KR20180029800A - Apparatus and Method for Adjusting Incident Rule for Error Anticipation of IoT Device - Google Patents

Abstract

The present invention relates to an incident rule adjusting method for providing an IoT device error anticipation service which comprises the following steps of: collecting reasonable data including installation data of an IoT device and real-time operation data; and searching for a performance variable influencing performance of the IoT device by analyzing the collected reasonable data and adjusting an incident rule in consideration of the searched performance variable to modify and control or replace a plurality of IoT devices.

Description

[0001] Apparatus and Method for Adjusting Incident Rule for Error Prediction for IoT Device Error Prediction [

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an Internet of Thing (IoT) technology interworking with a wireless network, and more particularly, to an apparatus and method for monitoring an IoT device

Recently, as the momentum of new growth, Internet of Things (also called "IoT") and Internet of Everything (also called "IoE") are being presented.

This IoT and all things internet means the concept that all objects that can communicate can be connected to the network to perform mutual communication. All objects that can be systematically recognized are categorized as things or objects. These objects are equipped with local and remote communication functions including RFID, and can be used as objects (or sensor nodes) capable of producing and using data, such as sensors, And may be included therein. Here, since the Internet of the future is an Internet of the future in which all things are connected to the Internet as IoT evolves, the Internet is collectively referred to as IoT.

These IoT devices are installed and operated in various places. After the IoT environment is established, it is time to take measures such as replacing parts as time passes. At this time, the IoT devices scattered in various places, The timing of replacement may not always be constant. If the management of many IoT devices installed at different positions is not performed, normal parts replacement will not be performed at the time of part replacement, so that the operation of the IoT device is interrupted and the normal operation of the IoT device becomes impossible .

Therefore, it is necessary to manage the operation state data of the IoT devices so that effective measures can be taken before the operation of the IoT devices is stopped.

The present invention provides an apparatus and method for adjusting an incident rule for IoT device error prediction, which enables effective measures to be taken before the operation of each IoT device is performed by managing the operation state data of the IoT device.

The present invention provides an apparatus and method for adjusting an incident rule for error prediction of an IoT device, such that error prediction corresponding to the environment in which the IoT device is installed can be performed.

The present invention relates to an incident rule adjustment method for providing an IoT device error prediction service, the method comprising: collecting basis data including installation data and real-time operation data of an IoT device; analyzing the collected basis data, And adjusting the incident rule in consideration of the detected performance variable.

The present invention relates to an incident rule coordinator for providing an IoT device error prediction service, comprising: a device data collection unit for collecting basis data including installation data and real-time operation data of an IoT device; And an incident rule adjuster for searching for a performance variable that affects the performance of the IoT device and adjusting an incident rule in consideration of the detected performance variable.

According to the present invention, it is possible to adjust the incident generation rule for error prediction of the IoT device according to the environment in which the IoT device is installed, so that accurate error prediction can be derived according to the installation environment and the application of the device correction, Or to suggest improved management measures.

1 is a schematic configuration diagram of an IoT device management system to which the present invention is applied.
2 is a schematic block diagram of an incident rule adjusting apparatus for error prediction of an IoT device according to an embodiment of the present invention.
3 is a diagram showing an example of IoT device data collected according to the present invention.
4 is a diagram showing an example of a layered structure of incident rules according to the present invention.
5 is a flowchart illustrating an incident-based rule adjustment method for error prediction of an IoT device according to an exemplary embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS 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 invention rather unclear. , Which may vary depending on the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification.

Each block of the accompanying block diagrams and combinations of steps of the flowcharts may be performed by computer program instructions (execution engines), which may be stored in a general-purpose computer, special purpose computer, or other processor of a programmable data processing apparatus The instructions that are executed through the processor of the computer or other programmable data processing equipment will generate means for performing the functions described in each block or flowchart of the block diagram.

These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible for the instructions stored in the block diagram to produce an article of manufacture containing instruction means for performing the functions described in each block or flowchart of the flowchart.

And computer program instructions may be loaded onto a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform the data processing equipment provide the steps for executing the functions described in each block of the block diagram and at each step of the flowchart.

Also, each block or step may represent a portion of a module, segment, or code that includes one or more executable instructions for executing the specified logical functions, and in some alternative embodiments, It should be noted that functions may occur out of order. For example, two successive blocks or steps may actually be performed substantially concurrently, and it is also possible that the blocks or steps are performed in the reverse order of the function as needed.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the following embodiments of the present invention may be modified into various other forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to enable those skilled in the art to more fully understand the present invention.

1 is a schematic configuration diagram of an IoT device management system to which the present invention is applied.

1, the IoT device management system includes a plurality of IoT devices 10-1, 10-2, ..., 10-n, an IoT device management server 20 and an administrator terminal 30, And is implemented in a communicable state via a network.

Here, the IoT devices 10-1, 10-2, ..., 10-n and the IoT device management server 20 exchange data with each other through an Internet-based network, It can be developed to increase the efficiency while considering compatibility by adopting the international standard Message Queuing Telemetry Transport (MQTT) or Device Message Transport Protocol (DMTP). Here, the MQTT protocol is a method in which a sender publishes a specific message through a message broker instead of a client / server method commonly used in push technology, and a receiver subscribes to a message And DMTP is a protocol that can express a large number of states that can not be represented by MQTT that can represent the existing four states.

The IoT devices 10-1, 10-2, ..., 10-n are devices capable of performing communication with each other by connecting to the Internet. The devices include sensors, smart devices, smart buildings, smart factories, Devices, drones, and the like. ..., 11-n) are assigned to the IoT devices 10-1, 10-2, ..., 10-n according to an embodiment of the present invention And is capable of communicating with the IoT device management server 20 in a NAT environment or the like, collecting real-time status measurement data according to an operation at a predetermined cycle, and transmitting the collected data to the IoT device management server 20. According to one embodiment, the agent 11 has a function of receiving control signals from the IoT device management server 20 to perform device control, and a function of controlling the IoT devices 10-1, 10-2, ..., 10-n can transmit screen data output to the IoT devices 10-1, 10-2, ..., 10-n in response to a remote control request from the IoT device management server 20 And the like.

The IoT device management server 20 includes agents 11-1, 11-2, ..., 11-n installed in the plurality of IoT devices 10-1, 10-2, ..., 10- (10-1, 10-2, ..., 10-n) on the basis of the big data consisting of the real-time state measurement data accumulated for a predetermined time And provides the analyzed statistical data to the administrator terminal 30.

In addition, the IoT device management server 20 predicts the occurrence of an error in advance and delivers an incident message to the administrator terminal 30 so that an action can be taken before the error occurs. That is, the measurement data is collected for each of the plurality of IoT devices 10-1, 10-2, ..., 10-n, and extracted by the manufacturer and standard data collected for a predetermined period of time The abnormal signal is automatically monitored and transmitted to the administrator terminal 30 before an error occurs. Here, the incident message can be set in steps of normal, warning, danger, replacement, and the like. Incident messages may also be sent via email, SMS, ARS, or the like.

The administrator terminal 30 is provided with a UI of the WISIWIG method for monitoring, and an application for each smart device that allows the administrator to carry it so that the administrator can confirm it and share the contents with his / her own device. The manager can access the IoT device management server 20 via the administrator terminal 30 to monitor data on the IoT devices 10-1, 10-2, ..., 10-n, Upon receipt of the incident message transmitted from the IOT device management server 20, the corresponding IoT device may take measures corresponding thereto to prevent the occurrence of an error in advance.

By the way, the IoT device management server 20 analyzes the collected data as described above, and provides the pre-service by applying the values capable of normal operation in each IoT device on the basis of the threshold of each step. Here, the threshold value is generally set to an operating time and an operation standard that can be used in accordance with a manufacturer's standard. That is, regardless of the environment in which the IoT device is installed, incidents are generated based on the same threshold value.

For example, if the operating temperature of the IoT device is 70 degrees or more, and if it is set to generate an 'alert' incidence, a warning is issued if the temperature is 70 degrees or more throughout the year. That is, the same criteria are applied in December, when the average temperature is 10 degrees Celsius, and in August, when the average temperature is 10 degrees Celsius, so seasonal factors including temperature, climate and humidity and various variable conditions Do not. However, in practice, the variables that determine the performance of the IoT device vary depending on the environment of the installation place, so it is necessary to determine the incident occurrence in consideration of these performance variables.

Accordingly, the present invention proposes an apparatus and method for adjusting an incident rule, which is a criterion for generating an incident, by taking into account variables that determine performance depending on the environment in which the IoT device is installed.

FIG. 2 is a schematic diagram of an incident rule adjusting apparatus for error prediction of an IoT device according to an embodiment of the present invention, and FIG. 3 is a diagram illustrating an example of IoT device data collected according to the present invention.

Referring to FIG. 2, an apparatus for adjusting an incident rule for error prediction of an IoT device according to an exemplary embodiment of the present invention includes an IoT device data collection unit 210 and an incident rule adjustment unit 220.

The IoT device data collection unit 210 collects basis data including installation data and real-time operation data of the IoT device, and more specifically includes a device installation data collection unit 211 and an incident-based data collection unit 212 .

The device installation data collection unit 211 collects installation data for each of the IoT devices 10-1, 10-2, ..., 10-n, and the device management item 310 shown in FIG. 3 is an example . That is, it may include at least one of installation company, installation point, installation place, installation date, date of receipt, date of manufacture of the apparatus, model information, and revision information.

The incident-based data collection unit 212 collects real-time operation state information of the IoT devices 10-1, 10-2, ..., 10-n. This is because the data measured at predetermined intervals by the agents 11-1, 11-2, ..., 11-n installed in the respective IoT devices 10-1, 10-2, ... 10- State information of the components or devices constituting each of the IoT devices 10-1, 10-2, ... 10-n, and status information of the process to be operated are received and acquired. The monitoring / control data 321, 322 shown in FIG. 3 may be an example. That is, the CPU usage (Usage), the memory usage, the device or CPU fan speed, the hard disk space (HDD) operation status, the component temperature, the device temperature and the CPU temperature . In addition, real-time status information about a process operated in the IoT devices 10-1, 10-2, ... 10-n, such as an application, may be included.

The incident rule adjuster 220 analyzes the collected evidence data to search for performance variables that affect the performance of the IoT device, and adjust the incident in consideration of the detected performance variable. That is, in order to actively expand the system in consideration of the aging of the apparatus, performance degradation, and seasonal variables and local variables, it is possible to automatically extract the parameters for each time period and region and automatically change the threshold value for each apparatus So that the function can be maintained as normal as possible. In other words, in order to judge the danger signal of each device through the incident (event) of each device, it is applied simply to the incident step, and the correlation index between the incidents is weighted to quantitatively analyze the status of the entire module and system, It is equipped with the function to cope with the risk. Here, the weights set for setting the correlation index may be automatically adjusted based on the superimposed data obtained through the operation using a variety of methods (for example, an average value within the standard deviation of the collected data) Or to provide suggestions to the administrator.

For example, the meteorological data on the climate is collected on the basis of Big Data (22), and 1-12 months after the data analysis for the past 10 years, the range that the device can operate is extracted and offered automatically by month / week / day.

In another example, when a module is configured as a combination of devices, a weight is set for the module, and this is automatically analyzed based on the Big Data. For example, for a device that combines a CPU and a memory, we assign a weight to the failure rate through analysis of big data on the failure rate of the same CPU and memory, and then extract and propose the failure rate of the entire module. These weights are extended to devices, modules, and the entire system, and the ruleset automation accordingly is handled.

Incident rules determined by the incident rule coordinator 220 have a hierarchical structure and may be interworked with each other.

4 is a diagram showing an example of a structure of a layered incident rule according to the present invention.

Referring to FIG. 4, an apparatus-specific incident rule 410, a multiple-apparatus complex incident weight rule 420, and an integrated incident weight rule 430 are configured for each layer. For example, in the case of a smart building, the device-specific incident rule 410 may be an incident rule of the IoT device installed in one room of one floor, and the multi- And the integrated incident-based rule 430 may correspond to the incidence rule of the entire building. That is, if the device-specific incident rules 411 and 412 are the incident rules of the IoT devices installed in the first floor, the multi-device compound incident rule 421 may be an incident rule corresponding to the first floor. Accordingly, the incident rule adjuster 220 adjusts the multiple incident multiple incident weight rules by assigning weights to each of the two or more IOT device incident rules, and adjusts the integrated incident weight rules by assigning weights to the two or more multiple component multiple incident weight rules . For example, if one floor of a smart building is changed from a shopping mall to a hospital, incident-based rules for each device may be adjusted for each of a plurality of IoT devices installed in the corresponding floor, depending on the device- , And multi-device complex incidence weighting rules for the layer may be adjusted by weighting the adjusted device-based incident-based rules. The integrated incidence weighting rule, which makes the adjusted multi-component complex incident weighting rule a lower layer, can also be weighted and adjusted.

The incident rule adjusting unit 220 provides the error predicting unit 21 with the adjusted incident rule as described above, and causes the error predicting unit 21 to perform the error predicting operation using the adjusted incident rule.

5 is a flowchart illustrating an incident rule adjustment method for providing an error prediction service of an IoT device according to an embodiment of the present invention.

Referring to FIG. 5, an incident rule coordinator (hereinafter referred to as 'device') for providing an IoT device error prediction service collects basis data including installation data of the IoT device and real-time operation data for a predetermined period of time ). Here, the installation data of the IoT device may include at least one of installation company, installation point, installation place, installation date, date of receipt, date of manufacture of the device, model information and revision information, Current status data of a part or a process operated on the IoT device.

The apparatus analyzes the collected basis data and searches performance variables that affect the performance of the IoT device (S520). Then, the incident rule is adjusted in consideration of the searched performance variable (S530). For example, when the apparatus is composed of a plurality of parts, the failure rate for each of the parts is weighted, and then the incident rule is adjusted according to the given weight.

Then, the device predicts an error of the IoT device based on the adjusted incident-based rule (S540). Although not shown in the figure, when an error is predicted to occur, the report is sent to the administrator terminal 30. [

Claims (9)

Collecting basis data including installation data of the IoT device and real-time operation data;
Analyzing the collected ground truth data to search for a performance parameter that affects the performance of the IoT device, and adjusting the incident rule in consideration of the detected performance parameter. Incident rule adjustment method for.
2. The apparatus according to claim 1, wherein the installation data of the IoT device
An installation company, an installation point, an installation location, an install date, an arrival date, an apparatus manufacture date, model information, and revision information.
2. The method of claim 1, wherein the real-
Wherein the IoT device includes current state data of a component constituting the IoT device or a process operating in the IoT device. 2. The method of claim 1, wherein the adjusting
Wherein when the device is a combination of a plurality of parts, the failure rule for each of the parts is weighted, and then the incident rule is adjusted according to the assigned weight. .
A device data collecting unit for collecting the basis data including the installation data and the real-time operation data of the IoT device,
And an incident rule adjuster for adjusting an incident rule in consideration of the detected performance parameter by analyzing the collected basis data to search for a performance variable that affects the performance of the IoT device, Incident rule coordinator for service delivery.
6. The apparatus of claim 5, wherein the device data collecting unit
And a device installation data collection unit for collecting at least one of installation company, installation point, installation place, installation date, date of purchase, device manufacturing date, model information and revision information. Device.
6. The apparatus of claim 5, wherein the device data collecting unit
And an incident-based data collection unit for collecting current state data of a component constituting the IoT device or a process operating in the IoT device.
The method of claim 5, wherein the incident rule adjustment unit
Wherein when the device is a combination of a plurality of parts, the failure rule for each of the parts is weighted, and then the incident rule is adjusted according to the assigned weight. .
The method of claim 5, wherein the incident rule adjustment unit
An integrated incident weighting rule which is determined by assigning a weight to each of the at least two IoT device incident rules and the at least two IoT device incident rules and weighting the at least two IoT device incident rules, And adjusting the state of the IoT device to have a hierarchical structure.

Images