure will be described in more detail with reference to the drawings.

1 is a diagram illustrating a home network system 1000 according to an embodiment of the present disclosure.

Referring to FIG. 1, a home network system 1000 includes a server 100 and a plurality of client devices 11 to 18 connected to the server 100.

The server 100 may be connected to a plurality of client devices 11 to 18 included in the home network through a wired or wireless communication method. The server 100 may be responsible for controlling, managing, and interworking of a plurality of client devices 11 to 18. The server 100 may exist as an independent apparatus or may be mounted on another apparatus.

The server 100 may serve as a gateway for interconnection and arbitration between a home network and an external network. In this case, the server 100 may transmit the control command provided from the external device to the plurality of client devices 11 to 18, or may collect the status information of the plurality of client devices 11 to 18 and transmit the collected status information to the external device .

The server 100 may receive a control command from the user terminal device to control the plurality of client devices 11 to 18 and may collect status information of the plurality of client devices 11 to 18 and transmit the status information to the user terminal device . In this case, the user terminal device may be a device such as a smart phone, a desktop computer, a notebook, a tablet PC, a PDA, or the like.

In order to manage, maintain, and repair a plurality of client devices as shown in FIG. 1, the server 100 can automatically determine errors of the plurality of client devices 11 to 18. In the present specification, the client device may in other words be represented by an electronic device included in the home network or a sensor included in the home network or the like.

The plurality of client devices 11 to 18 are sensors that can sense the environment, such as temperature / light intensity sensors 11, 12 and 17, power measurement sensors 15 and 18 in FIG. 1, A device to be sensed, such as a light bulb 10, 14, a TV 13, an air conditioner 16, etc., in Fig. Of course, devices such as the bulbs 10 and 14, the TV 13, the air conditioner 16 and the like may also have sensor functions.

For example, the bulbs 10, 14 may include an illuminance sensor and the brightness of the bulbs 10, 14 may be automatically adjusted based on the ambient brightness sensed by the sensor. The TV 13 may include an illuminance sensor, and the brightness of the display of the TV 13 may be automatically adjusted based on the ambient brightness detected by the sensor. The air conditioner 16 may include a temperature sensor, and the cooling temperature may be automatically controlled based on the temperature sensed by the sensor.

The server 100 can detect the device in which an error has occurred based on the operation relationship between the plurality of client devices 11-18.

For example, since the display of the TV is turned on when the power of the TV 13 is turned on, it is possible to detect a change in illuminance in the first temperature / ambient light sensor 10 around the TV, Power consumption can be measured according to the supply. This situation is error-free. When an error occurs in the first temperature / ambient light sensor 10, when the TV 13 is turned on, power consumption of the power measurement sensor 15 due to power supply to the TV is measured, and the first temperature / 10), no change in illumination is detected. In other words, it can be understood that there is a problem in the first temperature / ambient light sensor 10 as compared with the case of the normal state.

The server 100 stores information on the operation relationships of the plurality of client devices 11 to 18 in the normal operation state and based on this information, It is possible to detect which client device has an error.

In particular, according to the present disclosure, since information on the operation relationships of the plurality of client devices 11 to 18 in the normal operation state can be obtained in the course of using the client devices of the home network, Costs, time can be reduced. Above all, this information is adaptable to changes in the environment, such as adding a new device to the home network, so this disclosure is suitable for application in the IoT environment.

In addition, the server 100 can inform the user of the information about the device in which the error has occurred and the information on the operation status in which an error occurs, to the user terminal device.

Meanwhile, although the present invention has been described as a 'home' network system, the present disclosure is not limited to being used only in a home environment, and can be applied to various environments such as a school and a company.

On the other hand, although it is described that the server 100 is one, there may be a plurality of servers in the home network system 1000.

Hereinafter, the server 100 will be described in more detail with reference to FIG.

Referring to FIG. 2, the server 100 includes a communication unit 110, a storage unit 120, and a processor 130.

The communication unit 110 is configured to perform communication with various types of external devices according to various types of communication methods. The communication unit 110 may be connected to an external device through a local area network (LAN) or an Internet network, and may be connected to a wireless communication (e.g., Z-wave, 4LoWPAN, RFID, LTE D2D, BLE, GPRS , WiFi Direct, GSM, UMTS, LTE, WiBRO, etc.) to be connected to an external device. The communication unit 110 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, and a wireless communication chip.

The communication unit 110 may be connected to client devices included in a home network managed by the server 100 to receive status information. Also, the communication unit 110 can receive the sensing data from the sensors included in the home network.

The storage unit 120 may store various programs and information required for the control of the server 100. [ For example, the storage unit 120 may be implemented as a nonvolatile memory, a volatile memory, a flash memory, a hard disk drive (HDD), or a solid state drive (SSD). Meanwhile, the storage unit may be implemented not only as a storage medium in the server 100, but also as an external storage medium such as a micro SD card, a USB memory, and an external server.

The storage unit 120 may store various types of information required for home network management. For example, the storage unit 120 may include information on client devices connected to the server 100. [ More specifically, when the client device is a sensor, information about an object that can be sensed by the sensor may be stored in the storage unit 120.

The storage unit 120 may store a list of control commands for controlling client devices. The list of control commands may be stored in the storage unit 120 for each client device.

The storage unit 120 may store information generated by using the client devices. Specifically, the storage unit 120 may store a history of controlling client devices. The storage unit 120 may store the history of the sensing data generated by the sensor among the client devices.

In particular, the storage unit 120 may store the operation status of at least one electronic device in the home network and a plurality of sensor-specific reference sensing data. The reference sensing data may be stored in the storage unit 120 in the form of a lookup table for each of a plurality of sensors for each operation state.

The processor 130 is a configuration for controlling the overall operation of the server 100. [ For example, the processor 130 may include at least one CPU (or DSP, MPU, etc.), RAM, ROM, and a system bus. The processor may be implemented as a MICOM (MICOM COMPUTER), an ASIC (application specific integrated circuit), or the like.

The processor 130 may determine the operation status of client devices included in the home network. One or more client devices may be associated with the operation status.

In one example, the processor 130 may receive status information from client devices and may determine the operational status of the client devices based on the received status information.

The status information is information that enables the server 100 to know the operation status of the client device. Specifically, the status information may be information that enables the server 100 to recognize the operation status of the client device. For example, in the case of a TV, information indicating whether the TV is currently turned on or off, whether the operation mode is a power save mode, and the like can be status information. In the case of an air conditioner, Information indicating whether the dehumidifying function is being performed in the air conditioner, the air conditioner, or the like can be status information.

As another example, the status information may be information indicating the sensing status of the sensor. In this case, the status information can be determined based on the sensing data received from the sensor. For example, a precense sensor transmits sensing data to the server 100, and the processor 130 can determine whether or not the occupant sensor has sensed the occupant based on the received sensing data. As another example, the temperature sensor transmits sensing data to the server 100, and the processor 130 can determine whether the temperature sensor senses a certain degree of temperature based on the received sensing data.

Depending on the client device, the status information can be transmitted to the server 100 continuously or at a predetermined period. Alternatively, the processor 130 may request the status information to be transmitted to the client device through the communication unit 110, and the client device may transmit the status information to the server 100 according to the request. Alternatively, the processor 130 may control the communication unit 110 to transmit a control command for performing a specific operation to the client device, and the client device may perform an operation on the received control command, Status information can be transmitted as information.

As described above, the processor 130 may determine the operation status of the client devices of the current home network based on the status information received from the at least one client device.

In another embodiment, instead of the status information, the operating status can be determined based on the sensing data. Specifically, when the operation state of the processor 130 is determined, based on the sensing data received from the sensors included in the home network, the reference sensing data corresponding to the operation state is stored in the storage unit 120). Thereafter, when the sensing data is received from the sensors, the received sensing data may be compared with the stored reference sensing data to determine the current operation status.

Meanwhile, the processor 130 may use the sensing data itself received from the sensor, or may use processed sensing data by processing the received sensing data. For example, the processor 130 may store the temperature value itself received from the temperature sensor as reference sensing data, or may store information on the increase / decrease of the temperature determined based on the temperature value received from the temperature sensor, as reference sensing data.

The processor 130 may store the reference sensing data of each of the plurality of sensors included in the home network in the storage unit 120 for various operation states of the client devices. The reference sensing data is for use in determining whether the client devices are defective. The reference sensing data is not defined in advance, but is data generated by using client devices.

Specifically, the processor 130 determines the operation state of the client devices, and if the determined operation state is a new operation state, the processor 130 determines that the sensor data received from the sensors included in the home network at the time corresponding to the new operation state The reference sensing data corresponding to the new operation state can be stored in the storage unit 120. [

The reference sensing data of each of the plurality of sensors may be stored in the storage unit 120 in the form of a lookup table.

The processor 130 determines the current operation state of the client devices. If the determined operation state is registered in the lookup table, the processor 130 generates reference sensing data of a plurality of sensors corresponding to the operation state, The plurality of sensing data are compared with each other to determine whether the plurality of sensing data are within a predetermined allowable range of the plurality of sensor-specific reference sensing data, and based on the determination, can do.

Determining whether or not it is within the predetermined allowable range may mean determining whether the mismatch between the compared sensing data is within a predetermined error range.

An embodiment related to storing reference sensing data will be described with reference to FIG.

Referring to FIG. 3, the TV 31 is powered on, and the TV 31 transmits status information to the server 100 indicating that the power is turned on. The processor 130 can determine the operation state that the TV is turned on based on the state information received from the TV 31. If this operation state is a new operation state, that is, the first determined operation state, The sensing data received from the power measuring sensor 32 and the illuminance sensor 33 may be stored in the storage unit 120 as reference sensing data corresponding to the operating condition of 'TV power on'. The display portion of the TV is turned on as the power of the TV 31 is turned on. Therefore, the brightness of the illuminance sensor 33 may have been detected and the power consumption of the power measuring sensor 32 may have been detected. Each of such sensing data may be stored as reference sensing data corresponding to the power-on operation state of the TV.

After the reference sensing data is stored as described above, when the processor 130 determines based on the state information received from the TV 31 that the operation state of turning on the power of the TV 31 is determined, The sensing data received by the measuring sensor 32 and the illuminance sensor 33 are compared with the reference sensing data stored as described above. As a result of comparison, the sensing data received from the illuminance sensor 33 is within the predetermined allowable range of the reference sensing data of the illuminance sensor 33, The processor 130 may determine that an error has occurred in the power measurement sensor 32 if the power measurement sensor 32 is out of a predetermined tolerance range of the reference sensing data (e.g., no power change is detected).

If both the sensing data received from the illuminance sensor 33 and the sensing data received from the power measurement sensor 32 are out of a predetermined allowable range of the reference sensing data, There is a high possibility that an error has occurred in the TV 31 rather than an error in the sensor 32. [ In this situation, for example, the TV 31 may send status information indicating that the power is turned on to the server 100, but the display of the actual TV may not be turned on due to a problem of the internal parts of the TV 31. [

In this case, the illuminance sensor 33 can not detect a change in brightness because the display of the TV is not turned on. In the power measurement sensor 32, the display of the TV 31 is not activated, Is not detected. The processor 130 determines that the operation of the power supply of the TV 31 is the same as that of the TV 31 if the sensing data received from the power measuring sensor 32 and the illuminance sensor 33 do not coincide with the reference sensing data, It can be determined that an error has occurred.

On the other hand, the sensing data used for determining whether or not an error has occurred may be that the data received from the sensor is unprocessed or the data received from the sensor is analyzed and processed. For example, the temperature value received from the temperature sensor can be used as sensing data for determining whether or not an error has occurred, and the information on the temperature increase state or the temperature decrease state obtained by analyzing and processing the temperature value received from the temperature sensor, Can be used as sensing data.

As described above, the processor 130 determines the operation status of the electronic devices in the home network, and transmits the reference sensing data of each of the plurality of sensors corresponding to the determined operation state and the plurality of sensing data To determine whether the sensors and the electronic devices are erroneous.

However, the present invention is not limited to this, and the processor 130 may collect reference sensing data newly for the re-generated operating conditions, The newly collected reference sensing data and the previously stored reference sensing data are compared with each other. If it is determined that they coincide with each other within the predetermined allowable range, the newly collected reference sensing data is merged with the previously stored reference sensing data, It is possible to newly generate reference sensing data corresponding to the operation state.

Meanwhile, when the operation status of at least one electronic device in the home network is determined after the new sensor is registered in the home network, the processor 130 determines the sensing data received from the new sensor at the time corresponding to the determined operation state And store the reference sensing data of the new sensor in the storage unit 120 for the determined operation state. That is, the reference sensing data of the new sensor for the determined operating condition may be added to the lookup table. The reference sensing data may be generated and added to the lookup table based on the sensing data of the new sensor whenever an operation situation associated with the new sensor newly occurs.

For example, when a new second illuminance sensor is newly disposed adjacent to the TV 31 as well as the power measuring sensor 32 and the first illuminance sensor 33 in the situation shown in FIG. 3, The processor 130 determines whether the sensing data received from the second illuminance sensor is the first sensing data at the time of the occurrence of the operating condition. At this time, based on the sensing data received from the second illuminance sensor, The reference sensing data of the second illuminance sensor may be generated and added to the storage unit 120. [

As described above, according to the present disclosure, the reference sensing data can be automatically added to the lookup table according to the occurrence of a new operation situation or the addition of a new sensor. Therefore, whenever the environment of the home network changes, Is not required.

Meanwhile, the reference sensing data may store not only the sensing value but also information on the time taken until the sensing value corresponding to the operation state is detected before and after the corresponding operation situation occurs. Alternatively, the reference sensing data may include only the time information as described above. This will be described with reference to FIG.

4, the cooling of the air conditioner 41 is activated, and the air conditioner 41 transmits to the server 100 status information indicating that cooling has been performed. The state information may also include information on the cooling temperature. The processor 130 may determine an operation state that the cooling of the air conditioner 41 has been activated based on the state information received from the air conditioner 41. The processor 130 may perform the power measurement And analyzes the sensing data received from the sensor 44 and the temperature sensors 42 and 43. In particular, the processor 130 may calculate the time taken to detect a temperature change in the temperature sensors 42 and 43 from the cooling start time.

As shown in FIG. 4, the first temperature sensor 42 took 10 minutes to detect the temperature change, and the second temperature sensor 43 took 1 minute. The processor 130 converts the time information into the reference sensing data of the first temperature sensor 42 and the reference sensing data of the second temperature sensor 43 corresponding to the operation state of ' ). ≪ / RTI >

After the reference sensing data is stored as described above, when the processor 130 determines based on the status information received from the air conditioner 41 that the operation state of the air conditioner 41 is being operated again, The sensing data received from the sensors 42 and 43 and the power measurement sensor 44 is compared with the reference sensing data stored as described above.

Specifically, the processor 130 analyzes the sensing data received from the first temperature sensor 42 and determines whether a temperature change is detected within a predetermined allowable range based on 10 minutes from the cooling operation start time. The processor 130 analyzes the sensing data received from the second temperature sensor 43 to determine whether a temperature change is detected within a predetermined allowable range based on one minute from the cooling operation start time. The processor 130 then compares the sensing data received from the power measurement sensor 44 with the reference sensing data of the power sensor 44. [

For example, when the sensed data received from the first temperature sensor 42 is analyzed, if a temperature change is not detected within a predetermined allowable range (eg, 9 to 11 minutes) based on 10 minutes from the cooling start time , The processor 130 may determine that the sensing data received from the first temperature sensor 42 is out of the predetermined tolerance range of the first temperature sensor 42. [ If the processor 130 determines that the sensing data received from the remaining second temperature sensor 42 and the power measurement sensor 44 is within the predetermined allowable range of the reference sensing data, Can be judged to have occurred.

3 and 4, the processor 130 determines the operation status of all the electronic devices included in the home network, and transmits the reference sensing information corresponding to the determined operation state It is possible to judge whether or not the apparatus is erroneous based on the data. For example, the reference sensing data may be stored in the storage unit 120 for a complex operation state in which a plurality of electronic devices are associated with each other, such as an operation state in which the TV is powered on and the air conditioner is in operation. Accordingly, the processor 130 can accurately detect an error even in a complex operation situation in which a plurality of electronic devices are involved. This will be described with reference to FIG.

5, the air conditioning of the air conditioner 51 is activated, and the food is heated by the cooking device 52. As shown in FIG. The air conditioner 51 and the cooking apparatus 52 transmit status information to the server 100 and the processor 130 determines whether or not the condition information received from the air conditioner 51 and the status information received from the cooking apparatus 52 It is possible to determine the complex operation state that the cooling of the air conditioner 51 has been started and the food is being heated by the cooking device 52 at the same time. The processor 130 compares the sensing data received from the temperature sensor 53 with the reference sensing data of the temperature sensor 53 corresponding to the composite operation state at a time corresponding to the determined composite operation situation.

The reference sensing data corresponding to such a complex operating situation is generated by the first reference sensing data of the temperature sensor 53 corresponding to the operating condition of the air conditioner 51 and the cooking device 52 And the second reference sensing data of the temperature sensor 53 corresponding to the operating conditions. Alternatively, the sensing data received by the temperature sensor 53 may be stored in the storage unit 120 as separate reference sensing data different from the first reference sensing data and the second reference sensing data, .

The processor 130 can determine whether or not an error has occurred in consideration of such a complex operating situation. For example, in a situation where the air conditioner 51 is operating at 18 degrees Celsius, Even if the sensing value corresponding to the temperature higher than the permissible range is output or the time taken until the temperature change state is detected is increased due to the heating in the cooking device 53, it is determined that there is an error in the temperature sensor 53 Errors can be prevented.

In the situation shown in FIG. 5, it may be difficult to judge the error of the temperature sensor by only the temperature value. This is because the temperature value may be influenced not only by the condition of the apparatus but also by the weather. Therefore, as described above, if an increase or decrease in temperature is analyzed, error detection can be performed.

6 is a diagram for explaining reference sensing data for each operating condition stored in the form of a look-up table.

Referring to FIG. 6, reference sensing data of sensors included in a home network may be stored in a storage unit 120 in the form of a look-up table for each operation status of electronic devices included in a home network. The reference sensing data xx of the first sensor corresponding to the operating condition A, the reference sensing data xxx of the second sensor corresponding to the operating condition A, the reference sensing data xxxx of the third sensor corresponding to the operating condition A, May be included in the look-up table. The reference sensing data (x) of the first sensor corresponding to the B operation state, the reference sensing data (-) of the second sensor corresponding to the B operation state, the reference sensing data xx ) May be included in the lookup table.

For example, the A operation state corresponds to a situation in which the TV 13 is turned on in Fig. 1, and the reference sensing data xx of the first sensor corresponding to the A operation state corresponds to when the TV 13 is powered on The reference sensing data xxx of the second sensor corresponding to the operating condition A is the reference sensing data of the first temperature / And the reference sensing data xxxx of the third sensor corresponding to the operating condition A may be the reference sensing data of the second temperature / illuminance sensor 17 when the TV 13 is powered on.

For example, the operation state of B corresponds to a situation in which the TV 13 is in the power saving mode and the air conditioning of the air conditioner 16 is activated in FIG. 1, and the reference sensing data of the first sensor xx is the reference sensing data of the first temperature / ambient light sensor 11 when the TV 13 is in the power saving mode and at the same time the cooling of the air conditioner 16 is activated and the reference sensing data of the second sensor The data (-) is the reference sensing data of the ambient light sensor 14 when the TV 13 is in the power saving mode and the air conditioning of the air conditioner 16 is activated, and the reference sensing data of the third sensor xx may be the reference sensing data of the second temperature / ambient light sensor 17 when the TV 13 is in the power saving mode and the air conditioning of the air conditioner 16 is activated.

The reference sensing data of the plurality of sensors stored in the storage unit 120 may include sensing data of all the sensors included in the home network. Alternatively, the reference sensing data stored in the storage unit 120 may be composed of sensing data only of sensors associated with the operation status among the sensors included in the home network. The sensors associated with the operating conditions may be selected as sensors for outputting changed sensing values corresponding to the operating conditions. For example, when the processor 130 analyzes the sensing data received from the power measurement sensor 18 and the temperature sensors 12 and 17 in the operating state in which the air conditioning of the air conditioner 16 is activated in FIG. 1, A sensor associated with an operation state in which the cooling of the air conditioner 16 is activated when it is determined that the sensing value is changed at a time point corresponding to the operating condition, the power measuring sensor 18 and the temperature sensors 12 and 17 can be selected have. The processor 130 determines that the temperature sensor 11 is not related to the operation state in which the cooling operation is performed if the sensing value is not changed by the temperature sensor 11 in the operating state in which the cooling operation of the air conditioner 16 is active can do.

In other words, the processor 130 may convert sensing data showing a change in sensing value at a time corresponding to a determined operation state among a plurality of sensing data received from each of the plurality of sensors to reference sensing data corresponding to the determined operation state And may be stored in the storage unit 120.

When the sensor associated with each operation state is designated, only the sensors associated with the operation state can be selected and compared with the reference sensing data at the time of occurrence of a specific operation situation. Therefore, the cost of data processing can be reduced.

While the above description has been made on the case where an error is determined in an operation state constituted by a product such as a TV or an air conditioner, a specific operation state can also be constituted by sensors.

Specifically, the processor 130 can determine the operation state based on the sensing data received from the plurality of sensors, and outputs the received sensing data to the storage unit 120 as reference sensing data corresponding to the determined operation state Can be stored. When it is determined that the same operation situation has occurred again, the processor 130 compares the sensing data received from the plurality of sensors with previously stored reference sensing data at a time point corresponding to the operation state, Can be determined. A specific example related to this embodiment will be described with reference to Fig.

7 is a view for explaining a method of determining a defect of a sensor in an operating state configured by sensors.

7, a sensor A (73) for sensing the opening and closing of the door is disposed on the front door, a sensor B (72) for sensing motion is disposed in the door door, a sensor C (71) are arranged in the house. The situation where the presence is detected in the sensor C (71) corresponds to " a situation in which someone enters the house ". In this situation, sensor A (73) detects the opening of the door and sensor B (72) detects motion. Therefore, the sensing data generated by each of the sensor B 72 and the sensor A 73 at the time corresponding to the situation where the presence of the sensor C 71 is detected is the presence in the sensor C 71 And may be stored in the storage unit 120 as reference sensing data corresponding to the sensed situation.

Based on these reference sensing data, the processor 130 can determine which sensor among the plurality of sensors has failed. The processor 130 can determine that the 'presence of someone in the house' has occurred when the presence of the sensor C 71 is detected, and when the B sensor 72 and the A sensor 73 Compares the received sensing data with the reference sensing data of the B sensor 72 and the reference sensing data of the A sensor 73 to determine whether the received sensing data is within the allowable range of the reference sensing data. If it is determined that the data received by the sensor A is within a predetermined allowable range of the reference sensing data of the sensor A and the data received by the sensor B is outside the predetermined allowable range of the reference sensing data of the sensor B, It can be judged that there is an error. In other words, when a person enters the house, the sensor detects that the door is closed at sensor A and the sensor is detected at sensor C, and sensor B does not detect motion, which means sensor B has an error.

Hereinafter, a method of determining which device has an error based on a result of comparing the reference sensing data with the received sensing data will be described in detail.

The processor 130 determines the operation state of at least one electronic device included in the home network, and determines whether each of the sensing data received from the plurality of sensors is a predetermined one of a plurality of sensor-specific reference sensing data corresponding to the determined operation state And determine whether the plurality of sensors and the at least one electronic device are in error based on the determination.

In this case, the processor 130 may determine that the at least one electronic device is in an error state with respect to the determined operation state if the sensor out of the predetermined allowable range among the plurality of sensors is equal to or greater than a predetermined ratio . The processor 130 may determine that the sensor out of the predetermined tolerance is in an error state if the sensor out of the predetermined tolerance among the plurality of sensors is less than the preset ratio. This embodiment will be described with reference to FIG.

4, when the processor 130 determines that the air conditioner 41 is operating in the cooling mode, the sensors associated with the determined operating conditions, namely, the first temperature sensor 42, the second temperature sensor 43 And the power sensor 44 compare the sensing data received from the three sensors with the reference sensing data corresponding to the operating condition of the air conditioner 41 of each of the three sensors.

Then, the processor 130 determines whether each of the sensing data received from the three sensors is within a predetermined allowable range of each of the three reference sensing data, and if the ratio of the sensor that deviates from the predetermined allowable range is preset Ratio. If the ratio is set to 2/3, if the sensing data of one of the three sensors is out of the allowable range of the reference sensing data, the processor 130 determines that there is an error in the sensor. If it is determined that the sensing data of two or more sensors out of the three sensors is out of the allowable range of the reference sensing data, the processor 130 may determine that there is an error in the cooling function of the air conditioner 31 have.

Meanwhile, the predetermined allowable range which is a reference of the comparison operation may mean a predetermined error range. The predetermined ratio serving as a reference of the comparison operation may be determined according to how many total number of sensing data to be compared are. For example, if the total number of sensing data to be compared is five, the ratio can be determined to be 3/5, and if the total number of sensing data to be compared is two, the ratio can be determined to be 2/2 have. Alternatively, the predetermined ratio can be determined so that the score can be compared based on the inconsistency information. For example, even if there are a total of two sensing data to be compared, the ratio may be set to 1.5 / 2.

In the above-described embodiment, if the sensor 130 is out of the preset tolerable range among the plurality of sensors, the sensor that is out of the preset tolerable range is determined to be in the error state. However, According to another embodiment, the error determination process may be performed again for the sensor, rather than determining that the error condition is immediately present. This will be described with reference to FIG.

10 is a diagram for explaining an error judgment process according to an embodiment of the present disclosure.

10, when the processor 130 determines that the first bulb 1005 is turned on, the sensors associated with the determined operating conditions, i.e., the first illuminance sensor 1007, the second illuminance sensor 1030, And the third illuminance sensor 1040 compares the sensing data received from the three sensors with the reference sensing data corresponding to the operating state of the first light bulb 1005 of each of the three sensors on a sensor-by-sensor basis.

Then, the processor 130 determines whether each of the sensing data received from the three sensors is within a predetermined allowable range of each of the three reference sensing data, and if the ratio of the sensor that deviates from the predetermined allowable range is preset Ratio. If the sensor data of the sensor of the third illuminance sensor 1040 is out of the allowable range of the reference sensing data among the three sensors, It is determined that there is a possibility of error in the memory 1040.

The processor 130 again performs an error determination process for the third illuminance sensor 1040 determined to have an error possibility.

Specifically, when the processor 130 determines at a different point in time that the second bulb 1060 is turned on, the sensors associated with the determined operating conditions, i.e., the third illuminance sensor 1040 and the fourth illuminance sensor 1050, The sensing data received from the two sensors are compared with the reference sensing data corresponding to the operating state of the second bulb 1060 of each of the two sensors on a sensor-by-sensor basis. The processor 130 determines whether each of the sensing data received from the two sensors is within a preset allowable range of each of the two reference sensing data, The third illuminance sensor 1040 finally determines that it is not in an error state.

10, even though the first bulb 1005 is turned on, the door of the room in which the third illuminance sensor 1040 is located is closed so that the third illuminance sensor 1040 can detect the presence of the first bulb 1005 It is possible to prevent the problem that the third illuminance sensor 1040 is judged to be erroneous because there is an error in the situation such as when it is impossible to sense the on state. That is, the error state of the sensor can be more accurately determined by performing the error determination process as described above.

8 is a flowchart for explaining an error detection method of the server 100 according to an embodiment of the present disclosure.

Referring to FIG. 8, information (810) of client devices (or IoT devices) is stored in the storage unit 120 of the server 100. The client device can be divided into a sensor and an actuator. The sensor is a device for sensing temperature, humidity, motion, room, power consumption, etc., and the actuator is a device for performing a specific function to cause a change in environment that can be detected by the sensor, and means a TV, an air conditioner, do.

The information 810 of the client devices includes information about the object that the sensor can measure and a list of control commands for controlling the actuator.

If the server 100 determines that the client device (IoT devices) performs an action (action) (S820), the server 100 determines whether the information (or action execution information) The sensing data (or sensor information) of the sensor is recorded in the storage unit 120 (S830). The server 100 analyzes the recorded information and extracts information about the attribute of the sensing data generated by the sensor during the operation (during the execution of the action) (S840).

The attribute of the sensing data may include a sensing value of the sensor corresponding to the performance of the action and / or a time taken until the sensing value is measured after the performance of the action. 4, the sensed values (temperature values) of the temperature sensors 42 and 43 corresponding to the operating state of the air conditioner 41 and the temperature sensors 42, 43), information on the time taken for the temperature change to be detected (10 minutes, 1 minute) can be extracted. 7, the sensed values of the motion sensor 72 and the door open / close detection sensor 73 may be extracted at a time corresponding to an operation state in which the room sensor 71 is detected, , Information on the time taken for the motion sensor 72 and the door open / close detection sensor 73 to detect motion or to detect the door open / close is extracted before and after the room sensor is detected by the occupant sensor 71 .

In operation S850, the server 100 generates a graph of a change in the attribute of the sensing data generated by the plurality of sensors in response to the operation status. For example, referring to FIG. 4, when the cooling of the air conditioner 41 is activated, the server 100 defines the relationship between the attributes of the plurality of sensing data generated by the plurality of temperature sensors 42 and 43 Create a graph. 7, when the room 100 is detected by the room sensor 71, the server 100 determines whether or not the attributes of the sensing data generated by the motion sensor 72 and the door open / close detection sensor 73 Create a graph that defines the relationship.

Then, the server 100 stores the generated relationship graph 870 in the storage unit 120. Then, the server 100 stores the information 880 on the sensors associated with the operation state (or action) in the storage unit 120. [ For example, referring to FIG. 7, the server 100 stores information on the motion sensor 72 and the front door closed detection sensor 73 in association with an action in which the room is detected.

The stored information is used for error detection when the same operation situation is judged later. Building such information can be done offline.

The error detection operation will be described below. The error detection operation can be performed on-line.

First, when it is determined that the operation of the client devices (IoT devices) is performed in the server 100 (S820), it is determined whether there is a defect (or an error) in the actuator associated with the operation status (S880). For example, the server 100 determines whether there is a defect in the air conditioner when it is determined that the air conditioner is in operation. Alternatively, the server 100 may perform an operation to determine whether there is a defect in the sensor (S885) if a sensor other than the actuator is associated with the determined operation state. Whether or not the sensor is defective can be performed periodically, instead of every time the operation state is determined.

First, the server 100 extracts devices related to the operation status (S890). Then, the server 100 determines whether each of the associated devices is defective (S891). Specifically, the server 100 compares the change of the attribute of the sensing data (S830) received from the sensor associated with the operation state with the previously stored association graph 870.

The server 100 scales based on the inconsistency information between the compared sensing data (S892) and determines whether the device associated with the operation status is defective (S893). As a result of the determination, if there is a defect, information on the defect is informed to the user terminal (S894).

The server 100 can transmit information on the device determined as having an error to the user terminal device. In this case, the server 100 can notify the user terminal device only when the number of times that it is determined that there is an error exceeds the preset number of times.

On the other hand, the server 100 can transmit not only the information about the error device but also the information about the determined operation status to the user terminal device. For example, referring to FIG. 4, the server 100 receives information indicating that an operation state in which the air conditioner 41 is operating in the cooling operation has occurred, and transmits information indicating that an error has occurred to the first temperature sensor 42, To the terminal device.

9 is a flowchart illustrating a method of controlling a server according to an embodiment of the present disclosure.

Referring to FIG. 9, the server 100 stores operation conditions of at least one electronic device in the home network and reference sensor data for a plurality of sensors (S910).

In this case, the reference sensing data of each of the plurality of sensors may be stored in the form of a lookup table for each operation state.

Meanwhile, when it is determined that the operation status of the at least one electronic device is a new operation status, the server 100 transmits the sensing data received from each of the plurality of sensors at a time corresponding to the new operation status to the new operation status And can be stored as corresponding reference sensing data.

Alternatively, the server 100 may store not only all of the sensing data received from each of the plurality of sensors as the reference sensing data, but only the sensing data associated with the determined operation state as reference sensing data.

In this case, the server 100 can determine that the sensing data showing a change in the sensing value at the time corresponding to the determined operation state is the sensing data related to the operation state. For example, when a sensing value change due to a temperature change appears in sensing data received from a specific temperature sensor in a specific operation state and a change in sensing value due to a brightness change occurs in sensing data received from the specific illuminance sensor, the server 100 The sensing data received by the specific temperature sensor and the specific illuminance sensor may be determined to be sensing data related to the specific operating condition in the specific operation state.

Specifically, when it is determined that the operation state of at least one electronic device in the home network is a new operation state, the server 100 determines whether the operation state of the at least one electronic device The sensing data showing the change of the sensing value may be stored as the reference sensing data corresponding to the new operation state.

In addition, when the operation status of the at least one electronic device is determined after the new sensor is registered in the home network, the server 100 determines the sensing data received from the new sensor at the time corresponding to the determined operation state, As the reference sensing data of the new sensor with respect to the operating condition.

The server 100 receives sensing data from a plurality of sensors in the home network (S920). The server 100 can continuously receive and store sensing data from a plurality of sensors. Alternatively, the server 100 may receive and store sensing data from a plurality of sensors at predetermined intervals.

Then, the server 100 determines the operation status of at least one electronic device included in the home network (S930).

In this case, the server 100 can determine the operation status based on the status information received from the at least one electronic device.

Then, the server 100 compares the stored reference sensing data corresponding to the determined operation state with the received sensing data (S940).

In this case, the server 100 compares a plurality of sensing data stored for each of the plurality of sensors, corresponding to the determined operation state, with a plurality of sensing data received from the plurality of sensors, It is determined whether one electronic device has an error (S950).

Specifically, the server 100 determines whether each of the sensing data received from the plurality of sensors is within a predetermined allowable range of a plurality of sensor-specific reference sensing data corresponding to the determined operation state, and based on the determination, And determine whether the plurality of sensors and the at least one electronic device are in error.

In this case, the difference between the reference sensing data and the received sensing data may be calculated. If the calculated difference is within the predetermined error range, it may be determined that the received sensing data is within the predetermined allowable range of the reference sensing data.

The server 100 determines that the at least one electronic device is in an error state in relation to the determined operation state if the sensor out of the predetermined allowable range of the plurality of sensors is equal to or greater than a predetermined ratio, The sensor that is out of the predetermined tolerance range may determine that the sensor is in an error state.

In this case, the ratio can be set according to the number of sensors to be compared. For example, when the number of sensors to be compared is 3, the ratio can be set to 2/3, and when the number of sensors to be compared is 4, the ratio can be set to 3/4. When the number of sensors to be compared is 5, the ratio can be set to 3/5. Alternatively, a value obtained from the reference scores of each device may be used as a ratio. For example, when the number of sensors to be compared is three and each reference score is given as 0.8, 0.5, and 0.2, 1.5 / 3 can be set as a ratio. However, the present disclosure is not limited to the above-mentioned ratio.

On the other hand, the server 100 may transmit to the user terminal device information about the device, which is judged as having an error, among the at least one electronic device and the plurality of sensors.

The user terminal may be a device having a display, and on the display of the user terminal, the name of the device with the error, the type of the device with the error, The date of the first registration on the network, and the like.

In addition, the server 100 may transmit not only the information about the at least one electronic device and the plurality of sensors, which are determined as having an error, but also information about the determined operation status to the user terminal.

In an environment where various kinds of devices exist in a house, it may be difficult for the user to know where the errory device is located only by the device information. However, according to the present embodiment, the user can more easily find the device in which the error has occurred, taking into account the operation state in which the error is determined. For example, the server 100 can transmit to the user terminal a message such as 'an error has occurred in the temperature sensor A in the state where the cooling of the air conditioner is operating' to the user terminal, and the user terminal device can display the received message have. Based on this message, the user can first check the temperature sensors in the room where the air conditioner is present, and find the temperature sensor A with the error.

According to the various embodiments described above, it is possible to more easily maintain the devices in an IoT environment in which a plurality of devices exist. In particular, according to various embodiments described above, it is possible for a user to easily grasp whether or not a user has failed, such as a sensor, which is difficult to confirm whether a failure has occurred, and also to provide a function of an electronic device, Saving mode function and the like can be easily grasped by the user. First of all, since the database required for detecting the occurrence of errors can be automatically constructed in the process of using the device, there is an advantage in that effort and time are not required to manufacture such a database separately. A database for error detection suitable for each environment can be constructed even in an unstructured IoT environment in which a user can freely arrange devices and freely assign functions to the devices.

Meanwhile, the processor 130 of the server according to the embodiment of the present disclosure can determine whether there is an error in a plurality of sensors and electronic devices by using a learning algorithm, and provide information on a determination result to a user.

11 to 13 show a data learning unit and a data recognition unit, which are generated in a processor of a server according to an embodiment of the present disclosure.

Referring to FIG. 11, the processor 130 according to some embodiments may include a data learning unit 1010 and a data recognizing unit 1020.

The data learning unit 1010 may generate or learn such that the data recognition model has a criterion for determining whether or not an error has occurred in a plurality of sensors and electronic devices. The data learning unit 1010 can apply the learning data to the data recognition model to generate a data recognition model having a determination criterion in order to determine a predetermined situation.

For example, the data learning unit 1010 may generate or learn a data recognition model using state information of a plurality of sensors and electronic devices as learning data, according to an embodiment of the present disclosure.

The data recognition unit 1020 can determine the situation based on the recognition data. The data recognition unit 1020 can determine whether the client devices are defective based on the predetermined recognition data using the learned data recognition model. The data recognizing unit 1020 acquires predetermined recognition data in accordance with a predetermined reference and applies the obtained recognition data to the data recognition model as an input value so that a plurality of sensors and electronic devices based on predetermined recognition data, (Or can estimate) the current time.

Further, the output result obtained by applying the obtained recognition data to the data recognition model as an input value can be used for updating the data recognition model.

In particular, the data recognition unit 1020 can obtain the result of determining whether the client devices are defective by applying the state information of the client devices to the data recognition model as the input values, according to an embodiment of the present disclosure.

At least a part of the data learning unit 1010 and at least a part of the data recognition unit 1020 may be implemented in a software module or in a form of at least one hardware chip and mounted on an electronic device. For example, at least one of the data learning unit 1010 and the data recognition unit 1020 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or may be a conventional general-purpose processor Or application processor) or a graphics-only processor (e.g., a GPU) and may be mounted on a server. At this time, the dedicated hardware chip for artificial intelligence is a dedicated processor specialized for probability calculation, and it has a higher parallel processing performance than conventional general purpose processors, so that it can quickly process computation tasks in artificial intelligence such as machine learning. When the data learning unit 1010 and the data recognition unit 1020 are implemented as a software module (or a program module including an instruction), the software module may be a computer-readable and non-volatile readable recording medium non-transitory computer readable media. In this case, the software module may be provided by an operating system (OS) or provided by a predetermined application. Alternatively, some of the software modules may be provided by an Operating System (OS), and some of the software modules may be provided by a predetermined application.

12 is a block diagram of a data learning unit 1010 according to an embodiment of the present disclosure.

Referring to FIG. 12, the data learning unit 1010 according to some embodiments may include a data obtaining unit 1010-1 and a model learning unit 1010-4. The data learning unit 1010 may further include at least one of the preprocessing unit 1010-2, the learning data selecting unit 1010-3, and the model evaluating unit 1010-5.

The data acquisition unit 1010-1 can acquire learning data necessary for learning for defect determination of client devices.

The learning data may be data collected or tested by the data learning unit 1010 or the manufacturer of the client devices. For example, the learning data may include sensing data of the sensors according to the present disclosure and information about the operational status of the electronic device. That is, it may include operation state information and sensing data of the electronic device.

The model learning unit 1010-4 can use the learning data to learn such that the data recognition model has a determination criterion as to how to determine whether or not the client devices are defective. For example, the model learning unit 1010-4 can learn a data recognition model through supervised learning using at least some of the learning data as a criterion. Alternatively, the model learning unit 1010-4 may perform self-learning by using learning data without any special guidance, for example, by performing unsupervised learning to find a criterion for determining whether or not a client device is malfunctioning , A data recognition model can be learned.

Also, the model learning unit 1010-4 may learn a selection criterion about which learning data should be used for determining whether or not the client devices are defective.

In particular, the model learning unit 1010-4 according to an embodiment of the present disclosure can generate or learn a data recognition model using operation state information of an electronic device and sensing data of a plurality of sensors as learning data.

On the other hand, the data recognition model may be a model that is built in advance and updated by learning of the model learning unit 1010-4. In this case, the data recognition model may be in a pre-built state by receiving basic learning data (e.g., operating state information of electronic devices and sensing data of a plurality of sensors).

The data recognition model can be constructed considering the application field of the recognition model, the purpose of learning, or the computer performance of the device. The data recognition model may be, for example, a model based on a neural network. The data recognition model can be designed to simulate the human brain structure on a computer. The data recognition model may include a plurality of weighted network nodes that simulate a neuron of a human neural network. The plurality of network nodes may each establish a connection relationship so that the neurons simulate synaptic activity of sending and receiving signals through synapses. The data recognition model may include, for example, a neural network model or a deep learning model developed in a neural network model. In the deep learning model, a plurality of network nodes are located at different depths (or layers) and can exchange data according to a convolution connection relationship.

For example, models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Bidirectional Recurrent Deep Neural Network (BRDNN) may be used as a data recognition model, but the present invention is not limited thereto.

According to various embodiments, the model learning unit 1010-4 may include a data recognition model for learning a data recognition model having a large relation between the input learning data and the basic learning data when a plurality of data recognition models constructed in advance exist You can decide. In this case, the basic learning data may be pre-classified according to the type of data, and the data recognition model may be pre-built for each data type. For example, the basic learning data may be pre-classified by various criteria such as an area where the learning data is generated, a time at which the learning data is generated, a size of the learning data, a genre of the learning data, a creator of the learning data, .

Also, the model learning unit 1010-4 can learn a data recognition model using, for example, a learning algorithm including an error back-propagation method or a gradient descent .

Also, the model learning unit 1010-4 can learn a data recognition model through map learning using, for example, a determination criterion as an input value for learning. Alternatively, the model learning unit 1010-4 can learn the data recognition model through learning of self-learning using necessary learning data without any guidance, for example, through non-learning learning for finding a criterion for judgment of a situation . Also, the model learning unit 1010-4 can learn the data recognition model through reinforcement learning using feedback as to whether the result of the situation judgment based on learning is correct, for example.

Further, when the data recognition model is learned, the model learning unit 1010-4 can store the learned data recognition model. In this case, the model learning unit 1010-4 can store the learned data recognition model in the memory of the server 130. [

The data learning unit 1010 includes a preprocessing unit 1010-2 and a learning data selection unit 1010-3 in order to improve recognition results of the data recognition model or to save resources or time required for generating a data recognition model. As shown in FIG.

The preprocessing unit 1010-2 may preprocess the data obtained by the data obtaining unit 1010-1 for use in learning for determining whether the client devices are defective.

For example, the preprocessing unit 1010-2 can process the acquired data into a predefined format so that the model learning unit 1010-4 can easily use the data for learning the data recognition model. The preprocessed data may be provided to the model learning unit 1010-4 as learning data.

Alternatively, the learning data selection unit 1010-3 can selectively select learning data necessary for learning from the preprocessed data. The selected learning data may be provided to the model learning unit 1010-4. The learning data selection unit 1010-3 can select learning data necessary for learning from the preprocessed data in accordance with a predetermined selection criterion. The learning data selection unit 1010-3 may also select learning data necessary for learning according to a predetermined selection criterion by learning by the model learning unit 1010-4. In one embodiment of the present disclosure, the learning data selection unit 1010-3 can select only the sensing data related to a specific client device among the input sensing data.

The data learning unit 1010 may further include a model evaluation unit 1010-5 to improve the recognition result of the data recognition model.

The model evaluating unit 1010-5 inputs the evaluation data to the data recognition model, and if the recognition result output from the evaluation data does not satisfy the predetermined criterion, the model evaluating unit 1010-5 can instruct the model learning unit 1010-4 to learn again have. In this case, the evaluation data may be predefined data for evaluating the data recognition model.

For example, when the number or the ratio of the evaluation data whose recognition result is not correct out of the recognition results of the learned data recognition model for the evaluation data exceeds a predetermined threshold value, the model evaluation unit 1010-5 It can be evaluated as unsatisfactory. For example, when a predetermined criterion is defined as a ratio of 2%, when the learned data recognition model outputs an incorrect recognition result for evaluation data exceeding 20 out of a total of 1000 evaluation data, Can be estimated that the learned data recognition model is not suitable.

On the other hand, when there are a plurality of learned data recognition models, the model evaluation unit 1010-5 evaluates whether each of the learned data recognition models satisfies a predetermined criterion, Can be determined as a model. In this case, when there are a plurality of models satisfying the predetermined criterion, the model evaluating section 1010-5 can determine any one or a predetermined number of models preset in descending order of the evaluation score as a final data recognition model.

At least one of the data acquisition unit 1010-1, the preprocessing unit 1010-2, the learning data selection unit 1010-3, the model learning unit 1010-4, and the model evaluation unit 1010-5 May be implemented as a software module or at least one hardware chip and may be mounted on a server. For example, at least one of the data acquisition unit 1010-1, the preprocessing unit 1010-2, the learning data selection unit 1010-3, the model learning unit 1010-4, and the model evaluation unit 1010-5 One may be made in the form of a dedicated hardware chip for artificial intelligence (AI), or may be fabricated as part of a conventional general purpose processor (e.g., a CPU or application processor) or a graphics dedicated processor (e.g., GPU) It can also be mounted on a server.

At least one of the data acquisition unit 1010-1, the preprocessing unit 1010-2, the learning data selection unit 1010-3, the model learning unit 1010-4, and the model evaluation unit 1010-5 Software module. At least one of the data acquisition unit 1010-1, the preprocessing unit 1010-2, the learning data selection unit 1010-3, the model learning unit 1010-4, and the model evaluation unit 1010-5, (Or a program module including an instruction), the software module may be stored in a computer-readable, readable non-transitory computer readable media. Also, in this case, the at least one software module may be provided by an operating system (OS) or by a predetermined application. Alternatively, some of the at least one software module may be provided by an Operating System (OS), and some of the software modules may be provided by a predetermined application.

13 is a block diagram of a data recognition unit 1020 according to some embodiments.

Referring to FIG. 13, the data recognition unit 1020 according to some embodiments may include a data acquisition unit 1020-1 and a recognition result providing unit 1020-4. The data recognizing unit 1020 may further include at least one of the preprocessing unit 1020-2, the recognition data selecting unit 1020-3, and the model updating unit 1020-5.

The data acquisition unit 1020-1 can acquire recognition data necessary for determining whether or not the client devices are defective.

The recognition result providing unit 1020-4 can determine whether the client devices are defective by applying the data obtained from the data obtaining unit 1020-1 to the learned data recognition model as an input value. The recognition result providing unit 1020-4 can provide the recognition result according to the data recognition purpose. Alternatively, the recognition result providing unit 1020-4 may apply the data preprocessed by the preprocessing unit 1020-2, which will be described later, to the learned data recognition model as an input value to provide the recognition result. Alternatively, the recognition result providing unit 1020-4 may apply the data selected by the recognition data selecting unit 1020-3, which will be described later, to the data recognition model as an input value to provide the recognition result.

The data recognition unit 1210 may include a preprocessing unit 1020-2 and a recognition data selection unit 1020-3 in order to improve recognition results of the data recognition model or to save resources or time for providing recognition results .

The preprocessing unit 1020-2 can preprocess the data acquired by the data acquisition unit 1020-1 for use in recognition for determining whether or not an error has occurred in the electronic device.

The preprocessing unit 1020-2 can process the acquired data into a predetermined format so that the recognition result providing unit 1020-4 can easily use the data for the situation determination. In particular, according to one embodiment of the present disclosure, the data acquisition unit 1020-1 acquires sensing data of a plurality of sensors to determine whether the client devices are defective, and the preprocessing unit 1020-2, , The sensing data can be preprocessed in a predefined format.

The recognition data selection unit 1020-3 can select the recognition data necessary for the situation determination among the preprocessed data. The selected recognition data may be provided to the recognition result provider 1020-4. The recognition data selection unit 1020-3 can select recognition data necessary for determining whether or not the client devices are defective in the preprocessed data according to a predetermined selection criterion. The recognition data selection unit 1020-3 can also select data according to a predetermined selection criterion by learning by the model learning unit 1010-4.

The model updating unit 1020-5 can control the data recognition model to be updated based on the evaluation of the recognition result provided by the recognition result providing unit 1020-4. For example, the model updating unit 1020-5 provides the model learning unit 1010-4 with the recognition result provided by the recognition result providing unit 1020-4 so that the model learning unit 1010-4 It is possible to control to update the data recognition model.

Meanwhile, the various embodiments described above can be implemented in a recording medium that can be read by a computer or a similar device using software, hardware, or a combination thereof. In accordance with a hardware implementation, the embodiments described in this disclosure may be implemented as application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays ), A processor, microcontrollers, microprocessors, and an electrical unit for carrying out other functions. According to a software implementation, embodiments such as the procedures and functions described herein may be implemented with separate software modules. Each of the software modules may perform one or more of the functions and operations described herein.

On the other hand, a method of controlling a server according to various embodiments of the present disclosure described above may be stored in a non-transitory readable medium. Such non-transiently readable media can be used in various devices.

A non-transitory readable medium is a medium that stores data for a short period of time, such as a register, cache, memory, etc., but semi-permanently stores data and is readable by the apparatus. In particular, the programs for carrying out the various methods described above may be stored in non-volatile readable media such as CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM and the like.

Further, the method according to the disclosed embodiments may be provided as a computer program product.

The computer program product may include a S / W program, a computer readable storage medium storing the S / W program, or a merchandise traded between the merchant and the purchaser.

For example, a computer program product may be a software program product (e.g., a downloadable application) that is electronically distributed through an electronic device or a manufacturer of an electronic device or an electronic marketplace (e.g., Google Play Store, . For electronic distribution, at least a portion of the S / W program may be stored on a storage medium or may be created temporarily. In this case, the storage medium may be a manufacturer or a server of an electronic market, or a storage medium of a relay server.

While the present invention has been particularly shown and described with reference to preferred embodiments thereof, it is to be understood that the disclosure is not limited to the specific embodiments thereof, It should be understood that various modifications may be made by those skilled in the art without departing from the spirit and scope of the present disclosure.

1000: Home network system

Claims (19)

1. A server for managing a home network,
A storage unit for storing operation states of at least one electronic device in the home network and reference sensor data for a plurality of sensors;
A communication unit for receiving sensing data from the plurality of sensors; And
Determining the operating status of the at least one electronic device and comparing the stored reference sensing data corresponding to the determined operating condition with the received sensing data to determine whether the plurality of sensors and the at least one electronic device And a processor for judging whether or not the server is a server. The method according to claim 1,
The processor comprising:
Determining whether each of the sensing data received from the plurality of sensors is within a predetermined allowable range of a plurality of sensor-specific reference sensing data corresponding to the determined operating condition, and based on the determination, And determines whether an error of the electronic device of the server is an error. 3. The method of claim 2,
The processor comprising:
If the sensor out of the predetermined allowable range among the plurality of sensors is equal to or greater than a predetermined ratio, the at least one electronic device is determined to be in an error state in relation to the determined operating condition,
And a sensor that is out of the predetermined allowable range is determined to be in an error state if the sensor out of the predetermined allowable range among the plurality of sensors is less than the preset ratio. The method according to claim 1,
The processor comprising:
When the operation state of the at least one electronic device is determined to be a new operation state, sensing data received from each of the plurality of sensors at a time corresponding to the new operation state is converted into reference sensing data corresponding to the new operation state Server to store in storage. The method according to claim 1,
The processor comprising:
Sensing data indicating a change in a sensing value at a time point corresponding to the new operation state among a plurality of sensing data received from the plurality of sensors, respectively, when it is determined that the operation state of the at least one electronic device is a new operation state, And stores the reference sensing data in the storage unit as reference sensing data corresponding to a new operation situation. The method according to claim 1,
The processor comprising:
The method according to claim 1, further comprising: when the operation state of the at least one electronic device is determined after the new sensor is registered in the home network, sensing data received from the new sensor at a time corresponding to the determined operation state, And storing the reference sensing data of the new sensor in the storage unit. The method according to claim 1,
The processor comprising:
Receive status information from the at least one electronic device, and determine an operational status of the at least one electronic device based on the received status information. The method according to claim 1,
The processor comprising:
Wherein the control unit controls the communication unit to transmit information on a device determined as an error among the at least one electronic device and the plurality of sensors to the user terminal device. The method according to claim 1,
The processor comprising:
Wherein the control unit controls the communication unit to transmit information on the determined operation state to the user terminal device together with information on the device determined as having an error among the at least one electronic device and the plurality of sensors. A control method of a server for managing a home network,
Storing operating conditions of at least one electronic device in the home network and a plurality of sensor-specific reference sensing data;
Receiving sensing data from the plurality of sensors;
Determining an operational status of the at least one electronic device; And
And comparing the stored reference sensing data corresponding to the determined operating condition with the received sensing data to determine whether the plurality of sensors and the at least one electronic device are in error. 11. The method of claim 10,
The method of claim 1,
Determining whether each of the sensing data received from the plurality of sensors is within a predetermined allowable range of a plurality of sensor-specific reference sensing data corresponding to the determined operating condition, and based on the determination, And determining whether or not an error in the electronic device of the server is detected. 12. The method of claim 11,
The method of claim 1,
If the sensor out of the predetermined allowable range among the plurality of sensors is equal to or greater than a predetermined ratio, the at least one electronic device is determined to be in an error state in relation to the determined operating condition,
And when the sensor out of the predetermined allowable range among the plurality of sensors is less than the preset ratio, the sensor that is out of the predetermined allowable range is determined to be in an error state. 11. The method of claim 10,
Wherein the storing step comprises:
Storing sensing data received from each of the plurality of sensors as reference sensing data corresponding to the new operation state at a time point corresponding to the new operation state when it is determined that the operation state of the at least one electronic device is a new operation state To control the server. 11. The method of claim 10,
Wherein the storing step comprises:
Sensing data indicating a change in a sensing value at a time point corresponding to the new operation state among a plurality of sensing data received from the plurality of sensors, respectively, when it is determined that the operation state of the at least one electronic device is a new operation state, And stores the reference sensing data as reference sensing data corresponding to a new operation situation. 11. The method of claim 10,
Wherein the storing step comprises:
The method according to claim 1, further comprising: when the operation state of the at least one electronic device is determined after the new sensor is registered in the home network, sensing data received from the new sensor at a time corresponding to the determined operation state, A method of controlling a server for storing reference sensing data of a new sensor. 11. The method of claim 10,
Wherein the step of determining the operation status comprises:
Receiving status information from the at least one electronic device and determining an operational status of the at least one electronic device based on the received status information. 11. The method of claim 10,
And transmitting information about a device determined as an error among the at least one electronic device and the plurality of sensors to the user terminal device. 11. The method of claim 10,
And transmitting information on the determined operation state to the user terminal device together with information on the device that is determined as having an error among the at least one electronic device and the plurality of sensors. A computer-readable recording medium containing a program for executing a control method of a server managing a home network,
In the control method,
Storing operating conditions of at least one electronic device in the home network and a plurality of sensor-specific reference sensing data;
Receiving sensing data from the plurality of sensors;
Determining an operational status of the at least one electronic device; And
And comparing the stored reference sensing data corresponding to the determined operating condition with the received sensing data to determine whether the plurality of sensors and the at least one electronic device are in error.

Images