JP2022175553A - Radio communications system, connection destination learning device, connection destination learning program, and connection destination learning method - Google Patents

Abstract

To provide a radio communications system, or the like capable of optimizing a communication path among a plurality of communication terminals.SOLUTION: In a radio communications system comprising a plurality of communication terminals containing a master unit and slave units, mutual connection destinations for transmitting and receiving signals among the plurality of communication terminals are defined. The slave unit measures intensity of a received signal from another communication terminal of the plurality of communication terminals. The master unit comprises a learning part that calculates success rates of communications between itself and the respective slave units, leans so as to enhance the success rates of the communications, and outputs output information on the connection destination upon inputted with input information on a communication state containing the intensity of received signal and the success rate of communication. In addition, the master unit updates the connection destination on the basis of the output information.SELECTED DRAWING: Figure 10

Description

TECHNICAL FIELD The present invention relates to a radio communication system or the like in which connection destinations for transmitting and receiving signals between a plurality of communication terminals including a parent device and a child device are specified.

2. Description of the Related Art Conventionally, wireless communication systems are known that include a plurality of communication terminals such as sensors and repeaters. A wireless communication system includes a plurality of communication terminals connected to each other by wireless communication. Mutual connection destinations are defined between these communication terminals. In such a wireless communication system, connection destinations between communication terminals are determined based on, for example, radio field strength (received signal strength) (see, for example, Patent Document 1).

JP 2009-218913 A

In the configuration in which the connection destination is determined based on the radio wave intensity as described above, there is a risk that the connection will be concentrated on the repeater with the high radio wave intensity and the communication success rate will decrease, resulting in the network becoming unstable.

SUMMARY OF THE INVENTION An object of the present invention is to provide a wireless communication system and the like that can optimize communication paths between a plurality of communication terminals.

A wireless communication system provided by a first aspect of the present invention includes a plurality of communication terminals including a parent device and a child device, and a wireless communication system in which mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are defined. In a communication system, a child device measures received signal strengths from other communication terminals among a plurality of communication terminals, and a parent device calculates a communication success rate with each of the child devices, and calculates the communication success rate a learning unit that learns such that the communication is improved, and outputs output information regarding the connection destination when input information regarding the communication state including the received signal strength and the communication success rate is input. Also, the parent machine updates the connection destination based on the output information.

The input information may include the number of paths, which is the number of signal propagation paths in wireless communication between each of the plurality of communication terminals and other communication terminals, and the communication signal strength of each of the radio wave paths.

The learning unit may learn by reinforcement learning with a communication success rate as a reward.

The parent device communicates with the child device assigned to each of the plurality of time slots according to a communication schedule including the plurality of time slots, and each of the child devices communicates with the parent device or other devices among the plurality of time slots. The received signal strength may be measured based on a signal transmitted by the parent device or another child device in the time slot to which the child device is assigned.

Each of the parent device and the child device is configured to transmit a synchronization signal in an assigned time slot among the plurality of time slots, The received signal strength may be measured based on the synchronization signal transmitted by the master or another slave in the time slot assigned to the slave.

The communication success rate is the ratio of responses to reply requests sent from the parent device to the child device in wireless communication, and the parent device calculates the communication success rate for each child device. You may do so.

A connection destination learning device provided by a second aspect of the present invention is provided with a plurality of communication terminals including a parent device and a child device, and mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are specified. A connection destination learning device for application to a wireless communication system, which includes the received signal strength from other communication terminals measured by the child device and the communication state including the communication success rate between the parent device and the child device. acquisition means for acquiring input information regarding the connection destination, learning means for learning so as to improve the communication success rate, and output means for outputting output information regarding the connection destination when input information regarding the communication state is input.

A connection destination learning program provided by a third aspect of the present invention is provided with a plurality of communication terminals including a parent device and a child device, and mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are defined. Input related to the communication status including the received signal strength from other communication terminals measured by the child device and the success rate of communication with each of the parent device and the child device It functions as acquisition means for acquiring information, learning means for learning so as to improve the communication success rate, and output means for outputting output information regarding a connection destination when input information regarding a communication state is input.

A connection destination learning method provided by a fourth aspect of the present invention is provided with a plurality of communication terminals including a parent device and a child device, and mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are defined. A connection destination learning method for application to a wireless communication system, which includes the received signal strength from other communication terminals measured by the child device and the communication state including the communication success rate between the parent device and the child device. Acquisition processing for acquiring input information regarding the connection destination, learning processing for learning so as to improve the communication success rate, and output processing for outputting output information regarding the connection destination when input information regarding the communication state is input.

According to the present invention, learning is performed so as to improve the communication success rate, and the learning automatically updates the information regarding the mutual connection destinations between a plurality of communication terminals, thereby reducing communication failures (failures). It is possible to optimize communication paths between a plurality of communication terminals.

1 is a schematic diagram of a wireless communication system according to an embodiment of the present invention; FIG. 1 is a block diagram of a data station according to an embodiment of the invention; FIG. 1 is a block diagram of a repeater according to an embodiment of this invention; FIG. 1 is a block diagram of a sensor according to an embodiment of the invention; FIG. It is a figure which shows an example of the tree table based on embodiment of this invention. It is a figure which shows an example of the routing table based on embodiment of this invention. It is a figure which shows an example of the sensor table which concerns on embodiment of this invention. It is a figure which shows an example of the communication schedule which concerns on embodiment of this invention. 4 is a flow chart showing scan processing according to the embodiment of the present invention; It is a figure which shows the outline|summary of the learning part which concerns on embodiment of this invention. It is a figure which shows an example of the intensity|strength data list based on embodiment of this invention. It is a figure which shows an example of the success rate data list based on embodiment of this invention. It is a figure which shows an example of the scan data list|wrist which concerns on embodiment of this invention. FIG. 4 is a diagram showing an example of a multipath data list according to the embodiment of the present invention; FIG. 4 is a flow chart showing update processing according to the embodiment of the present invention; FIG. 10 is a diagram showing an example of a tree table after updating according to the embodiment of the present invention; FIG. It is a figure which shows an example of the routing table after update which concerns on embodiment of this invention.

A wireless communication system (connection destination learning device, connection destination learning program, connection destination learning method) according to an embodiment of the present invention will be described with reference to the drawings. In addition, the structure of this invention is not limited to embodiment. Further, the order of various processes constituting the flow described below is random as long as there is no contradiction or the like in the contents of the processes.

FIG. 1 is a schematic diagram of a wireless communication system 100 according to an embodiment of the invention.

A wireless communication system 100 includes a data station 10 , multiple repeaters 20 , and multiple sensors 30 . The data station 10, the repeater 20, and the sensor 30 are communication terminals, perform wireless communication with each other, and autonomously construct a network. That is, mutual connection destinations for transmitting and receiving signals between a plurality of communication terminals are defined. A multi-hop wireless network is formed in the wireless communication system 100 . The data station 10 functions as a parent device. The repeater 20 and the sensor 30 function as slaves. Basically, the data station 10 communicates with the repeater 20 and the sensor 30 communicates with the repeater 20 . The number of sensors 30 is greater than that of repeaters 20 .

The data station 10 and the repeater 20 form a tree-type network topology with the data station 10 as the apex (top). In this embodiment, the data station 10 side in the network is the upstream side or the upper side, and the terminal side of the tree is the downstream side or the lower side. Moreover, when the data station 10, repeater 20, and sensor 30 are not distinguished, they may simply be referred to as communication terminals. Moreover, when distinguishing each repeater 20, the alphabet is attached after code|symbol "20", and it distinguishes. Similarly, when distinguishing between the sensors 30, they are distinguished by adding an alphabet after the code "30".

In the wireless communication system 100 , the sensor 30 detects a predetermined physical quantity of an object, and the detected value, that is, the detected data is collected by the data station 10 via the repeater 20 . For example, wireless communication system 100 is installed in a factory having a steam system. The steam system has multiple steam traps T (only one is shown in FIG. 1). The object is the steam trap T. The sensor 30 detects the vibration frequency and temperature of the steam trap T.

Further, in the wireless communication system 100, machine learning (for example, reinforcement learning) of AI (Artificial Intelligence) is used to learn so as to improve the communication success rate between the parent device and the child device. Mutual connection destinations (communication paths) for transmitting and receiving signals between communication terminals are optimized.

<Configuration of data station>
FIG. 2 is a block diagram of data station 10. As shown in FIG. The data station 10 collects and manages detection values of the sensors 30 of the wireless communication system 100 . The data station 10 is also connected to a host server 90 (FIG. 1) or the like via an external network or the like. The data station 10 transfers the detected value of the sensor 30 to the server 90 as required. Furthermore, the data station 100 functions as a connection destination learning device and establishes a communication path of the wireless communication system 100 .

The data station 10 has a CPU 11 , a memory 12 , a storage section 13 , a wireless communication circuit 14 , a timer circuit 15 , a host interface section 16 and a power supply circuit 17 . Alternatively, the data station 10 may have a GPU.

Various programs and various information are stored in the storage unit 13 . The CPU 11 performs various processes by reading various programs from the storage unit 13 and executing them. For example, the storage unit 13 stores a program for forming a communication path of the network, a program for collecting detection values of the sensors 30, a tree table that defines the tree structure of the network, each sensor 30 to which repeater 20. A sensor table that defines whether or not there is a connection, a routing table that defines the route to the final destination, a program for creating the routing table from the tree table, schedule information that defines the schedule for communicating with the repeater 20, and Collected detection values and the like are stored.

The storage unit 13 also stores a program for calculating the communication success rate. The communication success rate is the ratio of replies to reply requests sent from the parent device (data station 10) to each child device (relay device 20 and sensor 30) in wireless communication. The data station 10 (CPU 11) calculates {(the number of times a reply is received)/(the number of times a reply is requested)} as the communication success rate. The data station 10 (CPU 11) calculates a communication success rate for each slave device. For example, it stores the communication success rate for a predetermined number of times (for example, five times in the past) that replies have been requested from the present time. The "number of times a reply was received" means the number of times the data station 10 received the reply. Therefore, when the sensor 30 returns the detection value, but the relay device 20 on the way fails to reply, it is not counted in the "number of times of reply". Also, the communication success rate is the communication success rate with the child device that requested a reply. Therefore, for example, when the data station 10 requests a reply from a certain sensor 30, even if the repeater 20 relays the signal on the way, the communication success rate between the data station 10 and the certain sensor 30 is Calculated. Note that data such as “the number of times a reply was received” for calculation and the calculated communication success rate are also stored in the storage unit 13 .

Furthermore, the storage unit 13 stores a connection destination learning program. The CPU 11 functions as a learning unit DL (learning model) by executing the connection learning program. The learning unit DL outputs output information regarding mutual connection destinations for transmitting and receiving signals between a plurality of communication terminals. The CPU 11 (data station 10) establishes (changes) the communication path of the wireless communication system 100 based on this output information. Details will be described later.

The wireless communication circuit 14 wirelessly communicates with other communication terminals such as the repeater 20 . The wireless communication circuit 14 operates under the control of the CPU 11, converts various signals into wireless signals by processing such as encoding and modulation, and transmits the wireless signals through an antenna. Also, the radio communication circuit 14 converts a signal received via an antenna into an appropriate signal through processing such as demodulation and decoding. Furthermore, the radio communication circuit 14 measures a received signal strength indicator (RSSI) based on the received signal. For the received signal strength, for example, an average value of received signals can be used. The received signal strength is stored in the storage unit 13 in association with the identification information of the transmitting terminal of the received signal.

The clock circuit 15 generates a predetermined clock and clocks a reference time for the data station 10 . The host interface unit 16 performs interface processing with the server 90 . The power supply circuit 17 is connected to an external power supply (not shown) and supplies power to each element of the data station 10 .

<Configuration of Repeater>
FIG. 3 is a block diagram of the repeater 20. As shown in FIG. The repeater 20 transmits the detected value of the sensor 30 to the data station 10 according to the command from the data station 10 . The repeater 20 has a CPU 21 , a memory 22 , a storage section 23 , a wireless communication circuit 24 , a timer circuit 25 , a power supply circuit 26 and a battery 27 .

Various programs and various information are stored in the storage unit 23 . The CPU 21 performs various processes by reading various programs from the storage unit 23 and executing them. For example, the storage unit 23 stores a program for forming a network communication path, a program for relaying the detection value of the sensor 30, a tree table, a routing table, a program for creating a routing table from the tree table, a connection Sensor connection information specifying the sensor 30 connected to the sensor 30, detection values obtained from the sensor 30, and the like are stored.

The storage unit 23 also stores a program for estimating the remaining amount of the battery 27 . By executing the program, the CPU 21 integrates power consumption according to various processes and estimates the remaining amount of the battery 27 .

The wireless communication circuit 24 performs wireless communication with other communication terminals. The wireless communication circuit 24 operates under the control of the CPU 21, converts various signals into wireless signals by processing such as encoding and modulation, and transmits the wireless signals via an antenna. Also, the radio communication circuit 24 converts a signal received via an antenna into an appropriate signal by processing such as demodulation and decoding. Further, wireless communication circuit 24 measures the received signal strength based on the received signal. For the received signal strength, for example, an average value of received signals can be used. The received signal strength is stored in the storage unit 23 in association with the identification information of the transmitting terminal of the received signal.

The timer circuit 25 generates a predetermined clock and measures a reference time for the repeater 20 . A battery 27 is connected to the power supply circuit 26 . A power supply circuit 26 supplies power to each element of the repeater 20 .

The relay device 20 has an active state in which various processes such as transmission and reception of signals with other communication terminals can be executed, and a sleep state in which the relay device 20 cannot execute processing such as transmission and reception of signals but consumes less power than in the active state. and are configured to be switchable. When the repeater 20 changes from the active state to the sleep state, the CPU 21 sets the time at which the relay device 20 should become the active state in the timer circuit 25, and becomes the inactive state. In the sleep state, clock circuit 25 continues clocking. When the set time comes, the timer circuit 25 notifies the CPU 21 of the arrival of the time, and the CPU 21 receiving this notification changes from the inactive state to the active state. Also, the CPU 21 in the active state permits power supply from the power supply circuit 26 to the memory 22 , the storage section 23 and the wireless communication circuit 24 . In this way, the repeater 20 goes from the sleep state to the active state.

<Sensor configuration>
FIG. 4 is a block diagram of sensor 30. As shown in FIG. The sensor 30 detects the vibration frequency and temperature of the steam trap T, and transmits the detected value to the corresponding repeater 20 . The sensor 30 has a sensor section 40 that detects a predetermined physical quantity of an object, and a processing section 50 that transmits the detection value of the sensor section 40 to another communication terminal.

The sensor section 40 includes a vibration sensor and a temperature sensor, and detects the vibration frequency and temperature of the steam trap T. The sensor unit 40 is installed so as to be in contact with the casing of the steam trap T (for example, the inflow portion into which steam and drain flow), and detects the vibration frequency and temperature of the contact portion. The sensor unit 40 outputs an electric signal corresponding to the detected vibration frequency and temperature to the processing unit 50 .

The processing unit 50 has a CPU 51 , a memory 52 , a storage unit 53 , a wireless communication circuit 54 , a timer circuit 55 , a sensor interface unit 56 , a power supply circuit 57 and a battery 58 .

Various programs and various information are stored in the storage unit 53 . The CPU 51 performs various processes by reading various programs from the storage unit 53 and executing them. For example, the storage unit 53 stores a program for forming a network communication path, a program for acquiring the vibration frequency and temperature from the sensor unit 40 and transmitting them as detected values to the repeater 20, the connected repeater 20 and repeater connection information specifying the , detection values, and the like are stored.

The storage unit 53 also stores a program for estimating the remaining amount of the battery 58 . By executing the program, the CPU 51 integrates power consumption according to various processes and estimates the remaining amount of the battery 58 .

A wireless communication circuit 54 performs wireless communication with other communication terminals. The wireless communication circuit 54 operates under the control of the CPU 51, converts various signals into wireless signals by processing such as encoding and modulation, and transmits the wireless signals via an antenna. Also, the radio communication circuit 54 converts the signal received via the antenna into an appropriate signal by processing such as demodulation and decoding. Further, wireless communication circuit 54 measures the received signal strength based on the received signal. For the received signal strength, for example, an average value of received signals can be used. The received signal strength is stored in the storage unit 53 in association with the identification information of the transmitting terminal of the received signal.

The clock circuit 55 generates a predetermined clock and clocks a reference time for the sensor 30 . The sensor interface section 56 performs interface processing with the sensor section 40 . A battery 58 is connected to the power supply circuit 57 . A power supply circuit 57 supplies power to each element of the sensor 30 .

As with the repeater 20, the sensor 30 has an active state in which various processes such as transmission and reception of signals with other communication terminals can be executed, and a state in which processing such as transmission and reception of signals cannot be executed but consumes less power than the active state. is configured to be switchable between the sleep state and the sleep state in which

<Communication terminal connection>
In the wireless communication system 100, the connection destination of each communication terminal is determined, and signal propagation is performed based on the connection relationship. The wireless communication system 100 holds a tree table, a routing table, a sensor table, sensor connection information, and relay connection information as connection relationships between the data station 10 , the repeater 20 and the sensor 30 .

The tree table is a table that defines the tree structure of the wireless communication system 100 and defines communication terminals that are higher than each repeater 20 . One tree table is created in the wireless communication system 100, and the data station 10 and all repeaters 20 hold a common tree table. FIG. 5 is a tree table corresponding to the wireless communication system 100 of FIG. The upper column of the tree table describes the target repeater 20, and the lower column specifies the upper communication terminal (data station 10 or repeater 20) to which each repeater 20 is connected. .

The routing table shows the correspondence relationship between all reachable final destination communication terminals from a certain communication terminal and the next (one-hop ahead) communication terminal in the communication route from the certain communication terminal to the final destination. That is, it defines a communication terminal that is one hop lower than a certain communication terminal on the communication route to the final destination. A routing table is created based on the tree table. Each data station 10 and each repeater 20 has its own routing table.

FIG. 6 is a routing table of the repeater 20a in the wireless communication system 100 of FIG. The upper column of the routing table describes the target final destination, and the lower column defines the repeater 20 that is one hop ahead when the repeater 20a is the starting point. From the repeater 20a, the repeaters 20b, 20c, 20d, 20e, 20f, 20g, 20h, and 20i can be reached. Repeaters 20 are defined respectively. Since the relays 20j and 20k cannot be reached from the relay 20a, the routing table of the relay 20a does not define the relay 20 that is one hop ahead when the relays 20j and 20k are the final destinations. .

The sensor table defines the connection relationship between the sensors 30 and the repeaters 20 (that is, which repeater 20 each sensor 30 is connected to). One sensor table is created in the wireless communication system 100 and held by the data station 10 . FIG. 7 is a sensor table corresponding to the wireless communication system 100 of FIG. The upper column of the sensor table describes the target sensor 30, and the lower column defines the repeater 20 to which each sensor 30 is connected.

The sensor connection information is information held by each of the repeaters 20 and is information specifying the sensor 30 connected to each repeater 20 (for example, the communication address of the sensor 30).

The repeater connection information is information held by each of the sensors 30 and is information specifying the repeater 20 to which each sensor 30 is connected (for example, the communication address of the repeater 20).

In the radio communication system 100, signals are propagated using these connection relationships. First, the case where the signal is transmitted from the data station 10 in the downlink direction will be described. For example, when the data station 10 transmits a signal to the sensor 30g, the data station 10 determines the repeater 20h to which the sensor 30g is connected based on the sensor table. Based on its own routing table, the data station 10 determines that the relay 20a is the relay 20 that is one hop ahead when the final destination is the relay 20h. The data station 10 sets the repeater 20h as the final destination and transmits a signal in which the repeater 20a is set as the destination one hop ahead.

After that, each repeater 20 that receives this signal changes the repeater 20 one hop ahead based on its own routing table, and propagates the signal to the repeater 20h. Specifically, the relay device 20a sets the relay device 20d as the transmission destination one hop ahead, and transfers the signal. The repeater 20d that has received the signal sets the repeater 20g as the transmission destination one hop ahead, and transfers the signal. The repeater 20g that has received the signal sets the repeater 20h as the transmission destination one hop ahead, and transfers the signal. Upon receiving the signal, the relay device 20h, which is the final destination, sets both the final destination and the one-hop destination to the sensor 30g based on its own sensor connection information, and transmits the signal. Thus, the signal is finally received by sensor 30g.

Next, the case where the signal is transmitted in the uplink direction to the data station 10 will be described. For example, when the sensor 30g transmits a signal to the data station 10, the sensor 30g transmits a signal in which both the final destination and the one-hop destination are set to the repeater 20h based on its own repeater connection information. Send. The signal is received by repeater 20h. Based on the tree table, the repeater 20h determines that the repeater 20 that is one hop higher is the repeater 20g. The repeater 20h transmits a signal in which the data station 10 is set as the final destination and the repeater 20g is set as the destination one hop ahead.

After that, each repeater 20 that receives this signal changes the repeater 20 one hop ahead based on the tree table, and propagates the signal to the data station 10 . Specifically, the relay device 20g sets the relay device 20d as the transmission destination one hop ahead, and transfers the signal. The repeater 20d sets the repeater 20a as the transmission destination one hop ahead, and transfers the signal. The repeater 20a sets the data station 10 as the transmission destination one hop ahead, and transfers the signal. Thus, the signal is finally received by data station 10 .

In this manner, the data station 10, repeater 20, and sensor 30 transmit signals based on the connection relationship (tree table, routing table, tree table, sensor connection information, and repeater connection information) of the communication terminals.

<Communication schedule>
The wireless communication system 100 configured in this manner performs collection processing for collecting detection values of the sensor 30 in the data station 10 as a normal driving operation. The data station 10 communicates with each repeater 20 according to the communication schedule shown in FIG.

The communication schedule in FIG. 8 indicates one cycle of collection processing, and the communication schedule in FIG. 8 is repeatedly executed. The communication schedule is divided into multiple time slots. Each repeater 20 is assigned a specific time slot. Each repeater 20 communicates with the data station 10 in the corresponding time slot, and transmits the detection value from the sensor 30 connected to the repeater 20 to the data station 10 (hereinafter, this process is also called "reply process"). Say).

Basically, each repeater 20 is in an active state in a specific assigned time slot (hereinafter also referred to as a "specific slot"), and is in a sleep state at times other than the specific slot. However, since it is necessary for the repeater 20 existing on the communication path between the other repeater 20 and the data station 10 to perform relay processing when the lower repeater 20 communicates with the data station 10, the lower repeater 20 Also in a time slot assigned to the machine 20 (hereinafter also referred to as a "relay slot"), it becomes active and executes relay processing. Moreover, since the sensor 30 transmits the detection value to the repeater 20 in the specific slot of the connected repeater 20 , the sensor 30 is in the active state in the specific slot of the repeater 20 . The sensor 30 is basically in a sleep state when it is not necessary to transmit the detected value to the repeater 20 .

In the communication schedule of FIG. 8, time slots are defined in a matrix. Basically, time slots are assigned according to the hierarchy of communication paths in a tree structure. Specifically, a tree structure hierarchy is assigned to each column. For example, column L0 is assigned the data station 10, column L1 is assigned the first tier (i.e. hop count 1), and column L2 is assigned the second tier (i.e. hop count 2). is assigned. The same applies to the third and subsequent hierarchies.

Usually, each repeater 20 is assigned any one time slot. Time slots in column L1 are assigned to the repeaters 20a and 20j of the first layer. Time slots in column L2 are assigned to the repeaters 20b, 20c, 20d, and 20k of the second hierarchy. Time slots in column L3 are assigned to the repeaters 20e, 20f, and 20g of the third layer. Time slots in column L4 are assigned to the repeaters 20h and 20i of the fourth layer.

On the other hand, since the data station 10 has more processing contents than the repeater 20, not one time slot but a plurality of time slots (in FIG. 8, all the time slots in column L0) are assigned to the data station 10. . Note that the number of time slots included in a row differs from the number of repeaters 20 included in each layer (usually, the number of time slots included in a row is greater than the number of time slots included in a row). Some have no repeaters assigned.

Further, as described above, in a specific slot of a certain repeater 20, the sensor 30 connected to the repeater 20 is also in an active state. It will be. However, since a plurality of sensors 30 can be connected to the repeater 20 , in such a case, a plurality of sensors 30 are assigned to a specific slot of the repeater 20 . For example, in the example of FIG. 8, the repeater 20e is assigned to the time slot of column L3 and row N1. Since two sensors 30d and 30e are connected to the repeater 20e (see FIG. 1), the two sensors 30 are substantially assigned to the time slot of column L3 and row N1.

In the communication schedule, the processing of time slots proceeds columnwise. For example, in a certain column (for example, column L1), time slot processing proceeds in ascending order with respect to the row number (that is, the order of rows N1 to Nm), and the time slot of the last row number (row Nm) of the row is processed. When slot processing is completed, processing proceeds in the same order from the time slot of the first row number (row N1) in the next column (eg, column L2).

<Determination of connection relationship and assignment of time slots>
When establishing a network communication path, the data station 10 establishes the connection relationship of the communication terminals and allocates time slots to complete the communication schedule. Specifically, at the time of initial setting for establishing the communication path of the network, the connection relationship of the communication terminals is determined, and time slots are assigned to complete the communication schedule.

For example, the data station 10 establishes which communication terminals are connected, that is, establishes the connection relationship among the data station 10, the repeater 20, and the sensor 30, and creates a tree table and a sensor table. Furthermore, the data station 10 creates a routing table based on the tree table. Once the connection relationship is established, the data station 10 assigns each repeater 20 a time slot to complete the communication schedule. The data station 10 stores the tree table, the sensor table, the routing table, and the communication schedule (that is, allocation of time slots to the repeaters 20) in the storage unit 13. FIG.

When the time slot allocation is completed, the data station 10 notifies each repeater 20 of the tree table and the slot number of the specific slot. At this time, in addition to the slot number of the specific slot of the repeater 20 that needs to perform the relay processing of the lower repeater 20, the slot number of the specific slot of the lower repeater 20, that is, the slot number of the relay slot is also notified. Further, the data station 10 notifies each repeater 20 of the sensor connection information and each sensor 30 of the repeater connection information based on the sensor table.

Each repeater 20 creates a routing table based on the tree table. Also, the repeater 20 notifies the connected sensor 30 of the slot number of the specific slot of the repeater 20 . The repeater 20 stores the slot numbers of the specific slot and the relay slot, the tree table, the routing table, and the sensor connection information in the storage unit 23 .

The sensor 30 stores the slot number of the specific slot of the connected repeater 20 and the repeater connection information in the storage unit 53 .

After initial setting, the communication path is updated by the output information (tree table and sensor table) output from the learning unit DL. Details will be described later.

<System operation>
Next, various processes of the wireless communication system 100 will be described.

- Collection process -
In the collection process, the data station 10 proceeds with the process according to the communication schedule. Specifically, the data station 10 performs the necessary processing for the data station 10 in its own assigned time slot. Subsequently, the data station 10 sequentially communicates with the repeaters 20 assigned to the time slots in the order of the time slots. At this time, the signal sent from the data station 10 to each repeater 20 includes at least a request signal requesting a return of the detection value of the sensor 30 .

On the other hand, the repeater 20 becomes active at the timing of a specific slot according to the communication schedule and waits for a request signal from the data station 10 . Also, the repeater 20 acquires a detection value from the sensor 30 connected to the repeater 20 according to the specific slot. Upon receiving the request signal, the repeater 20 returns the detected value from the sensor 30 to the data station 10 as a response to the request signal. The repeater 20 also becomes active in the relay slot and performs relay processing between the data station 10 and the lower repeater 20 .

The sensor 30 becomes active according to the specific slot of the connected repeater 20 and transmits the detected value to the repeater 20 . When multiple sensors 30 are connected to one repeater 20 , all of the multiple sensors 30 are active at least at the beginning of a specific slot of one repeater 20 . The multiple sensors 30 sequentially receive request signals from the repeater 20 and transmit detection values to the repeater 20 . The plurality of sensors 30 enter a sleep state in the order in which the transmission of the detection values to the repeater 20 is completed.

Also, during execution of the collection process, each of the data station 10, repeater 20 and sensor 30 measures the received signal strength based on the received signal.

For example, when the sensor 30 receives a request signal from the connected repeater 20, the sensor 30 measures the strength of the received signal and returns the measurement result to the repeater 20 together with the detected value. Further, each repeater 20 communicates with a higher-order communication terminal (data station 10 or repeater 20) and a lower-order communication terminal (sensor 30) to send back a detected value in its own specific slot during collection processing. is measured, and the measurement result is returned to the data station 10 together with the detected value of the sensor 30 and the received signal strength.

Incidentally, the received signal strength may be associated with the identification information of the measuring terminal and the identification information of the transmitting terminal of the received signal.

Also, the data station 10 measures the received signal strength from the low-order repeater 20 during reply processing. The data station 10 stores the received signal strength measured by itself and the received signal strength measured by another communication terminal together with the detection value in the storage unit 13 together with the acquisition time (date and time) (strength data in FIG. 11). see list). The data station 10 updates the data in the storage section 13 each time it acquires a new measurement result.

In addition, in the collection process, the process performed by the repeater 20 in a specific slot includes transmission of a synchronization signal. The repeater 20 broadcasts a synchronization signal in a specific slot and synchronizes with other repeaters 20 or sensors 30 that have received the synchronization signal. The data station 10 also broadcasts a synchronization signal in the assigned time slot and synchronizes with other repeaters 20 or sensors 30 that have received the synchronization signal.

Furthermore, the data station 10 calculates the communication success rate for each sensor 30 during execution of the collection process. In the collection process, {(the number of times a reply is received)/(the number of times a reply is requested)} is calculated as the communication success rate for one sensor 30 . The “number of times a reply has been requested” is the number of times the data station 10 has sent a request signal to a certain sensor 30 . The “number of times a response was received” is the number of times the data station 10 received a detection value from the certain sensor 30 . A communication success rate is calculated for each of all the sensors 30 in one cycle of the collection process. As described above, it is calculated with respect to the number of past five reply requests from the current time. Each communication success rate is stored in the storage unit 13 in association with the identification information of the sensor 30 (see, for example, the success rate data list in FIG. 12). The data in the storage unit 13 is updated each time the communication success rate is calculated.

Thus, in the basic processing of the collection process, the data station 10 collects the detection values of all the sensors 30 corresponding to each specific slot in each specific slot according to the communication schedule. to collect. The collection process varies depending on the number of sensors 30, but is executed once every 30 minutes, for example.

-Scan processing-
In the wireless communication system 100, mutual connection destinations (communication paths) through which signals are transmitted and received between a plurality of communication terminals are updated in connection destination update processing, which will be described later. At that time, information such as received signal strength and communication success rate in each child device is used. Therefore, in the wireless communication system 100, scanning processing for scanning received signal strength and the like is executed. In the collection process described above, the received signal strength and the like are obtained for communication terminals that are connected, but in the scan process, the received signal strength and the like are obtained for communication terminals that are not connected.

The scanning process is performed, for example, once every 12 hours (twice a day). FIG. 9 shows a flowchart of the scanning process. The data station 10 executes the scanning process when the period-based time arrives. First, the data station 10 transmits scan signals to all repeaters 20 and sensors 30 (step S10). The data station 10 transmits scan signals in parallel with the acquisition process. Specifically, the data station 10 transmits the scan signal together with the detection value request signal to the corresponding repeater 20 in each time slot. That is, the scanning process is performed together with the collecting process.

The repeater 20 and the sensor 30 that have received the scan signal perform a scan operation. Specifically, in the collection process, the repeater 20 becomes active not only in the specific slot but also in other time slots, and waits for signals from other communication terminals.

The repeater 20 that performs the scanning operation waits for a synchronization signal from other communication terminals (the data station 10 and the repeater 20) in a time slot other than its own specific slot in the collection process. The repeater 20 measures the strength of the received signal when the synchronization signal can be received.

In the collection process, the timing at which each repeater 20 transmits a synchronization signal is determined within each specific slot. In other words, the repeater 20 transmits a synchronization signal at a predetermined timing in a specific slot (for example, at the beginning or end of the specific slot). Also, in each specific slot, a period during which the corresponding repeater 20 does not transmit any signal is also determined. Therefore, the repeater 20 that performs the scanning operation is in an active state only for a part of the period including the timing when the synchronization signal is transmitted and a part of the period during which no signal is transmitted in time slots other than its own specific slot. The communication signal strength of the synchronizing signal is measured by the above-mentioned period, and the sleep mode is set except for the period described above. Thereby, power consumption in the scan operation can be reduced.

By performing this process (scanning operation) for one cycle of the communication schedule, the repeater 20 acquires the received signal strength of the synchronization signal in all time slots other than the specific slot. The repeater 20 stores, as scan data, data in which the identification information of the transmitting terminal that transmitted the synchronization signal is associated with the received signal strength of the synchronization signal in the storage unit 23 .

The sensor 30 also performs a scanning operation similar to that of the repeater 20 . The sensor 30 is in an active state only during a part of the period including the timing when the synchronization signal is transmitted and a part of the period during which no signal is transmitted in the time slots other than the specific slot of the connected repeater 20 . The sensor 30 measures the received signal strength when the synchronization signal can be received. Except for said period in the time slot, the sensor 30 is in a sleep state. The sensor 30 performs this process (scanning operation) for one cycle of the communication schedule.

The sensor 30 also measures the received signal strength of the synchronization signal in a specific slot of the connected repeater 20 . That is, the sensor 30 acquires the received signal strength of the synchronization signal in all time slots. The sensor 30 stores, as scan data, data in which the identification information of the transmitting terminal that transmitted the synchronization signal and the received signal strength of the synchronization signal are associated with each other in the storage unit 53 .

Each scan data stored in the storage unit is updated each time new data is acquired.

Subsequently, the data station 10 transmits a reply signal requesting the reply of the scan data to the repeater 20 and the sensor 30 (step S11). After one cycle of the communication schedule has elapsed since the scan signal was transmitted in the process of step S10, the data station 10 sequentially transmits reply signals to all the repeaters 20 and sensors 30 according to the time slots. That is, the data station 10 transmits the return signal when executing the acquisition process following the one-cycle acquisition process in which the scan signal was transmitted.

If the data station 10 has transmitted the scan signal only to the specific repeater 20 or the sensor 30 in the process of step S20, the data station 10 transmits the reply signal only to the repeater 20 or the sensor 30 that sent the scan signal. do it.

The repeater 20 and the sensor 30 that have received the return signal return, to the data station 10, the top five scan data with the highest received signal strength among the scan data, except for the communication terminals with which the connection relationship is established, for example. . That is, the scan data of another communication terminal that is not set in the connection relationship but is communicable is returned. Note that the repeater 20 and the sensor 30 may return all scan data to the data station 10 .

The data station 10 stores the scan data returned from the repeater 20 and the sensor 30 in the storage unit 13 in association with the acquisition time (for example, see the scan data list in FIG. 13) (step S12). Further, in the process of step S12, the data station 10 calculates the communication success rate with each of the relay machine 20 and the sensor 30 that transmitted the reply signal based on the reply result. Here, the “number of times a reply is requested” is the number of times the data station 10 has sent a reply signal requesting a return of scan data to a certain repeater 20 or sensor 30 . “Number of times of reply” is the number of times the data station 10 receives scan data from the certain repeater 20 or sensor 30 . The data station 10 then updates the corresponding communication success rate (success rate data list) in the storage unit 13 . Therefore, in the collection process described above, only the communication success rate for each sensor 30 is updated, but in the scan process, the communication success rate for each slave device is updated.

- Connection destination update process -
As described above, in the radio communication system 100, connection relationships between communication terminals are determined, and signals are propagated based on these connection relationships. However, the communication environment may change, and communication between communication terminals, which was previously good, may become unsatisfactory. Therefore, the data station 10 uses machine learning (for example, reinforcement learning) to update mutual connection destinations (communication paths) for transmitting and receiving signals between a plurality of communication terminals so as to improve the communication success rate.

In this embodiment, the hierarchy of the repeaters 20 in the tree-type network topology is not changed, nor is the slot assignment of each repeater 20 in the communication schedule changed.

First, the learning unit DL of the data station 10 will be described in detail. FIG. 10 is a diagram showing an outline of the learning unit DL. The learning unit DL outputs output information regarding the connection destination when input information regarding the communication state including received signal strength, communication success rate, and the like is input. In this embodiment, the tree table and sensor sable are output as output information. The learning part DL is generated by reinforcement learning using a neural network.

As shown in FIG. 10, the learning unit DL is composed of an input layer DL1, an intermediate layer DL2, an output layer DL3, and the like. Input information relating to the current communication state of the wireless communication system 100 is input to the input layer DL1. Specifically, received signal strength data, communication success rate data, received signal strength data of other communicable nodes, multipath data, and the like in the currently connected terminal are input as input information regarding the current communication state.

The received signal strength data in the connected terminal is data of the received signal strength during communication between communication terminals with which the connection relationship is established. For example, the intensity data list in FIG. 11 is used as intensity data. The strength data list includes the received signal strength values measured by each communication terminal at the time of request for the detection value in the collection process described above. Therefore, the strength data list does not include received signal strengths from other communication terminals with which one communication terminal can communicate but for which connection relationships have not been established.

The strength data list is composed of a measuring terminal ID, a transmitting terminal ID, an acquisition time, a received signal strength, and the like. The measurement terminal ID indicates identification information of the communication terminal that measured the received signal strength. The originating terminal ID indicates identification information of the communication terminal that transmitted the signal to the corresponding measuring terminal. When the repeater 20 corresponds to the measurement terminal, there are a plurality of calling terminal IDs (calling terminals). This is because the repeater 20 communicates with the upper repeater 20 or the data station 10 and the lower repeater 20 or the sensor 30 in the collection process. The acquisition time is the time when the data station 10 receives (acquires) the received signal strength data. The received signal strength indicates the received signal strength (average value) (dBm) of the corresponding calling terminal (calling terminal ID).

For example, in FIG. 11, the sensor 30a with the measuring terminal ID: 30a stores the received signal strength of the signal from the sensor 20a with the transmitting terminal ID: 20a.

The communication success rate data is data in which the communication success rate between the data station 10 (master device) and each of the relay device 20 and the sensor 30 is set. For example, the success rate data list in FIG. 12 is used as communication success rate data. The success rate data list is composed of target terminal IDs, communication success rates, and the like. The target terminal ID indicates the identification information of the other party's communication terminal to which the data station 10 requested a reply. The communication success rate indicates the communication success rate between the data station 10 and the target terminal (target terminal ID).

The received signal strength data of other nodes with which communication is possible is the aforementioned scan data. In other words, the top five scan data with the highest received signal strength among the scan data except for the communication terminals for which the connection relationship is set. For example, the scan data list shown in FIG. 13 is used as received signal strength data of other nodes with which communication is possible. The scan data list is also referred to as information for identifying other communication terminals with which each communication terminal can communicate, in addition to the received signal strength.

The scan data list has the same format as the strength data list described above, and is composed of the measurement terminal ID, the transmission terminal ID, the acquisition time, the communication signal strength, and the like. The measurement terminal ID indicates identification information of the communication terminal that measured the received signal strength. The originating terminal ID indicates identification information of a communication terminal that has not established a connection relationship with the corresponding measuring terminal but is capable of communicating with this measuring terminal and has transmitted a signal to this measuring terminal. Therefore, depending on the measuring terminal, there may be multiple calling terminal IDs or no calling terminal ID. The acquisition time is the time when the data station 10 receives (acquires) the received signal strength data. The received signal strength indicates the received signal strength (average value) (dbm) of the corresponding calling terminal (calling terminal ID).

Multipath data is data relating to multipath between communication terminals at two points. For example, the multipath data list shown in FIG. 14 is used as the multipath data. In wireless communication, multipath means a phenomenon such as reflection (reflected wave) caused by having two or more propagation paths when a signal propagates through space. Therefore, when the reflected wave is strong, it may collide with the original direct wave and cause data corruption or the like. As described above, since the wireless communication system 100 is installed in a factory having a steam system or the like, there is a possibility that multipaths may occur due to reflected waves from factory equipment such as tanks and pipes. Therefore, using multipath data as input information is also useful for improving the communication success rate.

The multipath data list is composed of terminal ID-1, terminal ID-2, number of multipaths, multipath signal strength, and the like. Terminal ID-1 and terminal ID-2 indicate communication terminal identification information, and specify between any two points of the communication terminal. Terminal ID-1 indicates identification information of a communication terminal that transmits a signal between two points. Terminal ID-2 indicates the identification information of the communication terminal that receives the signal. It is sufficient to prepare at least combinations for which connection relationships may be set.

The number of multipaths indicates the number of propagation paths (paths) generated between two points of terminal ID-1 and terminal ID-2. Specifically, it indicates the number of radio wave paths (reflected waves) generated except for one normal radio wave path (direct wave). The multipath signal strength indicates the received signal strength (average value) (dBm) of each radio wave path (reflected wave) indicated by the number of multipaths.

The number of multipaths and the multipath signal strength described above may be created using radio wave simulation software. The multipath data may be stored in the storage unit 13 of the data station 10 in advance. Data such as the number of multipaths may be prepared for all combinations of repeaters 20 and sensors 30 .

Returning to FIG. 10, the intermediate layer DL2 is subjected to reinforcement learning so that the output layer DL3 outputs information on the connection destination for improving the communication success rate. Note that the current tree table and sensor table are also referred to in the intermediate layer DL2.

The middle layer DL2 is configured to perform reinforcement learning with a communication success rate between the parent device and each child device as a reward. That is, parameters (weight etc.) will be updated. Examples of reinforcement learning include deep Q learning and AC (Actor-Critic). Also, instead of reinforcement learning, unsupervised learning using algorithms such as GAN and clustering may be performed.

In this embodiment, the learning unit DL is in a state where reinforcement learning is not progressing in the initial state. good too.

When the above-described input information is input to the input layer DL1, the output layer DL3 outputs a tree table and a sensor sable as output information regarding the connection destination. The data station 10 uses the output tree table and sensor sable to change the connection relationship.

FIG. 15 shows a flowchart of connection destination update processing. The data station 10 executes the update process, for example, after the collection process is completed. For example, the update process is performed during a predetermined period between a completed collection process and the next collection process.

First, the data station 10 inputs the aforementioned input information to the learning unit DL (input layer DL1) (step S20). After that, the data station 10 identifies the output information output from the learning unit DL (output layer DL3) (step S21).

Next, the data station 10 determines whether or not to update (change) the connection relationship based on the output information (step S22). Specifically, the current tree table and sensor table are compared with the output information, and if there is a change in the connection destination, it is determined to change the connection relationship.

If it is determined not to update the connection relationship (step S22: NO), the data station 10 proceeds to the process of step S24. On the other hand, if it is determined to update the connection relationship (step S22: YES), the data station 10 performs update execution processing (step S23). In the update execution process, a process for setting a new connection destination is executed.

Specifically, the data station 10 changes (updates) the tree table and sensor table stored in the storage unit 13 to the tree table and sensor table output in step S21. The data station 10 also creates a new routing table based on the tree table, and changes (updates) the routing table stored in the storage unit 13 .

Further, the data station 10 notifies the repeater 20 and the sensor 30 of the new connection destination. Specifically, the data station 10 notifies all repeaters 20 of the updated tree table. Further, when the connection destination of the sensor 30 is updated, the data station 10 notifies the relay machine 20 to which the new sensor 30 is connected of the sensor connection information, that is, the information specifying the connected sensor 30. At the same time, it notifies the sensor 30 whose connection destination has been changed of the relay connection information, that is, the information specifying the connected relay 20 and the slot number of the relay 20 . FIG. 16 shows the tree table after updating. In FIG. 16, updated information for the tree table of FIG. 5 is underlined. The connection destination of the repeater 20c is updated to the repeater 20b.

Upon receiving the updated tree table, the relay device 20 stores the tree table in the storage unit 23 and updates the routing table based on the tree table. FIG. 17 shows the updated routing table of the repeater 20a. In FIG. 17, updated information for the routing table of FIG. 6 is underlined. When the final destinations are the repeaters 20c and 20f, the destinations one hop ahead are updated to the repeater 20b.

Also, the repeater 20 that receives the new sensor connection information updates the sensor connection information. The repeater 20 performs processing on the newly connected sensor 30 in the subsequent processing (for example, the next collection processing).

Upon receiving the new repeater connection information and new slot number, the sensor 30 updates the repeater connection information and slot number. The sensor 30 becomes active in response to a specific slot of the new repeater 20 and transmits the detection value to the repeater 20 .

It should be noted that all the repeaters 20 and sensors 30 should be in the active state during execution of the connection destination update process. Then, the data station 10 should notify the repeater 20 and the sensor 30 of the new connection destination during this active state period.

Next, the data station 10 determines whether or not the learning execution condition is satisfied (step S24). The learning execution condition is, for example, that the scanning process has been executed five times after the previous learning process in step S25 was executed. Since the communication success rate is a numerical value for the past five times, if the learning execution condition is satisfied, the communication success rate for all slave devices is updated to the communication success rate after execution of the previous learning process. The learning execution condition may be that the collection process has been executed five times after the previous learning process was executed. Further, the execution of the collection process once may be set as the learning execution condition.

When determining that the learning execution condition is not satisfied (step S24: NO), the data station 10 terminates the change process. On the other hand, if it is determined that the learning execution condition is satisfied (step S24: YES), the data station 10 executes the learning process (step S25) and ends the change process. In the learning process, the latest communication success rate (success rate data list) is given to the learning unit DL as a reward, and reinforcement learning is performed on the middle layer DL2 so as to improve the communication success rate.

As described above, learning is performed so as to improve the communication success rate, and the learning automatically updates the information regarding the mutual connection destinations between a plurality of communication terminals, thereby reducing communication failures (failures). , it is possible to optimize communication paths between a plurality of communication terminals.

It should be noted that the input information in the above embodiment is not limited to the above embodiment. At least the received signal strength data (strength data list, scan data list) and communication success rate of each node should be included. Therefore, multipath data may not be included in the input information.

In the above-described embodiment, connection destination update processing is executed each time collection processing ends, but the present invention is not particularly limited to this. Each of learning and connection destination update may be executed at arbitrary timing. For example, it may be executed once a week.

In the above-described embodiment, the strength data list is generated by measuring the received signal strength in the collection process, but the present invention is not particularly limited to this. In the scanning process, the received signal strength may be measured in all communication terminals with respect to the synchronization signal, and the strength data list and the scan data list may be generated.

INDUSTRIAL APPLICABILITY The present invention is useful for optimizing communication paths between a plurality of communication terminals.

10 data station (communication terminal, base unit, connection destination learning device)
20 repeater (communication terminal, child device)
30 sensor (communication terminal, slave unit)
100 wireless communication system DL learning unit

Claims (9)

A wireless communication system comprising a plurality of communication terminals including a parent device and a child device, wherein mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are specified,
The slave device measures received signal strength from other communication terminals among the plurality of communication terminals,
The parent device calculates a communication success rate with each of the child devices,
a learning unit that learns to improve the communication success rate and outputs output information about the connection destination when input information about the communication state including the received signal strength and the communication success rate is input;
the parent device updates the connection destination based on the output information;
wireless communication system. The input information includes the number of paths, which is the number of signal propagation paths in wireless communication between each of the plurality of communication terminals and another communication terminal, and the communication signal strength of each of the radio wave paths,
A wireless communication system according to claim 1 . The learning unit learns by reinforcement learning with the communication success rate as a reward.
The radio communication system according to claim 1 or 2. the parent device communicates with the child device assigned to each of the plurality of time slots according to a communication schedule including a plurality of time slots;
Each of the child devices measures the received signal strength based on a signal transmitted by the parent device or the other child device in a time slot to which the parent device or the other child device is assigned among the plurality of time slots. Measure,
The radio communication system according to any one of claims 1-3. each of the parent device and the child device is configured to transmit a synchronization signal in an assigned time slot among the plurality of time slots;
Each of the child devices receives the received signal based on the synchronization signal transmitted by the parent device or the other child device in a time slot to which the parent device or the other child device is assigned among the plurality of time slots. measuring strength,
A wireless communication system according to claim 4. The communication success rate is a rate of reply to a reply request transmitted from the parent device to the child device in wireless communication,
the parent device calculates the communication success rate for each of the child devices;
The radio communication system according to any one of claims 1-5. A connection destination learning device for use in a wireless communication system provided with a plurality of communication terminals including a parent device and a child device and in which mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are specified,
Acquisition means for acquiring input information regarding a communication state including received signal strength from another communication terminal measured by the child device and a communication success rate between the parent device and the child device;
learning means for learning to improve the communication success rate;
output means for outputting output information regarding the connection destination when input information regarding the communication state is input;
A connected learning device with a A connection destination learning device for application to a wireless communication system in which a plurality of communication terminals including a base unit and a slave unit are provided and mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are defined,
Acquisition means for acquiring input information regarding a communication state including received signal strength from another communication terminal measured by the child device and a communication success rate between the parent device and the child device;
learning means for learning to improve the communication success rate;
output means for outputting output information regarding the connection destination when input information regarding the communication state is input;
A connection destination learning program that functions as a A connection destination learning method for application to a wireless communication system provided with a plurality of communication terminals including a parent device and a child device and in which mutual connection destinations for transmitting and receiving signals between the plurality of communication terminals are defined,
Acquisition processing for acquiring input information related to a communication state including received signal strength from another communication terminal measured by the child device and a communication success rate between the parent device and the child device,
a learning process for learning to improve the communication success rate;
output processing for outputting output information regarding the connection destination when input information regarding the communication state is input;
Destination learning methods, including

Images