WO2025177578A1 - Communication control device, wireless communication system, communication control method, and communication control program - Google Patents

Abstract

A communication control device (100) comprises an acquisition unit (131), a generation unit (132), a determination unit (133), and a control unit (134). The acquisition unit (131) acquires, as context information of a user of a terminal device (30), traffic information relating to traffic generated by the terminal device (30) for wireless communication with a base station (20), and movement information relating to movement of the terminal device (30) corresponding to the traffic. The generation unit (132) learns the relationship between the context information and result information indicating whether or not a frequency band, among frequency bands that the base station (20) can handle, that was used by the terminal device (30) when the context information was acquired is optimal for the context information, thereby generating a model indicating the tendency of user context corresponding to the frequency band. The determination unit (133) determines, on the basis of the model, a frequency band to be used that the terminal device (30) is allowed to use preferentially in wireless communication. The control unit (134) performs control so that wireless communication is executed in the frequency band to be used.

Description

COMMUNICATION CONTROL DEVICE, WIRELESS COMMUNICATION SYSTEM, COMMUNICATION CONTROL METHOD, AND COMMUNICATION CONTROL PROGRAM

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

With the recent spread of smartphones and tablet devices, wireless communication systems (wireless cellular network systems) have been established all over the country. Terminal devices, also known as mobile stations, perform handovers, switching between wireless base stations as they move. Therefore, technologies have been proposed to achieve low-latency handovers.

Japanese Patent Application Laid-Open No. 2022-123341

When looking at the traffic (e.g., traffic volume and traffic behavior) generated by terminal devices in response to user operations, there may be some terminal devices whose traffic is not enough to warrant the use of high-frequency bands, and for which sufficient communication quality can be ensured even if they are made to use mid- or low-frequency bands. On the other hand, there may be some terminal devices whose traffic is insufficient to use mid- or low-frequency bands, and for which high-frequency bands should be used to improve communication quality.

In this way, it can be said that there is an optimal frequency band for terminal devices to use in terms of traffic. However, because the base station is designed to determine the priority of frequency bands, terminal devices will communicate wirelessly with the base station by using specific frequency bands preferentially in accordance with the priority set by the base station, regardless of traffic.

This causes many terminal devices to use specific frequency bands, resulting in a shortage of wireless resources. Furthermore, because terminal devices generally perform cell searches starting with high-frequency bands, which are given higher priority, they tend to wait for cells in high-frequency bands. This results in frequent handovers due to terminal devices connecting to base stations using high-frequency bands with narrower coverage, creating a problem.

For these reasons, there is a demand for optimizing the frequency bands used by terminal devices. However, the above-mentioned conventional technology simply uses machine learning to determine frequencies predicted to be available as the frequencies to be used for wireless communication, and does not take into account the traffic of the terminal devices when determining the frequency bands to be used. For this reason, the above-mentioned conventional technology does not necessarily make it possible to optimize the frequency bands to be used by terminal devices.

The present invention therefore proposes a communication control device, wireless communication system, communication control method, and communication control program that can optimize the frequency bands used by terminal devices. As will be described later, the communication control device may be implemented, for example, as a RIC (RAN Intelligent Controller).

In order to solve the above problem, one embodiment of the present invention provides a communication control device that includes an acquisition unit that acquires, as context information of a user of a terminal device, traffic information related to traffic generated by the terminal device in wireless communication with a base station and movement information related to the movement of the terminal device in response to the traffic; a generation unit that generates a model that indicates the tendency of the user's context according to frequency band by learning result information indicating whether the frequency band used by the terminal device when the context information was acquired, among frequency bands supported by the base station, is optimal for the context information and the relationship with the context information; a determination unit that determines a target frequency band to be given priority use by the terminal device in the wireless communication based on the model; and a control unit that controls the wireless communication to be performed in the target frequency band.

According to the present invention, it is possible to optimize the frequency bands used by terminal devices.

FIG. 1 is an explanatory diagram illustrating the problem of frequent handovers. FIG. 2 is an explanatory diagram showing an example of a schematic configuration of a system according to this embodiment. FIG. 3 is a diagram simply illustrating the architecture of a 5G core of a wireless communication system according to an embodiment. FIG. 4 is a diagram conceptually showing the advantages of installing a communication control device in a regional center. FIG. 5 is a diagram showing the configuration of an AI-RAN. FIG. 6 is a diagram illustrating an example of the configuration of a communication control device according to the embodiment. FIG. 7 is a diagram illustrating the procedure of the learning process implemented in the wireless communication system. FIG. 8 is a diagram illustrating the procedure of the inference process implemented in the wireless communication system. FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the communication control device according to the embodiment.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functional configuration will be assigned the same reference numerals, and redundant explanations will be omitted.

One or more embodiments (including examples, modifications, and application examples) described below can be implemented independently. However, at least a portion of the multiple embodiments described below may be implemented in appropriate combination with at least a portion of another embodiment. These multiple embodiments may include novel features that are different from one another. Therefore, these multiple embodiments may contribute to solving different purposes or problems and may achieve different effects from one another.

(Embodiment)
1. Introduction
Consider a scenario in which an unspecified number of users are using their own terminal devices on a public transportation vehicle (e.g., a train). In this case, the movement status of the terminal devices is the same, but the usage status of the terminal device varies from user to user. For example, there may be terminal devices that acquire data with a high traffic volume in response to a user's video viewing operation, while there may be terminal devices that acquire data with a low traffic volume in response to a user's still image viewing operation. There may also be terminal devices that are in a standby state, where the user is not performing any operation and no wireless communication with a base station is occurring.

In this case, from the perspective of communication quality, it is appropriate to have terminal devices with high traffic volumes use high frequency bands. On the other hand, it may be possible to ensure sufficient communication quality by having terminal devices with low or no traffic volumes use medium or low frequency bands.

However, as mentioned above, the current specifications require that frequency band priorities be determined by the base station, meaning that terminal devices communicate wirelessly with the base station by using specific frequency bands in accordance with the priority set by the base station, regardless of traffic. This results in a bias toward the use of specific frequency bands by many terminal devices, leading to a shortage of wireless resources.

Furthermore, base stations generally have priorities set to prioritize higher frequency bands. In this case, the terminal device will perform a cell search starting from the high frequency band, which has a higher priority, and will therefore set a high frequency band cell as its standby destination. As a result, handovers will occur frequently as the terminal device moves while connected to a base station using the high frequency band, which has narrow coverage. This point will be explained using Figure 1.

Figure 1 is an explanatory diagram illustrating the problem of frequent handovers. Figure 1 shows base stations gNB1, gNB2, and gNB3 as examples of base stations gNBs for the fifth generation (5G), and these base stations gNB are adjacent to one another. In other words, the cell formed by base station gNB1, the cell formed by base station gNB2, and the cell formed by base station gNB3 are adjacent to one another, with some overlapping as shown in Figure 1.

In the example of Figure 1, base station gNB1 supports three frequency bands: high, medium, and low, and forms high frequency band cell CE11, medium frequency band cell CE12, and low frequency band cell CE13. Base station gNB3 also supports three frequency bands: high, medium, and low, and forms high frequency band cell CE31, medium frequency band cell CE32, and low frequency band cell CE33. On the other hand, base station gNB2 supports only the high frequency band, and forms high frequency band cell CE21.

In this example, an overlapping area H1 occurs between cells CE11 and CE21, and an overlapping area H2 occurs between cells CE21 and CE31. Furthermore, an overlapping area M1 occurs between cells CE12 and CE32, and an overlapping area L1 occurs between cells CE13 and CE33. From this example, it can be seen that there are often more overlapping areas between cells that support high frequency bands than between cells that support medium or low frequency bands.

Here, consider a scenario in which a terminal device UE performs a handover from base station gNB1 to base station gNB3. When moving between cells using a medium or low frequency band, only one handover in one overlapping area (overlap area M1 or overlap area L1) is required, but when moving between cells using a high frequency band, two handovers occur in two overlapping areas (overlap area H1 and overlap area H2). Furthermore, when the terminal device UE travels between base station gNB1 and base station gNB3, more handovers occur when using a high frequency band than when using a medium or low frequency band.

In other words, from the example in Figure 1, it can be seen that the terminal device UE performs more handovers when using the high frequency band than when using the medium or low frequency band, and communication delays can also be large when handovers are frequent. To reduce delays, it is necessary to reduce the frequency of handovers. However, terminal devices with a high volume of traffic should be made to use the high frequency band. On the other hand, it is considered acceptable to make terminal devices with a low volume of traffic or no traffic use the medium or low frequency band.

In this way, each terminal device UE has an optimal frequency band depending on traffic trends. Therefore, the inventors of the present invention focused on the fact that if the frequency band to be used preferentially by the terminal device UE is optimized depending on traffic trends, the handover problem in Figure 1 can also be optimized.

However, under the current circumstances where specifications are set on the base station gNB side that prioritize high frequency bands for terminal devices UE, all terminal devices UE will use high frequency bands regardless of their own traffic, and as a result, the handover problem in Figure 1 cannot be optimized.

Here, any terminal device UE is known to have identification information called SPID (Subscriber Profile I), which indicates the priority of the communication method. The base station gNB can instruct the terminal device UE on the frequency band set in the SPID. However, the SPID is not intended to be dynamically changed. For this reason, in principle, when there is no SPID, the terminal device UE waits in a frequency band according to the priority set by the base station gNB, and when there is an SPID, it waits in the frequency band set for that SPID.

In other words, the proposed technology of the present invention is an idea that takes advantage of the characteristic that SPID can be used to control the frequency band to be used preferentially. More specifically, the proposed technology of the present invention grasps the correlation between result information indicating whether the frequency band used by the terminal apparatus UE is optimal among the frequency bands supported by the base station gNB and the user context of the terminal apparatus UE, and determines the frequency band to be used preferentially by the terminal apparatus UE in wireless communication with the base station gNB based on the grasped correlation. As an example, if the proposed technology of the present invention can detect a certain trend between the movement status (movement route) of the terminal apparatus UE used by the user and the network usage status (traffic status) in a specific frequency band as the user context, it determines the optimal frequency band according to this trend as the frequency band to be used.

So far, we have explained the background and overview of the present invention. Below, we will explain embodiments of the present invention with reference to the drawings. Below, we will explain embodiments of the present invention assuming application to 3GPP (registered trademark) LTE/LTE-Advanced wireless communication systems and next-generation NR (New Radio) wireless communication systems (5th generation and later). However, the concept of the present invention can be applied to any system that uses a similar configuration.

A communication control device according to an embodiment described herein acquires, as context information for a user of a terminal device, traffic information related to traffic generated by the terminal device in wireless communication with a base station and movement information related to the movement of the terminal device in response to the traffic. The communication control device then generates a model indicating the tendency of the user's context according to frequency band by learning the relationship between the context information and result information indicating whether the frequency band used by the terminal device when the context information was acquired, among the frequency bands supported by the base station, is optimal for the context information. The communication control device then determines, based on the model, the target frequency band to be used by the terminal device for wireless communication. The communication control device also controls the wireless communication system (wireless cellular network system) so that wireless communication is performed in the target frequency band.

[2. System configuration overview]
Fig. 2 is an explanatory diagram showing an example of a schematic configuration of a system 1 according to the present embodiment. According to the example of Fig. 2, the system 1 includes a wireless communication system (wireless cellular network system) 5 including a communication control device 100 according to the embodiment.

In FIG. 2, the wireless communication system 5 according to the embodiment is a cellular mobile communication system conforming to the fifth-generation standard specifications, and includes a 5G core network 10, multiple base stations 20, and multiple terminal devices 30. Each terminal device 30 performs data communication (packet communication) via the base station 20, and further via the 5G core 10 and the Internet 60, with external devices in a cloud system (cloud) 70. In 5G, the base station 20 is called a gNodeB (gNB).

Furthermore, in FIG. 2, the area 10A covered by the wireless communication system 5 is the service area in which the wireless communication system 5 is provided. The wireless communication system 5 according to the embodiment may be deployed for each area 10A, and as an example, the area 10A may be on a prefecture-by-prefecture basis. In other words, the communication control device 100 may be installed for each regional area, such as a prefecture-by-prefecture basis.

The 5G core 10 is composed of core network devices having various functions (nodes) called network functions. The 5G core 10 corresponds to the part that connects the wireless communication system 5 owned by the telecommunications carrier T to the Internet 60. The telecommunications carrier T here may be a company that provides a connection service SV in which a designated frequency band is used preferentially using the communication control device 100 according to the embodiment.

Furthermore, according to the example of Figure 2, one area 10A includes base station 20(1) and base station 20(2). As shown in Figure 1, base station 20(1) and base station 20(2) support multiple frequency bands and form cells corresponding to each frequency band. Figure 2 shows two base stations, 20(1) and 20(2), as an example of base stations 20 included in area 10A, but the number of base stations within area 10A is not limited.

Base station 20(1) and base station 20(2) are each configured using hardware such as a computer device having a CPU, memory, etc., an external communication interface unit for 5G core 10, and a wireless communication unit, and by executing a specified program, they can perform wireless communication with terminal device 30, send and receive information with the core network device of 5G core 10, and send and receive information with communication control device 100 using a specified communication method and wireless communication resources.

The terminal device 30 is called user equipment (UE) because it is used by a user of a communication service. Furthermore, because the terminal device 30 is mobile, it may also be called a mobile station or mobile device, or a radio device.

In Figure 2, terminal device 30(1) used by user U1 is shown as an example of terminal device 30. As terminal device 30(1) moves, it may perform a handover to switch the connected base station 20 from base station 20(1) to base station 20(2).

When connected to base station 20(1), terminal device 30(1) can perform various communications via base station 20(1), and when connected to base station 20(2), can perform various communications via base station 20(2). Terminal device 30(1) is configured using hardware such as a computer device with a CPU, memory, etc., and a wireless communication unit, and can perform wireless communications with base station 20 by executing a specific program.

Note that while Figure 2 shows only one terminal device 30(1) used by user U1, in reality, multiple terminal devices 30 used by an unspecified number of multiple users U are connected to the base station 20.

The communication control device 100 is an information processing device that executes communication control processing related to the proposed technology of the present invention. The communication control device 100 acquires, as context information of user U of terminal device 30, traffic information related to traffic generated by the terminal device 30 in wireless communication with the base station 20 and movement information related to the movement of the terminal device 30 in response to the traffic. The communication control device 100 then learns the relationship between the context information and result information indicating which frequency band the terminal device 30 used among the frequency bands supported by the base station 20, thereby generating a model that indicates the tendency of user U's context according to frequency band, and determines the target frequency band to be given priority for use by the terminal device 30 in wireless communication based on the model. The communication control device 100 also controls the wireless communication system 5 so that wireless communication is performed in the target frequency band.

The communication control device 100 may be provided in the 5G core 10, or may be installed in a remote location such as a data center. For example, the communication control device 100 may be installed in a regional center located in each area 10A. This point will be explained later with reference to Figure 4.

Figure 3 is a simplified diagram showing the architecture of the 5G core 10 of the wireless communication system 5 according to the embodiment. The 5G core 10 is composed of a control plane portion (C-Plane) that serves as the overall control system for the mobile communication system, where control signals are mainly sent, received, and processed, and a user plane portion (U-Plane) where user data is mainly sent, received, and processed. In Figure 3, C-Plane communications are indicated by dotted lines, and U-Plane communications are indicated by solid lines.

The C-Plane contains the UPF (User Plane Function) 101, SMF (Session Management Function) 102, AMF (Access and Mobility Management Function) 103, UDM (Unified Data Management) 104, and UDR (Unified Data Repository) 105. An explanation of the C-Plane is omitted.

UPF 101 has functions such as forwarding subscriber communication packets. SMF 102 has functions such as subscriber session management. For example, SMF 102 establishes a PDU (Packet Data Unit) session while obtaining information about the base station 20 to which the terminal device 30 is connected from AMF 103.

AMF 103 has functions such as subscriber authentication and subscriber mobility management. For example, AMF 103 performs a series of access management tasks, such as querying UDM 104 and UDR 105 for subscriber information, authenticating whether the terminal device 30 has a contract with telecommunications carrier T, and providing connection if authentication is successful. AMF 103 also manages which base station 20's cell the terminal device 30 is in, so that when the terminal device 30 moves, it can connect to the nearest base station 20. In other words, AMF 103 can grasp the route taken by the terminal device 30, i.e., from which base station 20 to which base station 20.

UDM104 has functions such as subscriber information management. UDR105 has functions such as a subscriber information database.

Figure 4 is a conceptual diagram showing the advantages of installing a communication control device 100 in a regional center. For example, to support a society in which AI is evolving at an accelerating pace, it is necessary to build a next-generation social infrastructure that can handle the rapidly increasing demand for data processing and the power required for that data processing. Therefore, the AI-RAN concept involves building large-scale server clusters in data centers for each region (for example, each area 10A), and using the abundant computing resources to simultaneously run and link vRAN (virtual radio access network), MEC (multi-access edge computing), and AI applications.

Figure 4 shows a scenario in which the communication control device 100 is applied to the AI-RAN concept. The communication control device 100 present in each area 10A is an AI-RAN having a calculation platform and a learning platform, and is deployed in a distributed manner by region. In this way, the communication control device 100 as an AI-RAN may be a cloud server that is deployed as an edge server (also known as an MEC server) near the terminal device 30, and by utilizing a closed network separated from the Internet 60, high speed, large capacity, low latency, etc. can be achieved. Meanwhile, services that utilize data collected by the communication control device 100 in each location (for example, large-scale calculations or learning that requires large amounts of power) may be executed on the cloud 70 side via the Internet 60.

3. AI-RAN Configuration
Figure 5 is a diagram showing the configuration of an AI-RAN. Figure 5 shows the functional configuration of the AI-RAN possessed by the communication control device 100 corresponding to area 10A. First, AI-RAN is an architecture that allows AI and RAN (base station 20) to coexist, and it can maximize the performance of the RAN using AI, while also realizing an ultra-low latency, highly secure computing infrastructure for various AI applications at the regional level.

In the example of Figure 5, vRAN is a 5G virtualized radio access network in which the GPU of the communication control device 100 virtualizes the RAN, i.e., the base station 20 (the base station 20 included in area 10A). In other words, the communication control device 100 shown in Figure 5 is configured as an AI-RAN by further implementing a learning platform (AI) in a virtualized platform environment that combines 5G vRAN and MEC.

Furthermore, as an example of implementing a computational infrastructure at the regional level, computational resources corresponding to the base stations 20 included in area 10A are also provided.

The learning platform portion of the communication control device 100 may correspond to the generation unit 132 (Figure 6) described below.

4. Configuration of communication control device
The communication control device 100 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the configuration of the communication control device 100 according to the embodiment. As shown in Fig. 6, the communication control device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(Regarding the communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC), etc. For example, the communication unit 110 performs wireless communication with the 5G core 10 and the base station 20.

(Regarding the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 may store, for example, data and programs related to the communication control process according to the embodiment.

(Regarding the control unit 130)
The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like using RAM as a work area to execute various programs (e.g., a communication control program according to the embodiment) stored in a storage device inside the communication control device 100. The control unit 130 is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 6, the control unit 130 has an acquisition unit 131, a generation unit 132, a determination unit 133, and a communication control unit 134, and realizes or executes the information processing functions and actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 6, and may be other configurations that perform the information processing described below. Furthermore, the connection relationships between the processing units of the control unit 130 are not limited to the connection relationships shown in FIG. 6, and may be other connection relationships.

(Acquisition unit 131)
The acquisition unit 131 acquires, as context information of the user U of the terminal device 30, traffic information related to traffic generated by the terminal device 30 in wireless communication with the base station 20 and movement information related to the movement of the terminal device 30 in response to the traffic. The traffic information here includes the concepts of traffic volume or traffic behavior. Furthermore, traffic behavior may indicate a change in traffic volume over a certain period of time. Furthermore, the movement information related to the movement of the terminal device 30 may include a base station ID indicating the base station to which the terminal device 30 is connected, a base station ID indicating a base station to which the terminal device 30 is switched in response to handover, and the like. In other words, the movement information may include information indicating from which base station 20 the terminal device 30 has moved to which other base station 20.

The acquisition unit 131 may acquire base station location information indicating the installation location of the base station 20 from a base station design information DB, and may also acquire the movement route of the terminal device 30 by comparing this base station location information with the movement information. The location of the base station design information DB is not limited. For example, the storage unit 120 of the communication control device 100 may have a base station design information DB, or each base station 20 may have a base station design information DB.

(Generation unit 132)
The generation unit 132 generates a model indicating the tendency of the context of the user U according to the frequency band by learning the relationship between the context information and result information indicating whether the frequency band used by the terminal device 30 when the context information was acquired, among the frequency bands that the base station 20 can support, is optimal for the context information. When the context information of a specific user is input, the generation unit 132 causes the model to learn the relationship so as to output the frequency band that is optimal according to the context of the specific user, among the frequency bands that the base station 20 can support.

In addition, the information indicating whether the frequency band used by the terminal device 30 when the context information was acquired is optimal for the context information may be manually labeled, or may be dynamically assigned by providing labeling rules to the generation unit 132.

Furthermore, the acquisition unit 131 may further acquire location information of the terminal device as context information of the user U. In such a case, the generation unit 132 generates a model based on information identified based on the location information of the terminal device 30.

(Determination unit 133)
Based on the model, the determination unit 133 determines a target frequency band to be preferentially used by the terminal device 30 in wireless communication between the terminal device 30 and the base station 20. For example, when context information of a predetermined user U is input to the model, the determination unit 133 determines a target frequency band to be used based on information on the frequency band output by the model.

(Communication control unit 134)
The communication control unit 134 controls wireless communication so that it is performed in the frequency band to be used. For example, the communication control unit 134 controls the nodes in the 5G core 10 so that wireless communication is performed in the frequency band to be used.

(An example of the control unit 130)
In wireless communication between the terminal device 30 and the base station 20, the context information is associated with first identification information that identifies the user U of the terminal device 30 as a subscriber, and is linked to temporary second identification information that replaces the first identification information. The first identification information is an International Mobile Subscriber Identity (IMSI). The IMSI is information that identifies the user U or subscriber of the terminal device 30, and in this embodiment, is a number assigned to subscribers who use the services of the telecommunications carrier T. The second identification information is a 5G-S Temporary Mobile Subscription Identifier (5G-S-TMSI). The 5G-S-TMSI (hereinafter abbreviated as "S-TMSI") is a temporary subscription identifier assigned to the user U (user U's terminal device 30) instead of the IMSI.

In wireless communication, the S-TMSI is always used, not the IMSI. Therefore, the acquisition unit 131 acquires context information linked to the S-TMSI. For example, the acquisition unit 131 acquires, as the target context information to be used in generating the model, context information linked to the S-TMSI corresponding to the IMSI of a subscriber user Ux who subscribes to a connection service SV that prioritizes the use of a specified frequency band, among users U. The acquisition unit 131 also acquires information on the frequency band used by the terminal device 30 when the target context information was acquired.

In such a case, the generation unit 132 may generate a model for each subscriber user by learning the relationship between the context information and result information acquired for each subscriber user Ux. Then, the determination unit 133 determines the target frequency band to be preferentially used by the terminal device 30 for each subscriber user based on the model generated for each subscriber user. The target frequency band determined here is also associated with an S-TMSI. Therefore, the communication control unit 134 converts the S-TMSI associated with the target frequency band to an IMSI corresponding to that S-TMSI, and registers association information that associates the converted IMSI with an SPID (third identification information) indicating the priority of the frequency band to be used in the subscriber information database in which the IMSI is stored. The subscriber information database referred to here may be the UDR 105.

Here, when a terminal device 30 accesses a base station 20, the AMF 103, which is a core network device of the 5G core 10, performs authentication processing for the terminal device 30 based on the IMSI acquired from the terminal device 30 and the IMSI registered as subscriber information in the UDR 105. If the AMF 103 is able to authenticate the terminal device 30, it acquires linking information including the IMSI of the terminal device 30 from the UDR 105. In other words, the AMF 103 acquires the SPID corresponding to the IMSI of the terminal device 30. The AMF 103 then transmits the SPID to the base station 20 to which the terminal device 30 is connected. As a result, the base station 20 identifies the frequency band to be used by the connected terminal device 30 from the SPID, and becomes able to communicate wirelessly with the terminal device 30 using the identified frequency band.

Furthermore, by subscribing to the connection service SV, the subscriber user Ux can set up settings such as, for example, allowing the optimal frequency band based on the subscriber's own context information for commuting hours to be used only during commuting hours. Furthermore, to enable such settings to be realized, an application may be implemented to send and receive information between the terminal device 30 and the communication control device 100.

5. An example of model generation
The generation unit 132 may generate a model for each subscribing user Ux. For example, the generation unit 132 uses result information indicating whether the frequency band used by the terminal device 30 of the subscribing user Ux when the context information is acquired, among the frequency bands supported by the base station 20, is optimal for the context information as a target variable in machine learning. Furthermore, the generation unit 132 uses feature information extracted from the context information of the subscribing user Ux and the location information of the subscribing user Ux as explanatory variables in machine learning. Then, the generation unit 132 generates a model using the target variable and the explanatory variables. This allows the generation unit 132 to estimate, for example, the optimal frequency band according to the context of the subscribing user U1x.

For example, if the generation unit 132 can estimate the following tendency using the context information of subscribing user U1 as input: <traffic volume "A1" / traffic behavior "A2" / movement between base station 20(1) and base station 20(2) when using the high frequency band>, it can generate a model that can obtain an output indicating that the medium frequency band is optimal. Furthermore, if the generation unit 132 can estimate the following tendency using the context information of subscribing user U1 as input: <traffic volume "B1" / traffic behavior "B2" / movement between base station 20(2) and base station 20(3) when using the low frequency band>, it can generate a model that can obtain an output indicating that the high frequency band is optimal. As another example, if the generation unit 132 can estimate the following tendency using the context information of subscribing user U1 as input: <when moving between base station 20(3) and base station 20(4), the user remains in standby mode without connecting>, it can generate a model that can obtain an output indicating that standby in the high frequency band is optimal.

6. Learning Process
Next, the procedure of the learning process will be described. Fig. 7 is a diagram illustrating the procedure of the learning process implemented in the wireless communication system 5. Fig. 7 shows a scene in which learning data is collected in response to wireless communication and movement by the terminal device 30(1) of the subscribing user U1, and a model is generated from the collected data. Fig. 7 also shows, as a part of such a scene, an example in which learning data is collected during a band-over in which the terminal device 30(1) first connects to the base station 20(1) and then switches its connection to the base station 20(2).

In Figure 7, solid arrows indicate data transmission and reception between the base station 20 and the core network device of the 5G core 10, or data transmission and reception between core network devices. On the other hand, dotted arrows indicate the flow of data for learning. Step numbers indicating processing procedures are shown in parentheses. In the example of Figure 7 (similar to Figure 8), the combined functions of the learning device SV1, conversion device SV2, and association information SV3 are defined as the communication control device 100. The learning device SV1 has the control unit 130 described in Figure 6.

As shown in Figure 7, assume that terminal device 30(1) has IMSI "U1" and is powered on within the cell formed by base station 20(1). In this case, in order to be able to track terminal device 30(1) even if it moves, terminal device 30(1) requests registration of its own device from AMF103 via base station 20(1) (step S71).

AMF103 uses the IMSI "U1" acquired from terminal device 30 to reference the subscriber information in UDR105 and executes authentication processing to determine whether IMSI "U1" is registered as subscriber information (step S72). As will be described later, the communication control processing according to the embodiment registers association information linking the IMSI and SPID in UDR105. However, as shown in FIG. 7, at the current stage when the frequency band to be used for terminal device 30(1) has not been determined, the SPID associated with IMSI "U1" is assumed to be "N/A," indicating no match.

Going back to the explanation, AMF103 generates a temporary S-TMSI "U11" to replace IMSI "U1" (step S73) and transmits the generated S-TMSI "U11" to base station 20(1) and terminal device 30(1) (step S74). As a result, both base station 20(1) and terminal device 30(1) possess S-TMSI "U11", and data with S-TMSI "U11" assigned can be input from base station 20(1) to learning device SV1. Note that, although not shown in FIG. 7, SMF102 sets PDU session parameters upon receiving a request from AMF103, and a PDU session is established with UPF101 as the anchor point based on the parameters.

In this state, base station 20(1) inputs traffic information Trf11 linked to S-TMSI "U11" and frequency information F11 linked to S-TMSI "U11" to learning device SV1 (step S75).

The traffic information Trf11 may include the traffic volume and traffic behavior while the terminal device 30(1) is connected to the base station 20(1) and communicating wirelessly. The frequency information F11 includes the frequency band used according to the priority determined by the base station 20(1) and the base station ID "20(1)" that identifies the base station 20(1), in accordance with the current SPID "N/A."

The terminal device 30(1) is moving and performs a handover to switch the connection destination to the base station 20(2). At this time, a handover notification is sent to the AMF 103 via the base station 20(2) (step S76). The AMF 103 transmits the S-TMSI "U11" to the base station 20(2) and the terminal device 30(1) (step S77). As a result, the base station 20(2) also possesses the S-TMSI "U11", and data with the S-TMSI "U11" assigned can be input from the base station 20(2) to the learning device SV1. Note that, although not shown in FIG. 7, the SMF 102 receives a request from the AMF 103 and instructs the UPF 101 and the base station 20(2) to replace the PDU session, making the UPF 101 the anchor point and enabling the use of a PDU session using the new base station 20(2).

In this state, base station 20(2) inputs traffic information Trf21 linked to S-TMSI "U11" and frequency information F21 linked to S-TMSI "U11" to learning device SV1 (step S78).

The traffic information Trf21 may include the traffic volume and traffic behavior while the terminal device 30(1) is connected to the base station 20(2) and communicating wirelessly. The frequency information F21 includes the frequency band used according to the priority determined by the base station 20(2) and the base station ID "20(2)" that identifies the base station 20(2).

Figure 7 shows an example in which base station 20 inputs traffic information to learning device SV1, but a configuration in which a monitoring device for monitoring traffic connected to the Internet 60 is provided and the monitoring device inputs traffic information to learning device SV1 may also be adopted.

In addition, location information (terminal location information) corresponding to the movement of terminal device 30(1) may be sequentially input to learning device SV1, and location information (base station location information) where base station 20(1) and base station 20(2) are installed may also be input.

The learning device SV1 generates learning data from the data that has been input so far, and generates a model through machine learning using the generated learning data (step S79). For example, the learning device SV1 calculates the travel route RT that the terminal device 30(1) took from base station 20(1) to base station 20(2) based on the base station location information of each base station 20 identified by the base station ID included in the frequency information F11 and frequency information F12, and the terminal location information. Furthermore, the learning device SV1 calculates context information CX that indicates the frequency band, traffic volume, and traffic behavior of the terminal device 30(1) along the travel route RT, based on the traffic information Trf11, traffic information Trf21, and the travel route RT. The learning device SV1 then determines whether the frequency band at the time when the terminal device 30(1) indicated the context information CX is optimal for the context information CX. Here, the learning device SV1 assigns the determination result as a correct label to the frequency band when the terminal device 30(1) indicates the context information CX, and uses this as the objective variable. For example, the learning device SV1 may assign as a correct label the result of a determination as to whether the actually used frequency band was optimal, based on the frequency of handovers between base station 20(1) and base station 20(2), the usage status (congestion) of wireless resources at base station 20(1) and base station 20(2), the optimal frequency band for the traffic volume on the travel route RT, and the actually used frequency band.

Furthermore, the learning device SV1 uses the feature information extracted from the context information CX as explanatory variables in machine learning. As a result, when new data obtained through wireless communication between the terminal device 30(1) and the base station 20 is input, the learning device SV1 can estimate the context trend according to the input data and learn a model so that it outputs the frequency band that is optimal for the estimated trend as the frequency band to be used.

The learning device SV1 may also use the type of content (e.g., video content, still image content, etc.) estimated from traffic volume and traffic behavior as learning data. The learning device SV1 may use the period from when the connection service SV is subscribed to until use begins as the learning period, and generate a model using the learning data acquired during this period.

Furthermore, it is preferable that the learning device SV1 be configured to be able to identify that S-TMSI "U11" corresponds to IMSI "U1," which identifies subscribing user U1 who has subscribed to connection service SV. For example, the learning device SV1 may be configured to obtain a list of IMSI and S-TMSI combinations from AMF103, or to be configured to determine the IMSI that corresponds to the S-TMSI on its own. As a result, the learning device SV1 can extract only the learning data for subscribing user U1 from the data input from base station 20 for an unspecified number of users U other than subscribing user U1, and generate a model customized for subscribing user U1. While the explanation is given using subscribing user U1 as an example, the same applies to other users U.

7. Inference Processing Procedure
Next, the procedure of the inference process using the model generated by the procedure of Fig. 7 will be described. Fig. 8 is a diagram illustrating the procedure of the inference process implemented in the wireless communication system 5. Fig. 8 shows a scene in which, when the time period for which subscribing user U1 has applied for the connection service SV (e.g., commuting time) arrives, the optimal frequency band is determined according to the tendency of the context of subscribing user U1 during this time period.

In Figure 8, the flow of data for inference is indicated by dashed arrows, and wireless communication control using the target frequency band is indicated by dashed arrows. Step numbers indicating the processing procedure are also shown in parentheses.

For example, suppose that the time period designated by subscribing user U1 has arrived while the terminal device 30(1) of subscribing user U1 is conducting wireless communication with base station 20(1). As shown in FIG. 8, during the time period designated by subscribing user U1, base station 20(1) inputs traffic information Trf12 associated with S-TMSI "U11" and frequency information F12 associated with S-TMSI "U11" to learning device SV1 (step S81).

The traffic information Trf12 may include the traffic volume and traffic behavior while the terminal device 30(1) is connected to the base station 20(1) and communicating wirelessly. The frequency information F12 includes the frequency band used according to the priority determined by the base station 20(1) and the base station ID "20(1)" that identifies the base station 20(1), in accordance with the current SPID "N/A."

The learning device SV1 executes the inference process by inputting the data acquired from base station 20(1) in step S81 into the model as inference data (step S82). As a result, the model outputs the optimal frequency band according to the context trends during the time period specified by subscribing user U1. Therefore, the learning device SV1 determines the frequency band output by the model as the frequency band "X" to be used (step S82). "X" is assumed to be either H (high frequency band), M (medium frequency band), or L (low frequency band).

The frequency band "X" to be used is associated with S-TMSI "U11." Therefore, the conversion device SV2 converts S-TMSI "U11" to obtain the original IMSI "U1" (step S84).

The linking device SV3 generates linking information linking the IMSI "U1" obtained by the conversion with the SPID "X" that defines the target frequency band "X" as the preferred frequency band (step S85). In the following explanation, an example is used in which the terminal device 30(1) has previously used the high frequency band during the time period specified by the subscribing user U1, but "M" (medium frequency band) has been determined as the target frequency band. In this example, the linking device SV3 generates linking information LK that links the IMSI "U1" with the SPID "M", as shown in FIG. 8.

Then, the linking device SV3 transmits the linking information LK to the UDR 105, and registers it as the subscriber information of the subscribing user U1 (step S86). In the example of Figure 7, the SPID linked to IMSI "U1" was "N/A," indicating no match, but at this point this is replaced with SPID "M." As described above, the base station 20 becomes able to instruct the terminal device 30 on the frequency band set for the SPID. Therefore, based on SPID "M," the base station 20(1) can cause the terminal device 30(1) to use the medium frequency band instead of the high frequency band during the time period specified by the subscribing user U1. This is explained in detail below.

First, AMF103 extracts the linking information LK from the subscriber information of UDR105 (step S87). Then, AMF103 transmits the linking information LK to base station 20(1) (step S88).

Based on the linking information LK, the base station 20(1) determines that the frequency band that the terminal device 30(1) should preferentially use is the "medium frequency band," and instructs the terminal device 30(1) to use the "medium frequency band" (step S89).

So far, the flow of the communication control process according to the embodiment has been explained using Figures 7 and 8. According to the communication control process shown in Figures 7 and 8, the user U is connected to the optimal frequency band according to the traffic behavior and travel route without being biased towards a specific frequency band, thereby improving the user U's experience and reducing the load on the mobile network (e.g., handover processing). In addition, the user U can choose whether or not to benefit from the optimization of frequency selection due to mobility.

8. Other Embodiments
The above-described communication control device 100 may be implemented in various different forms other than the above embodiment, so other embodiments of the communication control device 100 will be described below.

In the above embodiment, the communication control device 100 generates a model for each subscriber user Ux who has applied for a connection service SV, and assigns the optimal frequency band according to the application details of the subscriber user Ux. However, the communication control device 100 may also forcibly control the frequency band for all users U, regardless of the connection service SV. As a result, for example, the telecommunications carrier T can activate the function of having each user U's terminal device 30 use the optimal frequency band according to the context tendency.

9. Hardware Configuration
The communication control device 100 according to the embodiment may be realized, for example, by a computer 1000 having a configuration as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the communication control device 100 according to the embodiment. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls each component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

The HDD 1400 stores programs executed by the CPU 1100 and data used by such programs. The communication interface 1500 receives data from other devices via a specified communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via a specified communication network.

The CPU 1100 controls output devices such as displays and input devices such as keyboards via the input/output interface 1600. The CPU 1100 acquires data from input devices via the input/output interface 1600. The CPU 1100 also outputs generated data to output devices via the input/output interface 1600.

Media interface 1700 reads programs or data stored on recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads the programs from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded programs. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical Disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

For example, when the computer 1000 functions as the communication control device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200, thereby realizing the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a specified communications network.

[10. Other]
Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above embodiments can be combined as appropriate to the extent that the processing content is not contradictory.

The above describes in detail some of the embodiments of the present application based on the drawings, but these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the "present invention" section.

REFERENCE SIGNS LIST 1 System 5 Wireless communication system 10 5G core network 20 Base station 30 Terminal device 60 Internet 70 Cloud system 100 Communication control device 110 Communication unit 120 Storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Determination unit 134 Communication control unit

Claims (10)

an acquisition unit that acquires, as context information of a user of a terminal device, traffic information related to traffic generated by the terminal device in wireless communication with a base station and movement information related to movement of the terminal device in response to the traffic;
a generation unit that generates a model that indicates a tendency of the user's context according to a frequency band by learning a relationship between result information that indicates whether a frequency band used by the terminal device when the context information is acquired, among frequency bands that the base station can support, is optimal for the context information and the context information; and
a determination unit that determines a frequency band to be preferentially used by the terminal device in the wireless communication based on the model;
a control unit that controls the wireless communication to be performed in the target frequency band;
A communication control device comprising: The acquisition unit further acquires location information of the terminal device as the context information of the user;
The communication control device according to claim 1 , wherein the generation unit generates the model based on information specified based on location information of the terminal device. 2. The communication control device according to claim 1, wherein the generation unit causes the model to learn the relationship so that, when context information of a predetermined user is input, a frequency band corresponding to the context of the predetermined user is output from among frequency bands that the base station can support. In the wireless communication, the context information is associated with first identification information that identifies a user of the terminal device as a subscriber, and is linked to temporary second identification information that replaces the first identification information;
The communication control device according to claim 1 , wherein the acquisition unit acquires the context information linked to the second identification information. the acquisition unit acquires, as target context information to be used in generating the model, the context information associated with the second identification information corresponding to the first identification information of a subscriber user who subscribes to a connection service in which a predetermined frequency band is preferentially used among the users, and acquires information on a frequency band used by a terminal device of the subscriber user when the target context information was acquired;
the generation unit generates the model for each of the subscribing users by learning a relationship between the target context information acquired for each of the subscribing users and the result information;
The communication control device according to claim 4 , wherein the determination unit determines a target frequency band to be preferentially used by the terminal device for each of the subscriber users based on the model generated for each of the subscriber users. the second identification information is associated with the determined target frequency band;
5. The communication control device according to claim 4, wherein the control unit converts the second identification information associated with the frequency band to be used into the first identification information corresponding to the second identification information, and registers association information that associates the converted first identification information with third identification information that indicates a priority of the frequency band to be used in a subscriber information database in which the first identification information is stored. The communication control device according to claim 6 ;
a base station that transmits the context information to the communication control device;
a core network to which the base station is connected;
A wireless communication system comprising:
A wireless communication system in which, when the terminal device accesses the base station, a predetermined core network device included in the core network connected to the base station performs authentication processing for the terminal device based on identification information obtained from the terminal device and the first identification information registered in the subscriber information database, and if the terminal device is successfully authenticated, transmits the third identification information corresponding to the authenticated terminal device to the base station to be accessed. The wireless communication system according to claim 7, wherein the base station to be accessed communicates wirelessly with the terminal device using the frequency band to be used that is prioritized in the third identification information obtained from the specified core network device. An information processing method executed by a communication control device,
an acquisition step of acquiring, as context information of a user of a terminal device, traffic information relating to traffic generated by the terminal device in wireless communication with a base station and movement information relating to movement of the terminal device in response to the traffic;
a generation step of generating a model indicating a tendency of the user's context according to a frequency band by learning a relationship between result information indicating whether or not a frequency band used by the terminal device when the context information is acquired, among frequency bands that the base station can support, is optimal for the context information, and the context information;
a determining step of determining a frequency band to be used preferentially by the terminal device in the wireless communication based on the model;
a control step of controlling the wireless communication to be performed in the target frequency band;
A communication control method including: an acquisition procedure for acquiring, as context information of a user of a terminal device, traffic information relating to traffic generated by the terminal device in wireless communication with a base station and movement information relating to movement of the terminal device in response to the traffic;
a generation procedure for generating a model indicating a tendency of the user's context according to a frequency band by learning result information indicating whether or not a frequency band used by the terminal device when the context information is acquired, among frequency bands that the base station can support, is optimal for the context information, and the relationship with the context information;
a determination procedure for determining a frequency band to be preferentially used by the terminal device in the wireless communication based on the model;
a control procedure for controlling the wireless communication to be performed in the target frequency band;
A communication control program that causes a computer to execute the above.