Integrated edge terminal with micro ai that enables simultaneous connection to massive IoT and WIFI network

Abstract

To provide an integrated edge terminal with a micro AI that enables simultaneous connection to a massive IoT and WiFi network.SOLUTION: An integrated edge terminal includes: a SOMAIoT adapter unit equipped with a massive IoT connection protocol and a micro AI function, configured to perform signal processing on data collected from an IoT device to be transmitted wirelessly to an AI edge gateway, and operated in cooperation with a SOMPAWiFi station unit to enable upgrade and management function; and a SOMPAWiFi station unit including SOMPA, equipped with a WiFi protocol and the micro AI function, configured to perform WiFi signal processing on data collected from a WiFi device to be transmitted to the AI edge gateway, and integrate the SOMAIoT adapter unit, for authentication, security and energy management and upgrade management for a micro AI model.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an integrated edge terminal equipped with ultra-compact AI that can simultaneously connect to ultra-large-scale IoT and WiFi networks and is equipped with a solution that can transmit not only ultra-large-scale IoT data but also video data in parallel, enables stable and reliable data transmission even in poor radio wave environments, and solves the problem of managing IoT terminals installed on an ultra-large scale. [Background technology]

[0002] Generally, a low power wide area network (LPWAN) is a low power wireless wide area network that has a very wide service area (10km or more) and provides communication speeds of several hundred kilobits per second (kbps). It is used as a dedicated network for the Internet of Things (IoT), which connects things to the network.

[0003] LPWANs include LoRa (registered trademark), SigFox (registered trademark), NB-IoT, etc., and most of them have technical limitations in terms of data stability and coverage. For example, some cities have installed LoRaWAN (Long Range WAN) and installed up to 45,000 meter reading devices for remote water meter reading, but problems have arisen on-site, such as a 4% non-reception rate due to the excessive number of connected devices.

[0004] Therefore, in the case of a hyper-connected smart city environment where various types of data are mixed, it is necessary to provide a stable and reliable connection environment for processing massive sensor data generated in applications such as transportation, environment, energy, and safety.

[0005] To solve this problem, the Korea Communications Technology Association (TTA) established the Differentiated Wireless Channel Access based Low Power Wide Area Network (dcaLPWAN) standard.

[0006] dcaLPWAN is an LPWAN technology that provides wireless channel access in a newly designed manner that is differentiated according to the characteristics of various IoT application services, while the physical layer is connected using the LoRa method. This technology is a low-power wide area network technology that can support priority-based competitive channel access and reservation-based non-competitive channel access in consideration of the characteristics of each service class.

[0007] As shown in FIG. 1, the dca LPWAN system includes an IoT device 10 that collects various types of data such as temperature, humidity, and PM2.5, a terminal 20 that transmits the data collected by the IoT device 10 to an RF gateway 30 through wireless communication, the RF gateway 30 that performs a packet transmission function between the terminal 20 and a network controller 40, the network controller 40 that manages the terminal 20 and the RF gateway 30, configures a network, processes user commands, etc., an edge gateway 50 that performs pre-processing and intelligent analysis of data collected in the dca LPWAN, and an application server 60 that performs computing functions for various applications and service processing.

[0008] One of the many challenges facing the widespread adoption of LPWANs, including dcaLPWANs, is the stable and reliable acquisition of sensor data.

[0009] Even if a low-power wide-area network is constructed, many problems can occur due to poor radio wave environments, such as mutual radio wave interference and failures, depending on the installation environment of large-scale sensors.

[0010] In addition, radio waves generally have a tendency to be difficult to reach underground, so in order to obtain sensor data from underground objects, a separate relay device must be installed underground and connected to a transmission device above ground, creating many bottlenecks in terms of cost and technology.

[0011] Many smart city applications have the problem that simply analyzing IoT data to grasp the situation is not enough to accurately recognize the on-site situation.

[0012] For example, in the case of flood detection applications in urban areas, accurate situation assessment can only be achieved by analyzing not only sensor data but also video data monitoring the site.

[0013] In addition, construction sites in urban areas may need to set up separate local networks that are separate from the smart city network, and collect and analyze various on-site sensor data and video data through these networks.

[0014] However, video data cannot be transmitted only through LPWAN, so it must usually be sent through WiFi. This can be solved by installing a separate WiFi terminal that can collect video data at the site along with the IoT terminal and connecting the camera.

[0015] However, depending on the situation at the site, it may be more cost-effective and efficient to integrate the terminal 20 into an IoT terminal and a WiFi terminal to reduce the number of terminals, rather than installing them separately, so application to a composite terminal is necessary.

[0016] Massive IoT is composed of numerous sensors and terminals. Therefore, the biggest problem is maintaining the large-scale terminals 20. Failures and errors in the terminals 20 are generally identified by the network controller 40 or the edge gateway 50.

[0017] However, it is difficult to determine whether the terminal 20 has broken down or there is an error in the wireless connection, and there is a problem in that it is necessary to check whether the terminal 20 has broken down on-site.

[0018] Another maintenance issue is updating terminal systems. LPWANs mostly require terminals to be updated over the wireless network, or by individual terminals using wired, NFC, Bluetooth, etc.

[0019] Such updates take a long time due to the very low transmission speed, and for a large number of installed terminals, a passive method would be very costly and time-consuming. If the update time is long, the sensor may not be able to collect data, causing serious disruption to the network operation.

[0020] Also, in the case of a terminal equipped with an ultra-compact AI function, a new model learned in a separate AI server using previously collected data must be updated to each corresponding terminal 20. Therefore, in the IoT field, a new method is required to solve the problem of maintaining and updating the terminal 20 and the problem of updating the inference SW when the terminal is intelligentized by equipping it with an ultra-compact AI. [Prior art documents] [Patent documents]

[0021] [Patent Document 1] Korean Patent Publication No. 10-2020-0023719 [Patent Document 2] Korean Patent No. 10-1017690 [Patent Document 3] Korean Patent No. 10-1591920 [Patent Document 4] Korean Patent No. 10-2422163 Summary of the Invention [Problem to be solved by the invention]

[0022] The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide an integrated edge terminal equipped with an ultra-compact AI that can simultaneously connect to ultra-large-scale IoT and WiFi networks, and that is capable of transmitting not only ultra-large-scale IoT data but also video data in parallel, and that is capable of stable and reliable data transmission even in poor radio wave environments and that is equipped with a solution that can solve the problem of managing IoT terminals installed on an ultra-large scale. [Means for solving the problem]

[0023] To achieve this objective, the present invention provides a terminal that integrates and connects IoT devices and WiFi devices on a low-power wide area network for IoT and a WiFi communication network, and is characterized by including: a SOMA IoT adapter unit equipped with SOMPA and having an ultra-large-scale IoT connection protocol and an ultra-compact AI function, which performs signal processing on data collected from the IoT device and wirelessly transmits it to an AI edge gateway, and performs upgrade and management functions in conjunction with a SOMPA WiFi station unit; and a SOMPA WiFi station unit equipped with SOMPA and having a WiFi connection protocol and an ultra-compact AI function, which performs WiFi signal processing on data collected from the WiFi device and transmits it to the AI ​​edge gateway, and integrates the SOMA IoT adapter unit to manage authentication, security, and energy, and manage upgrades to ultra-compact AI models.

[0024] In addition, according to the present invention, the SOMAIoT adapter unit is The IoT device interface is connected to an IoT device including an ultra-large-scale IoT sensor to transmit and receive signals; an IoT data processing unit that performs a series of tasks on an ultra-compact AI model base, such as analyzing and processing data received from the IoT device interface, checking the validity of the data, and filtering the data, and updates the AI ​​model in conjunction with an ultra-compact AI model update unit of the SOMPA WiFi station; and an IoT data transceiver unit that is equipped with SOMPA and wirelessly transmits data input from the IoT data processing unit to an IoT RF gateway of an external AI edge gateway and in conjunction with a system management unit of the SOMPA WiFi station.

[0025] In addition, according to the present invention, the IoT data processing unit periodically monitors the power consumption of the SOMA IoT adapter unit using the installed ultra-compact AI, and transmits a system status message of the SOMA IoT adapter unit to the system management unit of the SOMA WiFi station unit through the IoT data transceiver unit.

[0026] According to the present invention, the SOMPA WiFi station unit is The device includes a WiFi device interface connected to a WiFi device including a camera to transmit and receive data; a WiFi data processing unit that performs a series of operations of analyzing and processing the data received through the WiFi device interface, checking the validity of the data, and filtering the data based on an ultra-compact AI model; a WiFi data transceiver unit that is equipped with SOMPA and wirelessly transmits data input from the WiFi data processing unit to a WiFi access point of an external AI edge gateway to link the data; a security management unit that performs authentication, data encryption, and security protocol management of the SOMPA IoT adapter unit and the SOMPA WiFi station unit; an ultra-compact AI model update unit that integrates, updates, and manages the ultra-compact AI models of the SOMPA IoT adapter unit and the SOMPA WiFi station unit by updating a model learned in an external AI edge server based on new data to enable analysis of the latest data; and a system management unit that monitors energy usage to extend battery life through efficient energy management and manages the SOMPA IoT adapter unit and the SOMPA WiFi station unit.

[0027] In addition, according to the present invention, the system management unit uses the installed ultra-compact AI to periodically monitor the power consumption of the SOMPA WiFi station unit to check its status, periodically connects to the SOMAIot adapter unit to check its status, and transmits the confirmed status message to a higher-level WiFi access point or an integrated gateway.

[0028] In addition, according to the present invention, the SOMPA applied to the SOMAIoT adapter unit is an omni-antenna that uses the polarized current effect to radiate radio waves in a perfect circle in all directions of 360°, The SOMPA applied to the SOMPA WiFi station unit is characterized by being a directional MIMO antenna that radiates radio waves in a certain direction by utilizing the polarized current effect. Effect of the Invention

[0029] As described above, the present invention has the advantage that sensor data and video data can be simultaneously transmitted by an integrated terminal, allowing for more accurate and reliable analysis of on-site conditions, and greatly reducing installation costs even in difficult installation locations.

[0030] In addition, the present invention provides a solution that can fundamentally solve the problems of managing and maintaining a large number of terminals installed on a large scale, such as updating and fault detection for a large number of terminals, which are problems in conventional large-scale IoT network systems. [Brief description of the drawings]

[0031] [Figure 1] FIG. 1 is a diagram illustrating a conventional TTA standard differentiated channel access based low power consumption wide area network (dcaLPWAN) system. [Diagram 2] FIG. 2 is a diagram showing a dcaLPWAN system according to the present invention, which can be simultaneously connected to an ultra-large-scale IoT and WiFi network and is applied to an integrated edge terminal equipped with an ultra-compact AI. [Diagram 3] FIG. 3 is a detailed diagram of an integrated edge terminal equipped with ultra-compact AI that can be simultaneously connected to ultra-large-scale IoT and WiFi networks according to an embodiment of the present invention. [Figure 4] FIG. 4 is a diagram showing a manhole smart node system for explaining the SOMPA technology applied to the present invention. [Diagram 5] FIG. 5 is a diagram showing a configuration for testing the system of FIG. [Figure 6] FIG. 6 is a diagram showing a configuration in which the SOMPA of FIG. 4 is actually installed inside a manhole. [Figure 7] FIG. 7 is a table showing the results of technical comparison performance measurements between the SOMPA applied to the present invention and a conventional omni-antenna. [Figure 8] FIG. 8 is a graph comparing the performance of the ultra-large-scale IoT system according to the present invention with the conventional LoraWAN system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0033] First, when assigning reference numerals to components in each drawing, it should be noted that the same reference numerals are used for the same components even if they are shown in different drawings. Furthermore, when describing the present invention, detailed descriptions of related publicly known functions or configurations are omitted if it is determined that such descriptions may unnecessarily obscure the gist of the present invention.

[0034] FIG. 2 is a diagram showing a dcaLPWAN system according to the present invention, which can be simultaneously connected to an ultra-large-scale IoT and WiFi network and is applied to an integrated edge terminal equipped with an ultra-compact AI.

[0035] As shown in the figure, the dca LPWAN system to which the integrated edge terminal 200 according to the present invention is applied is as follows: It includes an IoT device 110, a WiFi device 120, an integrated edge terminal 200, an AI edge gateway 300, an edge network controller 400, and an AI edge server 500.

[0036] The IoT device 110 collects various types of data such as temperature, humidity, PM2.5, etc. and transmits it to the integrated edge terminal 200, and the WiFi device 120 includes a device such as a large-capacity data sensor or a camera and transmits the collected data (e.g., video signals) to the integrated edge terminal 200.

[0037] The AI ​​edge gateway 300 is located in front of the edge network controller 400 and integrates data received from the integrated edge terminals 200, analyzes the data based on an AI algorithm, and makes decisions.

[0038] The edge network controller 400 is connected to the AI ​​edge gateway 300 and serves to manage and control the integrated network.

[0039] The AI ​​edge server 500 performs pre-processing and intelligent analysis of data collected in the dca LPWAN.

[0040] In the dca LPWAN system having the above configuration, the integrated edge terminal 200 according to the present invention integrates and connects the IoT device 110 and the WiFi device 120, is equipped with an antenna that uses the electro-polarization effect (hereinafter referred to as "SOMPA" or "electro-polarization effect antenna"), embodies ultra-compact AI functions and management functions, and transmits data collected from the IoT device 110 and the WiFi device 120 to the AI ​​edge gateway 300 via the electro-polarization effect antenna (SOMPA: Synchronized Orthogonal Multi-Polarization Antenna).

[0041] More specifically, the integrated edge terminal 200 includes a SOMA (SOMPA Massive AI) IoT adapter unit 210 and a SOMPA WiFi station unit 220, as shown in FIG.

[0042] The SOMA IoT adapter unit 210 is equipped with a SOMPA 213a and has an ultra-large-scale IoT connection protocol and ultra-small AI functions, and is configured to process data collected from the IoT device 110, wirelessly transmit it to the AI ​​edge gateway 300, and perform upgrade and management functions in conjunction with the SOMPA WiFi station unit 220.

[0043] The SOMPA WiFi station unit 220 is equipped with a SOMPA 223a and has a WiFi connection protocol and ultra-small AI functions, and is configured to process the WiFi signal of data collected from the WiFi device 120 and transmit it to the AI ​​edge gateway 300, and to integrate the SOMA IoT adapter unit 210 to perform authentication, security, and energy management, as well as upgrade management for ultra-small AI models.

[0044] The SOMA IoT adapter unit 210 includes an IoT device interface 211, an IoT data processing unit 212, and an IoT data transmission / reception unit 213.

[0045] The IoT device interface 211 is connected to an IoT device 110 such as a super large-scale IoT sensor or actuator, and performs a function of transmitting and receiving signals.

[0046] The IoT data processing unit 212 performs a series of tasks of analyzing and processing the received data, checking the validity of the data, and filtering the data based on the ultra-compact AI model, and performs a function of updating the model in conjunction with the ultra-compact AI model update unit (ultra-compact AI model upgrade unit) 225 of the SOMPA WiFi station unit 220.

[0047] The IoT data transceiver 213 includes a SOMPA 213a and functions to interface with the IoT RF gateway 310 of the external AI edge gateway 300 and the system management unit 226 of the SOMPA WiFi station unit 220.

[0048] The SOMPA WiFi station unit 220 includes a WiFi device interface 221, a WiFi data processing unit 222, a WiFi data transmission / reception unit 223, a security management unit 224, an ultra-compact AI model update unit 225, and a system management unit 226.

[0049] The WiFi device interface 221 is connected to a WiFi device 120 such as a camera to transmit and receive data.

[0050] The WiFi data processing unit 222 is configured to perform a series of operations of analyzing and processing the received data, validating the data, and filtering the data based on a micro AI model.

[0051] The WiFi data transceiver 223 is equipped with a SOMPA 223a and functions to interface with the WiFi access point 320 of the external AI edge gateway 300.

[0052] The security management unit 224 performs authentication, data encryption, and security protocol management for the SOMPAIoT adapter unit 210 and the SOMPAWiFi station unit 220.

[0053] The ultra-compact AI model update unit 225 performs the function of integrating, updating, and managing the ultra-compact AI models of the SOMA IoT adapter unit 210 and the SOMPA WiFi station unit 220 by updating the model learned in the external AI edge server 500 based on new data and enabling analysis of the latest data.

[0054] The system management unit 226 monitors energy usage to extend battery life through efficient energy management, and manages the SOMA IoT adapter unit 210 and the SOMA WiFi station unit 220.

[0055] Next, the operation of the integrated edge terminal 200 configured in this manner will be described.

[0056] First, the IoT device interface 211 of the SOMA IoT adapter unit 210 receives various data from the sensors of the IoT device 110.

[0057] Here, the various data may be in various forms such as temperature, humidity, PM2.5, etc., associated with the realization of a smart city system.

[0058] The IoT data processing unit 212 uses an ultra-compact AI installed on board to check for abnormalities in various data input from the IoT device interface 211, converts the confirmed abnormality data into a transmission protocol format, and outputs it to the IoT data transmission / reception unit 213.

[0059] The IoT data transceiver unit 213 wirelessly transmits the abnormality presence / absence data to the IoT RF gateway 310 of the AI ​​edge gateway 300 via the SOMPA 213a.

[0060] At this time, the IoT RF gateway 310 receives the abnormality presence / absence data signal transmitted to the IoT data transceiver 213 via the installed SOMPA 310a.

[0061] In addition, the IoT data processing unit 212 periodically monitors the power consumption of the SOMA IoT adapter unit 210 using the installed ultra-compact AI, and transmits a system status message of the SOMA IoT adapter unit 210 to the system management unit 226 of the SOMA WiFi station unit 220 via the IoT data transceiver unit 213.

[0062] The system management unit 226 of the SOM A WiFi station unit 220 transmits messages related to the system operation of the SOM A IoT adapter unit 210 to the IoT data processing unit 212 via the IoT data transceiver unit 213.

[0063] The IoT data processing unit 212 updates or reconstructs a message to correspond to the transmitted system operation related message.

[0064] The WiFi device interface 221 of the SOMPA WiFi station unit 220 receives various data from the WiFi device 120 .

[0065] Here, the various data may be in various forms such as large-volume sensor data or camera image signals associated with the realization of a smart city system.

[0066] The WiFi data processing unit 222 checks whether or not there are abnormalities in various data input from the WiFi device interface 221 using an ultra-compact AI installed therein, converts the confirmed abnormality data into a transmission protocol format, and outputs it to the WiFi data transceiver unit 223.

[0067] The WiFi data transceiver 223 wirelessly transmits the abnormality presence / absence data input from the WiFi data processing unit 222 to the WiFi access point 320 of the AI ​​edge gateway 300 via the SOMPA 223a.

[0068] At this time, the WiFi access point 320 receives a data signal transmitted to the WiFi data transceiver 223 via a built-in SOMPA 320a.

[0069] The security manager 224 also constantly performs security checks on the IoT device interface 211, the WiFi device interface 221, and data received from the IoT RF gateway 310, the WiFi access point 320, the integrated gateway, and the like.

[0070] The ultra-compact AI model update unit 225 updates its own model or updates the model of the SOMAIoT adapter unit 210 according to instructions from the AI ​​edge server 500.

[0071] The system management unit 226 periodically monitors the power consumption of the SOMPA WiFi station unit 220 using the installed ultra-compact AI to check its status, periodically connects to the SOMAIOT adapter unit 210 to check its status, and transmits the confirmed status message to the upper WiFi access point 320 or the integrated gateway.

[0072] The polarization effect antennas (SOMPA) 213a and 223a applied to the present invention are antennas utilizing the polarization effect disclosed by the present applicant in order to solve the problem of poor radio wave environments.

[0073] Incidentally, the SOMPA technology utilizing the electric current polarization effect is based on the applicant's Korean Patent Publication No. 10-1017690 (Electric current polarization effect and its applications), and SOMPA is disclosed in Korean Patent Publication No. 10-1591920 (Directional MIMO antenna utilizing electric current polarization effect) and Korean Patent Publication No. 10-2422163 (Omni-directional antenna utilizing electric current polarization effect).

[0074] The MIMO (Multi-Input Multi-Output) antenna of Korean Patent No. 10-1591920 is a structure that radiates radio waves in a certain direction by aligning the phase of the array of antenna radiators to improve antenna gain, and provides the effect of directing radio waves only in a specific direction, thereby increasing the service distance in a specific direction. The omni antenna of Korean Patent No. 10-2422163 improves on the patch antenna that uses the polarized effect to radiate radio waves in a perfect circle in all directions 360°, thereby facilitating service in open areas and suppressing radio wave scattering to provide excellent long-distance and obstacle-overcoming characteristics.

[0075] Such SOMPA has demonstrated outstanding performance when combined with WiFi terminals, WiFi access points, IoT terminals, IoT RF gateways, etc.

[0076] In other words, by utilizing the bias current effect in a communication circuit, there is an advantage in that it is not necessary to use passive elements such as a filter duplexer and an isolator in the output section, which are necessary when constructing a communication circuit and a communication device. This reduces the loss generated by such passive elements, thereby improving the performance of the communication device. Furthermore, by omitting the passive elements, it is possible to realize a communication device that is cost-effective and lightweight.

[0077] In addition to enabling long-distance communication, scattering phenomena caused by rain, fog, dust, etc. can be prevented, and scattering phenomena caused by obstacles such as signs and facilities in urban areas can also be prevented, resulting in the effect of creating a stable wireless communication environment.

[0078] To verify its effectiveness, a terminal combining LoRa technology and SOMPA technology was installed underground, and monitoring data for facilities such as internal cables was transmitted through a manhole to an IoT gateway located 100m outside, and performance was measured.

[0079] FIG. 4 is a diagram showing a manhole smart node system for explaining the SOMPA technology applied to the present invention, FIG. 5 is a diagram showing a test configuration of the system of FIG. 4, and FIG. 6 is a diagram showing a configuration in which the SOMPA of FIG. 4 is actually installed inside a manhole.

[0080] The manhole smart node system is a disaster prevention IoT system that installs a sensor node inside a manhole to transmit and receive data on the internal condition of the manhole to the ground in order to grasp the safety condition inside the manhole of an underground power distribution line.

[0081] Up until now, various types of antennas have been applied and tested, but radio communication was not possible through the thick double manhole, so a wired method was used in which an optical cable was connected by drilling a manhole. However, by applying SOMPA technology, there is no need to drill a manhole at all, and it was confirmed that its performance far surpasses that of conventional technology.

[0082] In other words, as shown in the technical comparison performance measurement result table of the SOMPA applied to the present invention and the conventional omni-antenna in FIG. 7, the SOMPA technology method installed inside the manhole without drilling a hole can achieve a performance improvement of 20 dB compared to the method of using an existing antenna to transmit through a manhole.

[0083] The IoT communication method adopted by the SOMA IoT adapter unit 210 according to the present invention is ultra-high density (1Km 2 1 million sensors can communicate per 1m 2 This method is suitable for constructing urban communication infrastructure networks with a large-scale IoT system (one sensor per sensor). As shown in the performance comparison graph of the ultra-large-scale IoT system of the present invention and the conventional LoRaWAN system in Fig. 8, this method can ensure 99% sensor communication reliability in ultra-high-density environments compared to the conventional LoRaWAN system. In addition, by combining it with SOMPA technology, it is possible to ensure communication reliability of 99% or more, which is stable in climatic environments such as heavy rain, to ensure communication reliability of 99% or more by overcoming radio wave blocking caused by obstacles such as underground buildings and manholes, and to ensure communication reliability by overcoming radio wave interference factors such as high-voltage lines and electric signboards.

[0084] According to the present invention, the SOMPA 213a applied to the SOMAIOT adapter unit 210 is preferably an omni-antenna that utilizes the polarized current effect to radiate radio waves in a perfect circle in all directions of 360°, and the SOMPA 223a applied to the SOMPA WiFi station unit 220 is preferably a directional MIMO antenna that utilizes the polarized current effect to radiate radio waves in a fixed direction.

[0085] In addition, the integrated edge terminal 200 according to the present invention can be extremely effective in many application environments of smart cities, where accurate situation recognition on-site is difficult to achieve simply by analyzing IoT data to grasp the situation.

[0086] In the case of an urban flood detection application, the integrated edge terminal 200 can transmit not only sensor data but also video data monitoring the site, enabling accurate situation analysis.

[0087] As shown in Fig. 4, in the case of the manhole smart sensor node system, various status information in the manhole can be transmitted simultaneously with video data by the integrated edge terminal 200 in the manhole without relying only on IoT sensor information. Therefore, accurate situation analysis is possible without having to make a separate communication hole in the manhole cover or peek inside the manhole every time.

[0088] In addition, construction sites in urban areas can set up separate local networks that are not part of the smart city network, and integrated edge terminals can be used to collect and analyze various on-site sensor data, video data, etc.

[0089] The integrated edge terminal can be flexibly installed at minimal cost even in many smart city environments where it is difficult to install IoT devices or video cameras, and it also exhibits outstanding performance in terms of data transmission.

[0090] According to the present invention, in the integrated edge terminal 200, the SOMPA WiFi station unit 220 performs management and maintenance functions such as updating and fault detection of the SOM AIoT adapter unit 210.

[0091] The reason for this configuration is that the SOMAIoT adapter unit 210 generally uses a low-performance MCU (Micro Control Unit) and has a small memory capacity, and therefore uses the computing functions of the SOMAWiFi station unit 220, which has higher performance.

[0092] In addition, if a problem occurs during the transmission process of the SOMAIoT adapter unit 210, transmission is possible via the SOMAWiFi station unit 220, which has the advantage of further improving the reliability of data transmission.

[0093] Although the present invention has been described by way of limited examples, it is of course possible to make various modifications without departing from the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the above-described embodiments, but should be determined by the following claims as well as equivalents to the claims. [Explanation of symbols]

[0094] 110 IoT devices 120 WiFi devices 200 Integrated Edge Device 210 SOMAIoT adapter part 211 IoT Device Interface 212 IoT data processing section 213 IoT data transmission and reception unit 213a, 223a SOMPA 220 SOMPAWiFi Station Department 221 WiFi device interface 222 WiFi data processing unit 223 WiFi data transmitter and receiver 300 AI Edge Gateway 400 Edge Network Controller 500 AI Edge Servers

Claims

1. A terminal for integrating and connecting an IoT device and a WiFi device on a low power consumption wide area network for IoT and a WiFi communication network, A SOMA IoT adapter unit that is equipped with SOMPA and has a super-large-scale IoT connection protocol and a super-small AI function, processes data collected from the IoT device, wirelessly transmits the data to an AI edge gateway, and performs upgrade and management functions in conjunction with the SOMPA WiFi station unit; A SOMPA WiFi station unit that is equipped with a SOMPA and has a WiFi connection protocol and a micro AI function, processes data collected from the WiFi device, transmits the data to an AI edge gateway through WiFi signal processing, and integrates the SOMAIot adapter unit to manage authentication, security, and energy, and manage upgrades to the micro AI model; An integrated edge terminal capable of simultaneously connecting to ultra-large-scale IoT and Wi-Fi networks and equipped with ultra-compact AI.

2. The SOMA IoT adapter unit includes: an IoT device interface connected to an IoT device including a super-large scale IoT sensor to transmit and receive signals; An IoT data processing unit that performs a series of operations of analyzing and processing the data received from the IoT device interface, checking the validity of the data, and filtering the data on a micro AI model basis, and updates the AI ​​model in conjunction with a micro AI model update unit of the SOMPA WiFi station unit; The integrated edge terminal of claim 1, which is capable of simultaneously connecting to ultra-large-scale IoT and WiFi networks and is equipped with ultra-compact AI, further comprising: an IoT data transceiver unit that is equipped with SOMPA and wirelessly transmits data input from the IoT data processing unit to an IoT RF gateway of an external AI edge gateway and links with a system management unit of the SOMPA WiFi station unit.

3. The integrated edge terminal capable of simultaneously connecting to ultra-large-scale IoT and WiFi networks and equipped with ultra-small AI as described in claim 2, characterized in that the IoT data processing unit periodically monitors the power consumption of the SOMAI IoT adapter unit using the installed ultra-small AI and transmits a system status message of the SOMAI IoT adapter unit to the system management unit of the SOMAI WiFi station unit through the IoT data transceiver unit.

4. The SOMPA WiFi station unit includes: a WiFi device interface connected to a WiFi device including a camera for transmitting and receiving data; a WiFi data processing unit that performs a series of operations of analyzing and processing the data received through the WiFi device interface, validating the data, and filtering the data based on a micro AI model; a WiFi data transceiver unit equipped with SOMPA and wirelessly transmitting data input from the WiFi data processing unit to a WiFi access point of an external AI edge gateway; A security management unit that performs authentication, data encryption, and security protocol management for the SOMPA IoT adapter unit and the SOMPA WiFi station unit; An ultra-compact AI model update unit that integrates, updates, and manages the ultra-compact AI models of the SOMAI IoT adapter unit and the SOMAI WiFi station unit by updating the model learned by the external AI edge server based on new data and enabling analysis of the latest data; The integrated edge terminal of claim 1, which can be simultaneously connected to ultra-large-scale IoT and WiFi networks and is equipped with an ultra-compact AI, characterized in that it includes: a system management unit that monitors energy usage and extends battery life through efficient energy management, manages the SOM A IoT adapter unit, and operates and manages the SOM A WiFi station unit.

5. The integrated edge terminal capable of simultaneously connecting to ultra-large-scale IoT and WiFi networks and equipped with an ultra-small AI as described in claim 4, wherein the system management unit periodically monitors the power consumption of the SOMPA WiFi station unit to check its status using the installed ultra-small AI, periodically connects to the SOMAIot adapter unit to check its status, and transmits the confirmed status message to an upper WiFi access point or an integrated gateway.

6. The SOMPA applied to the SOMAIot adapter is an omni-antenna that uses the polarized current effect to radiate radio waves in a perfect circle in all directions of 360°. The SOMPA applied to the SOMPA WiFi station unit is a directional MIMO antenna that radiates radio waves in a certain direction by utilizing the polarized current effect. An integrated edge terminal capable of simultaneously connecting to ultra-large-scale IoT and WiFi networks and equipped with ultra-compact AI, as described in claim 1.

Images