Mobile communication system and communication method

The mobile communication system automatically selects the optimal SIM profile using reinforcement learning and neural networks to adapt to network conditions, addressing the need for manual switching in conventional multi-profile SIMs and enhancing connectivity.

JP2024158091AActive Publication Date: 2024-11-08INTERNET INITIATIVE JAPAN INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2023072960
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-27
Publication Date
2024-11-08
Estimated Expiration
2043-04-27

AI Technical Summary

Technical Problem

Conventional multi-profile SIMs require manual profile switching and lack automatic adaptation based on communication status, leading to suboptimal network connectivity.

Method used

A mobile communication system with a SIM profile switching device that employs reinforcement learning to manage communication status, determine remuneration, and automatically select the optimal SIM profile based on network conditions, using a neural network to learn and update profile selection.

Benefits of technology

Enables automatic and optimal SIM profile switching according to network conditions, ensuring seamless and efficient communication by selecting the best network profile for the user terminal.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158091000001_ABST
    Figure 2024158091000001_ABST
Patent Text Reader

Abstract

To allow profiles to be automatically switched depending on communication conditions of mobile phone networks in a multi-profile SIM.SOLUTION: A mobile communication system includes: a user terminal that is equipped with a multi-profile SIM; a plurality of mobile operator networks with which the user terminal can communicate; and a SIM profile switching device that is connected to the user terminal and the plurality of mobile operator networks. The SIM profile switching device includes a reward determination unit that determines a reward in reinforcement learning based on the communication conditions of each of the plurality of mobile operator networks. The user terminal includes: a learning model that is configured to learn to select an optimal SIM profile by reinforcement learning based on a state of the user terminal and the reward; and a SIM profile selection unit that selects a SIM profile based on the state of the user terminal using the learning model.SELECTED DRAWING: Figure 7
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a mobile communication system and a communication method, and in particular to profile switching in a multi-profile SIM. [Background technology]

[0002] Multi-profile SIMs have been developed that enable user terminals such as mobile phone terminals and smartphones to connect to multiple mobile phone networks with one SIM card (see, for example, Non-Patent Document 1). A multi-profile SIM holds profiles (information for connecting to mobile phone networks) of multiple telecommunications carriers in one SIM card, and the user terminal can switch between these multiple profiles. This makes it possible to ensure communication by switching the profile in the SIM card and connecting to a different mobile phone network, for example, in the event of a communication failure. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] "IIJ develops multi-profile SIM that can connect to multiple mobile phone networks with one SIM card", [online], Internet Initiative Japan Inc., [Retrieved April 24, 2023], Internet<https: / / www.iij.ad.jp / news / pressrelease / 2022 / 1025.html> Summary of the Invention [Problem to be solved by the invention]

[0004] However, with conventional multi-profile SIMs, the user of the user terminal must manually switch profiles, and automatic profile switching according to the communication conditions of the mobile phone network has not been realized. [Means for solving the problem]

[0005] According to one aspect of the present invention, there is provided a mobile communication system comprising: a user terminal equipped with a multi-profile SIM; a plurality of mobile operator networks with which the user terminal can communicate; and a SIM profile switching device connected to the user terminal and the plurality of mobile operator networks, the SIM profile switching device comprising: a communication status management unit that manages a communication status for each of the plurality of mobile operator networks; a reward determination unit that determines a reward in reinforcement learning based on the communication status of each of the plurality of mobile operator networks, the reward being related to a selection of a SIM profile to be used by the user terminal; and a transmission unit that transmits the reward to the user terminal, and the user terminal comprises: a learning model configured to learn to select an optimal SIM profile by reinforcement learning based on a state of the user terminal and the reward; a SIM profile selection unit that selects a SIM profile based on the state of the user terminal using the learning model; and a communication unit that communicates with one of the plurality of mobile operator networks using the selected SIM profile.

[0006] In addition, according to one aspect of the present invention, when the communication conditions of a mobile operator network corresponding to a SIM profile currently used by the user terminal are good, the reward determination unit may determine the reward so that the reward value for the SIM profile is maximized.

[0007] In addition, according to one aspect of the present invention, when the communication conditions of a mobile operator network corresponding to a SIM profile currently used by the user terminal are not good and the communication conditions of another mobile operator network are good, the reward determination unit may determine the reward so that the reward value for the SIM profile corresponding to the other mobile operator network is maximized.

[0008] According to another aspect of the present invention, the learning model is t An action a selects each SIM profile from among multiple SIM profiles using the input t The action value Q(s t ,a t ) may be a model constructed by a neural network based on deep reinforcement learning, with the output being

[0009] In addition, according to one embodiment of the present invention, when the communication conditions of the mobile operator network corresponding to the SIM profile currently used by the user terminal are good, the learning model may be trained using the maximum action value among multiple action values ​​output from the neural network.

[0010] In addition, according to one aspect of the present invention, when the communication conditions of a mobile operator network corresponding to a SIM profile currently used by the user terminal are not good, but the communication conditions of another mobile operator network are good, the learning model may be trained using an action value corresponding to the SIM profile of the other mobile operator network among the multiple action values ​​output from the neural network.

[0011] According to one aspect of the present invention, there is provided a communication method in a mobile communication system including a user terminal equipped with a multi-profile SIM, a plurality of mobile operator networks with which the user terminal can communicate, and a SIM profile switching device connected to the user terminal and the plurality of mobile operator networks, the communication method including the steps of: the SIM profile switching device acquiring a communication status for each of the plurality of mobile operator networks; the SIM profile switching device determining a reward in reinforcement learning based on the communication status of each of the plurality of mobile operator networks, the reward being related to a selection of a SIM profile to be used by the user terminal; the SIM profile switching device transmitting the reward to the user terminal; the user terminal training a learning model to select an optimal SIM profile by reinforcement learning based on a state of the user terminal and the reward; the user terminal using the learning model to select a SIM profile based on the state of the user terminal; and the user terminal communicating with one of the plurality of mobile operator networks using the selected SIM profile. Effect of the Invention

[0012] According to the present invention, a user terminal can select an optimum SIM profile from among a plurality of SIM profiles stored in a SIM card according to the communication conditions of a mobile operator network, and perform communication. [Brief description of the drawings]

[0013] [Figure 1] 1 is a network configuration diagram of a mobile communication system according to an embodiment. [Diagram 2] FIG. 11 is a network configuration diagram of a mobile communication system according to another embodiment. [Diagram 3] FIG. 2 is a schematic diagram showing state transitions of a user terminal; [Figure 4]2 is a block diagram showing functional configurations of a SIM profile switching device and a user terminal according to an embodiment of the present invention. FIG. [Diagram 5] FIG. 1 is a diagram showing an example of a learning model (DQN). [Figure 6] FIG. 13 is a diagram showing another example of a learning model (Fixed Target Q-Network). [Figure 7] 5 is a flowchart showing the operation of a SIM profile switching device and a user terminal according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0015] 1 is a network configuration diagram of a mobile communication system 10 according to an embodiment of the present invention. The mobile communication system 10 includes a user terminal 100, a first mobile operator network MN1, a second mobile operator network MN2, and a SIM profile switching device 400. Each of the mobile operator networks MN1 and MN2 includes a radio access network 200 and a core network 300. In the mobile communication system 10, the user terminal 100 can communicate with a network such as the Internet 500 via the radio access networks 200 and the core network 300 of the mobile operator networks MN1 and MN2. The number of mobile operator networks is not limited to two and may be any number.

[0016] The user terminal 100 is a wireless communication device such as a mobile phone terminal or a smartphone. The user terminal 100 includes one SIM card 110, and multiple SIM profiles are stored in the SIM card 110. The SIM profile is information for the user terminal 100 to connect to a mobile operator network. In the example of FIG. 1, the user terminal 100 has two SIM profiles SP1 and SP2 in the SIM card 110. The SIM profile SP1 corresponds to a first mobile operator network MN1, and the SIM profile SP2 corresponds to a second mobile operator network MN2. The user terminal 100 can connect to the first mobile operator network MN1 using the SIM profile SP1, and can connect to the second mobile operator network MN2 using the SIM profile SP2. The number of SIM profiles held in the SIM card 110 may be more than two.

[0017] The SIM profile switching device 400 is a device that controls switching of SIM profiles in the user terminal 100. The SIM profile switching device 400 is configured as a computer equipped with a processor and a memory, and a predetermined function is realized by the processor reading and executing a program stored in the memory. The function and operation of the SIM profile switching device 400 will be described in detail below.

[0018] In the mobile communication system 10 of Fig. 1, a first mobile operator network MN1 and a second mobile operator network MN2 are both compliant with the fifth generation (5G) communication standard. A radio access network (NG-RAN: Next Generation Radio Access Network) 200 includes a plurality of base stations. A core network 300 includes the following nodes: an Access and Mobility Management Function (AMF) 302, a Session Management Function (SMF) 304, a Policy Control Function (PCF) 306, a Unified Data Management (UDM) 308, a Unified Data Repository (UDR) 310, and a User Plane Function (UPF) 312.

[0019] The AMF 302 is a node that provides a mobility control function and performs mobility control such as location registration, paging, and handover. The SMF 304 is a node that provides a session management function and performs session maintenance, establishment, modification, and release. The PCF 306 is a node that provides a policy control function related to quality such as data transfer speed and delay time. The UDM 308 is a node that manages user contract information and authentication information. The UDR 310 is a node that stores a subscriber database that holds the identification number and location information of the user terminal. The UPF 312 is a node that communicates user data with the user terminal. Each of these nodes complies with the 5G communication standard, and detailed explanations thereof will be omitted here.

[0020] Either or both of the first mobile operator network MN1 and the second mobile operator network MN2 may be compliant with a fourth generation (4G) communication standard. FIG. 2 is a network configuration diagram of a mobile communication system 10 in which the first mobile operator network MN1 is compliant with a 5G communication standard and the second mobile operator network MN2 is compliant with a 4G communication standard. In the mobile communication system 10 of FIG. 2, a radio access network 200 of the second mobile operator network MN2 is an E-UTRAN (Evolved Universal Terrestrial Radio Access Network). In addition, a core network 300 of the second mobile operator network MN2 includes the following nodes: a Mobility Management Entity (MME) 314, a Serving Gateway (SGW) 316, a Packet data network Gateway-User Plane (PGW-U) 318, a Packet data network Gateway-Control Plane (PGW-C) 320, a Policy and Charging Rules Function (PCRF) 322, a Home Subscriber Server (HSS) 324, and a UDR 326. These comply with 4G communication standards, and detailed explanations will be omitted here.

[0021] 3 is a schematic diagram showing state transitions of the user terminal 100. The state of the user terminal 100 changes from state s1 to state s2, from state s2 to state s3, ..., state s t-1 From state s t To, state s t From state s t+1 Between each state, the user terminal 100 transitions to N actions a1, a2, ..., a N For example, the user terminal 100 may be in state s t-1 In the new state s t Then, it transitions to state s t In the state s t+1The user terminal 100 can transition to a state s of 100. Possible actions of the user terminal 100 include selecting one SIM profile from among a plurality of SIM profiles. For example, an action a1 of the user terminal 100 may correspond to selecting a SIM profile SP1 corresponding to a first mobile operator network MN1, an action a2 of the user terminal 100 may correspond to selecting a SIM profile SP2 corresponding to a second mobile operator network MN2, and so on. Note that the number of possible actions N is equal to the number of SIM profiles held in the SIM card 110 of the user terminal 100. The state s of the user terminal 100 can be selected from a plurality of SIM profiles. t may include, for example, RRC IDLE, RRC INACTIVE, RRC CONNECTED, etc., as specified by 3GPP (registered trademark).

[0022] 4 is a block diagram showing functional configurations of a SIM profile switching device 400 and a user terminal 100 in the mobile communication system 10. The SIM profile switching device 400 includes a user terminal information management unit 402, a communication status management unit 404, a reward determination unit 406, and a transmission unit 408. The user terminal 100 includes a learning model 102, a SIM profile selection unit 104, and a communication unit 106.

[0023] The user terminal information management unit 402 of the SIM profile switching device 400 receives the status s of the user terminal 100 from the user terminal 100. t and the action a selected by the user terminal 100 i (i is any of 1, 2, ..., N). The user terminal information management unit 402 is further configured to manage all possible states of the user terminal 100 and information regarding which state the user terminal 100 transitions to next when each action is taken in each state (for example, a state transition diagram as shown in FIG. 3).

[0024] The communication status management unit 404 of the SIM profile switching device 400 is configured to manage the communication status of each of a plurality of mobile operator networks in the mobile communication system 10. For example, the communication status management unit 404 periodically collects various information including the CPU usage rate of each of the NG-RAN 200, the AMF 302, the UDM 308, the UDR 310, and the UPF 312 in the mobile operator networks MN1 and MN2, the traffic volume of each of these devices, and fault occurrence information, and is able to grasp the communication status of each of the mobile operator networks MN1 and MN2 (for example, whether or not the communication band is tight and congestion is likely to occur, etc.) based on the collected information.

[0025] The reward determination unit 406 of the SIM profile switching device 400 is configured to determine a reward for learning an optimal SIM profile in the user terminal 100, based on the communication status of each mobile operator network identified by the communication status management unit 404. Specifically, the reward determination unit 406 determines a reward such that a reward value is high (e.g., maximum) for an action of selecting a SIM profile of a mobile operator network with a good communication status.

[0026] For example, when the SIM profile currently used by the user terminal 100 is the SIM profile SP1 of the first mobile operator network MN1 and the communication status of the first mobile operator network MN1 is good, the reward determination unit 406 assigns a reward value of “1” to the action a1 that is the action of selecting the SIM profile SP1, and assigns a reward value of “1” to all other actions a1. jFor example, if the SIM profile currently used by the user terminal 100 is the SIM profile SP1 of the first mobile operator network MN1, but the communication status of the first mobile operator network MN1 is not good and the communication status of the second mobile operator network MN2 is good, the reward determination unit 406 may assign a reward value of "1" to the action a2 that is the action of selecting the SIM profile SP2 corresponding to the second mobile operator network MN2, and assign a reward value of "0" to all other actions a2. j The reward may be determined to have a reward value of "0" for (j ≠ 2).

[0027] The transmission unit 408 of the SIM profile switching device 400 transmits the reward determined by the reward determination unit 406 and the state s of the user terminal 100 after the transition caused by the action of the user terminal 100. t+1 and to the user terminal 100. t+1 The user terminal information management unit 402 stores the current state s t and the current state s t Action selected in a i The suffix can be specified by specifying

[0028] In addition, communication between the SIM profile switching device 400 and the user terminal 100 (transmission of user terminal information from the user terminal 100 to the SIM profile switching device 400, and transmission of rewards and post-transition states from the SIM profile switching device 400 to the user terminal 100) is performed via a U-plane (user plane) communication path of the mobile operator network currently being used by the user terminal 100.

[0029] The learning model 102 of the user terminal 100 is configured to learn to select an optimal SIM profile by reinforcement learning based on the state of the user terminal 100 and the reward given by the SIM profile switching device 400. For example, as the learning model 102, as shown in FIG.t is input to the input layer, and the state s t All actions that the user terminal 100 can take in (selection of any one of a plurality of SIM profiles) a t The action value Q(s t ,a t A neural network based on DQN (Deep Q-Network) configured to output an action value Q(s) from each node of the output layer can be applied. Also, as shown in FIG. 6, the learning model 102 may be based on a Fixed Target Q-Network using two neural networks (main network and target network) with the same configuration as in FIG. 5. In the DQN in FIG. 5 and the Fixed Target Q-Network in FIG. 6, the action value Q(s) output from the output layer is t ,a t ) and the reward provided by the SIM profile switching device 400 to update the parameters (weights and thresholds) of the neural network, thereby learning the learning model 102.

[0030] The SIM profile selection unit 104 of the user terminal 100 is configured to select a SIM profile based on the output of the learning model 102. For example, the SIM profile selection unit 104 selects a SIM profile based on each action a output from the output layer of the neural network. t Action value Q(s t ,a t ), the SIM profile corresponding to the maximum behavioral value can be selected as the SIM profile to be used by the user terminal 100.

[0031] The communication unit 106 of the user terminal 100 is configured to communicate with one of the mobile operator networks using the SIM profile selected by the SIM profile selection unit 104 .

[0032] 7 is a flowchart showing the operation of the SIM profile switching device 400 and the user terminal 100 in the mobile communication system 10. In the following, an example will be described in which the learning model 102 of the user terminal 100 is configured as a neural network based on a Fixed Target Q-Network. Note that the user terminal 100 is currently connected to the J-th mobile operator network MN J SIM profile SP corresponding to J Using the mobile operator network MN J It is assumed that the device is connected to and communicating with the

[0033] In step 702, the state s of the user terminal 100 is input to the input layer of the main network constituting the learning model 102 of the user terminal 100. t is input. State s t In step 704, the learning model 102 receives the input of the state s t In SIM profile SP1~SP N (where N is an integer equal to or greater than 2 and represents the total number of SIM profiles held in the SIM card 110 attached to the user terminal 100) main (s t ,a i ) (i=1, 2, ..., N). For example, the output layer node 1 outputs the action value Q main (s t , a1) is output from node 2, and the action value Q main (s t , a2) is output, and so on. Note that the number of nodes in the output layer is the same as the number of SIM profiles in the SIM card 110.

[0034] Here, the learning model (main network and target network) 102 of the user terminal 100 is the SIM profile SP currently used by the user terminal 100. J In the next step 706, the user terminal 100 outputs the maximum action value Q main (s t ,a J ) corresponding to action a J and the state s of the user terminal 100 t The user terminal information including the above is transmitted to the SIM profile switching device 400 via the U-plane of the currently used mobile operator network. In step 708, the user terminal information management unit 402 of the SIM profile switching device 400 acquires the user terminal information.

[0035] Next, in step 710, the communication status management unit 404 of the SIM profile switching device 400 judges the communication status for each of the multiple mobile operator networks in the mobile communication system 10. In step 712, the reward determination unit 406 of the SIM profile switching device 400 acquires the user terminal information from the user terminal information management unit 402 and the communication status of each mobile operator network from the communication status management unit 404, and determines a reward R for updating the learning model 102 of the user terminal 100 depending on whether the communication status of the mobile operator network currently used by the user terminal 100 is good or not. t+1 For example, if the communication situation of the mobile operator network currently used by the user terminal 100 is good, the action a of selecting a SIM profile of that mobile operator network is determined. J In the case where the communication conditions of the mobile operator network currently used by the user terminal 100 are not good, the action a selects a SIM profile of another (e.g., K (≠ J)th) mobile operator network with good communication conditions so that the reward value for K The reward value for is maximized by R t+1 is determined.

[0036] Next, in step 714, the transmission unit 408 of the SIM profile switching device 400 transmits the reward R t+1 and state s t When the user terminal 100 performs an action a J The state s of the user terminal 100 after the transition when t+1 to the user terminal 100. Furthermore, in step 716, an update instruction (see below) for the learning model 102 of the user terminal 100 is transmitted from the SIM profile switching device 400 to the user terminal 100.

[0037] Next, in step 718, in order to obtain an action value to be used for updating the learning model 102, the next state s of the user terminal 100 is input to the input layer of the target network, which is the other neural network constituting the learning model 102 of the user terminal 100. t+1 In response to this input, in step 720, the target network of the learning model 102 outputs the state s t+1 Each action regarding a i Action value Q target (s t+1 ,a i ) to output.

[0038] Next, in step 722, the main network in the learning model 102 of the user terminal 100 is updated using the action value output from the target network. The update is performed in accordance with the contents of the update instruction sent from the SIM profile switching device 400 to the user terminal 100 in step 716. The contents of the update instruction are the reward R determined by the reward determination unit 406 of the SIM profile switching device 400. t+1 Specifically, (A) when the communication situation of the mobile carrier network currently used by the user terminal 100 is good, the maximum action value max among the action values ​​output from the target network is selected. ai Q target (s t+1,a i )=Q target (s t+1 ,a J ) is used to update the main network (max ai is all possible actions a i On the other hand, (B) when the communication situation of the mobile carrier network currently used by the user terminal 100 is not good, regardless of which of the action values ​​output from the target network is the largest, the action value Q corresponding to the SIM profile of the Kth mobile carrier network with good communication situation is used. target (s t+1 ,a K ) is used to update the main network. The specific update formula is as follows: The main network is trained so that the loss function E in the following formula is minimized.

[0039]

number

[0040] Here, γ is the time discount rate. Thus, in step 722, the main network in the learning model 102 of the user terminal 100 is updated (i.e., the parameters of the neural network are adjusted) according to the above formula (1) or (2) depending on the communication status of the mobile operator network. Thereafter, steps 702 to 722 are repeated again, and the learning of the main network progresses. Also, after each predetermined number of repetitions, in step 724 after step 722, the parameters of the target network are synchronized with the parameters of the main network.

[0041] Using the learning model 102 thus learned, the user terminal 100 can select a SIM profile to be used. Specifically, after step 704, the process can proceed to step 726, in which the SIM profile selection unit 104 of the user terminal 100 selects all the action values ​​Q main (s t ,ai ), and determines the SIM profile corresponding to the maximum action value as the optimal SIM profile. Next, in step 728, the communication unit 106 of the user terminal 100 uses the SIM profile selected by the SIM profile selection unit 104 to communicate with the mobile operator network corresponding to that SIM profile. In this way, the user terminal 100 can select the optimal SIM profile according to the communication status of the mobile operator network from the multiple SIM profiles held in the SIM card 110 and perform communication.

[0042] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and various modifications are possible without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0043] 10 Mobile communication systems 100 user terminals 102 Learning Model 104 SIM profile selection section 106 Communications Department 110 SIM card 200 Wireless Access Network 300 Core Network 400 SIM profile switcher 402 User terminal information management unit 404 Communication Status Management Department 406 Remuneration Determination Department 408 Transmitter 500 Internet MN1, MN2 mobile operator network SP1, SP2 SIM Profile

Claims

1. A mobile communication system comprising: a user terminal equipped with a multi-profile SIM; a plurality of mobile operator networks with which the user terminal can communicate; and a SIM profile switching device connected to the user terminal and the plurality of mobile operator networks, The SIM profile switching device includes: A communication status management unit that manages a communication status for each of the plurality of mobile operator networks; a reward determination unit that determines a reward in reinforcement learning based on a communication status of each of the plurality of mobile operator networks, the reward being related to a selection of a SIM profile to be used by the user terminal; A transmitter that transmits the reward to the user terminal, The user terminal, a learning model configured to learn to select an optimal SIM profile by reinforcement learning based on a state of the user terminal and the reward; a SIM profile selection unit that selects a SIM profile based on a state of the user terminal using the learning model; a communication unit for communicating with one of the plurality of mobile operator networks using the selected SIM profile. Mobile communication systems.

2. The mobile communication system according to claim 1 , wherein the reward determination unit determines the reward so that a reward value for a SIM profile currently used by the user terminal is maximized when a communication condition of a mobile operator network corresponding to the SIM profile is good.

3. 3. The mobile communication system according to claim 2, wherein, when a communication condition of a mobile operator network corresponding to a SIM profile currently used by the user terminal is not good and a communication condition of another mobile operator network is good, the reward determination unit determines the reward so that a reward value for a SIM profile corresponding to the other mobile operator network is maximized.

4. The learning model is the state s of the user terminal. t An action a t The action value Q (s t , a t The mobile communication system according to claim 1 , wherein the model is configured by a neural network based on deep reinforcement learning, and outputs a vector of the vectors.

5. The mobile communication system of claim 4, wherein the learning model is trained using the maximum action value among the multiple action values ​​output from the neural network when the communication conditions of the mobile operator network corresponding to the SIM profile currently used by the user terminal are good.

6. 6. The mobile communication system of claim 5, wherein, when the communication conditions of the mobile operator network corresponding to the SIM profile currently used by the user terminal are not good and the communication conditions of another mobile operator network are good, the learning model is trained using an action value corresponding to the SIM profile of the other mobile operator network among the multiple action values ​​output from the neural network.

7. A communication method in a mobile communication system including a user terminal equipped with a multi-profile SIM, a plurality of mobile operator networks with which the user terminal can communicate, and a SIM profile switching device connected to the user terminal and the plurality of mobile operator networks, comprising: The SIM profile switching device acquires communication status for each of the plurality of mobile operator networks; a step of the SIM profile switching device determining a reward in reinforcement learning based on communication conditions of each of the plurality of mobile operator networks, the reward being related to a selection of a SIM profile to be used by the user terminal; the SIM profile switching device transmitting the reward to the user terminal; a step of causing a learning model to learn selection of an optimal SIM profile by reinforcement learning based on a state of the user terminal and the reward, said user terminal using said learning model to select a SIM profile based on a state of said user terminal; the user terminal communicating with one of the plurality of mobile operator networks using the selected SIM profile; A communication method including: