Determine the equipment, determine the method and determine the procedure

Abstract

The determination device (100) according to the present application includes: a communication unit (110), an acquisition unit (131) and a determination unit (134). The communication unit (110) selectively connects to a plurality of communication networks and performs communication. The acquisition unit (131) acquires sensor information detected by a mobile communication device used by a user and communication information indicating the state of communication quality to each communication network. The determination unit (134) determines whether to perform switching to another communication network among the plurality of communication networks based on the sensor information and communication information acquired by the acquisition unit (131).

Description

Technical Field

[0001] The present invention relates to a determination device, a determination method and a determination program. Background Art

[0002] Conventionally, there are known technologies for switching and using a wireless local area network (LAN) communication function conforming to IEEE802.11 and a cellular communication function conforming to a communication standard such as 4G or Long Term Evolution (LTE) (see Patent Documents 1 to 3).

[0003] Citation List

[0004] Patent Literature

[0005] Patent Document 1: JP 2007-509590 A

[0006] Patent Document 2: JP 2009-503914 A

[0007] Patent Document 3: JP 2010-523024 A Summary of the invention

[0008] Technical issues

[0009] Conventional technology has room for improvement in determining the switching of communication networks. For example, in conventional technology, the switching of communication networks is performed according to a predetermined switching standard. However, there are cases where the communication quality of the communication network at the switching destination is not necessarily good, and the switching of communication networks cannot always be appropriately determined.

[0010] The present application is made in view of the above-mentioned situation, and an object thereof is to appropriately determine the switching of a communication network.

[0011] Problem Solution

[0012] According to the present disclosure, a determination device includes: a communication unit that selectively connects to multiple communication networks and communicates with the multiple communication networks; an acquisition unit that acquires sensor information detected by a mobile communication device used by a user and communication information indicating the state of communication quality to each communication network; and a determination unit that determines whether to switch to other communication networks among the multiple communication networks based on the sensor information and communication information acquired by the acquisition unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a diagram illustrating an example of information processing according to the embodiment.

[0014] Figure 2 is a diagram illustrating an example of information processing according to the embodiment.

[0015] Figure 3is a diagram illustrating a configuration example of an information processing system according to an embodiment.

[0016] Figure 4 is a diagram illustrating a configuration example of a terminal device according to the embodiment.

[0017] Figure 5 is a diagram illustrating a configuration example of an information providing device according to the embodiment.

[0018] Figure 6 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0019] Figure 7 is a diagram illustrating an example of a past communication related information storage unit according to the embodiment.

[0020] Figure 8 is a diagram illustrating an example of a model information storage unit according to the embodiment.

[0021] Fig. 9 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0022] Fig.10 is a flowchart illustrating an example of information processing according to an embodiment.

[0023] Fig.11 is a diagram illustrating a configuration example of a terminal device according to the embodiment.

[0024] Fig.12 is a diagram illustrating a configuration example of a terminal device according to the embodiment.

[0025] Fig.13 is a flowchart illustrating an example of information processing according to an embodiment.

[0026] Fig.14 is a flowchart illustrating an example of information processing according to an embodiment.

[0027] Fig.15 is a diagram illustrating an example of information processing according to the embodiment.

[0028] Fig.16 is a diagram illustrating an example of information processing according to the embodiment.

[0029] Fig.17 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0030] Fig.18 is a flowchart illustrating an example of information processing according to an embodiment.

[0031] Fig.19 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0032] Fig. 20 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0033] Fig.21 is a flowchart illustrating an example of information processing according to an embodiment.

[0034] Fig. 22 is a diagram illustrating a configuration example of a determination device according to an embodiment.

[0035] Fig.23 is a flowchart illustrating an example of information processing according to an embodiment.

[0036] Fig.24 is a diagram illustrating an example of information processing according to the embodiment.

[0037] Fig.25 is a hardware configuration diagram illustrating an example of a computer for realizing the function of the determination device. DETAILED DESCRIPTION

[0038] Hereinafter, a mode for implementing the determination device, determination method, and determination program according to the present application will be described in detail with reference to the accompanying drawings (hereinafter, referred to as an "embodiment"). It is noted that the determination device, determination method, and determination program according to the present application are not limited to the embodiments. In the following embodiments, the same parts are represented by the same reference numerals, and redundant descriptions will be omitted.

[0039] The present disclosure will be described according to the following order of items.

[0040] 1. Configuration of information processing system

[0041] 2. Examples of information processing

[0042] 3. Changes in processing

[0043] 3-1. Data Collection

[0044] 3-2. Installation of multiple learning models

[0045] 3-3. Switch

[0046] 3-4. Correct labeling

[0047] 3-5. Switching timing

[0048] 3-6. External Sensors

[0049] 3-7. Other sensor information

[0050] 3-8. Download

[0051] 3-9. Terminal equipment, information provision equipment and confirmation equipment

[0052] 3-10. Learning Model

[0053] 3-11. Combination of communication networks

[0054] 4. Configuration of terminal equipment

[0055] 5. Configuration of information provision equipment

[0056] 6. Determine the configuration of the device

[0057] 7. Determine the details of the equipment

[0058] 8. Information processing procedures

[0059] 9. Modifications

[0060] 9-1. First Modification (Another Configuration Example of Terminal Device)

[0061] 9-2. Second Amendment (Millimeter Wave Communication)

[0062] 9-3. Third modification (switching carriers according to applications)

[0063] 9-4. Fourth modification (score calculation for each carrier)

[0064] 9-5. Fifth modification (downloading training data according to location)

[0065] 9-6. Sixth revision (score calculation on the cloud 1)

[0066] 9-7. Seventh revision (score calculation on the cloud 2)

[0067] 9-8. Others (determination other than determination of passing score)

[0068] 10. Hardware Configuration

[0069] 11. Others

[0070] (Example)

[0071] [1. Configuration of information processing system]

[0072] exist Figure 1 Before the description of Figure 3 The configuration of the information processing system 1 is described. Figure 3 1 is a diagram illustrating a configuration example of an information processing system according to an embodiment. Figure 3 As shown in , the information processing system 1 includes a terminal device 10, an information providing device 50, and a determining device 100. The terminal device 10, the information providing device 50, and the determining device 100 are communicably connected by a wired or wireless system via a predetermined communication network (network N). Figure 3is a diagram illustrating a configuration example of an information processing system according to an embodiment. Note that, Figure 3 The information processing system 1 shown in FIG. 1 may include a plurality of terminal devices 10 , a plurality of information providing devices 50 , and a plurality of determining devices 100 .

[0073] The terminal device 10 is an information processing device used by a user. The terminal device 10 may be any device as long as the processing in this embodiment can be implemented. In addition, the terminal device 10 may be a device such as a smart phone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. Figure 1 In the example shown in , a case where the terminal device 10 is a smartphone is illustrated.

[0074] The information providing device 50 is, for example, an information processing device such as a PC or a workstation (WS), and is used to provide the determination device 100 with past communication-related information.

[0075] The determination device 100 is used to determine whether to switch to another communication network. The determination device 100 is, for example, an information processing device such as a PC or a workstation (WS), and performs processing based on information sent from the terminal device 10 or the like via the network N. The determination device 100 determines switching of the communication network of the terminal device 10 based on communication information or sensor information.

[0076] [2. Example of information processing]

[0077] exist Figure 1 In the present invention, during the Wi-Fi connection of the terminal device 10 used by the user, the determination device 100 determines whether to switch the connection of the communication network of the terminal device 10 from Wi-Fi to another communication network based on the information detectable by the terminal device 10 and the information about the connected Wi-Fi. Specifically, the determination device 100 determines whether to switch to another communication network by using a learning model (e.g., a neural network) for inferring the deterioration state of the communication quality of the Wi-Fi.

[0078] The Wi-Fi according to the embodiment is a wireless LAN network via a wireless LAN base station. In addition, the other communication network according to the embodiment can be any communication network, as long as it is a communication network that can be connected to the terminal device 10 and is a communication network other than the connected communication network. For example, the other communication network according to the embodiment can be a cellular network via a cellular communication base station, or can be a wireless LAN network. Note that it is assumed that the number of cellular communication base stations that can communicate with the terminal device 10 is not limited. In other words, the terminal device 10 can be in a state that can be connected to one cellular network or can be in a state that can be connected to two or more cellular networks. In addition, it is assumed that the multiple communication networks according to the embodiment include a wireless LAN network and a cellular network. Note that the communication network according to the embodiment can be a communication network that complies with the fifth generation communication standard, and the cellular network according to the embodiment can be a communication network that complies with the fifth generation communication standard.

[0079] The terminal device 10 according to the embodiment is an example of a mobile communication device. The mobile communication device may be any mobile communication device. For example, the mobile communication device may be a communication device that moves with a user. Specifically, the mobile communication device may be a communication device that can be moved and carried or worn by a user, such as a smart phone, a smart watch, or a business camera. For example, the mobile communication device may be a communication device that moves according to the operation of the user. Specifically, the mobile communication device may be a communication device that can be moved according to the operation of the user, such as a drone. Figure 1 The case where the mobile communication device is a smart phone is taken as an example for description.

[0080] In the following, we will use Figure 1 An outline of the determination process according to the embodiment is described. Figure 1Two cases are illustrated: a case where the user moves at high speed via a moving object such as a vehicle and a case where the user does not move at high speed. Note that the case where the user moves at high speed may be a case where the user moves at any speed as long as the user moves at a speed that satisfies a predetermined condition. Here, the speed that satisfies the predetermined condition may include not only a speed based on the user's moving state, but also a speed based on the user's moving state and the communication state of the communication network. For example, the speed that satisfies the predetermined condition may be a speed based on the user's moving state when the communication quality of the communication network satisfies the predetermined condition. As a specific example, when the communication quality of the communication network deteriorates to below a predetermined standard even when the user is walking, the speed that satisfies the predetermined condition may be the speed at which the user is walking. On the other hand, when the communication quality of the communication network does not drop below a predetermined standard even when the user is moving at high speed on a train, it can be determined that the user is not moving at a speed that satisfies the predetermined condition. For example, when taking the case where the user moves by train as an example, the speed that satisfies the predetermined condition may be the speed of the user when the train accelerates so that the RTT value of the communication network connected to the terminal device 10 cannot continue to be at a predetermined threshold or higher in a certain moving interval. In addition, Figure 1 The case where the user moves by a vehicle as a moving object is illustrated. However, the moving object is not limited to a vehicle, and may be any moving object, such as a moving object in a public transportation vehicle (such as an airplane or a train), or a moving object that moves automatically (such as an elevator or an escalator). In addition, the case where the user does not move at a high speed is, for example, the case where the user moves on foot. Note that the case where the user does not move at a high speed includes a case where the user stays at a predetermined point or a fixed point, a case where the user does not move, and the like.

[0081] exist Figure 1 , user U1 shows an example of a user moving at high speed, while user U2 shows an example of a user not moving at high speed. Assume that user U1 moves from position A1 to position B1 by vehicle. Assume that user U2 moves from position A2 to position B2 on foot. In addition, it is assumed that the terminal device 10A used by user U1 and the terminal device 10B used by user U2 are connected to Wi-Fi immediately before the users start moving. That is, it is assumed that the terminal device 10A is connected to Wi-Fi (S1) when user U1 is at position A1, and the terminal device 10B is connected to Wi-Fi (S2) when user U2 is at position A2. In addition, it is assumed that the terminal device 10A switches from Wi-Fi to communication with a cellular network when user U1 moves to position B1 at high speed (S3). Specifically, the determination device 100 predicts the deterioration state of the communication quality of Wi-Fi and instructs the terminal device 10A to switch to communication with other communication networks. In addition, it is assumed that when user U2 moves to position B2, the terminal device 10B does not switch to communication with a cellular network while being connected to Wi-Fi (S4).

[0082] In the following, we will use Figure 2 An example of determination processing according to an embodiment is described. Hereinafter, a process will be described in which the determination device 100 generates a learning model that outputs the degree of deterioration of the Wi-Fi connection by using past information about the communication network (hereinafter, appropriately referred to as "past communication related information"). For example, the determination device 100 generates a learning model using past communication related information in terminal devices used by other users (hereinafter, appropriately referred to as "other terminal devices"). Note that other users may include the user to be evaluated (in Figure 1 In other words, the determination device 100 may use the past communication related information of the user U1 to generate a learning model that outputs the degree of deterioration of the Wi-Fi connection of the terminal device 10A. In addition, the other users may be one user or multiple users.

[0083] The determination device 100 acquires the past communication related information LINF1 (step S101). For example, the determination device 100 acquires the past communication related information LINF1 transmitted from the information providing device 50. To simplify the description, Figure 2 An example is illustrated in which the determination device 100 acquires past communication related information LINF1 transmitted from the information providing device 50. Note that the past communication related information LINF1 includes sensor information that can be acquired on other terminal devices, information related to Wi-Fi that can be acquired on other terminal devices, and information related to cellular networks that can be acquired on other terminal devices (hereinafter, appropriately referred to as "cellular information"). Each piece of information included in the past communication related information LINF1 will be described below.

[0084] The determination device 100 acquires information that can be detected on other terminal devices. For example, the determination device 100 acquires sensor information detected by sensors set inside other terminal devices. Note that, according to an embodiment, there are mainly two types of sensor information as sensor information. Specifically, the sensor information according to the embodiment includes sensor information for estimating the state of the user in real time and sensor information for inferring (predicting) the state of the user in the near future.

[0085] The determination device 100 acquires, for example, sensor information for estimating information about the movement of other users as sensor information for estimating the state of other users in real time. Specifically, the determination device 100 acquires sensor information indicating the position or movement speed of other users. As a specific example, the determination device 100 acquires sensor information detected by acceleration, magnetism, direction, air pressure, position sensors, etc. It is noted that the determination device 100 can acquire sensor information detected by any sensor as long as the sensor is a sensor that can be used to estimate information about the movement of other users, but is not limited to the above examples.

[0086] The determination device 100 acquires sensor information, such as for estimating the context information of other users, as sensor information for inferring the state of other users. For example, the determination device 100 acquires sensor information for inferring the state of other users based on past information. For example, the determination device 100 acquires sensor information for inferring the actions of other users. Specifically, the determination device 100 acquires sensor information for inferring the actions of other users (such as walking, moving by train, moving by car, going up and down stairs, or going up and down by elevator). As a specific example, the determination device 100 acquires sensor information detected by acceleration, time, direction, air pressure, position, pedometer, etc. It is noted that the determination device 100 can acquire sensor information detected by any sensor, as long as the sensor is a sensor that can be used to infer the actions of other users, not limited to the above examples. In addition, the determination device 100 can acquire action information inferred from the acquired sensor information. For example, the determination device 100 can acquire the action information of the user from the change amount of the sensor information. As a specific example, the determination device 100 can calculate the moving speed or acceleration state of the user from the change amount of the acceleration or position information. Thus, for example, the determination device 100 may predict that Wi-Fi performance will deteriorate in a few seconds.

[0087] The determination device 100 acquires information of parameters related to each sensor as sensor information. For example, the determination device 100 acquires information of parameters related to acceleration, magnetism, direction, air pressure, position, time, pedometer sensor, etc.

[0088] Therefore, the determination device 100 can grasp the user's mobile state by using sensor information, and can select the optimal carrier according to the user's mobile state by using sensor information to make a switching determination. For example, the determination device 100 can choose to continue using cellular in a high-speed mobile communication state such as train travel.

[0089] In addition, the determination device 100 obtains information about Wi-Fi connected to other terminal devices. For example, the determination device 100 obtains parameter information related to Wi-Fi. For example, the determination device 100 obtains information such as LinkSpeed ​​and packet communication status as parameters related to Wi-Fi. As a specific example, the determination device 100 obtains the following items as parameters related to Wi-Fi: PHY protocol type (a / b / g / n / ac / ax), MAC protocol type (d / e / h / i / j / k / p / v / w / y / z), signal strength (RSSI), frequency used, SSID, BSSID, allocated bandwidth, RTT of the radio interval used for AP, S / N ratio, spectrum, the number of terminals in the same basic service set (BSS), authentication method, number of MIMO layers, number of signal conflicts, number of RTS / CTS per unit time, number of probe requests, number of beacons received, receive / send packet counter value, number of successful transmissions, number of successful receptions, number of retransmissions, number of frame failures, number of interface errors, length of time determined to be busy by the radio machine through carrier sensing (CC The information includes information such as the number of frames existing in the queue of the Wi-Fi transmission buffer (e.g., the number of packets staying in the transmission buffer and the length of time the packets stay in the transmission buffer). Note that the determination device 100 can obtain any parameter as long as the parameter is information related to Wi-Fi, and is not limited to the above examples. In addition, the determination device 100 can obtain a combination of the above multiple parameters as a parameter, or can obtain a result obtained by processing the combination of the above multiple parameters as a parameter. Note that the contention time can be an interval average value, an interval minimum value, or an interval maximum value within the predetermined interval. Note that the number of packets staying in the send buffer may be an instantaneous value, an interval average value within a predetermined interval, or an integral value at a certain time within a predetermined interval. Note that when the target parameter is x(t) and the target time interval is t1 to t2, an example of a calculation formula for the integral value at a certain time within the predetermined interval is expressed by the following formula (1). In addition, the length of time that the packet stays in the send buffer may be an interval average value within the predetermined interval.

[0090]

[0091] In addition, the determination device 100 obtains information about a cellular network that can be connected to other terminal devices. For example, the determination device 100 obtains information about parameters related to the cellular network. As a specific example, the determination device 100 obtains the following items as parameters related to the cellular network: the number of component carriers, the average rate (modulation and coding scheme (MCS)), the capability (LTE / HSPA+ / GSM), the signal strength, the number of MIMO layers, the number of communication allocations, the number of actual resource blocks, the receive / send packet counter value, the number of successful transmissions, the number of successful receptions, the number of frame retransmissions (MAC), the number of RLCs, the number of interface errors, the throughput (PHY / IP), the cell information (cell ID, the transmission power of the DL reference signal, the adjacent cell information, the cell capacity, and the backbone frequency band information), AsuLvel, Cqi, dbm, Level, RSRP, RSSI, RSSNR, TimingAdvance, the user's communication plan, and the information in the communication plan (such as the remaining communicable capacity within the month). Note that the determination device 100 can obtain any parameter as long as the parameter is information related to the cellular network, and is not limited to the above examples.

[0092] In addition, the determination device 100 stores the acquired past communication related information LINF1. For example, the determination device 100 stores the acquired information in a predetermined storage unit. For example, the determination device 100 stores the acquired information in the past communication related information storage unit 121.

[0093] Subsequently, the determination device 100 generates a model of the degree of deterioration of the output Wi-Fi connection (step S102). For example, the determination device 100 uses both or one of the sensor information and Wi-Fi-related information that can be obtained on other terminal devices as input information to generate a model of the degree of deterioration of the output Wi-Fi connection. For example, the determination device 100 uses both or one of the parameters related to the sensor and the parameters related to Wi-Fi as input information to generate a model of the degree of deterioration of the output Wi-Fi connection. In addition, the determination device 100 generates a learned model by assigning a correct label (flag) at the timing of switching the communication network using part or all of the acquired information. For example, the determination device 100 can generate a model by assigning a correct label at the timing when the RTT value exceeds a predetermined threshold or at the timing when the Wi-Fi connection is disconnected due to a weak current and performing learning. Note that the timing at which the determination device 100 assigns the correct label is not limited to this example. For example, the determination device 100 can generate a model by assigning a correct label and performing learning at a timing when the number of packets staying in the sending buffer becomes equal to or greater than a predetermined threshold, the length of time the packets stay in the sending buffer becomes equal to or greater than a predetermined threshold, or the number of lost packets in the case where the sending buffer is not successfully sent becomes equal to or greater than a predetermined threshold. In addition, the determination device 100 can combine multiple conditions, assign a correct label and perform learning at a timing when all the multiple conditions are met, thereby generating a model. Here, the correct label indicates the timing when the communication network should be switched. Specifically, the correct label indicates the timing when the communication network should be switched based on past communication-related information. In Figure 2 In , the determination device 100 assigns label “1” as a correct label at the timing when the communication network should be switched, and assigns label “0” as an incorrect label that is not a correct label at the timing when the communication network should not be switched. Note that the determination device 100 can obtain information about the timing when the communication network should be switched or information about the timing when the communication network should not be switched based on label “1” or label “0”. For example, the determination device 100 can obtain past communication-related information corresponding to the timing when the communication network should be switched or past communication-related information corresponding to the timing when the communication network should not be switched. In Figure 2 In the example shown in , the determination device 100 generates the model M1 using the information stored in the past communication related information storage unit 121. Note that there are two types of models generated by the determination device 100. Specifically, the determination device 100 generates a corresponding type of model according to the type of sensor information.

[0094] The determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in real time. For example, the determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in real time by using sensor information for estimating the state of other users in real time. For example, the determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection related to the movement of other users in real time by using sensor information for estimating information related to the movement of other users.

[0095] The determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in the near future. For example, the determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in a few seconds. For example, the determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in the near future by using sensor information for inferring the state of other users. For example, the determination device 100 generates a model that outputs the degree of deterioration of the Wi-Fi connection in the near future related to the actions of other users by using sensor information for inferring the actions of other users.

[0096] It is known that unless the communication status (e.g., error rate, throughput, etc.) is measured by actually sending communication packets, it is difficult to predict (determine) the degree of deterioration of the Wi-Fi connection of the terminal device 10 at a certain point in time. This is because the deterioration state of the Wi-Fi connection is the result of a combination of various factors and can change at any time. For example, there are deterioration such as deterioration caused by weak radio waves of the radio, deterioration caused by the influence of radio waves of other wireless communication devices, and deterioration caused by high-speed operation of mobile communication devices, and it is difficult to determine the current deterioration state. Moreover, it is still difficult to predict the deterioration state of the Wi-Fi connection in the future.

[0097] The determination device 100 can infer the degree of deterioration of the current or future Wi-Fi connection without actually sending communication packets and measuring the communication state. Therefore, for example, in the case where the terminal device 10 has multiple carriers of Wi-Fi and mobile communication, when the deterioration state of the current or future Wi-Fi connection is detected and the deterioration of Wi-Fi is determined, the determination device 100 can achieve comfortable communication on the terminal device 10 by switching the carrier from Wi-Fi to mobile communication.

[0098] The determination device 100 may output information about the RTT or information about the disconnection of the Wi-Fi connection as the information indicating the degree of deterioration of the Wi-Fi connection. For example, the determination device 100 outputs a score or value of the RTT. For example, the determination device 100 outputs a score or value indicating the probability of disconnection of the Wi-Fi connection as the information about the disconnection of the Wi-Fi connection. Note that the determination device 100 may output any information as long as the information is information indicating the degree of deterioration of the Wi-Fi connection, without being limited to the above examples.

[0099] The determination device 100 stores the generated model M1. For example, the determination device 100 stores the generated model M1 in a predetermined storage unit. For example, the determination device 100 stores the generated model M1 in the model information storage unit 122.

[0100] The process in which the determination device 100 generates a learning model of the degree of deterioration of the output Wi-Fi connection has been described above.

[0101] The determination device 100 acquires communication-related information TINF1 (step 103). The determination device 100 acquires communication-related information TINF1 transmitted from the terminal device 10 used by the user to be evaluated. Note that the communication-related information TINF1 includes sensor information that can be acquired by the terminal device 10, information related to Wi-Fi that can be acquired by the terminal device 10, and information related to a cellular network that can be acquired by the terminal device 10. Since the communication-related information TINF1 includes information similar to the past communication-related information LINF1, a description thereof will be omitted.

[0102] The determination device 100 inputs the sensor information and Wi-Fi related information in the acquired communication related information TINF1 into the model M1 (step S104 ). Specifically, the determination device 100 inputs the sensor related parameters and Wi-Fi related parameters into the model M1 .

[0103] The determination device 100 outputs information indicating the degree of deterioration of the Wi-Fi connection (step S105). Figure 2 In the example shown in , the determination device 100 outputs a score indicating the communication quality as information indicating the degree of deterioration of the Wi-Fi connection. For example, the determination device 100 may output an RTT value as a score indicating the communication quality. Figure 2 It is illustrated that the score indicating the communication quality output by the determination device 100 is 45.

[0104] The determination device 100 determines whether the output information indicating the degree of deterioration of the Wi-Fi connection satisfies a predetermined condition. For example, the determination device 100 determines whether the output information indicating the degree of deterioration of the Wi-Fi connection exceeds a predetermined threshold. When it is determined that the output information indicating the degree of deterioration of the Wi-Fi connection satisfies the predetermined condition, the determination device 100 determines to request the switching of the communication path. In addition, the determination device 100 may change the predetermined condition for switching the communication path according to the sensor information. For example, the determination device 100 may set the standard for switching the communication path to be higher or lower than the usual standard according to the sensor information. As a specific example, when it is determined according to the sensor information that the user moves on foot, etc., the determination device 100 may change the predetermined threshold value related to the switching to a low value so as to switch the communication path more easily. Therefore, the determination device 100 can switch the communication path more efficiently and effectively. On the other hand, when it is determined according to the sensor information that the user does not move or stop, the determination device 100 may change the predetermined threshold value related to the switching to a high value so that the user continues to use Wi-Fi as much as possible. Therefore, the determination device 100 can provide the user with a comfortable communication environment without interrupting the communication in the connected state. For example, the determination device 100 determines to switch to another communication network. In this case, the determination device 100 determines to switch the connection of the communication network to the cellular network. On the other hand, when the output information indicating the degree of deterioration of the Wi-Fi connection does not satisfy the predetermined condition, the determination device 100 determines to continue the Wi-Fi connection. Figure 2 In the example shown in , it is assumed that the determination device 100 determines that the output information indicating the degree of deterioration of the Wi-Fi connection satisfies a predetermined condition.

[0105] The determination device 100 transmits information about the determination result to the terminal device 10. For example, the determination device 100 transmits control information according to the determination result to the terminal device 10. For example, the determination device 100 transmits control information about switching of the communication network to the terminal device 10 according to the determination result.

[0106] The determination device 100 may send information for notifying the user that the communication network is unstable. For example, the determination device 100 may send information for notifying that stable communication cannot be performed using any carrier. As a specific example, when the user uses the elevator, the determination device 100 may estimate that the communication environment of both the cellular network and the Wi-Fi has deteriorated, and send information for notifying that stable communication cannot be performed using any carrier. More specifically, when it is determined that the user is in the elevator, etc., the determination device 100 may calculate information indicating that the communication network environment of both the Wi-Fi side and the cellular network side is not good, and send information for notifying the user that the communication network is unstable.

[0107] The terminal device 10 performs a process of switching the connection of the communication network according to the information on the determination result transmitted from the determination device 100. Figure 1 In the example shown in , the terminal device 10 of the user U1 releases the Wi-Fi connection and connects to the cellular network. Specifically, the determination device 100 instructs the terminal device 10 used by the user U1 to switch to the cellular network via the cellular communication base station identified by the cellular communication base station CI1.

[0108] Note that, Figure 1 and 2 The various types of information processing shown in are not limited to the above, and may be various modes. This will be described below.

[0109] [3. Changes in processing]

[0110] (3-1. Data collection)

[0111] In the above example, the case where the determination device 100 acquires the past communication related information LINF1 sent from the information providing device 50 has been described. However, the present invention is not limited to the example of providing information from the information providing device 50. For example, the determination device 100 may acquire the past communication related information separately from other terminal devices. For example, the determination device 100 may acquire the past communication related information uploaded to the cloud as meta information. That is, it is assumed that there is no limitation on the method by which the determination device 100 acquires the past communication related information. As such, the determination device 100 may acquire the past communication related information LINF1 in any manner. For example, the determination device 100 may acquire the past communication related information LINF1 stored in a predetermined storage unit. For example, the determination device 100 may acquire the past communication related information LINF1 stored in the past communication related information storage unit 121. For example, the determination device 100 may acquire one piece of past communication related information selected from the past communication related information sent from the information providing device 50 and the past communication related information stored in the predetermined storage unit based on a predetermined condition as the past communication related information LINF1. For example, the determination device 100 may calculate the similarity between the user's communication-related information and each acquired past communication-related information, and acquire a piece of past communication-related information with the largest calculated similarity as the past communication-related information LINF1.

[0112] (3-2. Installation of multiple learning models)

[0113] In the above example, the case of generating one learning model that outputs information indicating the degree of deterioration of the Wi-Fi connection has been described. However, the determination device 100 may generate multiple learning models. For example, the determination device 100 may generate multiple learning models that output multiple pieces of information indicating the degree of deterioration of the Wi-Fi connection and having different switching criteria. As a specific example, the determination device 100 may generate a learning model for predicting the disconnection of the Wi-Fi connection and a learning model for predicting the RTT on the Wi-Fi connection. In this case, the determination device 100 may use two learning models to select both or one of the result information and determine the degree of deterioration of the Wi-Fi connection. Therefore, the determination device 100 can effectively infer a variety of Wi-Fi deterioration scenarios that are difficult to cover with one learning model.

[0114] The determination device 100 may generate a plurality of different learning models for each state of the user. For example, the determination device 100 may pre-generate a learning model suitable for walking and a learning model suitable for high-speed movement. In this case, according to the estimated user state, for example, the determination device 100 may perform determination using a learning model suitable for walking when the user is walking, and perform determination using a learning model suitable for high-speed movement when the user is moving at high speed on a railway or the like. Specifically, the determination device 100 may perform determination using a learning model that can select an appropriate communication network while reducing the number of handovers according to the estimated user state. Therefore, the determination device 100 may predict the degradation of communication quality due to more complex and various conditions by performing predictions based on multiple switching criteria, so that the predicted switching for the user's movement can be more directly reflected. For example, in combination with a location sensor, when it is known that the user is at home or at work, the determination device 100 may perform determination using a learning model that suppresses switching, and when the user moves, a learning model that promotes switching may be used to perform determination. Therefore, the determination device 100 may suppress the deterioration of UX caused by being captured by a wireless LAN while suppressing switching when the user expects to use Wi-Fi more. For example, in combination with the acceleration sensor, when the user moves, the determination device 100 can perform determination using a learning model suitable for movement. Specifically, when the user moves, the determination device 100 can perform determination using a learning model that makes it difficult to connect to a public Wi-Fi and makes it easy to switch to a cellular network. For example, in combination with the acceleration sensor, when the user is in a stopped state, the determination device 100 can perform determination using a learning model suitable for a stationary state. Specifically, when the user is in a stopped state, the determination device 100 can perform determination using a learning model that makes it difficult to switch to a cellular network.

[0115] The determination device 100 may select one learning model from a plurality of learning models and perform determination, or may select a plurality of learning models and perform determination. In addition, when selecting a plurality of learning models and performing determination, the determination device 100 may use a plurality of learning models simultaneously, or may use a plurality of learning models separately.

[0116] (3-3. Switch)

[0117] In the above example, the case where the switch from Wi-Fi to other communication networks is determined according to the degree of deterioration of the Wi-Fi connection has been explained. However, the switching target is not limited to Wi-Fi, and any communication network can be used as long as it is a communication network. For example, the determination device 100 can determine the switch from a predetermined cellular network to other communication networks by generating a learning model that outputs information indicating the degree of deterioration of the connection of the predetermined cellular network. As a specific example, the determination device 100 can determine to switch from 5G mmW to other cellular networks such as 5G Sub6 or LTE. For example, the determination device 100 can determine to switch from a predetermined cellular network such as 5G mmW to a Wi-Fi connection.

[0118] (3-4. Correct label)

[0119] In the above example, an example of assigning a correct label at the timing when the communication network should be switched has been described. The determination device 100 may also assign a label at a timing other than the timing when the communication network should be switched. For example, the determination device 100 may assign a correct label (e.g., 1) at the timing when the communication network should be switched, and assign an incorrect label (e.g., 0) at a timing other than the timing when the communication network should be switched.

[0120] In addition, the determination device 100 is not limited to the case where the correct label is assigned at the timing when the communication network should be switched, and the correct label can be assigned before the event of the timing when the communication network should be switched occurs (for example, a few seconds ago). For example, when the determination device 100 determines to assign the correct label, the determination device 100 can assign the correct label before the event that becomes the basis (for example, the reason) for determining that the switch is to be performed occurs. For example, when the determination device 100 determines to assign the correct label, the determination device 100 can assign the correct label before determining the timing of the switch. Note that the timing of assigning the correct label can be a timing arbitrarily determined by the user using the terminal device 10 to be switched, or can be a timing determined by the determination device 100. In this case, the determination device 100 can assign the correct label before the event occurs by shifting a predetermined time. In addition, when the determination device 100 assigns the correct label at a determined timing, the determination device 100 can assign the correct label before the event occurs by shifting the time corresponding to the information of the event (such as the scale, content or type of the event). Therefore, by assigning the correct label before an event occurs, the determination device 100 can reduce user stress and improve usability.

[0121] (3-5. Switching Timing)

[0122] In the above example, it has been explained that the timing of switching the communication network is the timing when the RTT value exceeds a predetermined threshold or the timing of disconnecting the Wi-Fi connection. However, the present invention is not limited to the above example, and any timing can be used. For example, the determination device 100 can set the timing of communication difficulties caused by Wi-Fi congestion, the timing of communication difficulties caused by the time required to process the Wi-Fi access point or base station, the timing of communication difficulties caused by the large RTT to the Wi-Fi access point or base station, and the timing of communication difficulties caused by interference waves in the radio wave environment as the timing of switching the communication network. In addition, the determination device 100 can not only set the timing of the above-mentioned communication device or communication path to have a fault, but also set the timing of the UX deterioration used for communication to the timing of switching the communication network. As a specific example, the determination device 100 can set the timing of the progress bar stagnation in the browser or the timing of displaying the icon indicating that the reading is in progress to the timing of switching the communication network. For example, the determination device 100 can set the timing of the reading failure and the error display on the browser to the timing of switching the communication network. For example, the determination device 100 may set the timing of displaying an icon indicating video interruption, video stop, error occurrence, or video being read in a video stream as the timing when the communication network should be switched. For example, the determination device 100 may set the timing of screen loading failure in an application and displaying an error message as the timing when the communication network should be switched.

[0123] (3-6. External sensor)

[0124] In the above example, the case of acquiring sensor information detected by a sensor provided inside the terminal device 10 has been described. However, it is determined that the device 100 can acquire sensor information detected by an external sensor. In this case, the device 100 acquires sensor information that can be detected by an external sensor connected via the input unit and the output unit of the terminal device 10. For example, the device 100 can acquire sensor information that can be detected by an external sensor connected to the input unit and the output unit of the terminal device 10 via an interface such as a universal serial bus (USB) or Bluetooth (registered trademark). Note that the device 100 can acquire sensor information that can be detected by an external sensor connected via any interface, not limited to interfaces such as USB or Bluetooth (registered trademark). For example, the device 100 can acquire sensor information such as the user's pulse, number of steps, and acceleration from a device that can be used as an activity meter (such as a smart watch attached to the user's arm).

[0125] (3-7. Other sensor information)

[0126] In the above example, an example in which sensor information for estimating the state of the user in real time and sensor information for inferring the state of the user have been obtained has been explained. The determination device 100 may obtain sensor information for estimating the situation or attribute (type) of the user as other sensor information. For example, the determination device 100 may obtain image information captured by a camera, blood pressure information, or application information for measuring the immersion or stress level of the user. For example, the determination device 100 may estimate the activity state of the user by acquiring image information, blood pressure information, etc. of the user. As a specific example, the determination device 100 may estimate that the user is training in a gym by combining the user's location information and blood pressure information, or may estimate that the user is driving by combining acceleration information and the user's blood pressure information. In addition, the determination device 100 may estimate whether the user is in a train, company, store, etc. Therefore, the determination device 100 may grasp the state of the user with higher accuracy. In addition, the determination device 100 may adjust the switching criteria so that a high-speed carrier may be selected according to the state of the user. Therefore, for example, even in a state where the user feels stressed, the determination device 100 may estimate the stress state of the user, adjust the switching threshold according to the estimated stress state, and appropriately switch the carrier to a higher-speed carrier.

[0127] (3-8. Download)

[0128] When information such as a file is being downloaded to the terminal device 10, the determination device 100 can determine to switch to other communication networks based on information about the target of the download and the context information of the user. For example, the determination device 100 can determine to switch to other communication networks based on the time required for download and the time required for movement based on the context information of the user. Specifically, when the time required for download is shorter than the user's movement time required to exceed the communicable range of the connected communication network, the determination device 100 can determine not to switch to other communication networks until the download to the terminal device 10 is completed. More specifically, when a file is being downloaded and can be downloaded within the remaining three seconds, the determination device 100 can switch to and connect to a Wi-Fi that can only be connected for 10 seconds (> three seconds), but can not switch to a Wi-Fi that can only be connected for two seconds (< three seconds). In addition, the determination device 100 can determine whether to switch to other communication networks during download based on information such as the importance of the file, the capacity of the file, the attributes of the file, and whether the file is a file downloaded by a segmented datagram.

[0129] (3-9. Terminal equipment, information provision equipment and determination equipment)

[0130] In the above example, the case where the terminal device 10 and the determination device 100 are separate devices has been described. However, the terminal device 10 and the determination device 100 may be integrated. In this case, the mobile communication device may have all or part of the functions of the determination device 100 and perform all or some of the processing performed by the determination device 100. In addition, when the mobile communication device has some of the functions of the determination device 100 and performs some of the processing performed by the determination device 100, the mobile communication device may cause the external information processing device to perform the remaining processing performed by the determination device 100.

[0131] (3-10. Learning Model)

[0132] The learning model according to the embodiment is not limited to a model based on a neural network such as deep learning, and may be any model as long as it is based on a machine learning algorithm. For example, the learning model may be a model based on a random forest.

[0133] (3-11. Combination of communication networks)

[0134] exist Figure 1In the illustrated example, a state in which the terminal device 10 can connect to a wireless LAN network and a cellular network is illustrated. However, it is assumed that there is no limitation on the combination of communication networks to which the terminal device 10 can connect. For example, the terminal device 10 may be in a state in which it can only connect to a plurality of cellular networks, in a state in which it can only connect to a wireless LAN network, or in a state in which it can connect to a communication network other than a wireless LAN network and a cellular network. In addition, in Figure 1 In the example shown, a case where the terminal device 10 switches the communication connection to a cellular network while being connected to a wireless LAN network is illustrated. However, it is assumed that there is no restriction on the communication network that is the target before the terminal device 10 switches and the communication network that is the target of the switching destination. For example, the terminal device 10 may switch the communication connection to a wireless LAN network while being connected to a cellular network, or may switch the communication connection to a communication network other than a cellular network while being connected to a cellular network.

[0135] [4. Configuration of terminal equipment]

[0136] Next, we will use Figure 4 The configuration of the terminal device 10 according to the embodiment is described. Figure 4 1 is a diagram illustrating a configuration example of a terminal device 10 according to an embodiment. Figure 4 As shown in FIG. 1 , the terminal device 10 has a communication unit 11 , an input unit 12 , an output unit 13 , a control unit 14 , and a sensor unit 15 .

[0137] Note that the terminal device 10 may not have the sensor unit 15. In this case, it is assumed that the terminal device 10 is connected to an external sensor or an external information processing device having a sensor in some way. The terminal device 10 and the external sensor or the external information processing device having a sensor may be connected by any connection method as long as it is a method by which the terminal device 10 can obtain sensor information.

[0138] (Communication unit 11)

[0139] The communication unit 11 is realized by, for example, a network interface card (NIC) etc. Furthermore, the communication unit 11 is connected to a predetermined network N in a wired or wireless manner, and transmits and receives information to and from the determination device 100 etc. via the predetermined network N.

[0140] (Input unit 12)

[0141] The input unit 12 receives various operations from the user. Figure 1In the example shown, various operations from the user U1 are received. For example, the input unit 12 can receive various operations from the user via the display surface through the touch panel function. In addition, the input unit 12 can receive various operations from buttons provided in the terminal device 10 or a keyboard or mouse connected to the terminal device 10.

[0142] (Output unit 13)

[0143] The output unit 13 is a display screen of a tablet terminal or the like implemented by, for example, a liquid crystal display, an organic electroluminescent (EL) display, etc., and is a display device for displaying various types of information. For example, the output unit 13 outputs information for notifying the user that the communication network is unstable.

[0144] (Sensor unit 15)

[0145] The sensor unit 15 is an internal sensor provided inside the terminal device 10. The sensor unit 15 detects sensor information on the terminal device 10. For example, the sensor unit 15 is an acceleration sensor, a magnetic sensor, a direction sensor, an air pressure sensor, a position sensor, a time sensor, a pedometer, etc. The sensor unit 15 is not limited to the above examples, and may be any sensor as long as it is a sensor that detects sensor information that can be used to estimate the state of the user in real time or infer the future state of the user. In addition, the sensor unit 15 may be a sensor that detects sensor information that can be used to measure the user's immersion or stress level. In addition, the sensor unit 15 may be a sensor that detects sensor information that can be used to estimate the activity state of the user.

[0146] exist Figure 4 In the illustrated example, an example is illustrated in which the sensor unit 15 is connected to the control unit 14. However, the sensor unit 15 may be connected to the input unit 12 and the output unit 13. Note that the sensor unit 15 may be connected to an input / output unit (I / O unit) that performs input and output processing on the terminal device 10.

[0147] (Control unit 14)

[0148] The control unit 14 is, for example, a controller, and is implemented by executing various programs stored in a storage device inside the terminal device 10 using a random access memory (RAM) as a work area by a central processing unit (CPU), a microprocessing unit (MPU), etc. For example, the various programs include programs of applications installed in the terminal device 10. For example, the various programs include programs of applications that display information for notifying a user that a communication network is unstable. In addition, the control unit 14 is implemented by, for example, an integrated circuit such as an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0149] like Figure 4 As shown in , the control unit 14 has a transmission unit 141, a reception unit 142, an application control unit 143, and a communication unit 144, and implements or executes the function of information processing described below.

[0150] (Sending unit 141)

[0151] The sending unit 141 provides various types of information to an external information processing device. The sending unit 141 sends various types of information to an external information processing device. The sending unit 141 sends various types of information to other information processing devices such as the determination device 100. For example, the sending unit 141 sends communication related information.

[0152] (Receiving unit 142)

[0153] The receiving unit 142 receives various types of information. The receiving unit 142 receives various types of information from an external information processing device. The receiving unit 142 receives various types of information from other information processing devices such as the determination device 100. For example, the receiving unit 142 receives information about the determination result of the determination device 100. For example, the receiving unit 142 receives control information corresponding to the determination result of the determination device 100. For example, the receiving unit 142 receives information for notifying a user that the communication network is unstable.

[0154] (Application Control Unit 143)

[0155] The application control unit 143 controls various types of information on the application started on the terminal device 10. The application control unit 143 transmits various types of information on the started application to the communication unit 144.

[0156] (Communication unit 144)

[0157] The communication unit 144 controls communication of various types of information. The communication unit 144 controls communication to a communication network. The communication unit 144 controls switching of communication. The communication unit 144 controls switching of communication according to a determination result by other information processing devices such as the determination device 100. The communication unit 144 controls switching of communication according to various types of information about an application acquired from the application control unit 143.

[0158] [5. Configuration of information provision equipment]

[0159] Next, we will use Figure 5 The configuration of the information providing device 50 according to the embodiment is described. Figure 5 1 is a diagram illustrating a configuration example of an information providing device 50 according to an embodiment. Figure 5As shown in FIG. 5 , the information providing device 50 has a communication unit 51, a storage unit 52, and a control unit 53. Note that the information providing device 50 may have an input unit (e.g., a keyboard, a mouse, etc.) for receiving various operations from an administrator of the information providing device 50 and a display unit (e.g., a liquid crystal display, etc.) for displaying various types of information.

[0160] (Communication unit 51)

[0161] The communication unit 51 is implemented by, for example, a NIC, etc. Furthermore, the communication unit 51 is connected to the network N in a wired or wireless manner, and transmits and receives information to and from the determination device 100 via the network N.

[0162] (Storage unit 52)

[0163] The storage unit 52 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a storage device such as a hard disk or an optical disk, etc. The storage unit 52 stores past communication related information.

[0164] (Control Unit 53)

[0165] The control unit 53 is a controller and is implemented by executing various programs stored in a storage device inside the information providing device 50 using RAM as a work area by, for example, a CPU, an MPU, etc. In addition, the control unit 53 is a controller and is implemented by, for example, an integrated circuit such as an ASIC or an FPGA.

[0166] like Figure 5 As shown in FIG. 5 , the control unit 53 has a transmission unit 531 and implements or executes the function of the information processing described below. Note that the internal configuration of the control unit 53 is not limited to Figure 5 The configuration shown in , and may be another configuration as long as it is a configuration that performs information processing described later.

[0167] (Sending unit 531)

[0168] The sending unit 531 provides various types of information to the external information processing device. The sending unit 531 sends various types of information to the external information processing device. The sending unit 531 notifies the external information processing device of various types of information. The sending unit 531 sends various types of information to other information processing devices such as the determination device 100. For example, the sending unit 531 sends past communication related information. For example, the sending unit 531 sends past communication related information LINF1.

[0169] [6. Determine the configuration of the device]

[0170] Next, we will use Figure 6The configuration of the determination device 100 according to the embodiment is described. Figure 6 1 is a diagram illustrating a configuration example of a determination device 100 according to an embodiment. Figure 6 As shown in FIG, the determination device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the determination device 100 may include an input unit (e.g., a keyboard, a mouse, etc.) for receiving various operations from an administrator of the determination device 100 and a display unit (e.g., a liquid crystal display, etc.) for displaying various types of information.

[0171] (Communication unit 110)

[0172] The communication unit 110 is implemented by, for example, a NIC, etc. Also, the communication unit 110 is connected to the network N in a wired or wireless manner, and transmits and receives information to and from the terminal device 10, etc. via the network N. In addition, the communication unit 110 can perform communication by selectively connecting to a plurality of communication networks.

[0173] (Storage unit 120)

[0174] The storage unit 120 is implemented by, for example, a semiconductor memory element such as a RAM or a flash memory, a storage device such as a hard disk or an optical disk. Figure 6 As shown in FIG. 1 , the storage unit 120 has a past communication related information storage unit 121 and a model information storage unit 122 .

[0175] The past communication related information storage unit 121 stores past communication related information. Figure 7 An example of the past communication related information storage unit 121 according to the embodiment is illustrated. Figure 7 As shown in , the past communication related information storage unit 121 has items such as “data ID”, “sensor information”, “cellular information”, “Wi-Fi information”, and “correct label”.

[0176] "Data ID" indicates identification information for identifying past communication related information. "Sensor information" indicates sensor information included in past communication related information. Figure 7 As shown in , “Sensor Information” may have items of sensor information of each sensor, such as “acceleration”, “magnetism”, “direction”, “air pressure”, and “position”. In addition, “Sensor Information” is not limited to the above examples, and may have items corresponding to any sensor as long as it is an item of sensor information that can be acquired on the terminal device 10. Figure 7In the example shown, an example of storing conceptual information such as "acceleration #1", "magnetism #1", "direction #1", "air pressure #1", and "position #1" in "sensor information" has been illustrated. However, in reality, data such as values ​​or scores output based on information detected for each sensor is stored. "Cellular information" indicates information related to a cellular network included in past communication-related information. Figure 7 As shown in , “Cellular Information” may have items for each cellular network, such as “5G mmW” and “LTE”. In addition, “Cellular Information” is not limited to the above example, and may have items corresponding to any cellular network as long as it is an item for each cellular network that can perform communication on the terminal device 10. Figure 7 In the example shown, an example of storing conceptual information such as "5G mmW#1" and "LTE#1" in "Cellular Information" has been illustrated. However, in reality, data such as values ​​or scores output based on the communication quality (RTT, RSSI, etc.) of each cellular network is stored. "Wi-Fi Information" indicates information related to Wi-Fi included in past communication-related information. Figure 7 As shown in , the “Wi-Fi information” may have items such as “RTT” and “disconnection probability”. In addition, the “Wi-Fi information” is not limited to the above example, and may have any item as long as it is an item corresponding to information indicating the communication quality of Wi-Fi. Figure 7 In the example shown, an example of storing conceptual information such as "RTT#1" and "disconnection probability #1" in "Wi-Fi information" has been illustrated. However, in reality, data such as a value or a score output based on the communication quality of Wi-Fi is stored. "Correct Tag" indicates whether the timing is the timing at which the communication network should be switched. "1" included in the "Correct Tag" indicates that the timing is the timing at which the communication network should be switched. "0" included in the "Correct Tag" indicates that the timing is not the timing at which the communication network should be switched.

[0177] The model information storage unit 122 stores information about the model. For example, the model information storage unit 122 stores information about a model that outputs information indicating the degree of deterioration of the communication network. Figure 8 An example of the model information storage unit 122 is shown. Figure 8 As shown in , the model information storage unit 122 has items such as “model ID” and “model (calculation formula)”.

[0178] "Model ID" indicates identification information for identifying a model. "Model (calculation formula)" indicates the calculation formula of the model. Figure 8In the example shown, an example is illustrated in which conceptual information such as "model #1" and "model #2" is stored in "model (calculation formula)". However, in reality, data of functions are stored. For example, data of a function that outputs information indicating the degree of deterioration of a communication network is stored in "model (calculation formula)".

[0179] (Control Unit 130)

[0180] The control unit 130 is a controller and is implemented by executing various programs stored in a storage device inside the determination device 100 using RAM as a work area by, for example, a CPU, an MPU, etc. In addition, the control unit 130 is a controller and is implemented by, for example, an integrated circuit such as an ASIC or an FPGA.

[0181] like Figure 6 As shown in FIG. 1 , the control unit 130 has an acquisition unit 131, a generation unit 132, a calculation unit 133, a determination unit 134, and a provision unit 135, and implements or executes the following information processing functions. Note that the internal configuration of the control unit 130 is not limited to Figure 6 The configuration shown in , and may be another configuration as long as it is a configuration that performs information processing described later.

[0182] (Acquisition unit 131)

[0183] The acquisition unit 131 acquires various types of information. The acquisition unit 131 acquires various types of information from an external information processing device. The acquisition unit 131 acquires various types of information from other information processing devices such as the terminal device 10.

[0184] The acquisition unit 131 acquires various types of information from the storage unit 120. The acquisition unit 131 acquires various types of information from the past communication related information storage unit 121 or the model information storage unit 122.

[0185] The acquisition unit 131 stores the acquired various types of information in the storage unit 120. The acquisition unit 131 stores various types of information in the past communication related information storage unit 121 or the model information storage unit 122.

[0186] The acquisition unit 131 acquires various types of information generated, calculated, and determined by other functional configurations.

[0187] The acquisition unit 131 acquires past communication related information. The acquisition unit 131 acquires communication related information. The acquisition unit 131 acquires sensor information detected by a mobile communication device used by a user. The acquisition unit 131 acquires sensor parameters regarding the sensor information. The acquisition unit 131 acquires communication information indicating the state of the communication quality to each communication network. The acquisition unit 131 acquires communication parameters regarding each communication network in the communication information.

[0188] (Generation Unit 132)

[0189] The generation unit 132 generates various types of information. The generation unit 132 generates various types of information from the storage unit 120. The generation unit 132 generates various types of information from the past communication related information storage unit 121 or the model information storage unit 122.

[0190] The generation unit 132 stores the generated various types of information in the storage unit 120. The generation unit 132 stores various types of information in the past communication related information storage unit 121 or the model information storage unit 122.

[0191] The generation unit 132 generates various types of information acquired, calculated, and determined by other functional configurations. The generation unit 132 generates various types of information based on various types of information acquired, calculated, and determined by other functional configurations.

[0192] The generation unit 132 generates a model. The generation unit 132 learns a model. The generation unit 132 generates a model for causing a computer to function so as to output a score indicating the degree of deterioration of a communication network. The generation unit 132 generates a model that outputs a score indicating the degree of deterioration of a communication network based on the input of communication-related information. The generation unit 132 generates a model using past communication-related information that is determined as a timing at which the communication network should be switched as correct information in the past communication-related information. The generation unit 132 generates a model using past communication-related information that is determined as a timing at which the communication network should not be switched as incorrect information in the past communication-related information. The generation unit 132 generates a model using past communication-related information that has been assigned a correct label as correct information at the corresponding timing. The generation unit 132 generates a model using past communication-related information that has been assigned an incorrect label as incorrect information at the corresponding timing. It is noted that the generation unit 132 can generate a model based on past communication related information that has been assigned correct labels by excluding past communication related information that has been assigned incorrect labels, or can generate a model based on past communication related information that has been assigned correct labels and past communication related information that has been assigned incorrect labels by learning past communication related information that has been assigned incorrect labels as incorrect information.

[0193] (Calculation unit 133)

[0194] The calculation unit 133 calculates various types of information. The calculation unit 133 calculates various types of information from the storage unit 120. The calculation unit 133 calculates various types of information from the past communication related information storage unit 121 or the model information storage unit 122.

[0195] The calculation unit 133 stores the calculated various types of information in the storage unit 120. The calculation unit 133 stores the various types of information in the past communication related information storage unit 121 or the model information storage unit 122.

[0196] The calculation unit 133 calculates various types of information acquired, generated, and determined by other functional configurations. The calculation unit 133 calculates various types of information based on various types of information acquired, generated, and determined by other functional configurations.

[0197] The calculation unit 133 calculates a score indicating the degree of deterioration of the communication network. The calculation unit 133 calculates the score indicating the degree of deterioration of the communication network according to the input of the communication related information. The calculation unit 133 calculates the score indicating the degree of deterioration of the communication network based on the model generated by the generation unit 132.

[0198] (Determination unit 134)

[0199] The determination unit 134 determines various types of information. The determination unit 134 determines various types of information from the storage unit 120. The determination unit 134 determines various types of information from the past communication related information storage unit 121 or the model information storage unit 122.

[0200] The determination unit 134 stores the determined various types of information in the storage unit 120. The determination unit 134 stores the various types of information in the past communication related information storage unit 121 or the model information storage unit 122.

[0201] The determination unit 134 determines various types of information acquired, generated, and calculated by other functional configurations. The determination unit 134 determines various types of information based on various types of information acquired, generated, and calculated by other functional configurations.

[0202] The determination unit 134 determines whether to switch to another communication network among the plurality of communication networks. The determination unit 134 determines whether to switch to another communication network among the plurality of communication networks based on the sensor information and the communication information acquired by the acquisition unit 131 .

[0203] The determination unit 134 determines whether to switch to another network based on sensor information for estimating the state of the user in real time among the sensor information acquired by the acquisition unit 131. For example, the determination unit 134 determines whether to switch to another network based on sensor information indicating the position or movement speed of the user.

[0204] The determination unit 134 determines whether to switch to another network based on sensor information used to infer the state of the user among the sensor information acquired by the acquisition unit 131. The determination unit 134 determines whether to switch to another network based on the context information of the user. For example, the determination unit 134 determines whether to switch to another network based on sensor information used to infer the user's action. For example, the determination unit 134 determines whether to switch to another network based on sensor information used to infer the user's action (such as walking, moving by train, moving by car, going up and down stairs, or going up and down in an elevator).

[0205] The determination unit 134 determines whether to switch the wireless LAN network to the cellular network. For example, the determination unit 134 determines whether to switch the wireless LAN network to the cellular network based on the communication information of the communication performed via the wireless LAN network. In addition, the determination unit 134 determines whether to switch the cellular network to the wireless LAN network. For example, the determination unit 134 determines whether to switch the cellular network to the wireless LAN network based on the communication information of the communication performed via the cellular network. In addition, the determination unit 134 determines whether to switch one cellular network to the other cellular network. For example, the determination unit 134 determines whether to switch one cellular network to the other cellular network based on the communication information of the communication performed via the one cellular network.

[0206] The determination unit 134 determines whether to switch to another communication network based on the communication parameters acquired by the acquisition unit 131. The determination unit 134 determines whether to switch to another communication network based on RSSI, LinkSpeed, packet communication status, etc. as communication parameters.

[0207] The determination unit 134 determines whether to switch to another communication network based on the sensor parameters acquired by the acquisition unit 131 .

[0208] The determination unit 134 takes at least one of the communication parameter and the sensor parameter as input information and uses a learning model that outputs a score indicating a measure of whether to perform switching of the communication network to determine whether to switch to another communication network. The determination unit 134 takes at least one of the communication parameter and the sensor parameter as input information and uses a learning model that outputs a score for each communication network to determine whether to switch to another communication network.

[0209] (Provided by Unit 135)

[0210] The providing unit 135 provides various types of information to the external information processing device. The providing unit 135 sends various types of information to the external information processing device. The providing unit 135 notifies the external information processing device of various types of information. The providing unit 135 distributes various types of information to the external information processing device. The providing unit 135 provides various types of information to other information processing devices such as the terminal device 10.

[0211] The providing unit 135 provides various types of information acquired, generated, and determined by other functional configurations.

[0212] The providing unit 135 provides information about the determination result determined by the determining unit 134. The providing unit 135 provides control information according to the determination result. For example, the providing unit 135 provides control information about switching of the communication network according to the determination result. The providing unit 135 provides information for notifying the user that the communication network is unstable.

[0213] [7. Determine the details of the equipment]

[0214] like Fig. 9 As shown in FIG. 1 , the communication unit 110 of the determination device 100 according to the embodiment has a communication path control unit 111 and implements or executes the function of the information processing described below. Note that the internal configuration of the communication unit 110 is not limited to Fig. 9 The configuration shown in , and may be another configuration as long as it is a configuration that performs information processing described later.

[0215] (Communication Path Control Unit 111)

[0216] The communication path control unit 111 controls various types of information about switching of the communication network. The communication path control unit 111 controls various types of information based on the various types of information about switching of the communication network. For example, the communication path control unit 111 performs switching of the communication network based on a communication carrier switching request. For example, the communication path control unit 111 switches the connection of the communication network from a cellular network (e.g., 5GmmW and Sub6) to Wi-Fi. For example, the communication path control unit 111 switches the connection of the communication network from Wi-Fi to a cellular network. In this way, the communication path control unit 111 selectively connects to a plurality of communication networks and performs communication. Fig. 9 In the illustrated example, a case where the communication path control unit 111 is a part of the communication unit 110 has been illustrated. However, the communication path control unit 111 may have a configuration different from that of the communication unit 110. Specifically, the communication path control unit 111 may be one of other components included in the determination device 100 other than the communication unit 110. For example, the communication path control unit 111 may be one component included in the control unit 130.

[0217] In addition, if Fig. 9 As shown in FIG. 1 , the acquisition unit 131 of the determination device 100 according to the embodiment has a communication parameter acquisition unit 1311 and a sensor information acquisition unit 1312, and implements or executes the following information processing functions. Note that the internal configuration of the acquisition unit 131 is not limited to Fig. 9 The configuration shown in , and may be another configuration as long as it is a configuration that performs information processing described later.

[0218] (Communication Parameter Acquisition Unit 1311)

[0219] The communication parameter acquisition unit 1311 acquires communication information about each communication network. For example, the communication parameter acquisition unit 1311 acquires communication parameters about each communication network.

[0220] (Sensor information acquisition unit 1312)

[0221] The sensor information acquisition unit 1312 acquires sensor information. For example, the sensor information acquisition unit 1312 acquires sensor parameters related to the sensor.

[0222] exist Fig. 9 In the illustrated example, a case where the communication parameter acquisition unit 1311 is a part of the acquisition unit 131 has been illustrated. However, the communication parameter acquisition unit 1311 may have a configuration different from that of the acquisition unit 131. For example, the communication parameter acquisition unit 1311 may be one of other components included in the control unit 130 that are different from the acquisition unit 131. In addition, Fig. 9 In the illustrated example, a case has been illustrated where the sensor information acquiring unit 1312 is a part of the acquiring unit 131. However, the sensor information acquiring unit 1312 may have a configuration different from that of the acquiring unit 131. For example, the sensor information acquiring unit 1312 may be one of other components included in the control unit 130 that is different from the acquiring unit 131.

[0223] [8. Information processing flow]

[0224] Next, we will use Fig.10 The procedure of information processing by the information processing system 1 according to the embodiment is described. Fig.10 is a flowchart illustrating the procedure of information processing by the information processing system 1 according to the embodiment.

[0225] like Fig.10As shown in , the determination device 100 acquires sensor information detected by a mobile communication device used by a user and communication information indicating the state of the communication quality to each communication network (step S201). The determination device 100 uses the acquired sensor information and communication information as input information to calculate a value or score indicating the degree of deterioration of the communication network (step S202). The determination device 100 determines whether the calculated value or score exceeds a predetermined threshold (step S203). When it is determined that the calculated value or score does not exceed the predetermined threshold (step S203; no), the determination device 100 ends the information processing. On the other hand, when it is determined that the calculated value or score exceeds the predetermined threshold (step S203; yes), the determination device 100 changes the connected communication network to another network (step S204).

[0226] [9.Modification]

[0227] The information processing system 1 according to the above-described embodiment can be implemented in various different modes other than the above-described embodiment. Therefore, other embodiments of the information processing system 1 will be described below. Note that the information processing system 1 will be appropriately omitted. Figure 1 and Figure 2 The description of points similar to those of the embodiment shown in FIG.

[0228] [9-1. First modification (another configuration example of the terminal device)]

[0229] In the above example, the case where the terminal device 10 and the determination device 100 are separate devices has been described. However, the terminal device 10 and the determination device 100 may be integrated. Fig.11 Hereinafter, in order to simplify the description, the configuration in the case where the terminal device 10 and the determination device 100 according to the embodiment are integrated will be described as another configuration example of the terminal device 10. Note that description of processes similar to those of the terminal device 10 and the determination device 100 according to the embodiment will be omitted. Fig.11 2 is a diagram illustrating a configuration of a terminal device 20 as another configuration example of the terminal device 10 according to the embodiment. Fig.11 As shown in FIG. 1 , the terminal device 20 has a communication unit 21, an input / output (I / O) unit 22, a control unit 23, and an internal sensor unit 24. Fig.11 As shown in FIG. 1 , the communication unit 21 of the terminal device 20 according to the embodiment may have a communication control unit 211. The communication control unit 211 switches the bearer according to the communication bearer switching request. Fig.12 2 is a diagram illustrating details of the control unit 23. Fig.12As shown in FIG. 1 , the control unit 23 of the terminal device 20 according to the embodiment may have a communication parameter unit 231. The communication parameter unit 231 acquires communication parameters from each carrier. Note that the internal configuration of the control unit 23 may not be limited to Fig.12 The configuration shown in .

[0230] [9-2. Second Amendment (Millimeter Wave Communication)]

[0231] Hereinafter, a case where millimeter wave communication in 5G is used as a communication network will be described. In general, millimeter wave communication in 5G performs communication using beamforming, but it is necessary to adjust the radio wave reception direction as the terminal device 10 moves. Figure 1 In the example shown, the case where the degree of deterioration of the Wi-Fi connection is predicted and the communication network is switched has been illustrated. The determination device 100 can predict the deterioration of the millimeter wave communication quality and select appropriate beamforming. Specifically, the determination device 100 obtains the communication state of the millimeter wave communication during communication and the mobile state of the terminal device 10, predicts the deterioration of the millimeter wave communication quality, and selects appropriate beamforming. In this case, since the communication network complies with the fifth generation of millimeter wave communication, the cellular network is a communication network that complies with the fifth generation of millimeter wave communication.

[0232] The determination device 100 may acquire the movement state of the terminal device 10 through a positioning system such as a magnetic sensor, an air pressure sensor, an acceleration sensor, or GPS / GNSS, for example. Note that the determination device 100 may acquire the movement state of the terminal device 10 not only through the above examples but also through any sensor.

[0233] The determination device 100 can determine the communication state of millimeter wave communication during communication by parameters such as signal strength, coding scheme, number of MIMO, number of communication allocation times, receive / send packet counter value, number of successful transmissions, number of successful receptions, number of retransmissions, number of frame failures, number of interface errors, throughput, cell information, new radio (NR) cell information, NR absolute radio frequency, physical cell id, MCC, MNC, beam ID, reception strength of synchronization signal reference signal, reception quality and S / N, reception strength of CSI signal, reception quality and S / N, ASU and CSI-RSRP. Note that the determination device 100 can determine the communication state of millimeter wave communication during communication not only by the above examples but also by any parameters. For example, the determination device 100 can calculate the disconnection probability of communication in the near future in order to determine the communication state of millimeter wave communication. In this case, when the calculated disconnection probability exceeds a predetermined threshold, the determination device 100 changes the direction of the antenna array or performs a handover to a different beam.

[0234] When it is recognized that the user is walking or staying at a fixed point, the determination device 100 can determine to use millimeter wave communication, and when it is recognized that the user is moving at high speed in a vehicle, etc., the determination device 100 can determine to use a cellular network such as Sub6 or LTE. In this case, the determination device 100 performs determination by measuring the communication quality of each carrier and performing disconnection prediction.

[0235] In the following, we will use Fig.13 The procedure of information processing by the information processing system 1 according to the second modification is described. Fig.13 is a flowchart illustrating the procedure of information processing by the information processing system 1 according to the second modification.

[0236] The determination device 100 determines whether the 5G carrier is in a communicative state (step S301). When the 5G carrier is not in a communicative state (step S301; No), the determination device 100 can end the information processing, or can move to, for example, a handover prediction engine of LTE only. When the 5G carrier is in a communicative state (step S301; Yes), the determination device 100 acquires sensor information detected by a mobile communication device used by a user and communication information indicating the state of the communication quality of millimeter wave communication in 5G (step S302). The determination device 100 uses the acquired sensor information and communication information as input information to calculate a score indicating the degree of deterioration of millimeter wave communication (step S303). The determination device 100 determines whether the calculated score exceeds a predetermined threshold (step S304). For example, the determination device 100 determines whether the calculated score is higher than the score of the currently selected carrier. When it is determined that the calculated score does not exceed the predetermined threshold (step S304; No), the determination device 100 ends the information processing. On the other hand, when it is determined that the calculated score exceeds the predetermined threshold value (step S304; Yes), the determination device 100 requests switching of the communication path (step S305). Specifically, the determination device 100 changes the connected communication network to another network.

[0237] [9-3. Third modification (switching of bearers according to application)]

[0238] Hereinafter, a case where a carrier is switched according to an application to be used will be described. In general, there are cases where cellular is better than using Wi-Fi in terms of latency, such as a case where mobile edge computing (MEC) installed in an operator network can be used. For example, in the case where an online game requires low latency, a carrier with a small amount of latency can be selected. In this case, cellular can be used even in an environment where Wi-Fi can be used. In addition, in the case of optimizing the amount of latency and performing comfortable communication, it is necessary to optimally perform handover.

[0239] The determination device 100 combines sensor information (eg, moving direction, moving speed, and acceleration) through sensors provided inside the terminal device 10, and performs optimal handover or beam selection for a user requesting low latency. Fig.14 The procedure of information processing by the information processing system 1 according to the third modification is described. Fig.14 is a flowchart illustrating the procedure of information processing by the information processing system 1 according to the third modification.

[0240] The determination device 100 acquires sensor information indicating the movement information of the user and application information used in the terminal device 10 (step S401). For example, as a result of activity recognition, the determination device 100 acquires the movement speed of the terminal device 10, and the application used and the amount of delay or throughput required thereof. The determination device 100 selects a carrier with the smallest amount of delay based on the acquired sensor information and application information (step S402). The determination device 100 instructs the terminal device 10 to perform handover to the selected carrier (step S403).

[0241] like Fig.15 As shown in , the determination device 100 can send the moving speed of the terminal device 10, the application used and the delay amount or throughput required by the terminal device 10 to the base station or the cellular network as a result of activity recognition. In addition, the determination device 100 can request the base station or the cellular network to select the optimal carrier based on the sent information. In addition, the determination device 100 can instruct the terminal device 10 to perform a handover to the selected carrier based on the information sent from the base station or the cellular network.

[0242] [9-4. Fourth modification (score calculation for each carrier)]

[0243] In the above-mentioned embodiment, the case where multiple learning models are used for one carrier at the same time has been described. The determination device 100 may generate and use a learning model for each carrier. Specifically, the determination device 100 may generate a learning model for each carrier, calculate a score for each carrier, and predict the communication quality of each carrier in the near future. Fig.16 and 17 Give a description.

[0244] Will use Fig.16An example of a determination process according to the fourth modification is described. The determination device 100 acquires past communication-related information LINF1A (step S501). The determination device 100 acquires a plurality of different cellular information for each carrier. For example, the determination device 100 acquires cellular information P, cellular information Q, and cellular information R. The determination device 100 generates a learning model for each carrier by using different cellular information for each carrier (step S502). For example, the determination device 100 generates a model MP1 based on sensor information and cellular information P. For example, the determination device 100 generates a model MQ1 based on sensor information and cellular information Q. For example, the determination device 100 generates a model MR1 based on sensor information and cellular information R. In addition, the determination device 100 stores all or part of the generated model. For example, the determination device 100 stores all or part of the generated model in a predetermined storage unit. For example, the determination device 100 stores all or part of the generated model in the model information storage unit 122A. In addition, the determination device 100 may store the generated model for each carrier. For example, the determination device 100 may store the generated model in the storage unit of each carrier.

[0245] and Figure 2 Similarly to the example shown in , the determination device 100 acquires the communication related information TINF1A (step S503). Note that the communication related information TINF1A includes cellular information P, cellular information Q and cellular information R as information related to the cellular network that can be acquired by the terminal device 10.

[0246] The determination device 100 inputs each combination of sensor information and cellular information in the acquired communication-related information TINF1A into the corresponding model. For example, the determination device 100 inputs cellular information P and sensor information into the model MP1. In this case, the determination device 100 outputs information indicating the degree of deterioration of the cellular network corresponding to the cellular information P. Fig.16 In the example, the determination device 100 outputs the score indicating the communication quality is 30 as the information indicating the degree of deterioration of the cellular network corresponding to the cellular information P. For example, the determination device 100 inputs the cellular information Q and the sensor information into the model MQ1. In this case, the determination device 100 outputs the information indicating the degree of deterioration of the cellular network corresponding to the cellular information Q. Fig.16 In , the determination device 100 outputs the score indicating the communication quality is 50 as information indicating the degree of deterioration of the cellular network corresponding to the cellular information Q. For example, the determination device 100 inputs the cellular information R and the sensor information into the model MR1. In this case, the determination device 100 outputs information indicating the degree of deterioration of the cellular network corresponding to the cellular information R. Fig.16, the determination device 100 outputs the score indicating that the communication quality is 60 as the information indicating the degree of deterioration of the cellular network corresponding to the cellular information R.

[0247] The determination device 100 inputs a combination of the sensor information and the Wi-Fi information in the acquired communication related information TINF1A into the corresponding model. For example, the determination device 100 inputs the Wi-Fi information and the sensor information into the model MW1. In this case, the determination device 100 outputs information indicating the degree of deterioration of the Wi-Fi connection. Fig.16 , the determination device 100 outputs the score indicating that the communication quality is 45 as information indicating the degree of deterioration of the Wi-Fi connection.

[0248] The determination device 100 selects the optimal communication network based on the output score indicating the communication quality. For example, the determination device 100 selects the communication network with the maximum output score. In the above example, the determination device 100 compares the score 30 of the cellular information P, the score 50 of the cellular information Q, and the score 60 of the cellular information R, and selects the cellular network corresponding to the cellular information R with the maximum score 60. Note that the determination device 100 can select the optimal cellular network based on the output score, compare the optimal cellular network with Wi-Fi, and select the optimal communication network. In the above example, the determination device 100 can select the cellular network corresponding to the cellular information R with the maximum score, compare the score 60 of the selected cellular network with the score 45 of Wi-Fi, and select the cellular network corresponding to the cellular information R with the larger score as the optimal communication network.

[0249] Note that the determination device 100 may use the RTT value as a score indicating the communication quality. In this case, the determination device 100 selects the communication network with the smaller RTT value as the optimal communication network. Using the above example, the determination device 100 selects the cellular network corresponding to the cellular information P with the smallest RTT value among the cellular information P, the cellular information Q, and the cellular information R. In addition, the determination device 100 compares the RTT value 30 of the selected cellular network with the RTT value 45 of Wi-Fi, and selects the cellular network corresponding to the cellular information P with the smaller RTT value as the optimal communication network.

[0250] Fig.17 The diagram shows the use of LTE, Sub6 and mmWave (millimeter wave). Fig.17In a state where the carriers of mmWave, Sub6, and LTE are selectable, the determination device 100 combines the sensor information to calculate the score of the communication quality of each carrier in the near future. Specifically, the determination device 100 inputs the cellular information of LTE into a learning model corresponding to LTE to calculate the score of LTE, and predicts the degree of deterioration of the communication state of LTE. For example, the determination device 100 inputs the cellular information of Sub6 into a learning model corresponding to Sub6, calculates the score of Sub6, and predicts the degree of deterioration of the communication state of Sub6. For example, the determination device 100 inputs the cellular information of mmWave into a learning model corresponding to mmWave to calculate the score of mmWave, and predicts the degree of deterioration of the communication state of mmWave. Fig.17 In the embodiment, the determination device 100 calculates a score of the communication quality of each bearer in the near future in combination with the sensor information in a state where the bearers of mmWave, Sub6, and LTE can communicate with the terminal device 10 .

[0251] Generally speaking, in mmWave carriers, since the throughput is high but the coverage is small, there is a possibility of frequent disconnection. In this case, the determination device 100 simultaneously predicts the communication quality of Sub6 and LTE in the near future, and determines the carrier of the transfer destination from mmWave. In addition, when Wi-Fi is available at the same time, the determination device 100 predicts the communication quality of Wi-Fi in the near future, thereby determining the destination to which the carrier should be switched even when a connection to Wi-Fi is established. Therefore, the determination device 100 can achieve seamless transfer of network carriers and can always continue to select the optimal network.

[0252] In the following, we will use Fig.18 The procedure of information processing by the information processing system 1 according to the fourth modification is described. Fig.18is a flowchart illustrating the process of information processing of the information processing system 1 according to the fourth modification. The determination device 100 acquires sensor information detected by a mobile communication device used by a user and communication information indicating the state of the communication quality of each communication network (step S601). The determination device 100 uses the acquired sensor information and communication information as input information corresponding to each learning model to calculate a score indicating the degree of deterioration of the communication network for each carrier (step S602). The determination device 100 selects the optimal cellular network based on the calculated score (step S603). The determination device 100 determines whether the calculated score is higher than the score of Wi-Fi (step S604). When the calculated score is lower than the score of Wi-Fi, the determination device 100 ends the information processing. When the calculated score is higher than the score of Wi-Fi, the determination device 100 requests the switching of the communication path (step S605). For example, the determination device 100 instructs the terminal device to change to a cellular network.

[0253] Note that in Fig.18 In the above, a process has been described in which the determination device 100 selects the best network from the cellular networks, compares the score of the network with the score of Wi-Fi, and switches the network. Here, a process will be described in which the determination device 100 compares the scores of all communication networks including the cellular network and Wi-Fi at the same time and switches to the communication network with the largest score. In this case, the determination device 100 performs the same process as described above. Fig.18 . In steps S603 and S604, the determination device 100 compares all calculated scores including cellular networks and Wi-Fi and selects the communication network with the maximum score. In step S605, the determination device 100 requests switching to the communication network with the maximum score. For example, the determination device 100 calculates each score indicating the degree of deterioration of each communication network in LTE, Sub6, mmWave, and Wi-Fi, and instructs the terminal device to switch to the communication network with the maximum score.

[0254] [9-5. Fifth modification (downloading training data according to location)]

[0255] In the above-described embodiment, the case where a learning model generated or installed in the terminal device 10 is used has been described. However, a learning model provided from the outside may be used. For example, the determination device 100 may use a learning model provided by updating from the outside, etc. Hereinafter, a case where a learning model is downloaded from the outside based on location information obtained from sensor information and switching is performed based on the downloaded learning model will be described.

[0256] Therefore, the determination device 100 can implement switching of carriers optimized for areas that cannot be learned from general data. For example, the determination device 100 can effectively utilize the wireless LAN point or on-board Wi-Fi on the platform by downloading a learning model optimized for the route the user takes to get on the train. Generally speaking, when the upstream of the on-board Wi-Fi is WiMAX, etc., there is a possibility that the access to the WAN disappears and the network communication disappears when the vehicle enters the tunnel. In this case, etc., the determination device 100 can predict the vehicle entering the tunnel by externally adapting the learning model that is optimal for the route, and can switch to the cellular before the upstream network is disconnected. In addition, the determination device 100 can improve the overall communication quality by adapting as many learning models tuned to offload to Wi-Fi as possible in areas where a large number of people are expected to gather (such as stadiums or events) and the terminal density in the cell increases.

[0257] Fig.19 An example of the determination process according to the fifth modification is illustrated. The determination device 100 estimates the position information of the user based on the sensor data. In this case, the determination device 100 may have a position estimation unit 136 that estimates the position information of the user based on the sensor data. Fig. 20 As shown in , the control unit 130A may further have a position estimation unit 136. The determination device 100 requests a learning model corresponding to the position information of the user and downloads the learning model from the outside. The determination device 100 calculates a score on communication quality by inputting communication information to the learning model downloaded from the outside.

[0258] In the following, we will use Fig.21 The procedure of information processing by the information processing system 1 according to the fifth modification is described. Fig.21is a flowchart illustrating the process of information processing of the information processing system 1 according to the fifth modification. The determination device 100 determines whether the learned model is available (step S701). When the learned model is not available (step S701; No), the determination device 100 may end the information processing, or may use the default score calculator stored in the terminal device 10 or the determination device 100 to calculate the score. When the learned model is available (step S701; Yes), the determination device 100 downloads the learned model from the outside (step S702). The determination device 100 acquires sensor information detected by the mobile communication device used by the user and communication information indicating the state of the communication quality of each communication network (step S703). The determination device 100 calculates the score by using the downloaded learning model using the acquired sensor information and communication information as input information (step S704). The determination device 100 determines whether the calculated score exceeds a predetermined threshold (step S705). When the calculated score does not exceed the predetermined threshold (step S705; No), the determination device 100 ends the information processing. When the calculated score exceeds a predetermined threshold value (step S705; Yes), the determination device 100 requests switching of the communication path (step S706). For example, the determination device 100 changes the connected communication network to another network.

[0259] [9-6. Sixth revision (score calculation on the cloud 1)]

[0260] In the above-mentioned embodiment, the case of using the learning model in the terminal device 10 has been described. However, it is possible to determine that the device 100 can use an external learning model. In addition, in the embodiment according to the above-mentioned fifth modification, the case of using a learning model provided by downloading from the outside, etc. has been described. However, in the embodiment according to the sixth modification, the case of determining that the device 100 uses an external learning model by providing input information to the outside is described. For example, the device 100 uses a learning model on a cloud server, a mobile edge computing server, etc. Note that the external according to the sixth modification is not limited to the cloud or mobile edge computing, and can be any medium as long as it is a medium that can store the learning model. In this case, the providing unit 135 provides the sensor information and the communication information to a medium other than the mobile communication device that outputs the score.

[0261] Will use Fig. 22An example of determination processing according to the sixth modification is described. The determination device 100 uploads the communication information and sensor information of each carrier acquired from the terminal device 10 to the outside at a predetermined interval. Note that the predetermined interval may be a constant interval (such as every few seconds, every few hours, or every few days), or may be an interval that varies based on a predetermined condition. For example, whenever the amount of information acquired from the terminal device 10 meets a predetermined threshold, the determination device 100 may upload the information to the outside. In addition, the determination device 100 may upload the information to the outside by any format or method, and may be performed by using, for example, a JSON format, a REST API, etc. In this case, the outside outputs a score by using a learning model stored in the outside with the communication information and sensor information of each carrier provided from the determination device 100 as input information. In addition, the determination device 100 receives the result output by the external learning model from the outside. The determination device 100 determines whether to switch the carrier of the terminal device 10 by comparing the received score with a predetermined threshold. In addition, the determination device 100 may determine whether to switch the carrier of the terminal device 10 by comparing the score calculated based on the received score with a predetermined threshold. For example, the determination device 100 can determine whether to switch the carrier of the terminal device 10 by comparing the score calculated by multiplying the received score by the weight based on the predetermined algorithm with the predetermined threshold. For example, the determination device 100 can determine whether to switch the carrier of the terminal device 10 by comparing the score obtained by calculating the received score and the weight of the information acquired by the determination device 100 by the predetermined algorithm with the predetermined threshold. When the determination device 100 determines to switch the carrier of the terminal device 100, the determination device 100 requests the communication unit 110 to switch the communication path. For example, the determination device 100 requests the communication path control unit to switch the communication path. Therefore, even a large-scale score calculation in which the amount of calculation within the terminal device 10 is insufficient, the determination device 100 can be implemented by using external computing resources.

[0262] The determination device 100 may determine whether the result provided from the outside and the result output by the determination device 100 deviate from each other. When the score provided from the outside and the score output by the determination device 100 deviate from each other by a predetermined threshold or more, the determination device 100 may determine the switching of the carrier by using the score output by the determination device 100 instead of the score provided from the outside. In addition, in the case where the time before and after the input information in the calculation by the outside and the calculation by the determination device 100 is different, the determination device 100 may determine whether the result provided from the outside and the result output by the determination device 100 deviate from each other.

[0263] In the following, we will use Fig.23 The procedure of information processing by the information processing system 1 according to the sixth modification is described. Fig.23is a flowchart illustrating the process of information processing of the information processing system 1 according to the sixth modification. The determination device 100 acquires sensor information detected by the mobile communication device used by the user and communication information indicating the state of the communication quality to each communication network (step S801). The determination device 100 uploads the acquired sensor information and communication information to the outside (step S802). The determination device 100 receives a score calculated externally (step S803). The determination device 100 determines whether the received score exceeds a predetermined threshold value (step S804). When the received score does not exceed the predetermined threshold value (step S804; no), the determination device 100 ends the information processing. When the received score exceeds the predetermined threshold value (step S804; yes), the determination device 100 requests switching of the communication path (step S805).

[0264] [9-7. Seventh revision (score calculation on the cloud 2)

[0265] In the embodiment according to the sixth modification, the case where a learning model stored externally is used has been described. However, in the embodiment according to the seventh modification, the case where the learning model is learned externally such as in the cloud is described. For example, a score calculator including a single switching model is used as a unified switching standard, rather than as an engine optimized for the user's action pattern or the location where the user is located. In the following, the description of the processing similar to that of the sixth modification will be appropriately omitted. Fig.24 An example of determination processing according to the seventh modification is described. When the handover cannot be performed normally in the learning model stored in the terminal device 10, the determination device 100 uploads the information when the handover fails (for example, communication information, location information, and information of the SSID of the connection destination) to the outside. For example, the determination device 100 records the time point of the message outputting the network error output by the application, and detects the situation where the handover cannot be performed normally. Note that the determination device 100 is not limited to recording the time point when the error message is output, and can detect how the handover cannot be performed normally. Specifically, the determination device 100 uploads information based on the network information and location information in which an error occurred within a predetermined time from the handover failure. In this case, the external to be uploaded can learn location information such as latitude and longitude as a parameter, or can use data uploaded in an area limited to a predetermined area to learn other engines. Therefore, since the learning data at the same location are aggregated, the determination device 100 can realize the determination based on the information output from the learning model that is more suitable for the place. In this case, the providing unit 135 uses different learning models learned for each area to provide sensor information and communication information to a medium other than the mobile communication device that outputs the score.

[0266] [9-8. Others (determination other than determination of passing score)]

[0267] In the above-mentioned embodiment, the case where the switching process of the communication network is performed according to whether the score calculated by the determination device 100 exceeds a predetermined threshold value has been described. The determination device 100 is not limited to this example, and a specific condition can be used to perform the switching process of the communication network. Specifically, the determination device 100 can perform the switching process of the communication network by prohibiting switching to a network pre-defined as a default network so as not to switch the communication network. For example, when at least one of the communication parameters acquired by the acquisition unit 131 does not meet the predetermined condition after the communication network switching as a specific condition, the determination device 100 can perform the switching process of the communication network so that the switching to the default network is not performed again. For example, in the case where the RSSI does not change a predetermined threshold value or more, the determination device 100 can determine that there is no environmental change and perform the switching process of the communication network so as not to perform the switching to the default network again. Therefore, since the determination device 100 can prevent the jitter of repeated switching, the determination device 100 can perform a more advanced switching control of the communication network. Therefore, the determination device 100 can achieve the effect of installing a fail-safe (Fail Safe) therein.

[0268] [10. Hardware Configuration]

[0269] In addition, the terminal device 10, the information providing device 50 and the determination device 100 according to the above-mentioned embodiment are composed of, for example, Fig.25 The configuration shown in FIG. 1 is implemented by a computer 1000 . Fig.25 1 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the terminal device 10, the information providing device 50, and the determination device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a medium interface (I / F) 1700.

[0270] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts, a program depending on the hardware of the computer 1000, and the like.

[0271] HDD 1400 stores programs executed by CPU 1100, data used by the programs, etc. Communication interface 1500 receives data from other devices via a predetermined communication network, transmits data to CPU 1100, and transmits data generated by CPU 1100 to other devices via a predetermined communication network.

[0272] The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs generated data to the output device via the input / output interface 1600.

[0273] The medium interface 1700 reads a program or data stored in the recording medium 1800, and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 to the RAM 1200 via the medium interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a digital versatile disk (DVD) or a phase-change rewritable disk (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0274] For example, in the case where the computer 1000 is used as the terminal device 10, the information providing device 50, and the determining device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control units 14, 53, and 130 by executing the programs loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes the programs. However, as another example, the CPU 1100 may acquire these programs from other devices via a predetermined communication network.

[0275] [11. Others]

[0276] In addition, all or part of the processing described as being automatically performed among the processing described in the above embodiments and modifications may be performed manually, or all or part of the processing described as being manually performed may be automatically performed by a known method. In addition, unless otherwise specified, the processing procedures, specific names, and information including various data and parameters shown in the document and the drawings may be changed arbitrarily. For example, the various types of information illustrated in each figure are not limited to the illustrated information.

[0277] In addition, each component of each device shown in the drawings is conceptual in function and is not necessarily physically configured as shown in the drawings. That is, the specific form of distribution and integration of each device is not limited to the illustrated form, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0278] Furthermore, the above-described embodiments and modifications can be appropriately combined within a range not inconsistent with the processing contents.

[0279] Although some embodiments of the present application have been described in detail based on the drawings, these are merely examples, and the present invention may be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the disclosure of the present invention.

[0280] In addition, the above-mentioned "part (section), module or unit)" can be replaced by "mechanism", "circuit", etc. For example, the acquisition unit can be replaced by an acquisition mechanism or an acquisition circuit.

[0281] Note that the present technology can also adopt the following configurations. (1)

[0283] A determination device, comprising:

[0284] a communication unit that selectively connects to and communicates with a plurality of communication networks;

[0285] an acquisition unit that acquires sensor information detected by a mobile communication device used by a user and communication information indicating a state of communication quality to each communication network; and

[0286] A determination unit determines whether to switch to another communication network among the plurality of communication networks based on the sensor information and the communication information acquired by the acquisition unit. (2)

[0288] The determination device according to (1), wherein

[0289] The determination unit determines whether to switch to the other communication network based on sensor information indicating a state of a user among the sensor information acquired by the acquisition unit. (3)

[0291] The determination device according to (1) or (2), wherein

[0292] The determination unit determines whether to switch to the other communication network based on sensor information indicating a moving speed of a user. (4)

[0294] The determination device according to any one of (1) to (3), wherein

[0295] The determination unit determines whether to switch to the other communication network based on context information of the user estimated from the state of the user in the sensor information acquired by the acquisition unit. (5)

[0297] The determination device according to any one of (1) to (4), wherein

[0298] The plurality of communication networks include a wireless LAN network via a wireless LAN base station and a cellular network via a cellular communication base station, and

[0299] The determination unit determines whether to switch the wireless LAN network to a cellular network based on the communication information of the communication performed via the wireless LAN network. (6)

[0301] The determination device according to (5), wherein

[0302] The determination unit determines whether to switch to the other communication network based on at least one of RSSI, LinkSpeed, or packet communication status as the communication information. (7)

[0304] The determination device according to any one of (1) to (6), wherein

[0305] The determination unit determines whether to switch to the other communication network using a learning model that outputs a score indicating a measure of whether to perform switching of the communication network, taking at least one of the communication information and the sensor information as input information. (8)

[0307] The determination device according to any one of (1) to (7), wherein

[0308] The determination unit determines whether to switch to the other communication network using a learning model that outputs a score regarding the communication quality of each communication network, taking at least one of the communication information and the sensor information as input information. (9)

[0310] The determination device according to any one of (1) to (8), wherein

[0311] The determination unit uses at least one of the communication information and the sensor information as input information and uses a plurality of learning models that output scores corresponding to the respective communication networks to determine whether to switch to the other communication network. (10)

[0313] The determination device according to (9), wherein

[0314] The determination unit determines switching to a communication network having a maximum score among the plurality of communication networks using the plurality of learning models. (11)

[0316] The determination device according to any one of (1) to (10), wherein

[0317] The determination unit determines to switch to a communication network having a minimum delay amount based on throughput among the plurality of communication networks. (12)

[0319] The determination device according to any one of (1) to (11), further comprising:

[0320] a providing unit that provides the sensor information and communication information acquired by the acquiring unit to a device other than the mobile communication device that outputs the score, wherein

[0321] The determination unit determines whether to switch to the other communication network based on a score calculated by a device other than the mobile communication device. (13)

[0323] The determination device according to (12), wherein

[0324] The providing unit provides the sensor information and the communication information acquired by the acquiring unit to a device other than the mobile communication device that outputs a score using a different learning model learned for each area. (14)

[0326] The determination device according to (5), wherein

[0327] The cellular network is a communication network that complies with the fifth generation communication standard. (15)

[0329] The determination device according to (5), wherein

[0330] The cellular network is a communication network compliant with fifth-generation millimeter wave communications. (16)

[0332] A determination method comprising:

[0333] causing a computer to selectively connect to and communicate with a plurality of communication networks;

[0334] causing the computer to acquire sensor information detected by a mobile communication device used by a user and communication information to each communication network; and

[0335] The computer is caused to determine whether to switch to another communication network among the plurality of communication networks based on the acquired sensor information and communication information. (17)

[0337] A program for causing a computer to:

[0338] selectively connect to and communicate with a plurality of communication networks;

[0339] acquiring sensor information detected by a mobile communication device used by a user and communication information to each communication network; and

[0340] Whether to switch to another communication network among the plurality of communication networks is determined based on the acquired sensor information and communication information.

[0341] Label list

[0342] 1 Information Processing System

[0343] 10 Terminal Equipment

[0344] 50 Information provision equipment

[0345] 100 Confirm device

[0346] 110 Communication unit

[0347] 111 Communication path control unit

[0348] 120 storage units

[0349] 121 Storage unit for information related to past communications

[0350] 122 Model information storage unit

[0351] 130 Control unit

[0352] 131 Get Unit

[0353] 1311 Communication parameter acquisition unit

[0354] 1312 Sensor information acquisition unit

[0355] 132 Generation Unit

[0356] 133 Computing Unit

[0357] 134 Determine unit

[0358] 135 units provided

[0359] 136 Position estimation unit

[0360] N Network

Claims

1. A determination device, comprising: a communication unit that selectively connects to and communicates with a plurality of communication networks; an acquisition unit that acquires current sensor information detected by a mobile communication device used by a user and current communication information indicating a state of communication quality between each of the plurality of communication networks and the mobile communication device, and acquires past communication-related information including sensor information and communication information acquired in the past on the mobile communication device and other mobile communication devices; a generating unit that generates a learning model based on the past communication related information to which the correct label has been assigned and the past communication related information to which the incorrect label has been assigned, by learning the past communication related information to which the incorrect label has been assigned as incorrect information; as well as a determining unit that receives a score indicating a degree of deterioration of the communication network output by the learning model based on the current sensor information and the current communication information acquired by the acquiring unit, and determines whether to switch the communication network of the mobile communication device to another communication network other than the currently connected communication network among the plurality of communication networks based on whether the score exceeds a predetermined condition about a predetermined threshold for switching the communication path, Among them, the determination unit is capable of changing the predetermined condition according to the sensor information. When it is determined according to the sensor information that the user is moving, the predetermined threshold is reduced to make it easier to switch the communication path. When it is determined according to the sensor information that the user is not moving or stopped, the predetermined threshold is increased to make it difficult to switch the communication path so as to use the currently connected communication network as much as possible.

2. The determination device according to claim 1, wherein The determination unit determines whether to switch to the other communication network based on sensor information indicating a state of a user among the sensor information acquired by the acquisition unit.

3. The determination device according to claim 2, wherein The determination unit determines whether to switch to the other communication network based on sensor information indicating a moving speed of a user.

4. The determination device according to claim 1, wherein The determination unit determines whether to switch to the other communication network based on context information of the user estimated from the state of the user in the sensor information acquired by the acquisition unit.

5. The determination device according to claim 1, wherein The plurality of communication networks include a wireless LAN network via a wireless LAN base station and a cellular network via a cellular communication base station, and The determination unit determines whether to switch the wireless LAN network to a cellular network based on the communication information of the communication performed via the wireless LAN network.

6. The determination device according to claim 5, wherein The determination unit determines whether to switch to the other communication network based on at least one of RSSI, LinkSpeed, or packet communication status as the communication information.

7. The determination device according to claim 1, wherein The determination unit determines whether to switch to the other communication network using a learning model that outputs a score indicating a measure of whether to perform switching of the communication network, taking at least one of the communication information and the sensor information as input information.

8. The determination device according to claim 1, wherein The determination unit determines whether to switch to the other communication network using a learning model that outputs a score regarding the communication quality of each communication network, taking at least one of the communication information and the sensor information as input information.

9. The determination device according to claim 1, wherein The determination unit uses at least one of the communication information and the sensor information as input information and uses a plurality of learning models that output scores corresponding to the respective communication networks to determine whether to switch to the other communication network.

10. The determination device according to claim 9, wherein The determination unit determines switching to a communication network having a maximum score among the plurality of communication networks using the plurality of learning models.

11. The determination device according to claim 1, wherein The determination unit determines to switch to a communication network having a minimum delay amount based on throughput among the plurality of communication networks.

12. The determination device according to claim 7, further comprising: a providing unit that provides the sensor information and communication information acquired by the acquiring unit to a device other than the mobile communication device that outputs the score, wherein The determination unit determines whether to switch to the other communication network based on a score calculated by a device other than the mobile communication device.

13. The determination device according to claim 12, wherein The providing unit provides the sensor information and the communication information acquired by the acquiring unit to a device other than the mobile communication device that outputs a score using a different learning model learned for each area.

14. The determination device according to claim 5, wherein The cellular network is a communication network that complies with the fifth generation communication standard.

15. The determination device according to claim 5, wherein The cellular network is a communication network compliant with fifth-generation millimeter wave communications.

16. A determination method, comprising: causing a computer to selectively connect to and communicate with a plurality of communication networks; causing the computer to acquire current sensor information detected by a mobile communication device used by a user and current communication information indicating a state of communication quality between each of the plurality of communication networks and the mobile communication device, and to acquire past communication-related information including sensor information and communication information acquired in the past on the mobile communication device and other mobile communication devices; causing the computer to generate a learning model based on the past communication-related information to which the correct label has been assigned and the past communication-related information to which the incorrect label has been assigned by learning the past communication-related information to which the incorrect label has been assigned as incorrect information; as well as causing the computer to input the acquired current sensor information and current communication information into the learning model, receive a score indicating the degree of deterioration of the communication network output by the learning model according to the current sensor information and the current communication information, and determine whether to switch the communication network of the mobile communication device to another communication network other than the currently connected communication network among the plurality of communication networks according to whether the score exceeds a predetermined condition about a predetermined threshold for switching the communication path, In which, the computer is able to change the predetermined condition according to the sensor information, and when it is determined according to the sensor information that the user is moving, the predetermined threshold is reduced to make it easier to switch the communication path, and when it is determined according to the sensor information that the user is not moving or stopped, the predetermined threshold is increased to make it difficult to switch the communication path so as to use the currently connected communication network as much as possible.

17. A computer program product storing a determination program for causing a computer to perform the following operations: selectively connect to and communicate with a plurality of communication networks; acquiring current sensor information detected by a mobile communication device used by a user and current communication information indicating a state of communication quality between each of the plurality of communication networks and the mobile communication device, and acquiring past communication-related information including sensor information and communication information acquired in the past on the mobile communication device and other mobile communication devices; generating a learning model based on the past communication-related information to which the correct label has been assigned and the past communication-related information to which the incorrect label has been assigned, by learning the past communication-related information to which the incorrect label has been assigned as incorrect information; as well as inputting the acquired current sensor information and current communication information into the learning model, receiving a score indicating the degree of deterioration of the communication network output by the learning model based on the current sensor information and the current communication information, and determining whether to switch the communication network of the mobile communication device to another communication network other than the currently connected communication network among the plurality of communication networks according to whether the score exceeds a predetermined condition about a predetermined threshold for switching the communication path, Among them, the predetermined condition can be changed according to the sensor information. When it is determined according to the sensor information that the user is moving, the predetermined threshold is reduced to make it easier to switch the communication path. When it is determined according to the sensor information that the user is not moving or stopped, the predetermined threshold is increased to make it difficult to switch the communication path so as to use the currently connected communication network as much as possible.

Images