WO2022158068A1 - 通信システム、通信制御プログラム、および通信制御方法 - Google Patents
通信システム、通信制御プログラム、および通信制御方法 Download PDFInfo
- Publication number
- WO2022158068A1 WO2022158068A1 PCT/JP2021/039413 JP2021039413W WO2022158068A1 WO 2022158068 A1 WO2022158068 A1 WO 2022158068A1 JP 2021039413 W JP2021039413 W JP 2021039413W WO 2022158068 A1 WO2022158068 A1 WO 2022158068A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- terminal device
- data
- server
- transmission
- communication system
- Prior art date
Links
- 238000004891 communication Methods 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims description 51
- 230000005540 biological transmission Effects 0.000 claims abstract description 204
- 230000006870 function Effects 0.000 claims description 52
- 238000010801 machine learning Methods 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 37
- 238000002360 preparation method Methods 0.000 claims description 17
- 230000004044 response Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 69
- 238000004458 analytical method Methods 0.000 description 33
- 230000008569 process Effects 0.000 description 12
- 238000013135 deep learning Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 9
- 238000007405 data analysis Methods 0.000 description 8
- 230000010365 information processing Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 238000012508 change request Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000007257 malfunction Effects 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000006837 decompression Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- ADTDNFFHPRZSOT-PVFUSPOPSA-N ram-330 Chemical compound C([C@H]1N(CC2)C)C3=CC=C(OC)C(OC)=C3[C@]32[C@@]1(O)CC[C@@H](OC(=O)OCC)C3 ADTDNFFHPRZSOT-PVFUSPOPSA-N 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010011469 Crying Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/52—Allocation or scheduling criteria for wireless resources based on load
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/12—Wireless traffic scheduling
- H04W72/1263—Mapping of traffic onto schedule, e.g. scheduled allocation or multiplexing of flows
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities
- H04W8/24—Transfer of terminal data
Definitions
- the present invention relates to a communication system, a communication control program, and a communication control method.
- 5G 5th generation mobile communication system
- private 5G also called local 5G
- 5G private 5G
- SoCs System-on-a-Chips
- FPGAs Field-Programmable Gate Arrays
- GPU Graphics Processing Unit
- DSP Demand-Side Platform
- one communication line is shared between upstream and downstream. For this reason, when downloading update data, there is no choice but to send it at a timing when the downlink communication situation is relatively free, or to divide it into low-capacity units and send it over a long period of time.
- Patent Document 1 data is uploaded from a terminal device equipped with an in-vehicle sensor to a server through a communication line.
- a terminal device equipped with an in-vehicle sensor to a server through a communication line.
- either the information of the in-vehicle sensor or the information of the analysis result in the terminal device is transmitted according to the change in the line speed of the communication line.
- the line speed drops when uploading data, the real-time nature of the information will not be lost.
- Patent Document 2 an operating environment after software update is constructed in a second information processing system, and an operating environment before software update in the first information processing system is moved to the second information processing system.
- a second information processing system is caused to execute updated software, and processing target information of the second information processing system is changed from information obtained by executing the pre-update software to post-update software. Change the information obtained by running the software.
- software update processing executed by an information processing device having limited information processing resources such as a server in an IoT (Internet of Things) system can be performed without stopping the information processing device. It is said to be feasible.
- Patent Document 1 does not take any countermeasures against the delay when data is transmitted from the server to the edge device.
- the technique of Patent Document 2 does not take any countermeasures against communication line delays.
- the terminal device when the terminal device is equipped with versatile hardware such as FPGA and GPU/DSP, and the function is changed by rebuilding them, the data for rebuilding can be sent quickly and accurately and restarted. need to let However, with the conventional technology, if there is a delay in the communication line during download, it is necessary to reduce the frequency of rebuilding due to updates, making it difficult to update or rebuild for each connected terminal device.
- an object of the present invention is to provide a communication system, a communication control program, and a communication control method that enable real-time reconstruction of a terminal device by reflecting data from a server in the terminal device in real time. is.
- a terminal device having a sensing device; a network system including, at least in part, wireless communication;
- a communication system comprising a server that performs data transmission with the terminal device via wireless communication by the network system,
- the communication system has a control unit that dynamically controls a transmission ratio between the uplink and the downlink, with a direction from the terminal device to the server being an uplink and a direction from the server to the terminal device being a downlink. death,
- the communication system wherein the control unit adjusts the transmission ratio according to the status of data transmission or the type of data transmission.
- control unit adjusts the transmission ratio so that the uplink transmission amount increases.
- control unit adjusts the transmission ratio so that the downlink transmission amount increases.
- the communication system according to (1) or (2) above.
- control unit adjusts the transmission ratio in response to a request from the terminal device.
- the server notifies the terminal device whether or not data transmission can be interrupted;
- the terminal device has a storage for storing data, The communication system according to any one of (5) to (7) above, wherein the terminal device stores data from the sensing device in the storage when data transmission interruption is not permitted.
- control unit If the control unit does not receive a request for changing the transmission ratio from the terminal device within a predetermined period of time after adjusting the downlink transmission amount to increase, the control unit increases the uplink transmission amount.
- the server If the server does not receive a data transmission request from the terminal device within a predetermined time period after the control unit has adjusted the transmission ratio so that the downlink transmission amount increases, the server The communication system according to (9) above, wherein a request is made to the control unit to increase the amount of uplink transmission.
- control unit adjusts the transmission ratio so that the downlink transmission amount increases when transmitting the control program and/or the logical data.
- a terminal device having a sensing device; a network system having wireless communication at least in part;
- a communication control program for controlling a communication system having a server that performs data transmission with the terminal device via wireless communication by the network system,
- the communication system has a computer that dynamically controls a transmission ratio between uplink and downlink, with a direction from the terminal device to the server being an uplink and a direction from the server to the terminal device being a downlink.
- a communication control program for causing the computer to execute the step (a) of adjusting the transmission ratio according to the status of data transmission or the type of data transmission.
- step (a) when the amount of data from the terminal device to the server is larger than the amount of data from the server to the terminal device, the transmission ratio is set so that the uplink transmission amount increases.
- step (a) when the amount of data from the server to the terminal device is larger than the amount of data from the terminal device to the server, the transmission ratio is set so that the downlink transmission amount increases.
- (23) a terminal device having a sensing device; a network system having wireless communication at least in part;
- the transmission ratio of uplink to downlink is adjusted according to the data transmission situation or the type of data transmission.
- the priority of the line can be adjusted according to the necessity of uplink and downlink in data transmission, the delay in data transmission can be reduced, and the data from the server can be reflected in the terminal device in real time. This makes it possible to reconfigure the terminal device in real time.
- FIG. 1 is a diagram showing a schematic configuration of a communication system according to one embodiment of the present invention
- FIG. 1 is a block diagram for explaining functions of a communication system according to an embodiment
- FIG. It is a block diagram which shows an example of the hardware constitutions of a terminal device.
- 1 is a block diagram showing an outline of hardware that constitutes a network system
- FIG. 3 is a block diagram showing an outline of hardware that constitutes the server
- FIG. 4 is a flow chart showing a processing procedure according to the first embodiment
- 9 is a flow chart showing a processing procedure in Embodiment 2
- 11 is a flow chart showing a processing procedure in Embodiment 3.
- FIG. 14 is a flow chart showing a processing procedure in Embodiment 4.
- FIG. 1 is a diagram showing a schematic configuration of a communication system according to one embodiment of the present invention
- FIG. 1 is a block diagram for explaining functions of a communication system according to an embodiment
- FIG. It is a block diagram which shows an example
- FIG. 1 is a diagram showing a schematic configuration of a communication system 1 according to one embodiment of the present invention.
- FIG. 2 is a block diagram for explaining functions of the communication system 1 according to one embodiment.
- the communication system 1 includes terminal devices 100 (100a, 100b, 100c, . . . ), a network system 200, and a server 300.
- the communication system 1 is, for example, a private 5G communication system.
- the terminal device 100 includes a sensing device (simply referred to as a sensor 109 hereinafter) and transmits information detected by the sensor 109 to the server 300 .
- the terminal device 100 also performs machine learning and determination based on information detected by the sensor 109 .
- Such a terminal device 100 is also called an edge device, an edge terminal, etc., and is an electronic device that can also be used for IoT.
- the terminal device 100 is, for example, a mobile terminal device 100a such as a smart phone or a tablet computer, a fixed terminal device 100b such as a personal computer, or a monitoring camera device 100c having a wireless device attached to a camera.
- a mobile terminal device 100a such as a smart phone or a tablet computer
- a fixed terminal device 100b such as a personal computer
- a monitoring camera device 100c having a wireless device attached to a camera.
- Each of these terminal devices 100a, 100b, and 100c is a device in which a sensor 109 and a computer having a wireless communication function are integrated or locally connected.
- these terminal devices 100a, 100b, and 100c are described as the terminal device 100 unless otherwise distinguished.
- the terminal device 100 has a wireless communication unit 101, a line transmission ratio change request unit 102, a data reception processing unit 103, an analysis learning internal setting change unit 104, and a control program/logical data unit 105, as shown in FIG.
- the terminal device 100 is connected (or integrated) with a storage 106 and a sensor 109 .
- the wireless communication unit 101 performs communication with the network system 200 by 5G.
- the line transmission ratio change request unit 102 requests the network system 200 to change the line transmission ratio.
- a line for communication from the terminal device 100 to the server 300 is called an up line, and a line for communication from the server 300 to the terminal device 100 is called a down line.
- the transmission ratio is the ratio of the amount of transmission on the downlink to the amount of transmission on the uplink.
- the line transmission ratio change request unit 102 requests the network system 200 to change the transmission ratio.
- the data reception processing unit 103 processes data transmitted/received to/from the server 300 .
- the data transmitted from the terminal device 100 is, for example, data collected by the sensor 109, data generated by the analysis learning internal setting changing unit 104, and the like.
- the data reception processing unit 103 once receives these data from each unit, performs necessary processing, and outputs the data to the wireless communication unit 101 .
- the required processing includes, for example, data labeling, integration, compression, and other data processing.
- the wireless communication unit 101 transmits these data to the network system 200.
- these data are transmitted to the server 300 according to the destination.
- data received from server 300 is, for example, a control program and/or logic data for controlling terminal device 100 .
- These data transmitted from the server 300 are received by the wireless communication unit 101 of the terminal device 100 via the network system 200 .
- the received data is temporarily output from wireless communication section 101 to data reception processing section 103 .
- the data reception processing unit 103 performs necessary processing on the received data and outputs the processed data to each unit.
- the required processing includes, for example, integration, decompression and decompression of compressed data, sorting by label, and reprocessing and restoration of other processed data.
- the analysis learning internal setting changing unit 104 analyzes and/or learns data input from the sensor 109 .
- the analysis by the analysis learning internal setting change unit 104 analyzes the image data in time series by image processing, determines changes in the image, and identifies a person or an object.
- the learning by the analysis learning internal setting changing unit 104 is, for example, machine learning using image data.
- Machine learning includes deep learning. Specifically, for example, in the analysis by the analysis learning internal setting change unit 104, based on the previous learning result or the control program and/or logic data transmitted from the server 300, from the image data detected by the sensor 109, the person and instant identification of objects, counting of people and objects, and so on.
- the analysis by the analysis learning internal setting changing unit 104 specifies the temperature of a person or an object, and determines a person or an object whose temperature is higher than a certain level. Further, in the learning by the analysis learning internal setting change unit 104, machine learning is performed using image data from the sensor 109 as input and, for example, a person as teaching data, thereby obtaining a learning result used for identifying the person. Note that the analysis learning internal setting changing unit 104 may perform either analysis or learning, or both, depending on the performance of the terminal device 100 .
- the analysis learning internal setting changing unit 104 changes and optimizes the settings inside the terminal device 100 based on the results of the analysis and/or learning.
- the control program/logical data unit 105 stores a control program and/or logical data for operating the terminal device 100 based on the results analyzed and/or learned by the analysis learning internal setting changing unit 104. Also, the control program/logical data unit 105 stores a control program and/or logical data for operating the terminal device 100 downloaded from the server 300 . Although the details will be described later, in the case of FPGA as a hardware configuration, the control program/logical data section 105 is configured as a memory area within the same chip as the CPU function. If the hardware configuration is such that the CPU and the memory are separate, the control program/logical data unit 105 is composed of a semiconductor memory such as a RAM connected to the CPU. In either case, the control program/logical data unit 105 stores the control program and/or logical data in an immediately executable state.
- the storage 106 stores the results analyzed and/or learned by the analysis learning internal setting changing unit 104 . Also, the storage 106 stores data from the sensor 109 . The storage 106 also stores control programs and/or logical data for operating the terminal device 100 . The control programs and/or logical data stored in the storage 106 are not to be executed immediately, but are stored to be read out to the control program/logical data section 105 when there is an instruction to change the function.
- the capacity of the storage 106 is determined according to the cost of the terminal device 100, and the contents to be stored are appropriately changed according to the capacity. do it.
- storage 106 may store only data from sensor 109 .
- the terminal device 100 downloads the control program and/or the logical data from the server 300 and uses them.
- the storage 106 does not necessarily have to be provided.
- the terminal device 100 downloads the control program and/or the logical data from the server 300 and uses them. By not including the storage 106, the cost of the terminal device 100 can be further reduced.
- the sensor 109 is, for example, an image sensor.
- An image sensor is, for example, a camera that primarily detects visible light. Further, the sensor 109 is an infrared camera, a thermo camera (temperature detection camera), or the like.
- Other sensors 109 include, for example, an acoustic sensor that detects sound like a microphone, an altitude sensor that detects altitude (elevation), an air pressure sensor, an underwater depth sensor (water pressure sensor), a vibration sensor, an orientation sensor, an angle sensor, Various sensors can be used such as temperature sensors, voltage sensors, current sensors, and power sensors.
- the data detected by these sensors 109 are transmitted to the server 300 as required. Data detected by the sensor 109 is also stored in the storage 106 as necessary.
- the terminal device 100 may include, for example, a network interface conforming to standards such as Ethernet (registered trademark) and IEEE1394, a wireless communication interface such as Bluetooth (registered trademark) and IEEE802.11. good.
- a network interface conforming to standards such as Ethernet (registered trademark) and IEEE1394, a wireless communication interface such as Bluetooth (registered trademark) and IEEE802.11. good.
- FIG. 3 is a block diagram showing an example of the hardware configuration of the terminal device 100. As shown in FIG.
- the terminal device 100 is a computer.
- the terminal device 100 has an SoC FPGA 110, a storage 106, a 5G communication interface 150, and an operation display section 160, as shown in FIG.
- the SoC FPGA 110 is a semiconductor element (including a semiconductor element in which multiple chips are joined together) in which an FPGA capable of rewriting the processing contents to be executed is formed on one chip as a system.
- the SoC FPGA 110 is also called Programmable SoC.
- the SoC FPGA 110 has functions such as a CPU (Central Processing Unit) as an arithmetic element, a ROM (Read Only Memory) and a RAM (Random Access Memory) as memory elements (or has a plurality of these functions). multiple chips integrated).
- the SoC FPGA 110 may be equipped with an accelerator such as a GPU/DSP.
- SoC FPGA 110 stores control programs and/or logic data necessary for operation (including rewriting of gate circuits in FPGA), and by executing them, the functions of each unit of terminal device 100 described above are realized. be done. Therefore, SoC FPGA 110 functions as line transmission ratio change request section 102 , data reception processing section 103 , analysis learning internal setting change section 104 , and control program/logical data section 105 .
- the storage 106 is a storage medium such as eMMC (embedded MultiMediaCard), SSD (Solid State Drive), and HDD (Hard Disk Drive). Also, the storage 106 may be a portable storage medium such as a memory card.
- eMMC embedded MultiMediaCard
- SSD Solid State Drive
- HDD Hard Disk Drive
- the storage 106 may be a portable storage medium such as a memory card.
- the 5G communication interface 150 is the wireless communication unit 101 for communicating with the network system 200 by 5G, and is configured by a communication module chip. Note that the 5G communication interface 150 may also be integrated as the SoC FPGA 110 .
- the operation display unit 160 is, for example, a touch panel display, which displays various information and accepts various inputs from the user. Also, depending on the terminal device 100, an input device such as a keyboard or a mouse and a monitor may be connected.
- terminal device 100 is not limited to the SoC FPGA 110, and may be an FPGA other than the SoC, or may have a configuration in which the CPU, RAM, and ROM are independent and connected via a bus. .
- the network system 200 has a 5G wireless communication function and controls communication between the terminal device 100 and the server 300 .
- the network system 200 has a wireless communication control unit 201, a line transmission ratio control unit 202, and a processing relay determination unit 203, as shown in FIG.
- the network system 200 performs communication with the terminal device 100 and the server 300 by 5G. Therefore, the network system 200 is a 5G radio base station and core network equipment.
- the wireless communication control unit 201 controls communication with other electronic devices.
- the wireless communication control unit 201 controls 5G communication between the terminal device 100 and the server 300 in this embodiment.
- the line transmission ratio control unit 202 (control unit) dynamically adjusts the transmission ratio of the uplink and downlink.
- the transmission ratio is adjusted, for example, according to the situation and type of data transmitted and received between the terminal device 100 and the server 300 .
- the line transmission ratio control unit 202 determines the status of data to be transmitted and received based on the difference in the amount of data transmitted and received between the terminal device 100 and the server 300, and performs transmission according to the determined data status. Adjust the ratio. Specifically, for example, the line transmission ratio control unit 202 monitors the communication volume of the wireless communication control unit 201, acquires and compares the transmission volume of each of the uplink and the downlink, and thereby determines the terminal device 100 and the server 300. determine the status of data sent and received between For example, in a situation where the amount of downlink data is large, line transmission ratio control section 202 adjusts so that the amount of downlink transmission increases. Conversely, when the amount of uplink data is large, line transmission ratio control section 202 adjusts the uplink transmission amount to increase.
- the line transmission ratio control unit 202 adjusts the transmission ratio according to the type of data transmitted and received between the terminal device 100 and the server 300, for example.
- the types of data to be sent and received are, for example, data related to the function change of terminal device 100 by server 300, data detected by sensor 109 of terminal device 100, data of analysis and/or learning result by terminal device 100, and the like.
- the data related to the function change of the terminal device 100 is data downloaded from the server 300 to the terminal device 100 and transmitted using the downlink.
- the data detected by the sensor 109 of the terminal device 100 and the data of the analysis and/or learning results by the terminal device 100 are data uploaded from the terminal device 100 to the server 300 and transmitted using the uplink. be.
- the data type determination is performed by the terminal device 100 in the first embodiment.
- the terminal device 100 transmits a transmission ratio change request to the line transmission ratio control unit 202 according to the determined data type.
- the line transmission ratio control section 202 adjusts the transmission ratio according to the request received from the terminal device 100 .
- the line transmission ratio control section 202 adjusts the uplink transmission amount to increase.
- the line transmission ratio control section 202 adjusts the downlink transmission amount to increase.
- the line transmission ratio control unit 202 may adjust the transmission ratio in response to a request not only from the terminal device 100 but also from the server 300 .
- the line transmission ratio control unit 202 gives priority to a predetermined line when neither the terminal device 100 nor the server 300 requests to change the transmission ratio.
- a line with priority when there is no request is, for example, an uplink.
- the adjustment of the uplink pair and downlink transmission ratios can be implemented, for example, by methods such as those described in the following references.
- Reference 2 discloses a technique for flexibly setting a DL (download)/UL (upload) switching cycle as Semi-static TDD, and a technique for switching DL/UL for each symbol as Dynamic TDD.
- the adjustment of the uplink pair and downlink transmission ratios may be implemented by other methods.
- the processing relay determination unit 203 When the processing relay determination unit 203 detects the occurrence of communication failure, it stops communication and restores the original settings.
- FIG. 4 is a block diagram outlining the hardware that constitutes the network system 200. As shown in FIG. 4
- the network system 200 is a computer.
- the network system 200 has a CPU 210, a ROM 220, a RAM 230, a storage 240, a 5G communication interface 250, and an operation display section 260, as shown in FIG.
- Each component is communicatively connected to each other via a bus 270 .
- the CPU 210 executes the functions of each part of the network system 200 described above by executing programs recorded in the ROM 220 and the storage 240 .
- the ROM 220 stores various programs and various data.
- the RAM 230 temporarily stores programs and data as a work area.
- the storage 240 stores various programs including the operating system and various data.
- the storage 240 is a storage medium such as eMMC (embedded MultiMediaCard), SSD (Solid State Drive), and HDD (Hard Disk Drive).
- eMMC embedded MultiMediaCard
- SSD Solid State Drive
- HDD Hard Disk Drive
- the 5G communication interface 250 performs 5G communication with the terminal device 100 and the server 300 as the wireless communication control unit 201 .
- the operation display unit 260 is, for example, a touch panel display, which displays various information and accepts various inputs from the user. Further, as the operation display unit 260, an input device such as a keyboard or a mouse and a monitor may be connected.
- the line transmission ratio control unit 202 does not have to be provided in the network system 200 .
- the line transmission ratio control unit 202 may be realized by a computer installed at a remote location.
- a computer serving as the line transmission ratio control unit 202 may be connected to the network system 200 having the wireless communication control unit 201 and the processing relay determination unit 203 to perform processing for dynamically controlling the transmission ratio.
- Server 300 analyzes and/or learns data transmitted from terminal device 100 .
- Server 300 also stores control programs and/or logical data for changing the functions of terminal device 100 .
- the server 300 generates control programs and/or logic data for changing the functions of the terminal device 100 .
- the server 300 also changes the settings (functions) of the terminal device 100 .
- the server 300 has a wireless communication unit 301, a terminal data analysis learning unit 302, a control program/logical data generation unit 303, and a generation completion notification unit 304, as shown in FIG.
- the server 300 may be called an edge server.
- the server 300 is also called a cloud server because it stores data collected by the terminal device 100 from the sensor 109, control programs and/or logic data used by the terminal device 100, etc. on the network.
- the wireless communication unit 301 executes communication with the network system 200 by 5G.
- the terminal data analysis learning unit 302 analyzes the data received from the terminal device 100 and learns.
- Terminal data analysis learning section 302 analyzes the status of terminal device 100 based on the data received from terminal device 100 . Also, the terminal data analysis learning unit 302 performs machine learning using data received from the terminal device 100 .
- the server 300 has higher performance and functions than the terminal device 100 . Therefore, the terminal device 100 can perform difficult machine learning.
- the results of analysis and machine learning are output to the control program/logic data generation unit 303 .
- the control program/logical data generation unit 303 generates the optimal control program and/or logical data for the terminal device 100 from the results of analysis and machine learning.
- the control program and/or logic data are programs and/or data for operating the terminal device 100. For example, when the terminal device 100 is performing machine learning from data detected by the sensor 109 provided in itself, it is a program and / or data necessary when another learning is required. . What control program and/or logic data to generate may be determined by the control program/logic data generator 303, for example, based on the results of machine learning.
- control program for the hardware of the terminal device 100 is a program that is mainly executed by the CPU of the terminal device 100 or the CPU function circuit in the FPGA.
- logic data is mainly data for rewriting circuit data of FPGA.
- control program and/or logic data are, for example, programs and/or data that serve as criteria for determining the data of the sensor 109 by the terminal device 100 .
- the control program/logical data generation unit 303 when a person or an object is determined by the terminal device 100, the control program/logical data generation unit 303 generates a program and/or data necessary for the terminal device 100 to determine the person or the object.
- the control program/logical data generation unit 303 outputs the control program and/or logic data generation completion to the generation completion notification unit 304 .
- the control program and/or logical data may be stored in the storage 340 of the server 300 in advance.
- a control program and/or logical data may be stored in accordance with an assumption in advance in which case the function of the terminal device 100 will be changed.
- the generation completion notification unit 304 receives the generation completion output from the control program/logical data generation unit 303 and notifies the terminal device 100 that preparations for transmission of the control program and/or logic data have been completed. Further, in the case of transmitting the stored control program and/or logic data, the generation completion notification unit 304 outputs to the wireless communication unit 301 that the transmission preparation is completed when the preparation for transmitting these data is completed. do. The wireless communication unit 301 notifies the terminal device 100 of transmission preparation completion via the network system 200 .
- the terminal device 100 requests the network system 200 to give priority to the downlink upon receiving the data transmission preparation completion notification from the server 300 .
- the network system 200 is adjusted so that the amount of downlink transmission increases.
- server 300 transmits the control program and/or logical data to terminal device 100 from wireless communication unit 301 through network system 200 .
- control programs and/or logical data can be transmitted from the server 300 to the terminal device 100 efficiently and in real time.
- FIG. 5 is a block diagram outlining the hardware that makes up the server 300. As shown in FIG. 5
- the server 300 is a computer.
- the server 300 has a CPU 310, a ROM 320, a RAM 330, a storage 340, a 5G communication interface 350, and an operation display section 360, as shown in FIG.
- Each component is communicatively connected to each other via a bus 370 .
- the CPU 310 executes the functions of each section of the server 300 described above by executing programs recorded in the ROM 320 and storage 340 .
- the ROM 320 stores various programs and various data.
- the RAM 330 temporarily stores programs and data as a work area.
- the storage 340 stores various programs including the operating system and various data.
- Storage 340 stores control programs and/or logical data.
- the storage 340 is mainly a large-capacity storage medium such as an HDD.
- a semiconductor storage medium such as eMMC or SSD may be used together with the HDD or instead of the HDD.
- the 5G communication interface 350 performs 5G communication with the network system 200 as the wireless communication unit 301 .
- the operation display unit 360 is, for example, a touch panel display, which displays various information and accepts various inputs from the user. Further, as the operation display unit 360, an input device such as a keyboard or a mouse and a monitor may be connected.
- FIG. 6 is a flow chart showing the processing procedure in the first embodiment.
- the terminal device 100 has an image sensor.
- the terminal device 100 itself also executes predetermined machine learning.
- the server 300 stores control programs and/or logical data for changing the functions of the terminal device 100 in the storage 340 of the server 300 .
- the server 300 analyzes the data from the terminal device and changes the functions of the terminal device 100 according to the result.
- a control program is, for example, a program for controlling a deep learning network.
- the logical data is, for example, circuit data for FPGA using a model file of a deep learning network trained in advance.
- the processing procedure of network system 200 corresponds to processing executed according to a communication control program.
- the terminal device 100 transmits (uploads) the image data detected by the image sensor and the analysis result data of the image to the server 300 via the network system 200 (S101).
- the transmission ratio has already been adjusted so as to prioritize the uplink (S201).
- the server 300 receives data from the terminal device 100 (S301).
- the analysis and/or learning in the terminal device 100 is, for example, machine learning using image data acquired by an image sensor as input, and includes, for example, inference by deep learning.
- the terminal device 100 executes a skeleton detection machine learning algorithm.
- the terminal device 100 acquires the coordinate data of each joint point of the object recognized as a human being.
- the terminal device 100 recognizes the height of the person to be photographed.
- the terminal device 100 analyzes the posture and height of each person from the obtained coordinate data, and transmits the analysis results to the server 300 .
- the terminal device 100 After transmitting the data, the terminal device 100 continues machine learning from the images acquired by the image sensor for a certain period of time. For example, if the average height of people being photographed is short, the terminal device 100 learns that the current learning target is a child. In this case, the terminal device 100 recognizes that it wants to acquire child data, and if a person with a height of 160 cm or more, for example, is detected, it is assumed that the person is not an object of analysis. Set the threshold for excluding people from analysis targets. Also, if the terminal device 100 already has a height threshold, the terminal device 100 changes the threshold.
- server 300 which has received data from terminal device 100, further analyzes and/or learns the received data in chronological order (S302), and generates a control program and/or logic data for changing the function of terminal device 100. prepare to send the When the server 300 completes preparations for transmission of the control program and/or logical data, the server 300 notifies the terminal device 100 of completion of transmission preparations (S303).
- the server 300 analyzes the posture by skeleton detection in the received data in chronological order and learns it as an action of getting lost. Then, the server 300 further analyzes the data from the terminal device 100 based on the learning result, and executes human action determination.
- the server 300 determines an algorithm to be executed next by the terminal device 100 based on the action determination result.
- the terminal device 100 is caused to execute a machine learning algorithm for human attribute detection.
- the server 300 stores control programs and/or logic data to be executed by the terminal device 100 in accordance with presumed behavior determination. Therefore, here, the control program and/or logic data for causing the terminal device 100 to execute the machine learning algorithm for human attribute detection is stored in the server 300 .
- the data to be notified to the terminal device 100 is the data size of the control program and/or logical data scheduled to be transmitted to the terminal device 100, and whether or not data transmission can be interrupted. Whether data transmission can be interrupted indicates whether data transmission from the server 300 can be interrupted.
- the terminal device 100 Upon receiving the notification from the server 300, the terminal device 100 transmits a request to the network system 200 to give priority to the downlink transmission ratio (S102). At this time, the terminal device 100 determines the type of data transmitted from the server 300 based on the notification from the server 300 . In the terminal device 100, it is determined for which type of data a downlink priority is requested. In the first embodiment, when the type of data is data related to the function change of the terminal device 10, downlink priority is requested. The control program and/or logic data are data relating to functional changes of the terminal device 100 . Therefore, the terminal device 10 requests downlink priority.
- the terminal device 100 may determine whether or not to execute the downlink priority request based on the data size included in the notification received from the server 300 before executing the downlink priority request. For example, the terminal device 100 compares the data size included in the notification from the server 300 with a predetermined threshold (threshold of data size), and determines that the data size included in the notification is the data size. is less than the threshold, the downlink priority request may not be executed.
- the data size threshold is, for example, a data size that is a time interval during which data to be uploaded from the terminal device 100 is allowed to be missing while the data is being downloaded from the server 300 . Since the time interval at which data loss is allowed varies depending on the data communication status, such a data size threshold value may be determined based on past performance or the like.
- the uplink to downlink transmission ratio may be requested by the terminal device 100 .
- the transmission ratio is determined, for example, according to what is to be processed next by the terminal device 100 .
- the transmission ratio for downlink priority may be determined in advance in network system 200 .
- the terminal device 100 changes its own operation to processing for receiving data (data reception preparation) (S103).
- data reception preparation the analysis and/or learning processing that the terminal device 100 has been performing and the transmission (upload) of data to the server 300 are temporarily suspended.
- the control program/logic data can be received from the server 300 .
- a program for executing data reception preparation processing is stored in terminal device 100 in advance, for example.
- the terminal device 100 executes a data reception preparation program triggered by the reception of the data transmission preparation completion notification from the server 300 .
- the terminal device 100 activates its own storage 106 and accumulates data from the sensor 109 . This is to prevent data detected by the sensor 109 from disappearing during a long time required to download data from the server 300 to the terminal device 100 . For example, if it takes 30 seconds to transfer data from the server 300 to the terminal device 100, the data detected by the sensor 109 will disappear for 30 seconds. Therefore, the terminal device 100 activates the storage 106 and stores the data detected by the sensor 109 in the storage 106 for the 30 seconds. It should be noted that whether or not to store in the storage 106 is determined based on the data size and the information regarding whether or not data transmission can be interrupted notified from the server 300 .
- the terminal device 100 predicts the time required for data transfer from the notified data size, and the predicted data transfer time is set to a threshold value (transfer time). threshold) or more, the data detected by the sensor 109 is stored in the storage 106 . It is preferable that the transfer time threshold is, for example, a time interval in which data detected by the sensor 109 is allowed to be missing. Since the data transfer time varies depending on the data communication status, the transfer time threshold value may be determined based on past records.
- the terminal device 100 executes a request for suspending data transmission from the server 300 as necessary. For example, the terminal device 100 suspends data transmission when the free space of the storage 106 is small and the data detected by the sensor 109 cannot be stored. Although not shown, a request to suspend data transmission is executed after step S304.
- the network system 200 that has received the downlink priority request adjusts the transmission ratio to downlink priority according to the request (S202). After completing the adjustment, the network system 200 notifies the terminal device 100 of the completion of the downlink priority adjustment (S203).
- the terminal device 100 which has received notification of the completion of the transmission ratio adjustment from the network system 200, requests the server 300 to transmit data (S104).
- the server 300 After receiving the data transmission request, the server 300 transmits (downloads) the control program and/or the logical data to the terminal device 100 (S304).
- the terminal device 100 uses the received control program and/or logic data to change its own functions (S105). Terminal device 100 restarts itself as necessary in order to operate the received control program and/or logic data.
- the terminal device 100 operates the changed machine learning algorithm.
- the modified machine learning algorithm is here the machine learning algorithm of human attribute detection, as described above.
- the machine learning algorithm for human attribute detection is, for example, learning for lost child determination.
- the terminal device 100 to which the control program and/or logic data have been downloaded switches to the machine learning algorithm for human attribute detection.
- the terminal device 100 detects the child from the image data acquired by the image sensor and learns the behavior of the child.
- the terminal device 100 recognizes the color of the child's top and bottom clothes and the color of the glasses. , gender, hat, presence of bag, etc.
- the terminal device 100 transmits information to the lost child center, such as the location where the child was detected, height, gender, color of upper and lower clothes, glasses, a hat, and the presence or absence of a bag.
- the Lost Child Center will announce the lost child.
- the terminal device 100 requests the network system 200 to prioritize the uplink (S106).
- the network system 200 that has received the request for uplink priority adjusts to uplink priority (S204).
- uplink priority S204
- data can be sent from the terminal device 100 to the server 300 stably and at high speed.
- the first embodiment described above has the following effects.
- the functions of the terminal device 100 are changed by replacing the control program and/or the logical data.
- downlink priority is given according to a request from the terminal device 100 .
- various functions can be satisfied by minimizing the hardware resources of the terminal device 100 and reconfiguring the terminal device 100 frequently.
- Embodiment 2 differs from Embodiment 1 in the control mode.
- the first embodiment described above is an example in which control programs and/or logical data are stored in advance in the storage 340 of the server 300 .
- the server 300 learns the data transmitted from the terminal device 100 to generate a new control program and/or logical data, and transmits it to the terminal device 100 for reflection.
- the configuration of the communication system 1 of Embodiment 2 is the same as that of Embodiment 1, so a description thereof will be omitted.
- FIG. 7 is a flow chart showing the processing procedure in the second embodiment.
- the terminal device 100 has an image sensor.
- the terminal device 100 itself also executes predetermined machine learning.
- Server 300 generates control programs and/or logical data for changing the functions of terminal device 100 .
- the server 300 changes the functions of the terminal device 100 according to the learning result.
- the same step numbers are assigned to the same processes as in the first embodiment, and the description thereof is omitted.
- the terminal device 100 transmits the image data obtained by the image sensor and the data of the analysis result of the image to the server 300 via the network system 200 (S101).
- the transmission ratio has already been adjusted so as to prioritize the uplink (S201).
- the server 300 receives data from the terminal device 100 (S301).
- the analysis and/or learning in the terminal device 100 is, for example, machine learning using images acquired by an image sensor as input, such as inference by deep learning.
- a result with a low reliability score may appear.
- Such results are presented to the user to receive feedback on correct answers.
- the terminal device 100 stores the fed-back correct answer together with the image acquired by the image sensor in the storage 106 as learning data.
- machine learning is performed to determine a person. For example, in machine learning for judging people, erroneous judgments are likely to occur because people wearing suits or wearing work clothes have similar features.
- the terminal device 100 can improve the accuracy of the learning data by presenting the result to the user and accepting the input of the correct answer when the reliability of the score is low according to the degree of learning. Note that the terminal device 100 may give an erroneous result to the user even if the reliability score is high, so the terminal device 100 may receive input of learning data from the user.
- the terminal device 100 transmits the results of such machine learning to the server 300 as learning data.
- the timing of transmitting the learning data may be, for example, when the amount of image data detected by the sensor 109 is stored at a threshold value or more. At this time, the terminal device 100 may transmit the image data together with the learning data.
- server 300 After receiving the learning data, the server 300 newly executes machine learning based on the received learning data (S312). Subsequently, server 300 generates a control program and/or logical data for changing the functions of terminal device 100 based on the new learning result (S313).
- the machine learning algorithm used in the machine learning performed on the terminal device 100 is confirmed. Confirmation of the machine learning algorithm is performed by, for example, storing the control program and/or logic data previously transmitted to the terminal device 100 in the storage 340 and confirming it.
- the server 300 can identify the machine learning algorithm that is the basis of the received learning data. Determine your network, etc.
- the determined algorithm may be the same as or different from the algorithm used in terminal device 100 . Specifically, for example, if the deep learning network used in the terminal device 100 is an old version, a new version of the deep learning network is determined from the deep learning networks of the same system.
- the server 300 analyzes and/or learns the image data from the terminal device 100 using the determined machine learning algorithm.
- the server 300 After the learning is completed, the server 300 generates control programs and/or logical data based on the learning results. Specifically, for example, the server 300 generates a control program for controlling the deep learning network used. At that time, the generated program may be changed according to parameters such as input resolution and input channel. Also, as logic data, FPGA circuit data is generated using a learned deep learning network description file and a deep learning model file.
- Subsequent processing procedures are the same as those in the first embodiment, including control program and/or logical data transmission notification from server 300 (S303), downlink priority request (S102), data reception preparation (S103), downlink priority adjustment. (S202), adjustment completion notification (S203), data transmission request (S104), control program and/or logical data transmission (S304), terminal device 100 function change (S105), uplink priority request (S106), uplink Processing such as priority adjustment (S204) is executed.
- the second embodiment described above has the following effects in addition to the effects of the first embodiment.
- the server 300 performs learning based on the data of the terminal device 100, and based on the learning result of the server 300, the control program and/or logical data of the terminal device 100 are generated.
- AI Artificial Intelligence
- the server 300 which is more sophisticated than the terminal device 100, can perform more advanced machine learning or machine learning involving a large amount of data, which cannot be achieved by the terminal device 100 alone.
- the hardware resources of the terminal device 100 can be minimized, and the functions of the terminal device 100 can be changed based on advanced learning.
- Embodiment 3 is a control form when a problem occurs in the terminal device 100 . Since the configuration of the communication system 1 according to the third embodiment is the same as that of the first embodiment, the explanation is omitted.
- the third embodiment is a case where the terminal device 100 does not output a data transmission request (S104) to the server 300 after receiving the notification of completion of downlink priority adjustment (S203) from the network system.
- FIG. 8 is a flow chart showing the processing procedure in the third embodiment.
- a processing procedure when a problem occurs in the terminal device 100 will be described. Therefore, since the basic processing procedure is the same as that of Embodiment 1 or 2, description thereof will be omitted.
- FIG. 8 shows the processing procedure after the step in which the terminal device 100 transmits a downlink priority request (S102) in the processing procedure of the first embodiment.
- S102 downlink priority request
- the server 300 determines whether or not a data transmission request has been received from the terminal device 100 within a predetermined time after receiving this notification (S321).
- the predetermined time is preferably the time until a request from the terminal device 100 to the server 300 reaches the server 300 as an actual result. Specifically, for example, it is about 0.1 sec to 30 sec.
- step S321 if a data transmission request is received from the terminal device 100 within a predetermined time (S321: YES), the server 300 transmits the control program and/or logical data (S304). After that, the server 300 returns to S301 to continue the process if there is no instruction to end the process (S305: NO), and ends the process if there is an instruction to end the process (S305: YES).
- the server 300 requests the network system 200 to prioritize the uplink (S322).
- the network system 200 that has received the request for uplink priority adjusts the transmission ratio to give uplink priority (S204). At this time, the network system 200 adjusts to, for example, a predetermined standard transmission ratio with uplink priority.
- the server 300 outputs to the terminal device 100 used by the user (other than the terminal device in which the problem occurred) that the problem has occurred in the terminal device 100 (S323). After that, the server 300 returns to S301 to continue the process if there is no instruction to end the process (S305: NO), and ends the process if there is an instruction to end the process (S305: YES).
- the third embodiment described above has the following effects in addition to the effects of the first and second embodiments.
- the terminal device 100 If the terminal device 100 is normal, the terminal device 100 requests the server 300 to transmit data (S104) after receiving the notification of completion of downlink priority (S203), as in the first or second embodiment described above. On the other hand, if the terminal device 100 does not output a data transmission request (S104) to the server 300, it is assumed that the terminal device 100 has some problem.
- a malfunction of the terminal device 100 is detected by determining whether the server 300 has received a data transmission request within a predetermined time. Then, if the server 300 does not receive a request for data transmission from the terminal device 100 within a predetermined period of time, the server 300 assumes that the terminal device 100 has a problem and requests upstream priority. As a result, in the third embodiment, for example, data can be efficiently transmitted from the terminal device 100 to the server 300 after the malfunctioning terminal device 100 recovers. Further, in the third embodiment, the server 300 outputs the failure occurrence to the terminal devices 100 other than the terminal device 100 in which the failure has occurred.
- the user of the terminal device 100 and the server 300 can know the occurrence of the malfunction of the terminal device 100 through the terminal device 100 other than the terminal device 100 in which the malfunction has occurred. Also, the occurrence of a malfunction of the terminal device 100 may be displayed on the operation display unit 360 of the server 300 .
- the server 300 is caused to determine whether a problem has occurred in the terminal device 100 .
- the network system 200 (control unit) may be allowed to determine whether a problem has occurred in the terminal device 100 .
- network system 200 monitors whether or not data is transmitted to terminal device 100 that has requested downlink priority. Then, if there is no data transmission from the server 300 to the terminal device 100 within a predetermined period of time, the network system 200 adjusts so as to restore priority to the uplink.
- Embodiment 4 is a control form regarding the timing of changing the function of the terminal device 100 . Since the configuration of the communication system 1 in the fourth embodiment is the same as that in the first embodiment, the description is omitted.
- the fourth embodiment is an example of changing the function of the terminal device 100 when there is no change in the content of the data transmitted from the terminal device 100.
- the sensor 109 of the terminal device 100 is an image sensor such as a surveillance camera, and if there is no moving person or object and image data of the same content continues to be transmitted, the server 300 detects that the person or object is Change the functionality of the terminal device 100 to stop sending data until detected.
- FIG. 9 is a flow chart showing the processing procedure in the fourth embodiment.
- a processing procedure for changing the function of the terminal device 100 by the server 300 is shown. This processing procedure is executed, for example, before step S303 of the first embodiment.
- Other processing procedures are the same as those of the first embodiment, so description thereof is omitted.
- the server 300 determines whether or not there is any change in the content of the data received from the terminal device 100 (S331). The results of the analysis and/or learning (S302) are used to determine the content of the data. In the data analysis and/or learning process (S302), as already described, data analysis and/or learning is performed in time series. In the case of image data, the server 300 determines that there is no change when there is no change in the image (or there is no change in the number of pixels equal to or greater than a predetermined number) within a predetermined period of time.
- the predetermined time period for determining that there is no change to be long for example, in a facility where many people come and go or in a time zone when many people come and go. This eliminates the need to frequently change the functions of the terminal device 100 . Conversely, it is preferable to set a short time period for a facility where there are few people going in and out or in a time period when there are few people coming and going. This can reduce unnecessary data transmission.
- server 300 prepares a control program and/or logical data for changing the function of terminal device 100 (S332).
- the control program and/or logic data prepared here causes the terminal device 100 to determine a change in the image, to stop data transmission (upload), and to transmit data (upload) when there is a change in the image. ) is restarted.
- the control program and/or logic data may also cause the terminal device 100 to accumulate data detected by the sensor 109 in the storage 106 while the terminal device 100 stops uploading data.
- step S331 If it is determined that there is a change in step S331 (S331: NO), the server 300 proceeds to step S303 and continues subsequent processing, as in the first embodiment.
- the fourth embodiment described above has the following effects in addition to the effects of the first to third embodiments.
- data transmission from the terminal device 100 is stopped when the data content does not change, and data transmission from the terminal device 100 is restarted when the data content changes. .
- the amount of data sent to the communication line can be reduced, and the load on the communication line can be reduced.
- the terminal device 100 or the server 300 transmits a downlink priority request, and during this time, the control program and/or logical data are separately transmitted from the server 300 to the terminal device 100. You can also send. This makes it possible to effectively utilize the time while the upload is stopped.
- the terminal device 100 or the server 300 can also be used as past performance data by recording the time during which the upload is stopped. By utilizing the past performance data, for example, it is possible to confirm that there is a period of time in which the image does not change, such as meal time or bath time, in the residential facility.
- the server 300 determines to stop uploading and changes the function of the terminal device 100, but the present invention is not limited to this. For example, by storing a control program and/or logic data for judging an image change in the terminal device 100 in advance, the terminal device 100 itself judges whether or not there is an image change, thereby stopping and resuming the upload. You may let
- uploading may be stopped periodically based on past performance data or other data. For example, as described above, it is possible to stop uploading during a time period in which it is determined from past performance data that there is no person, and resume uploading when a person is detected. Stopping an upload may also be performed by leveraging other data. As other data, for example, at stations, etc., information on the arrival and departure timetables of public transportation is used. In this case, uploading may be stopped when people leave the station, and restarted when people are detected.
- the communication control program according to the present invention can also be realized by a dedicated hardware circuit.
- this communication control program can be provided by computer-readable recording media such as USB (Universal Serial Bus) memory and DVD (Digital Versatile Disc)-ROM (Read Only Memory), or can be provided on the Internet, etc., regardless of the recording medium. It is also possible to provide online through the network of When provided online, this communication control program is recorded on a recording medium (storage) such as a magnetic disk in a computer connected to a network.
- a recording medium storage
- 1 a communication system; 100 terminal device, 100a mobile terminal device, 100c surveillance camera device, 101 wireless communication unit, 102 line transmission ratio change request unit; 103 data reception processing unit, 104 analysis learning internal setting change unit, 105 control program/logical data section, 106 storage, 109 sensors, 110 SoC FPGAs, 150 5G communication interface, 160 operation display unit, 200 network system 201 wireless communication control unit, 202 line transmission ratio control unit (control unit), 203 processing relay determination unit, 300 server, 301 wireless communication unit, 302 terminal data analysis learning unit, 303 control program/logical data generator, 304 generation completion notification unit;
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Mobile Radio Communication Systems (AREA)
- Selective Calling Equipment (AREA)
Abstract
Description
少なくとも一部に無線通信を含むネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーと、を有する通信システムであって、
前記通信システムは、前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、上り回線と下り回線の伝送比を動的に制御する制御部を有し、
前記制御部は、データ伝送の状況またはデータ伝送の種類に応じて前記伝送比を調整する、通信システム。
前記端末装置は、データを記憶するストレージを有し、
前記端末装置は、データ送信中断の可否が否である場合、前記センシングデバイスからのデータを前記ストレージに記憶する、上記(5)~(7)のいずれか一つに記載の通信システム。
少なくとも一部に無線通信を有するネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーとを有する通信システムを制御するための通信制御プログラムであって、
前記通信システムは、前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、上り回線と下り回線の伝送比を動的に制御するコンピューターを有し、
データ伝送の状況またはデータ伝送の種類に応じて前記伝送比を調整する段階(a)を、前記コンピューターに実行させるための通信制御プログラム。
少なくとも一部に無線通信を有するネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーとを有する通信システムを制御するための通信制御方法であって、
前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、データ伝送の状況またはデータ伝送の種類に応じて、上り回線と下り回線の伝送比を動的に制御する、通信制御方法。
(通信システム)
図1は、本発明の一実施形態に係る通信システム1の概略構成を示す図である。図2は、一実施形態に係る通信システム1の機能を説明するためのブロック図である。
まず、端末装置100について説明する。端末装置100は、センシングデバイス(以下単にセンサー109という)を備え、センサー109が検知した情報をサーバー300へ送信する。また、端末装置100は、センサー109が検知した情報から自身においても機械学習や判定を実行する。
次に、ネットワークシステム200について説明する。ネットワークシステム200は、5Gによる無線通信機能を有し、端末装置100とサーバー300との間の通信を制御する。
次に、サーバー300について説明する。サーバー300は、端末装置100から送信されたデータを解析および/または学習する。また、サーバー300は、端末装置100の機能変更のための制御プログラムおよび/または論理データを記憶する。また、サーバー300は、端末装置100の機能変更のための制御プログラムおよび/または論理データを生成する。また、サーバー300は、端末装置100の設定(機能)を変更する。
次に、通信システム1の処理手順を説明する。
実施形態2は、前述した実施形態1と制御形態が異なる。前述した実施形態1は、制御プログラムおよび/または論理データが、あらかじめサーバー300のストレージ340に記憶されている例であった。本実施形態2においては、サーバー300が、端末装置100から送信されたデータを学習することで、新たに制御プログラムおよび/または論理データを生成し、端末装置100に送信して反映させる。
実施形態3は、端末装置100に不具合が発生した場合の制御形態である。本実施形態3における通信システム1の構成は、実施形態1と同様であるので、説明を省略する。
実施形態4は、端末装置100の機能変更のタイミングに関する制御形態である。本実施形態4における通信システム1の構成は、実施形態1と同様であるので、説明を省略する。
100 端末装置、
100a 携帯端末装置、
100c 監視カメラ装置、
101 無線通信部、
102 回線伝送比変更リクエスト部、
103 データ受信処理部、
104 解析学習内部設定変更部、
105 制御プログラム/論理データ部、
106 ストレージ、
109 センサー、
110 SoCFPGA、
150 5G通信インターフェース、
160 操作表示部、
200 ネットワークシステム
201 無線通信制御部、
202 回線伝送比制御部(制御部)、
203 処理中継判定部、
300 サーバー、
301 無線通信部、
302 端末データ解析学習部、
303 制御プログラム/論理データ生成部、
304 生成完了通知部。
Claims (23)
- センシングデバイスを有する端末装置と、
少なくとも一部に無線通信を含むネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーと、を有する通信システムであって、
前記通信システムは、前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、上り回線と下り回線の伝送比を動的に制御する制御部を有し、
前記制御部は、データ伝送の状況またはデータ伝送の種類に応じて前記伝送比を調整する、通信システム。 - 前記制御部は、前記端末装置から前記サーバーへのデータ量が前記サーバーから前記端末装置へのデータ量より多い場合は、前記上り回線の伝送量が多くなるように前記伝送比を調整する、請求項1に記載の通信システム。
- 前記制御部は、前記サーバーから前記端末装置へのデータ量が前記端末装置から前記サーバーへのデータ量より多い場合は、前記下り回線の伝送量が多くなるように前記伝送比を調整する、請求項1または2に記載の通信システム。
- 前記制御部は、前記端末装置からのリクエストに応じて、前記伝送比を調整する、請求項1~3のいずれか一つに記載の通信システム。
- 前記端末装置は、前記サーバーからデータの送信準備完了の通知を受信することで、前記制御部へ下り回線の伝送量を多くするようにリクエストする、請求項4に記載の通信システム。
- 前記サーバーは、前記端末装置へ送信するデータのデータサイズを、前記端末装置へ通知する、請求項5に記載の通信システム。
- 前記端末装置は、前記データサイズに応じて、前記伝送比を調整するようにリクエストする、請求項6に記載の通信システム。
- 前記サーバーは、データ送信中断の可否を前記端末装置へ通知し、
前記端末装置は、データを記憶するストレージを有し、
前記端末装置は、データ送信中断の可否が否である場合、前記センシングデバイスからのデータを前記ストレージに記憶する、請求項5~7のいずれか一つに記載の通信システム。 - 前記端末装置は、前記サーバーから送信されたデータの受信完了後、前記制御部へ上り回線の伝送量を多くするようにリクエストする、請求項1~8のいずれか一つに記載の通信システム。
- 前記制御部は、前記下り回線の伝送量が多くなるように調整した後、所定時間内に、前記端末装置から伝送比変更のリクエストがない場合に、前記上り回線の伝送量が多くなるように前記伝送比を調整する、請求項9に記載の通信システム。
- 前記サーバーは、前記制御部によって前記下り回線の伝送量が多くなるように前記伝送比が調整された後、所定時間内に、前記端末装置からデータ送信のリクエストがない場合に、前記上り回線の伝送量が多くなるように前記制御部へリクエストする、請求項9に記載の通信システム。
- 前記サーバーは、前記端末装置を動作させるための制御プログラムおよび/または論理データを生成し、前記端末装置へ前記制御プログラムまたは前記論理データを送信する、請求項1~11のいずれか一つに記載の通信システム。
- 前記制御部は、前記制御プログラムおよび/または前記論理データの送信時に、前記下り回線の伝送量が多くなるように前記伝送比を調整する、請求項12に記載の通信システム。
- 前記制御プログラムまたは前記論理データは、前記端末装置内で使用する機械学習のアルゴリズムを有する、請求項13に記載の通信システム。
- 前記サーバーは、前記制御プログラムおよび/または前記論理データの送信準備が完了したことを前記端末装置に通知する、請求項12~14のいずれか一つに記載の通信システム。
- 前記端末装置および/または前記サーバーは、前記センシングデバイスから得られたデータにより学習し、前記端末装置の機能を変更する、請求項1~15のいずれか一つに記載の通信システム。
- 前記端末装置は、複数の前記センシングデバイスを有する、請求項1~16のいずれか一つに記載の通信システム。
- センシングデバイスを有する端末装置と、
少なくとも一部に無線通信を有するネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーとを有する通信システムを制御するための通信制御プログラムであって、
前記通信システムは、前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、上り回線と下り回線の伝送比を動的に制御するコンピューターを有し、
データ伝送の状況またはデータ伝送の種類に応じて前記伝送比を調整する段階(a)を、前記コンピューターに実行させるための通信制御プログラム。 - 前記段階(a)は、前記端末装置から前記サーバーへのデータ量が前記サーバーから前記端末装置へのデータ量より多い場合は、前記上り回線の伝送量が多くなるように前記伝送比を調整する、請求項18に記載の通信制御プログラム。
- 前記段階(a)は、前記サーバーから前記端末装置へのデータ量が前記端末装置から前記サーバーへのデータ量より多い場合は、前記下り回線の伝送量が多くなるように前記伝送比を調整する、請求項18または19に記載の通信制御プログラム。
- 前記段階(a)は、前記端末装置からのリクエストに応じて、前記伝送比を調整する、請求項18~20のいずれか一つに記載の通信制御プログラム。
- 前記段階(a)において前記下り回線の伝送量が多くなるように前記伝送比を調整した後、所定時間内に、前記端末装置から伝送比変更のリクエストがない場合、前記上り回線の伝送量が多くなるように前記伝送比を調整する段階(b)を有する、請求項21に記載の通信制御プログラム。
- センシングデバイスを有する端末装置と、
少なくとも一部に無線通信を有するネットワークシステムと、
前記ネットワークシステムにより無線通信を介して前記端末装置とデータ伝送を行うサーバーとを有する通信システムを制御するための通信制御方法であって、
前記端末装置から前記サーバーへの方向を上り回線、前記サーバーから前記端末装置への方向を下り回線として、データ伝送の状況またはデータ伝送の種類に応じて、上り回線と下り回線の伝送比を動的に制御する、通信制御方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/272,447 US20240080835A1 (en) | 2021-01-25 | 2021-10-26 | Communication system, communication control program, and communication control method |
JP2022576981A JP7332063B2 (ja) | 2021-01-25 | 2021-10-26 | 通信システム、通信制御プログラム、通信制御方法、および制御部 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021009446 | 2021-01-25 | ||
JP2021-009446 | 2021-01-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022158068A1 true WO2022158068A1 (ja) | 2022-07-28 |
Family
ID=82548711
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/039413 WO2022158068A1 (ja) | 2021-01-25 | 2021-10-26 | 通信システム、通信制御プログラム、および通信制御方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20240080835A1 (ja) |
JP (1) | JP7332063B2 (ja) |
WO (1) | WO2022158068A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006025016A (ja) * | 2004-07-06 | 2006-01-26 | Matsushita Electric Ind Co Ltd | Adslモデム装置及び通信制御方法 |
JP2015502118A (ja) * | 2012-03-30 | 2015-01-19 | エヌイーシー(チャイナ)カンパニー, リミテッドNEC(China)Co.,Ltd. | アップリング−ダウンリンク設定を動的に調整するための方法および装置 |
JP2018508130A (ja) * | 2014-12-17 | 2018-03-22 | ホアウェイ・テクノロジーズ・カンパニー・リミテッド | ワイヤレスネットワークにおける時分割復信通信のための方法およびシステム |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6959171B2 (en) * | 2002-02-28 | 2005-10-25 | Intel Corporation | Data transmission rate control |
-
2021
- 2021-10-26 WO PCT/JP2021/039413 patent/WO2022158068A1/ja active Application Filing
- 2021-10-26 JP JP2022576981A patent/JP7332063B2/ja active Active
- 2021-10-26 US US18/272,447 patent/US20240080835A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006025016A (ja) * | 2004-07-06 | 2006-01-26 | Matsushita Electric Ind Co Ltd | Adslモデム装置及び通信制御方法 |
JP2015502118A (ja) * | 2012-03-30 | 2015-01-19 | エヌイーシー(チャイナ)カンパニー, リミテッドNEC(China)Co.,Ltd. | アップリング−ダウンリンク設定を動的に調整するための方法および装置 |
JP2018508130A (ja) * | 2014-12-17 | 2018-03-22 | ホアウェイ・テクノロジーズ・カンパニー・リミテッド | ワイヤレスネットワークにおける時分割復信通信のための方法およびシステム |
Also Published As
Publication number | Publication date |
---|---|
US20240080835A1 (en) | 2024-03-07 |
JPWO2022158068A1 (ja) | 2022-07-28 |
JP7332063B2 (ja) | 2023-08-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220256647A1 (en) | Systems and Methods for Collaborative Edge Computing | |
US11564277B2 (en) | Method and apparatus for supporting early data transmission in inactive state in wireless communication system | |
US20200322847A1 (en) | Method and apparatus for enhancing handover procedure for supporting conditional handover in wireless communication system | |
US20210306887A1 (en) | Mobile terminal for displaying whether qos is satisfied in wireless communication system | |
WO2019052266A1 (zh) | 一种智能物联网管理系统、方法以及服务器 | |
US20220053390A1 (en) | Support of inter-gnb handover in higher layer multi-connectivity | |
US11503516B2 (en) | Method and apparatus for providing beam related information for connection failure detection in wireless communication system | |
CN104049575A (zh) | 在过程控制系统中收集并且向大数据机器递送数据 | |
CN109313841B (zh) | 用于在传感器网络中实现自适应聚类的方法和系统 | |
US20190163530A1 (en) | Computation apparatus, resource allocation method thereof, and communication system | |
CN108899082A (zh) | 维修服务管理方法、系统、终端及计算机可读存储介质 | |
US10574764B2 (en) | Automated learning universal gateway | |
CN108446207B (zh) | 计算机系统容灾能力评估方法、装置及系统 | |
Ksentini et al. | IoT/Cloud‐enabled smart services: a review on QoS requirements in fog environment and a proposed approach based on priority classification technique | |
Ahammad et al. | Software-defined dew, roof, fog and cloud (SD-DRFC) framework for IoT ecosystem: the journey, novel framework architecture, simulation, and use cases | |
CN109165261A (zh) | 数据同步方法、装置、服务器及计算机存储介质 | |
CN106154906A (zh) | 面向智能操作系统的故障报告方法及机器人操作系统 | |
WO2022158068A1 (ja) | 通信システム、通信制御プログラム、および通信制御方法 | |
WO2020207252A1 (zh) | 数据存储方法、装置、存储介质及电子设备 | |
AU2023248156A1 (en) | Arrival detection for battery-powered optical sensors | |
CN112132338A (zh) | 机器人全自动配送的调度优化方法和装置 | |
JP6558452B1 (ja) | 品質チェック装置、品質チェック方法及びプログラム | |
Abdellaoui et al. | Dynamic reconfiguration of lpwans pervasive system using multi-agent approach | |
Lu et al. | IoT and smart infrastructure | |
CAO et al. | An os for internet of everything: Early experience from a smart home prototype |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21921171 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022576981 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18272447 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21921171 Country of ref document: EP Kind code of ref document: A1 |