JP7517746B2 - Learning device, communication system, learning method, and learning program - Google Patents

Description

The present invention relates to a learning device, a communication system, a learning method, and a learning program.

In recent years, communication networks have become faster, and one of the attractions of a product is how quickly it can transmit data. However, power consumption is increasing in proportion to the increase in communication network speed, and communication devices consume a certain amount of power even when not communicating. In particular, wireless communication consumes a large amount of power because it periodically transmits signals called beacons to all terminal devices in the network regardless of whether there is an access request.

Related technologies include, for example, Patent Documents 1 and 2. Patent Document 1 describes how, when a communication transmission request occurs in a mobile device such as a smartphone, the timing of executing transmission processing in response to the transmission request is determined from the perspective of power saving, based on the results of predicting future communications and the connection state of the communications. Patent Document 2 describes how power consumption is reduced in network devices such as LAN (Local Area Network) switches by lowering the communication speed, etc.

JP 2015-201698 A JP 2011-234304 A

As described above, the related technology reduces power consumption by controlling the timing of executing transmission processing in response to a transmission request, the communication speed, etc. However, the related technology has a problem in that it is difficult to appropriately reduce the power consumption of a communication device.

In view of these problems, the present disclosure aims to provide a learning device, a communication system, a learning method, and a learning program that can appropriately reduce the power consumption of a communication device.

The learning device according to the present disclosure includes an acquisition unit that acquires communication status information of a terminal device from a communication device to which the terminal device is connected, and a learning unit that machine-learns the communication status information using the energy saving level of the communication device as training data.

The communication system according to the present disclosure includes a communication device to which a terminal device is connected, and a learning device, and the learning device includes an acquisition unit that acquires communication status information of the terminal device from the communication device, and a learning unit that machine-learns the communication status information using the energy saving level of the communication device as teacher data.

The learning method disclosed herein involves acquiring communication status information of a terminal device from a communication device to which the terminal device is connected, and machine learning the communication status information using the energy saving level of the communication device as training data.

The learning program disclosed herein is a learning program for causing a computer to execute a process of acquiring communication status information of a terminal device from a communication device to which the terminal device is connected, and machine learning the communication status information using the energy saving level of the communication device as training data.

The present disclosure provides a learning device, a communication system, a learning method, and a learning program that can appropriately reduce the power consumption of a communication device.

1 is a configuration diagram showing an overview of a communication system according to an embodiment; 1 is a configuration diagram showing an overview of a learning device according to an embodiment; 1 is a configuration diagram showing a configuration example of a communication system according to a first embodiment; FIG. 2 is a configuration diagram showing a configuration example of a connection terminal according to the first embodiment; 1 is a configuration diagram showing a configuration example of a communication device according to a first embodiment; 1 is a configuration diagram showing a configuration example of a learning device according to a first embodiment; 4 is a flowchart showing an operation example of the communication system according to the first embodiment; 1 is a diagram for explaining an example of operation of a communication system according to a first embodiment; FIG. 2 is a diagram showing an example of data used in the communication system according to the first embodiment; FIG. 2 is a sequence diagram showing an example of operation of the communication system according to the first embodiment. FIG. 4 is a diagram showing a display example of a connection terminal according to the first embodiment; FIG. 4 is a diagram showing an example of data used in the learning device according to the first embodiment; 6 is a diagram showing the correspondence relationship between energy saving levels, request contents, and communication volumes according to the first embodiment; FIG. FIG. 2 is a diagram showing the relationship between assumed usage status and communication volume in the first embodiment. FIG. 4 is a diagram showing an example of data used in the learning device according to the first embodiment; FIG. 2 is a diagram for explaining a learning method according to the first embodiment; FIG. 2 is a sequence diagram showing an example of operation of the communication system according to the first embodiment. FIG. 4 is a diagram showing an example of data used in the learning device according to the first embodiment;

The following describes the embodiments with reference to the drawings. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are given the same reference numerals, and duplicate explanations will be omitted as necessary.

(Overview of the embodiment)
As described above, in recent years, power consumption has increased due to faster communication speeds, and therefore there is a demand for a method of reducing power consumption while maintaining the communication speed when in use. For example, it is desirable to maintain high communication speeds when a user wants to use the system, while reducing power consumption when the system is not in use.

One option would be for users to determine their own activity times and create a schedule, but creating a schedule every time their lifestyle changes would be a huge burden on the user. In addition, few users are aware of the times of day when they use the most data, so adjusting data speeds based on a schedule is not realistic.

The embodiment is concerned with the power consumption of communication devices, and is characterized by learning the usage patterns of the user to predict times when communication will not be performed in accordance with the user's lifestyle, and reducing power consumption during those times, thereby enabling the user to conserve energy without feeling stressed.

In an embodiment, the system learns the user's usage status and uses the predicted results to adjust communication speeds and restrict functions, reducing the burden on users of individually setting usage times and enabling them to reduce power consumption without being dissatisfied with communication speeds.

An overview of the embodiment will be described with reference to Figures 1 and 2. Figure 1 shows an overview of a communication system according to the embodiment, and Figure 2 shows an overview of a learning device according to the embodiment. As shown in Figure 1, a communication system 1 according to the embodiment includes a learning device 10, a communication device 20, and a terminal device 30. The learning device 10 and the communication device 20 are communicatively connected, and the communication device 20 and the terminal device 30 are communicatively connected.

As shown in FIG. 2, the learning device 10 according to the embodiment includes an acquisition unit 11 and a learning unit 12. The acquisition unit 11 acquires communication status information indicating the communication status of the terminal device 30 from the communication device 20 to which the terminal device 30 is connected. The learning unit 12 performs machine learning on the communication status information acquired by the acquisition unit 11 using the energy saving level that reduces the power consumption of the communication device 20 as teacher data.

In this way, in the embodiment, by performing machine learning on the communication status information of the terminal device using the energy saving level of the communication device as training data, it is possible to obtain an energy saving level according to the communication status. Therefore, by using the learning results of the learning device, it is possible to appropriately reduce the power consumption of the communication device.

(Embodiment 1)
The configuration and operation of the first embodiment will be described below with reference to the drawings.

<Configuration>
The configuration of this embodiment will be described with reference to Figures 3 to 6. Figure 3 shows an example of the configuration of a communication system according to this embodiment, Figure 4 shows an example of the configuration of a connection terminal according to this embodiment, Figure 5 shows an example of the configuration of a communication device according to this embodiment, and Figure 6 shows an example of the configuration of a learning device according to this embodiment.

As shown in FIG. 3, the communication system 2 according to this embodiment includes a learning device 100, a communication device 200, and a connection terminal 300. The communication system 2 may include a plurality of connection terminals 300. Note that some or all of the functions of the learning device 100 may be included in the communication device 200. For example, the learning device 100 and the communication device 200 may be combined into one device. Also, the configuration of each device is merely an example, and other configurations may be used as long as the operation (method) described below is possible.

The connection terminal 300 is a user terminal operated by a user, and is a terminal device that communicates with the communication device 200 in response to an application program, user operation, etc. For example, the connection terminal 300 is a wireless terminal that performs wireless communication, but it may also be a wired terminal that performs wired communication. The connection terminal 300 may be a mobile device such as a smartphone, mobile phone, or tablet terminal, or a computer device such as a personal computer.

As shown in FIG. 4, the connection terminal 300 includes a communication unit 310, a request transmission unit 320, a display unit 330, and an operation unit 340. The communication unit 310 communicates with the communication device 200 via a wired or wireless connection. For example, the communication unit 310 communicates with the communication device 200 via a wireless connection, but may also be connected via a wire if necessary.

The request sending unit 320 sends a control request to the communication device 200 in response to a user operation. The control request is a command for controlling the communication speed of the communication device 200 and turning functions on and off. As described below, the control request corresponds to an energy saving level, so the energy saving level may be requested by the control request.

The display unit 330 is a display device that displays the communication status, a GUI (Graphical User Interface), etc. on a display screen. The display unit 330 is, for example, a liquid crystal display or an organic EL (Electro Luminescence) display.

The operation unit 340 is an input interface (input unit) that inputs information in response to user operations. The operation unit 340 is, for example, a GUI displayed on the display unit 330, and information in response to user operations is input from an input device such as a keyboard, mouse, or touch panel.

The communication device 200 is a network device (communication device) that communicates with the connection terminal 300 for the user, and also communicates with the learning device 100 for learning. The communication device 200 is capable of communicating with a plurality of connection terminals 300. For example, the communication device 200 is a wireless relay device that performs wireless communication, but it may also be a wired relay device that performs wired communication. The communication device 200 may be a wireless LAN access point or router, a mobile phone base station device, or a wired LAN router or switch.

As shown in FIG. 5, the communication device 200 includes a communication unit 211, a communication unit 212, a communication control unit 220, a wireless communication control unit 230, a communication status notification unit 240, a prediction result acquisition unit 250, an operation control unit 260, a request receiving unit 270, and a request notification unit 280.

The communication unit 211 communicates with the connection terminal 300 via a wired or wireless connection. For example, the communication unit 211 communicates with the connection terminal 300 via a wireless connection, but a wired connection may be used if necessary. The communication unit 212 communicates with the learning device 100 via a wired or wireless connection. The communication unit 212 may be connected by any method as long as communication for learning is possible. Note that the communication units 211 and 212 may be treated as a single communication unit to communicate with both the connection terminal 300 and the learning device 100.

The communication control unit 220 is a control unit that controls communication with the connected terminal 300 in the communication unit 211, and is also a measurement unit that measures the communication status of the connected terminal 300 (user) in the communication unit 211. For example, the communication control unit 220 controls communication at a layer higher than the physical layer (wireless layer). The communication control unit 220 includes a communication volume measurement unit 221 and a communication time measurement unit 222 as examples of measurement units. The communication volume measurement unit 221 measures the communication volume for each communication (connection) of the connected terminal 300 in the communication unit 211. The communication time measurement unit 222 measures the communication time (connection time) for each communication of the connected terminal 300 in the communication unit 211.

The wireless communication control unit 230 is a control unit that controls wireless communication with the connected terminal 300 in the communication unit 211, and is also a measurement unit that measures the wireless communication status of the connected terminal 300 (user) in the communication unit 211. For example, the communication control unit 220 controls communication in the physical layer (wireless layer). The wireless communication control unit 230 includes a radio wave strength measurement unit 231 and a connected terminal measurement unit 232 as examples of measurement units. The radio wave strength measurement unit 231 measures the radio wave strength for each wireless communication (wireless connection) of the connected terminal 300 in the communication unit 211. The connected terminal measurement unit 232 measures the number of connected terminals connected to the communication unit 211.

The communication status notification unit 240 notifies the learning device 100 of the communication status (communication status information) measured by the communication control unit 220 and the wireless communication control unit 230. The communication status notification unit 240 notifies the learning device 100 of the measured communication volume, communication time, radio wave strength, number of connected terminals, as well as the date, day of the week, etc.

The prediction result acquisition unit 250 acquires the prediction result predicted by the learning device 100 from the current communication situation. For example, the prediction result acquisition unit 250 acquires the energy saving level predicted by the learning model as the prediction result. The request receiving unit 270 receives a control request in response to a user operation from the connection terminal 300. The request notifying unit 280 notifies the learning device 100 of the request content of the control request received from the connection terminal 300.

The operation control unit 260 controls the operation of the communication unit 211 according to the energy saving level predicted by the learning device 100 or the control request received from the connection terminal 300. It is to be noted that the communication unit 212 may be controlled instead of the communication unit 211. By controlling the two communication units, power consumption can be further reduced. The operation control unit 260 includes a communication speed control unit 261 and a function control unit 262 as examples of the control unit. The communication speed control unit 261 controls the communication speed of the communication unit 211 according to the energy saving level and the control request. The function control unit 262 controls the ON/OFF of the function of the communication unit 211 according to the energy saving level and the control request. For example, the entire communication function of the communication unit 211 may be turned ON/OFF, or a part of the communication function of the communication unit 211 may be turned ON/OFF. When controlling a part of the function, the wireless function (physical layer) may be turned ON/OFF, or a part of the communication port may be turned ON/OFF. It is to be noted that other control for reducing power consumption may be performed in addition to the communication speed and the ON/OFF of the function. For example, when transmitting a beacon, the beacon transmission interval may be controlled, or the strength of the radio waves to be output may be controlled. If multiple communication methods are available, a communication method with low power consumption may be selected.

The learning device 100 is a learning model generation device that learns the communication status in the communication device 200, and is also a prediction device that predicts an energy saving level (next communication status) according to the current communication status from the learning results. The learning device 100 is, for example, a computer device such as a personal computer or a server computer.

As shown in FIG. 6, the learning device 100 includes a communication unit 110, a communication status acquisition unit 120, a request acquisition unit 130, an information control unit 140, an information storage unit 150, a state observation unit 160, a judgment data acquisition unit 170, a learning unit 180, and a prediction unit 190. The communication unit 110 communicates with the communication device 200 via a wired or wireless connection. As with the communication device 200, the communication unit 110 may be connected in any manner as long as communication for learning is possible.

The communication status acquisition unit 120 acquires the communication status (communication status information) of the connected terminal 300 from the communication device 200. For example, during a learning operation, the communication status acquisition unit 120 acquires multiple communication statuses to use for learning, and during a prediction operation, acquires the current communication status to use for prediction. The request acquisition unit 130 acquires the request contents of a control request requested by the connected terminal 300 from the communication device 200. For example, during a learning operation, the request acquisition unit 130 acquires the request contents to use for learning.

The information storage unit 150 stores information necessary for the learning operation, prediction operation, etc. of the learning device 100. For example, the information storage unit 150 is a non-volatile memory such as a flash memory or a hard disk device. The information control unit 140 controls the storage and acquisition of information in the information storage unit 150. The information control unit 140 includes an information management unit 141 and an information registration unit 142.

The information management unit 141 acquires the requested information from the information storage unit 150. For example, the information management unit 141 acquires data used by the state observation unit 160 or the judgment data acquisition unit 170 from the information storage unit 150, and outputs the acquired data to the state observation unit 160 or the judgment data acquisition unit 170. The information registration unit 142 registers (stores) the acquired information in the information storage unit 150. The information registration unit 142 stores the communication status and request content (behavioral data) acquired from the communication device 200 in the information storage unit 150. For example, the communication status information is stored as status data in a data format for learning, or judgment data in a data format for prediction.

During the learning operation, the state observation unit 160 acquires state data used to generate the learning model 181 from the information storage unit 150 via the information management unit 141. The learning unit 180 uses a neural network to learn the state data including the acquired multiple communication situations. For example, the learning unit 180 inputs the state data to the input layer of the neural network, and classifies (generates) teacher data from the state data (or request content) to generate the learning model 181. The learning model 181 may be stored in the information storage unit 150. The learning unit 180 can also be said to be a generation unit that generates teacher data for machine learning. For example, the learning unit 180 performs machine learning using the energy saving level as teacher data. The learning unit 180 generates teacher data based on the communication volume included in the communication situation information and the request content of the control request. The learning model 181 is a prediction model that predicts the energy saving level corresponding to the communication situation at the next time from the current communication situation. The energy saving level is a level at which the power consumption of the communication device 200 is reduced and corresponds to the connection state. The higher the energy saving level, the more the communication function is restricted and the communication speed is slowed down, thereby making it possible to reduce the amount of power consumption. The energy saving level is also an index for the communication device 200 to control the communication speed of the communication device 200 or the ON/OFF of the communication function of the communication device 200.

It can be said that the learning model 181 predicts the communication status (connection status) at the next time from the current communication status. The next time to be predicted may be any time after the present. The connection status indicates how long the user is communicating with the wireless terminal (connection terminal 300) at that time. For example, the connection status includes "communication that requires a real-time response (state requiring real-time)" such as video calling, "state requiring a fast communication speed" where the user communicates frequently such as video playback and file downloading, "state where data is sent and received infrequently but a slow communication speed does not cause any problems," "state where the wireless terminal is connected but "the user is not operating it," and "state where no terminal is connected." Energy saving levels corresponding to each of these states are predicted.

During prediction operation, the judgment data acquisition unit 170 acquires judgment data for predicting the energy saving level from the information storage unit 150 via the information management unit 141. The prediction unit 190 predicts the energy saving level (control operation) from the judgment data using the learning model 181 generated by the learning unit 180, and notifies the communication device 200 of the prediction result. This makes it possible to predict the user's next action and automatically control the operation of the communication device 200.

<Overview of operation>
Next, an overview of the operation of this embodiment will be described with reference to Figs. 7 and 8. Figs. 7 and 8 show the flow of the operation of the communication system according to this embodiment. Here, an operation will be described in which the learning device 100 collects and learns the communication status (connection information) of the user, and feeds back the prediction result predicted from the learning model to the communication device 200. In Figs. 7 and 8, S101 to S104 show the learning operation of learning the communication status, and S105 to S107 show the prediction operation (prediction control operation) of making prediction and control from the learning result. Note that the learning operation and the prediction operation are repeated as necessary. That is, after the learning model is generated, the learning model is further updated (learned) based on the communication status and the control request.

First, the communication device 200 establishes communication (connection) with the learning device 100 and is in a state in which it can communicate with the learning device 100. In addition, the connection terminal 300 used by the user is connected (wirelessly connected) to the communication device 200.

7 and 8, after a certain period of time has elapsed, the communication device 200 notifies the learning device 100 of the communication status (communication status information) of the connection terminal 300 (S101). The communication device 200 notifies the communication status information of the connection terminal 300, and the learning device 100 holds the notified communication status information as status data for learning. The learning device 100 accumulates multiple status data (communication status information) required for learning for a certain period of time.
FIG. 9 shows an example of communication status information to be notified and learned. As shown in FIG. 9, the communication status information includes, for example, the date, day of the week, Mac address, connection time (communication time), communication volume, radio wave strength, and number of connected terminals for each communication (connection). The date and day of the week are the date (date and time) and day of the week on which the communication was performed, for example, the date and day on which the communication (connection) was established (started). The Mac address is identification information of the connected terminal 300, and may be other identification information such as an IP address. The connection time is the time (e.g., seconds) from when the communication (connection) is established (started) to when it is disconnected (ended). The communication volume is the amount of data (e.g., bytes) transmitted and received through the established communication (connection). The radio wave strength is the received signal strength (RSSI: Received Signal Strength Indicator) of the radio wave of the connected terminal 300, that is, the strength of the radio wave received from the connected terminal 300 (e.g., dBm). The number of connected terminals is the number of terminals (terminals in a connected state) connected to the communication unit 211 while the communication of the connected terminal 300 is being performed. The communication status information is information related to at least prediction (learning) of the connection state, and may include any of these, or may include other information. For example, from the day of the week and the communication volume, the characteristics of the communication volume on a specific day of the week can be extracted, and the required communication speed on the specific day of the week can be predicted. From the connection time and the communication volume, the usage time of the connected terminal can be predicted, and the required communication speed at the specific time can be predicted. From the signal strength and the communication volume, the characteristics of the communication volume at a specific signal strength (the user's current location according to the distance from the communication device) can be extracted, and the "state where the user is not operating" at a specific signal strength can be predicted. From the number of connected terminals and the day of the week, the "state where no terminal is connected" on a specific day of the week can be predicted.

When the communication device 200 receives a control request from the connection terminal 300, it notifies the learning device 100 of the content of the received control request (S102). When the communication device 200 receives a request to change the communication speed, a function ON request, or a function OFF request from the connection terminal 300, it controls the communication speed or the operation of the function according to the received request and notifies the learning device 100 of the content of the request. The learning device 100 holds the notified request content as behavioral data for learning. When the communication device 200 receives a control request from the connection terminal 300, it also notifies the learning device 100 of the communication status information of the connection terminal 300 in the same manner as S101.

Next, the learning device 100 generates teacher data to perform supervised learning (S103). In this example, the teacher data (teacher label) is an energy saving level corresponding to the communication speed or the ON/OFF stage of the function. Note that the teacher data may include the status data and the energy saving level. Generating teacher data for status data can be said to classify the status data into energy saving levels, and also to assign an energy saving level (teacher label) corresponding to the status data.

For example, when a control request is received from the connection terminal 300, the teacher data is generated based on the behavioral data that constitutes the request. When a control request is not received from the connection terminal 300, the teacher data is generated based on the communication charges included in the status data. In other words, when the communication volume is large, the system learns that a high communication speed is optimal, so the system classifies the communication volume according to its size.

Next, the learning device 100 learns the communication status (status data) and generates a learning model 181 (S104). The learning device 100 generates a learning model (prediction model) 181 using the status data and teacher data (energy saving level). The learning device 100 generates a learning model 181 that predicts the communication status at the next time by machine learning a plurality of status data in a time series. At this time, in order to learn so that the user's requests are given top priority, the status data is weighted so that the behavioral data (request content) serves as the teacher.

Next, the learning device 100 predicts the energy saving level from the current communication status (S105). After the learning model 181 is generated, similar to S101, the communication device 200 notifies the connection terminal 300 of the communication status (communication status information), and the learning device 100 predicts the energy saving level (the user's next connection status) using the learning model, using the notified current communication status as judgment data.

Next, the learning device 100 notifies the communication device 200 of the energy saving level, which is the prediction result (S106), and the communication device 200 controls the operation of the communication unit 211 according to the notified energy saving level (S107). The communication device 200 controls the communication speed and function ON/OFF corresponding to the energy saving level. If the energy saving level is high, the communication speed is controlled to be low and the function is controlled to be OFF, and if the energy saving level is low, the communication speed is controlled to be high and the function is controlled to be ON. In this way, the communication device 200 can reduce power consumption corresponding to the user's usage status using the result predicted by the learning device 100.

<Specific operations>
Next, a specific operation of this embodiment will be described. A process in which the learning device 100 generates a learning model from data acquired from the communication device 200 will be described with reference to Fig. 10. Note that Fig. 10 corresponds to the learning operation of S101 to S104 in Fig. 7.

As shown in FIG. 10, the communication unit 212 of the communication device 200 and the communication unit 110 of the learning device 100 establish communication (connection) between the communication device 200 and the learning device 100 (S201). In addition, the communication unit 211 of the communication device 200 and the communication unit 310 of the connection terminal 300 establish communication (wireless connection) between the communication device 200 and the connection terminal 300 (S202). As a result, data communication is possible (connected) between the communication device 200 and the learning device 100, and between the communication device 200 and the connection terminal 300.

Next, the request transmission unit 320 of the connection terminal 300 determines whether or not to transmit a control request (function control request) in response to the user's operation (S203), and if it is determined that a control request should be transmitted, transmits the control request to the communication device 200 with which communication has been established (S204). For example, if a user wishes to change the communication status while using the connection terminal 300, the user operates the connection terminal 300, and the connection terminal 300 transmits a control request in response to the operation.

Figure 11 shows an example of a GUI for control requests displayed on the display unit 330 of the connection terminal 300. For example, the connection terminal 300 is equipped with an application program for sending a control request to the communication device 200, and the GUI for control requests is displayed on the display unit 330 by executing the application program. In the example of Figure 11, buttons B1 to B4 indicating control requests corresponding to energy saving levels (high speed communication/low speed communication/some functions OFF/functions OFF) are displayed on the display unit 330. When the user selects any of the buttons B1 to B4, a control request corresponding to the selected button is transmitted. This function makes it possible to immediately change the control of the communication device 200 and reflect it in the learning if the user is dissatisfied with the prediction results after the generation of the learning model.

Next, the request receiving unit 270 of the communication device 200 determines whether or not a control request has been received from the connection terminal 300 (S205), and if it is determined that a control request has been received, the operation control unit 260 controls the operation of the communication unit 211 in accordance with the received control request (S206). For example, the communication speed control unit 261 controls the communication speed of the communication unit 211 to high/low speed in response to a request for high/low speed communication, and the function control unit 262 turns off some/all functions of the communication unit 211 in response to a request for partial/function OFF.

Next, the request notification unit 280 of the communication device 200 notifies the learning device 100 of the request content (high-speed communication/low-speed communication/partial function OFF/function OFF) of the received control request (S207). The request acquisition unit 130 of the learning device 100 acquires the request content from the communication device 200, and the information storage unit 150 stores the acquired request content (behavioral data).

Next, after notifying the request contents or if no control request is received, the communication volume measurement unit 221 of the communication device 200 measures the volume of communication (connection) of the established connection terminal 300 (S208), the communication time measurement unit 222 measures the communication time of the connection terminal 300's communication (S209), and the radio wave strength measurement unit 231 measures the radio wave strength of the connection terminal 300's communication (S210). In addition, the connection terminal measurement unit 232 measures the number of connection terminals connected to the communication unit 211 during the connection terminal 300's communication.

Next, the communication status notification unit 240 of the communication device 200 adds the measured communication volume, communication time, radio wave strength, and number of connected terminals to the date and day of the communication, and the Mac address of the connected terminal 300 to generate communication status information, and notifies the learning device 100 (S211).

Next, the communication status acquisition unit 120 of the learning device 100 acquires communication status information from the communication device 200, and the information storage unit 150 (status database) stores the acquired communication status information in the form of status data that will become input data when learning (S212).

Next, the state observation unit 160 of the learning device 100 acquires the stored state data, and the learning unit 180 generates a learning model 181 from the acquired state data (S213).

Figure 12 is an example of data used to generate a learning model. As shown in Figure 12, the status data includes the days of the week when the wireless device is actually used, the amount of communication for each date, and the time the wireless device is used, i.e., the communication time (connection time), in order to predict the usage of the wireless device taking into account the user's lifestyle. The status data also includes radio wave strength in order to predict the usage of the wireless device from the user's current location by learning the amount of communication when the user is in a specific location (bathroom, living room, etc.).

The status data includes the date, day of the week, Mac address, connection time, communication volume, signal strength, and number of connected terminals (i.e., communication status information), as well as the presence or absence of a request. For example, the presence or absence of a request is set depending on whether a control request has been received when the status data is stored (when communication status information is received).

The learning unit 180 receives as input data the date, day of the week, Mac address, connection time, communication volume, radio wave strength, and number of connected terminals (i.e., communication status information) contained in the status data, and refers to the request content of the control request from the behavioral data depending on whether or not there is a request. If there is a control request, the learning unit 180 uses the energy saving level corresponding to the request content as training data, and if there is no control request, the energy saving level according to the size of the communication volume as training data. The energy saving level is assigned using the communication volume as an index so that the higher the value, the greater the power consumption.

Figure 13 shows an example of the correspondence between energy saving levels, request contents, and communication volume (energy saving level data). As shown in Figure 13, the request contents of high speed communication, low speed communication, partial functions OFF, and function OFF correspond to energy saving levels 1 to 4, respectively. Furthermore, the communication volume divided into four levels corresponds to energy saving levels 1 to 4 in descending order. The learning device 100 and communication device 200 store such energy saving level data in advance. The learning unit 180 generates teacher data according to the request contents or communication volume based on the correspondence in Figure 13.

Figure 14 shows an example of the relationship between the assumed usage status and the communication amount, specifically, the relationship between the energy saving level, the communication amount, the connection status, and the assumed usage status. In this example, energy saving levels 1 to 5 correspond to a large communication amount, a small communication amount, and no communication. For example, energy saving level 1 is a "state where real-time communication is required" and is assumed to be a situation where "data is exchanged frequently and a decrease in speed interferes with user operation (such as image distortion in video chat)". Energy saving level 2 is a "state where a high communication speed is required" and is assumed to be a situation where "the user continues to use the wireless terminal". Energy saving level 3 is a "state where slow communication speeds do not cause any problems" and is assumed to be a situation where "the user is not continuing to use the wireless terminal, but is sending and receiving data". Energy saving level 4 is a "state where the user is not operating" and is assumed to be a "state where only data is being received". Energy saving level 5 is a "state where no terminal is connected".

An example of the learning operation of the learning unit 180 will be described with reference to Figs. 15 and 16. For example, as shown in Fig. 15, when input data (date, day of the week, Mac address, connection time, communication volume, signal strength, number of connected terminals) is input to the input layer of the neural network, an energy saving level according to the feature amount of the data is output as output data from the output layer via the intermediate layer. In the intermediate layer, features for determining each level are acquired from the common and non-common parts of each data, and learning is performed so that the output for the input data approaches the teacher data, and a learning model is generated. By learning to determine the energy saving level determined from the communication volume for each acquired state data, information that is characteristic of the energy saving level prediction, a specific day of the week, signal strength, and connection time are identified from similar items of the data.

Figure 16 shows an example of a neural network used to generate a learning model. The learning unit 180 uses, for example, a Long Short Term Memory (LSTM) to learn time-series state data. As shown in Figure 16, by inputting time-series input data (x) (date, day of the week, Mac address, connection time, communication volume, signal strength, number of connected terminals) to the LSTM, the energy saving level for each time is output as output data (y). Note that instead of the LSTM, a Recurrent Neural Network (RNN) capable of learning time-series data may also be used.

LSTM is a deep learning method, and its characteristic is that it is a model that handles time series data. Conventional neural networks can classify unknown data, but are not suitable models for predicting the next action, so LSTM, which handles time series data, has been extended. Time series data is data observed over time, and the status data in this embodiment is time series data because it is acquired over time as dates change. By handling time series data, it is possible to learn while retaining the state of the previous time period. Therefore, by reflecting the flow of communication status at each hour in the learning, it is possible to predict the communication status of the next user.

Next, with reference to FIG. 17, a process in which the learning device 100 predicts an energy saving level using the generated learning model and the communication device 200 performs function control will be described. Note that FIG. 17 corresponds to the prediction operations of S105 to S107 in FIG. 7.

As shown in FIG. 17, similar to S201 in FIG. 10, the communication unit 212 of the communication device 200 and the communication unit 110 of the learning device 100 establish communication (connection) between the communication device 200 and the learning device 100 (S301). This brings the communication device 200 and the learning device 100 into a state in which data communication is possible (connected state).

Next, similar to S208 to S211 in FIG. 10, the communication volume measurement unit 221 of the communication device 200 measures the communication volume of the connecting terminal 300 with which a connection has been established (S302), the communication time measurement unit 222 measures the communication time of the connecting terminal 300 (S303), the radio wave strength measurement unit 231 measures the radio wave strength of the connecting terminal 300 (S304), and the communication status notification unit 240 notifies the learning device 100 with which communication has been established of communication status information including the measurement results (S305).

Next, the communication status acquisition unit 120 of the learning device 100 acquires communication status information from the communication device 200, and the information storage unit 150 (judgment database) stores the acquired communication status information in the form of judgment data that serves as input data for prediction (S306).

Next, the judgment data acquisition unit 170 of the learning device 100 acquires the stored judgment data, and the prediction unit 190 inputs the acquired judgment data into the learning model 181 (S307) and predicts the energy saving level (connection state) (S308).

Figure 18 shows an example of data used to predict energy saving levels. The judgment data, like the communication status information, includes date, day of the week, Mac address, connection time, communication volume, signal strength, and number of connected terminals, and these are input as input data to the learning model. For example, when making a prediction, the number of connected terminals from the current date is obtained from the communication device 200 and used as judgment data. The prediction unit 190 (learning model) calculates the similarity with the features obtained by learning from the judgment data, and determines the energy saving level with the most similar data.

Next, the prediction unit 190 of the learning device 100 notifies the communication device 200 of the energy saving level that specifies the stage of function control, which is the prediction result (S309). The prediction result acquisition unit 250 of the communication device 200 acquires the prediction result from the learning device 100, and the operation control unit 260 controls the operation according to the received prediction result (S310). For example, based on the correspondence relationship in FIG. 13, in the case of energy saving level 1, the communication speed control unit 261 controls the communication speed of the communication unit 211 to a high speed, in the case of energy saving level 2, the communication speed control unit 261 controls the communication speed of the communication unit 211 to a low speed, in the case of energy saving level 3, the function control unit 262 controls some functions of the communication unit 211 to be OFF, and in the case of energy saving level 4, the function control unit 262 controls all functions of the communication unit 211 to be OFF.

＜Effects＞
As described above, in this embodiment, based on a learning model that is learned by tallying up the user's communication volume, connection time, number of connected terminals, and radio wave strength, the future usage status of the user is predicted from the current user's status, and the power consumption of the communication device can be reduced based on the prediction result. This provides the following effects. As a first effect, the power consumption can be automatically reduced according to the user's lifestyle, so that the user's load in operations related to power saving settings can be reduced. As a second effect, the result of predicting the user's connection status can be used to switch to an appropriate communication speed when the user wants to use it. As a third effect, the application can reflect the user's reaction, so that the connection status can be predicted taking into account the user's intention. As a fourth effect, the connection status can be predicted from the user's positional relationship by learning the radio wave strength.

(Other embodiments)
In the above embodiment, the following configurations and methods may be used.
(1) It is also possible to use the user's actions as emotions determined from the user's facial expressions or the contents of what the user has said to the app. In other words, learning and prediction may be performed including this information.
(2) The communication information used to learn the user's connection information can be changed or added.
(3) In the above example, the amount of communication traffic is used as training data, but other data can also be used.
(4) During learning, weights are assigned only to state data for which user requests serve as training data. However, it is possible to assign weights to other state data, such as data at the time of disconnection.
(5) In addition to using neural networks as a learning method, it is also possible to use reinforcement learning or the like to determine whether the user's current connection state is correct or incorrect, and then learn the results to predict the user's usage time period.
(6) Although the energy saving levels are determined by communication speed and function OFF, it is possible to change or add other factors.

Note that this disclosure is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present disclosure.

Each component in the above-described embodiments may be configured with hardware or software, or both, and may be configured with one piece of hardware or software, or may be configured with multiple pieces of hardware or software. The functions (processing) of each device may be realized by a computer having a CPU, memory, etc. For example, a program for performing the method in the embodiment may be stored in a storage device, and each function may be realized by executing the program stored in the storage device with a CPU.

These programs can be stored and supplied to a computer using various types of non-transitory computer readable media. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R/Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memories)). The programs may also be supplied to a computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable media can supply the programs to a computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.
(Appendix 1)
an acquisition unit that acquires communication status information of a terminal device from a communication device to which the terminal device is connected;
a learning unit that performs machine learning on the communication status information using an energy saving level of the communication device as training data;
A learning device comprising:
(Appendix 2)
The communication status information includes any one of a date, a day of the week, a communication time, a communication volume, a radio wave intensity, and a number of connected terminals connected to the communication device.
2. A learning device as described in claim 1.
(Appendix 3)
The learning unit generates the teacher data based on the communication volume.
3. A learning device as described in claim 2.
(Appendix 4)
The learning unit generates the teacher data based on a control request issued from the terminal device.
3. A learning device according to claim 1 or 2.
(Appendix 5)
The learning unit generates the energy saving level for the communication device to control a communication speed of the communication device or ON/OFF of a communication function of the communication device.
A learning device according to any one of claims 1 to 4.
(Appendix 6)
the learning unit learns the communication status information in a time series manner and generates a learning model that predicts the energy saving level corresponding to the communication status at the next time.
A learning device according to any one of claims 1 to 5.
(Appendix 7)
The learning unit generates the learning model using a Long Short Term Memory (LSTM).
7. A learning device as described in appendix 6.
(Appendix 8)
a prediction unit that predicts the energy saving level from the communication status information by using the learning model;
8. A learning device according to claim 6 or 7.
(Appendix 9)
A communication device connected to a terminal device and a learning device,
The learning device includes:
an acquisition unit that acquires communication status information of the terminal device from the communication device;
a learning unit that performs machine learning on the communication status information using an energy saving level of the communication device as training data;
A communication system comprising:
(Appendix 10)
the learning device includes a prediction unit that predicts the energy saving level corresponding to the communication status at the next time from the communication status information based on the machine learning result,
10. The communication system of claim 9.
(Appendix 11)
The communication device has a control unit that controls a communication operation in accordance with the predicted energy saving level.
11. The communication system of claim 10.
(Appendix 12)
acquiring communication status information of the terminal device from a communication device to which the terminal device is connected;
Using the energy saving level of the communication device as training data, machine learning is performed on the communication status information.
How to learn.
(Appendix 13)
The communication status information includes any one of a date, a day of the week, a communication time, a communication volume, a radio wave intensity, and a number of connected terminals connected to the communication device.
13. The learning method according to claim 12.
(Appendix 14)
A communication device having a function of executing the learning method described in appendix 12 or 13.
(Appendix 15)
acquiring communication status information of the terminal device from a communication device to which the terminal device is connected;
Using the energy saving level of the communication device as training data, machine learning is performed on the communication status information.
A learning program that allows a computer to carry out processing.
(Appendix 16)
The communication status information includes any one of a date, a day of the week, a communication time, a communication volume, a radio wave intensity, and a number of connected terminals connected to the communication device.
16. The study program described in appendix 15.
(Appendix 17)
A communication device having a function of executing the learning program described in appendix 15 or 16.

1, 2 Communication system 10 Learning device 11 Acquisition unit 12 Learning unit 20 Communication device 30 Terminal device 100 Learning device 110 Communication unit 120 Communication status acquisition unit 130 Request acquisition unit 140 Information control unit 141 Information management unit 142 Information registration unit 150 Information storage unit 160 State observation unit 170 Judgment data acquisition unit 180 Learning unit 181 Learning model 190 Prediction unit 200 Communication device 211, 212 Communication unit 220 Communication control unit 221 Communication amount measurement unit 222 Communication time measurement unit 230 Wireless communication control unit 231 Radio wave intensity measurement unit 232 Connected terminal measurement unit 240 Communication status notification unit 250 Prediction result acquisition unit 260 Operation control unit 261 Communication speed control unit 262 Function control unit 270 Request reception unit 280 Request notification unit 300 Connected terminal 310 Communication unit 320 Request transmission unit 330 Display unit 340 Operation unit

Claims (10)

an acquisition unit that acquires communication status information of a terminal device from a communication device to which the terminal device is connected;
a learning unit that performs machine learning on the communication status information using behavior data of the communication device as training data;
Equipped with
the learning unit generates the teacher data based on a control request issued from the terminal device, learns the communication status information in a time series using the teacher data, and generates a learning model that predicts an energy saving level corresponding to the communication status at the next time;
A prediction unit that predicts the energy saving level from the communication status information by using the learning model.
Learning device. The communication status information includes any one of a date, a day of the week, a communication time, a communication volume, a radio wave intensity, and a number of connected terminals connected to the communication device.
The learning device according to claim 1 . The learning unit generates the teacher data based on the communication volume.
The learning device according to claim 2 . The learning unit generates the energy saving level for the communication device to control a communication speed of the communication device or ON/OFF of a communication function of the communication device.
A learning device according to any one of claims 1 to 3. The learning unit generates the learning model using a Long Short Term Memory (LSTM).
A learning device according to any one of claims 1 to 4. The prediction unit notifies the communication device of the predicted energy saving level and controls a communication operation of the communication device.
A learning device according to any one of claims 1 to 5. A communication device connected to a terminal device and a learning device,
The learning device includes:
an acquisition unit that acquires communication status information of the terminal device from the communication device;
a learning unit that performs machine learning on the communication status information using behavior data of the communication device as training data;
Equipped with
the learning unit generates the teacher data based on a control request issued from the terminal device, learns the communication status information in a time series using the teacher data, and generates a learning model that predicts an energy saving level corresponding to the communication status at the next time;
The learning device further includes a prediction unit that predicts the energy saving level from the communication status information by using the learning model.
Communications system. The communication device has a control unit that controls a communication operation in accordance with the predicted energy saving level.
8. The communication system according to claim 7. acquiring communication status information of the terminal device from a communication device to which the terminal device is connected;
Using behavioral data of the communication device as training data, machine learning is performed on the communication status information;
In the machine learning, the teacher data is generated based on a control request issued from the terminal device, the communication status information is learned in a time series using the teacher data, and a learning model is generated that predicts an energy saving level corresponding to the communication status at the next time;
and predicting the energy saving level from the communication status information using the learning model.
How to learn. acquiring communication status information of the terminal device from a communication device to which the terminal device is connected;
Using behavioral data of the communication device as training data, machine learning is performed on the communication status information;
In the machine learning, the teacher data is generated based on a control request issued from the terminal device, the communication status information is learned in a time series using the teacher data, and a learning model is generated that predicts an energy saving level corresponding to the communication status at the next time;
and predicting the energy saving level from the communication status information using the learning model.
A learning program that allows a computer to carry out processing.

Images