Base station, terminal device, program, communication method, and data generation method

Abstract

To provide a base station, a terminal device, a program, a communication method, and a data generation method capable of collecting learning data for machine learning from terminal devices that are not in a state in which learning data can be generated.SOLUTION: In a communication system including a base station and a user device, the base station transmits information (start instruction) instructing the terminal to transition to a state in which the terminal can generate learning data to the user device ST11, transmits a signal (beam sweep) used by the user device to generate learning data to the terminal device ST12, receives the learning data transmitted from the user device ST13, and performs machine learning using the received learning data ST14.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a base station, a terminal device, a program, a communication method, and a data generation method. [Background technology]

[0002] In conventional communication systems, data used for machine learning (hereinafter referred to as "learning data") cannot be collected from terminal devices (UE (user equipment)) that are not in an active state, such as an idle state or an inactive state. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] 3GPP TR 38.802, September 2017 [Retrieved September 27, 2022] Internet<URL:https: / / www.3gpp.org / ftp / Specs / archive / 38_series / 38.802 / 38802-e20.zip> [Non-patent document 2] R1-2203143(#109e Huawei Contribution), May 9-20, 2022 [Retrieved September 27, 2022] Internet<URL:https: / / www.3gpp.org / ftp / TSG_RAN / WG1_RL1 / TSGR1_109-e / Docs / R1-2203143.zip> Summary of the Invention [Problem to be solved by the invention]

[0004] The problem that the embodiments of the present invention aim to solve is to provide a base station, a terminal device, a program, a communication method, and a data generation method that can collect learning data for machine learning from a terminal device that is not in a state where it is possible to generate learning data. [Means for solving the problem]

[0005] A base station according to an embodiment includes a base station communication unit. The base station communication unit transmits, to a terminal device, information instructing the terminal device to transition to a state in which training data can be generated. The base station communication unit transmits, to the terminal device, a signal used by the terminal device to generate training data. The base station communication unit receives the training data transmitted from the terminal device. [Effects of the Invention]

[0006] The present invention can collect learning data for machine learning from terminal devices that are not in a state where they can generate learning data. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a block diagram showing an example of a communication system according to an embodiment and a main configuration of components included in the communication system; [Figure 2] 2 is a flowchart showing an example of processing by a processor of the base station in FIG. 1; [Figure 3] 2 is a flowchart showing an example of processing by a processor of the base station in FIG. 1; [Figure 4] 2 is a flowchart showing an example of processing by a processor of the base station in FIG. 1; [Figure 5] 2 is a flowchart showing an example of processing by a processor of the user device in FIG. 1; [Figure 6] 2 is a flowchart showing an example of processing by a processor of the user device in FIG. 1; [Figure 7] FIG. 2 is a sequence diagram showing an example of an information flow in the communication system according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, a communication system according to an embodiment will be described with reference to the drawings. Note that the scale of each part in each drawing used in the following description of the embodiment may be changed as appropriate. Also, for the sake of explanation, each drawing used in the following description of the embodiment may omit configurations. Also, in each drawing and in this specification, the same reference numerals indicate similar elements. FIG. 1 is a block diagram showing an example of a communication system 1 according to an embodiment and a main configuration of components included in the communication system 1. The communication system 1 is, for example, a system that provides communication services to users. The communication system 1 includes, as an example, a base station 100 and a user device 200. The communication system 1 typically includes multiple base stations 100 and multiple user devices 200. However, the following description will focus on one base station 100 and one user device 200.

[0009] The base station 100 communicates with user devices 200 within its communication range. In this way, the communication system 1 provides communication services to the users. The base station 100 includes, for example, a processor 101, a read-only memory (ROM) 102, a random-access memory (RAM) 103, an auxiliary storage device 104, a wireless I / F (interface) 105, and a network I / F (interface) 106. A bus 107 and the like connect these components together.

[0010] The processor 101 is the central part of a computer that performs various calculations and processes, such as calculations and controls, necessary for the operation of the base station 100. The processor 101 is, for example, a central processing unit (CPU), a microprocessing unit (MPU), a system on a chip (SoC), a digital signal processor (DSP), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field-programmable gate array (FPGA). Alternatively, the processor 101 may be a combination of several of these. The processor 101 may also be a combination of these with a hardware accelerator or the like. The processor 101 controls each unit to realize various functions of the base station 100 based on programs such as firmware, system software, and application software stored in the ROM 102 or the auxiliary storage device 104. The processor 101 also executes the processes described below based on the programs. Note that some or all of the programs may be incorporated into the circuitry of the processor 101.

[0011] The ROM 102 and RAM 103 are main storage devices of the computer with the processor 101 at its core. The ROM 102 is a non-volatile memory used exclusively for reading data. The ROM 102 stores, for example, firmware among the above programs. The ROM 102 also stores data used by the processor 101 when it performs various processes. The RAM 103 is a memory used for reading and writing data. The RAM 103 is used as a work area for storing data that is temporarily used when the processor 101 performs various processes. The RAM 103 is typically a volatile memory.

[0012] The auxiliary storage device 104 is an auxiliary storage device of a computer centered around the processor 101. The auxiliary storage device 104 is, for example, an EEPROM (electric erasable programmable read-only memory), an HDD (hard disk drive), or a flash memory. The auxiliary storage device 104 stores, for example, system software and application software among the above programs. The auxiliary storage device 104 also stores data used by the processor 101 when performing various processes, data generated by the processes in the processor 101, various setting values, and the like.

[0013] The wireless I / F 105 is an interface for performing wireless communication. The wireless I / F 105 includes, for example, an antenna for wireless communication. The base station 100 uses the wireless I / F 205 to communicate with user devices 200 and the like within its communication range. The processor 101 functions as an example of a base station communication unit in cooperation with the wireless I / F 105. The wireless I / F 105 is an example of a communication device. The processor 101, which controls the wireless I / F 105, functions as an example of a base station communication control unit that controls the communication device.

[0014] The network I / F 106 is an interface for the base station 100 to communicate via a network NW etc. The user device 200 is connected to the network NW via the base station 100. The network NW is typically a communication network including the Internet. The network NW is typically a communication network including a WAN (wide area network). The network NW may be a wireless line, a wired line, or a combination of wireless and wired lines.

[0015] The bus 107 includes a control bus, an address bus, a data bus, etc., and transmits signals exchanged among the various parts of the base station 100 .

[0016] The user device 200 is, for example, a device capable of communicating with the base station 100. The user device 200 is, for example, a device used by a user who utilizes a communication service. The user device 200 is, for example, a smartphone, a tablet terminal, a laptop PC, etc. The user device 200 includes, for example, a processor 201, a ROM 202, a RAM 203, an auxiliary storage device 204, a wireless I / F 205, and a touch panel 206. A bus 207 and the like connect these components. The user device 200 is an example of a terminal device.

[0017] The processor 201 is the central part of a computer that performs various calculations and processes, such as calculations and controls, necessary for the operation of the user device 200. The processor 201 may be, for example, a CPU, MPU, SoC, DSP, GPU, ASIC, PLD, or FPGA. Alternatively, the processor 201 may be a combination of several of these. The processor 201 may also be a combination of these with a hardware accelerator. The processor 201 controls each component to realize various functions of the user device 200 based on programs such as firmware, system software, and application software stored in the ROM 202 or the auxiliary storage device 204. The processor 201 also executes the processes described below based on the programs. Note that some or all of the programs may be incorporated into the circuitry of the processor 201.

[0018] The ROM 202 and RAM 203 are main storage devices of the computer with the processor 201 at its core. The ROM 202 is a non-volatile memory used exclusively for reading data. The ROM 202 stores, for example, firmware among the above programs. The ROM 202 also stores data used by the processor 201 when it performs various processes. The RAM 203 is a memory used for reading and writing data. The RAM 203 is used as a work area for storing data that is temporarily used when the processor 201 performs various processes. The RAM 203 is typically a volatile memory.

[0019] The auxiliary storage device 204 is an auxiliary storage device of a computer centered around the processor 201. The auxiliary storage device 204 is, for example, an EEPROM, a HDD, or a flash memory. The auxiliary storage device 204 stores, for example, system software and application software among the above programs. The auxiliary storage device 204 also stores data used by the processor 201 when performing various processes, data generated by the processes in the processor 201, various setting values, and the like.

[0020] The wireless I / F 205 is an interface for wireless communication. The wireless I / F 205 includes, for example, an antenna for wireless communication. The user device 200 communicates with the base station 100 and the like using the wireless I / F 205. The processor 201 functions as an example of a terminal communication unit in cooperation with the wireless I / F 205. The wireless I / F 205 is an example of a communication device. The processor 201, which controls the wireless I / F 205, functions as an example of a terminal communication control unit that controls the communication device.

[0021] Touch panel 206 is a stack of a display, such as a liquid crystal display or an organic EL (electro-luminescence) display, and a pointing device that accepts touch input. The display of touch panel 206 functions as a display device that displays a screen for notifying the operator of user device 200 of various information. Touch panel 206 also functions as an input device that accepts touch operations by the operator. Note that the display device and input device are not limited to touch panels.

[0022] The bus 207 includes a control bus, an address bus, a data bus, etc., and transmits signals exchanged among the various parts of the user device 200 .

[0023] The operation of the communication system 1 according to the embodiment will be described below with reference to FIGS. 2 to 7. Note that the processing described below is merely an example, and various other processing may be used as appropriate to achieve similar results. FIGS. 2 to 4 are flowcharts illustrating an example of processing performed by the processor 101 of the base station 100. The processor 101 executes the processing illustrated in FIGS. 2 to 4 based on a program stored in, for example, the ROM 102 or the auxiliary storage device 104. FIGS. 5 and 6 are flowcharts illustrating an example of processing performed by the processor 201 of the user device 200. The processor 201 executes the processing illustrated in FIGS. 5 and 6 based on a program stored in, for example, the ROM 202 or the auxiliary storage device 204. FIG. 7 is a sequence diagram illustrating an example of information flow in the communication system 1. FIG. 7 is a sequence diagram illustrating a case where the base station 100 executes the processing illustrated in FIG. 4 following the processing illustrated in FIG. 2, and the user device 200 executes the processing illustrated in FIG. 6 following the processing illustrated in FIG. 5. Note that FIG. 7 does not comprehensively illustrate the information flow in the communication system 1, and information flows not illustrated may exist.

[0024] When collecting training data from user equipment 200 in an idle state or an inactive state, the processor 101 of the base station 100 executes the process shown in Fig. 2. When collecting training data from user equipment 200 in an active state, the processor 101 executes the process shown in Fig. 3. The active state is also called a connected state.

[0025] The user equipment 200 in the idle state cannot generate training data. The idle state is, for example, a state in which some bearers are established.

[0026] A user equipment 200 in an inactive state cannot generate training data. The inactive state is, for example, a state in which the user equipment 200 is disconnected from a radio access network (RAN). However, the core network retains session information for the user equipment 200 in the inactive state. A transition from the inactive state to the active state requires fewer signaling procedures than a transition from the idle state to the active state.

[0027] The user equipment 200 in the active state is capable of generating training data. The active state is, for example, a state in which all bearers are established.

[0028] In step ST11 of FIG. 2, the processor 101 of the base station 100 generates start instruction information. The start instruction information is, for example, information instructing the user equipment 200 to transition to a state in which learning data can be generated. The state in which learning data can be generated is, for example, an active state. After generating the start instruction information, the processor 101 instructs the wireless I / F 105 to transmit the start instruction information to the user equipment 200. Upon receiving this transmission instruction, the wireless I / F 105 transmits the start instruction information to the user equipment 200. Note that, for example, a system information block (SIB) or paging DCI (downlink control information) is used to transmit the start instruction information. That is, the SIB or paging DCI includes the start instruction information. The transmitted start instruction information is received by the wireless I / F 205 of the user equipment 200.

[0029] The processor 101 works in cooperation with the wireless I / F 105 to perform the processing of step ST11, thereby functioning as an example of a base station communication unit that transmits information to the terminal device instructing it to transition to a state in which learning data can be generated.

[0030] Meanwhile, the processor 201 of the user device 200 starts the processing of FIG. 5, for example, when the user device 200 is started. 5, the processor 201 determines whether the user device 200 is in an active state. If the user device 200 is not in an active state, that is, if the user device 200 is in an idle state or an inactive state, the processor 201 determines No in step ST31 and proceeds to step ST32.

[0031] In step ST32, the processor 201 waits for reception of start instruction information via the wireless I / F 205. If the start instruction information is received, the processor 201 determines Yes in step ST32 and proceeds to step ST33. Note that in Fig. 7, the transmission and reception of the start instruction information is shown as step S1.

[0032] The processor 201 cooperates with the wireless I / F 205 to function as an example of a terminal communication unit that receives start instruction information from the base station to instruct the terminal to transition to a state in which learning data can be generated.

[0033] In step ST33 of FIG. 5, the processor 201 performs a process of changing the user device 200 from an idle state or an inactive state to an active state.

[0034] By performing the processing of steps ST32 and ST33, processor 201 functions as an example of a transition unit that transitions the terminal device to a state in which learning data can be generated when it receives information instructing it to transition to a state in which learning data can be generated.

[0035] In step ST34, the processor 201 determines whether or not a beam for beam sweep has been received by the wireless I / F 105. If a beam has not been received, the processor 201 determines No in step ST34 and proceeds to step ST35. Note that in FIG. 7, the transmission and reception of the beam is shown as step S2.

[0036] A beam for beam sweeping is an example of a signal used to generate training data. The processor 201 cooperates with the wireless I / F 205 to receive beams for beam sweeping, thereby functioning as an example of a terminal communication unit that receives signals used to generate training data from a base station.

[0037] In step ST35, the processor 201 determines whether the user device 200 is in an active state. If the user device 200 is not in an active state, the processor 201 determines No in step ST35 and returns to step ST31. On the other hand, if the user device 200 is in an active state, the processor 201 determines Yes in step ST35 and returns to step ST34. Thus, the processor 201 enters a standby state in which it repeats steps ST34 and ST35 until a beam is received or the user device 200 is no longer in an active state.

[0038] Meanwhile, in step ST12 of FIG. 2, the processor 101 of the base station 100 executes a full beam sweep. A beam sweep is a process of transmitting beams in multiple different directions. A direction ID (identifier) ​​is assigned to each direction in which a beam is transmitted. The direction ID is identification information uniquely assigned to each direction. The direction ID may be referred to as an SSB (Synchronization Signal / PBCH (Physical Broadcast Channel) block) ID, for example. The full beam sweep of step ST12 is a full beam sweep of an SCI-RS (channel state information reference signal). A beam transmitted in a beam sweep includes the direction ID of the beam. A full beam sweep is a beam sweep in which a beam is transmitted in all directions within a predetermined range. Here, all directions refer to all directions to which direction IDs are assigned.

[0039] The processor 101 works in cooperation with the wireless I / F 105 to perform the processing of step ST12, thereby functioning as an example of a base station communication unit that transmits to the terminal device a signal that the terminal device uses to generate learning data.

[0040] On the other hand, if a beam is received while processor 201 of user device 200 is in a standby state where steps ST34 and ST35 in FIG. 5 are repeated, processor 201 determines "Yes" in step ST34 and proceeds to step ST36.

[0041] In step ST36, processor 201 generates training data by measuring the reception strength (reference signal received power (RSRP)) of each beam received in step ST34. The training data includes, for example, the reception strength of each beam and location information of user device 200. Note that processor 201, for example, associates the reception strength of a beam with the direction ID of the beam and includes it in the training data. Processor 201 also detects the optimal narrow beam. The training data includes information indicating which beam is the optimal narrow beam. The optimal narrow beam is the beam with the highest reception strength.

[0042] By performing the processes of steps ST34 and ST36, the processor 201 functions as an example of a generating unit that, when receiving a signal used to generate learning data, generates learning data using the signal.

[0043] In step ST37, the processor 201 performs feedback on the beam sweep. That is, the processor 201 instructs the wireless I / F 205 to transmit the learning data generated in step ST36 to the base station 100. In response to this transmission instruction, the wireless I / F 205 transmits the learning data to the base station 100. The transmitted learning data is received by the wireless I / F 105 of the base station 100. After processing step ST37, the processor 201 returns to step ST34.

[0044] The processor 201 cooperates with the wireless I / F 205 to perform the process of step ST37, thereby functioning as an example of a terminal communication unit that transmits learning data.

[0045] 2, the processor 101 of the base station 100 waits for the wireless I / F 105 to receive learning data. If the learning data is received, the processor 101 determines "Yes" in step ST13 and proceeds to step ST14. In FIG. 7, the transmission and reception of learning data is shown as step S3.

[0046] The processor 101 cooperates with the wireless I / F 105 to perform the process of step ST13, thereby functioning as an example of a base station communication unit that receives learning data transmitted from the terminal device.

[0047] In step ST14, processor 101 performs machine learning using the learning data received in step ST13. For example, processor 101 performs machine learning using the beam direction and the position information of user device 200 as explanatory variables and the beam reception strength as a target variable. Through such machine learning, processor 101 generates AI (artificial intelligence) for determining the optimal beam direction. Note that the learning in step ST14 may be additional learning or other learning. After processing step ST14, processor 101 ends the processing shown in FIG. 2.

[0048] Furthermore, the processor 101 does not need to perform learning every time learning data is received. For example, the processor 101 performs learning at predetermined time intervals using learning data received during the passage of the predetermined time. Alternatively, the processor 101 does not perform learning until the amount of learning data not used for learning reaches or exceeds a predetermined amount, and when the amount reaches or exceeds the predetermined amount, it performs learning using the predetermined amount of learning data not used for learning.

[0049] In the process of FIG. 3, processor 101 performs the processes of steps ST12 to ST14 in the same manner as in the process of FIG.

[0050] Furthermore, when processor 101 connects to user device 200 using the trained AI, it executes the processing shown in Fig. 4. Furthermore, when processor 101 connects to user device 200 following the processing of Fig. 2 or Fig. 3, it proceeds to the processing of Fig. 4 after the processing of Fig. 2 or Fig. 3.

[0051] 5. When connecting to the base station 100 following the transmission of the training data, the processor 201 of the user device 200 starts the process of FIG. 6 after the process of step ST37 of FIG.

[0052] In step ST21 of Figure 4, processor 101 of base station 100 performs a sparse beam sweep. Unlike a full beam sweep, a sparse beam sweep transmits beams in discrete directions rather than in all directions. Therefore, a sparse beam sweep transmits fewer beams than a full beam sweep. A sparse beam sweep is also called an SSB beam sweep. Note that in Figure 7, the transmission and reception of an SSB beam sweep is shown as step S4.

[0053] 6, processor 201 of user device 200 waits for a beam for beam sweep to be received by wireless I / F 205. If a beam for beam sweep is received, processor 201 determines "Yes" in step ST41 and proceeds to step ST42.

[0054] In step ST42, the processor 201 measures the reception strength of each beam received in step ST41.

[0055] In step ST43, the processor 201 performs feedback on the beam sweep. That is, the processor 201 instructs the wireless I / F 205 to transmit the measurement results measured in step ST42 and the location information of the user device 200 to the base station 100. Upon receiving this transmission instruction, the wireless I / F 205 transmits the measurement results and the location information to the base station 100. The transmitted measurement results and location information are received by the wireless I / F 105 of the base station 100.

[0056] 4, the processor 101 of the base station 100 waits for the measurement results and location information to be received by the wireless I / F 105. If the measurement results and location information are received, the processor 101 determines "Yes" in step ST22 and proceeds to step ST23. Note that in FIG. 7, the transmission and reception of the measurement results and location information is shown as step S5.

[0057] In step ST23, the processor 101 infers an optimal beam using the measurement results and location information received in step ST22 and the trained AI. The trained AI is, for example, the AI ​​trained in step ST14 of FIG. 2 or 3. The trained AI, for example, receives the measurement results and location information as input and outputs information indicating which direction the beam is suitable for communication with the user device 200. The trained AI, for example, receives the measurement results and location information as input and outputs an optimality for each direction. The optimality is a value indicating how suitable a beam is for communication with the user device 200. The trained AI, for example, receives the measurement results and location information as input and selects the top k beams suitable for communication with the user device 200. Note that k is an integer equal to or greater than 1. Preferably, k is an integer equal to or greater than 2. k may be fixed or not. The trained AI, for example, selects a beam whose optimality is equal to or greater than a predetermined value. In this case, the number of selected beams is k. The trained AI, for example, takes the measurement results and location information as input and selects beams suitable for communication with user device 200 that have an optimality equal to or greater than a predetermined value. The trained AI, for example, takes the measurement results and location information as input and outputs information indicating the degree to which each direction is a beam suitable for communication with user device 200. Note that the beam selected by the trained AI is selected, for example, from beams in all directions.

[0058] In step ST24, the processor 101 executes a Top-k beam sweep, which is a beam sweep that transmits the k beams selected in step ST23.

[0059] Meanwhile, in step ST44 of Fig. 6, processor 201 of user device 200 waits for a beam for beam sweep to be received by wireless I / F 205. If a beam for beam sweep is received, processor 201 determines "Yes" in step ST44 and proceeds to step ST45. Note that in Fig. 7, the transmission and reception of Top-k beam sweep is shown as step S6.

[0060] In step ST45, the processor 201 measures the reception strength of each beam received in step ST44.

[0061] In step ST46, the processor 201 performs feedback on the beam sweep. That is, the processor 201 instructs the wireless I / F 205 to transmit the measurement result measured in step ST45 to the base station 100. Upon receiving this transmission instruction, the wireless I / F 205 transmits the measurement result to the base station 100. The transmitted measurement result is received by the wireless I / F 105 of the base station 100.

[0062] In step ST25, the processor 101 waits for the measurement result to be received by the wireless I / F 105. If the measurement result is received, the processor 101 determines "Yes" in step ST25 and proceeds to step ST26. In FIG. 7, the transmission and reception of the measurement result is shown as step S7.

[0063] In step ST26, processor 101 determines a beam to be used for communication with user device 200 from among the k beams selected in step ST23. For example, processor 101 refers to the measurement results received in step ST25 and determines the beam with the highest reception strength to be the optimal beam for communication with user device 200, and determines it as the beam to be used for communication with user device 200.

[0064] As described above, by performing the processes of steps ST23 to ST26, the processor 101 functions as an example of a decision unit that decides a communication method with a terminal device using a trained AI that has undergone machine learning using training data.

[0065] In step ST27, the processor 101 starts transmitting information using the beam determined in step ST26. After the process of step ST27, the processor 101 ends the process of FIG.

[0066] On the other hand, in step ST47 of Fig. 6, the processor 201 of the user device 200 starts receiving information transmitted from the base station 100. This information is the information whose transmission started in step ST27 of Fig. 3. After processing step ST47 of Fig. 6, the processor 201 ends the processing shown in Fig. 6.

[0067] The base station 100 and the user device 200 start communication using the beam determined in step ST26 in Fig. 4 through the processes of step ST27 in Fig. 4 and step ST47 in Fig. 6. In Fig. 7, this communication is shown as step S8.

[0068] According to the communication system 1 of the embodiment, the base station 100 instructs the user equipment 200 in the idle state or the inactive state to transition to the active state. Then, the base station 100 transmits a beam that the user equipment 200 uses to generate training data. This allows the communication system 1 of the embodiment to collect training data from the user equipment 200 in the idle state or the inactive state.

[0069] When the number of active user devices 200 within a cell (communication range of the base station 100) is small, machine learning may not be performed correctly. Specifically, a small amount of training data may result in degraded inference performance. Furthermore, in cases where the location of the user device 200 is dependent (e.g., beam management), learning may be optimized for a specific location, resulting in a loss of generalization performance. Furthermore, when calling the user device 200 from the base station 100 side without using the method of the embodiment, initial access must be performed, which incurs beam search overhead for initial access.

[0070] The communication system 1 of the embodiment uses training data generated by the user device 200 for AI training to determine the direction of the optimal beam to be used for communication between the base station 100 and the user device 200. This makes it easier for the communication system 1 of the embodiment to determine the optimal beam. Furthermore, the communication system 1 of the embodiment improves the accuracy of determining the optimal beam.

[0071] According to the communication system 1 of the embodiment, the base station 100 uses AI trained with training data generated by the user device 200 to determine the direction of the optimal beam to be used for communication between the base station 100 and the user device 200. This makes it easier for the communication system 1 of the embodiment to determine the optimal beam. Furthermore, the communication system 1 of the embodiment improves the accuracy of determining the optimal beam.

[0072] According to the communication system 1 of the embodiment, the base station 100 transmits the start indication information using the SIB or the paging DCI, which allows the base station 100 of the embodiment to activate the user equipment 200 with fewer steps than other methods.

[0073] The above embodiment can be modified as follows. In the above embodiment, the base station 100 performs machine learning using the training data. However, a server (not shown) may also perform the machine learning. In this case, the base station 100 transmits the training data to the server via, for example, the network I / F 106 and the network NW. The base station 100 then receives the trained AI, which has been trained using the training data, from the server.

[0074] In the above embodiment, the communication system 1 determines the beam direction using the trained AI. However, the communication system 1 may also determine parameters other than the beam direction using the trained AI.

[0075] In the above embodiment, the training data is data indicating the reception intensity of the beam, etc. However, the training data may be other data.

[0076] The start instruction information may include information specifying a reference signal for which the reception strength is to be observed, thereby reducing the overhead of the communication system 1.

[0077] In response to receiving the start instruction information, the user device 200 may transition to a state (CSI-RS occasion) in which the CSI-RS is accepted. In this case, the start instruction information is information indicating that the user device 200 will transition to a state in which the CSI-RS is accepted. This reduces overhead in the communication system 1.

[0078] The processor 101 and the processor 201 may implement part or all of the processing that is implemented by a program in the above-described embodiments by a hardware circuit configuration.

[0079] The program for implementing the processes of the embodiments is transferred, for example, stored in a non-transitory storage medium within the device. However, the device may also be transferred without the program stored therein. The program may then be transferred separately and written to the device. The program may be transferred, for example, by recording it on a removable non-transitory storage medium or by downloading it via a network such as the Internet or a local area network (LAN).

[0080] Although the embodiments of the present invention have been described above, they are merely examples and are not intended to limit the scope of the present invention. The embodiments of the present invention can be implemented in various forms without departing from the spirit of the present invention. [Explanation of symbols]

[0081] 1. Communication Systems 100 base stations 101,201 processors 102,202 ROM 103,203 RAM 104,204 Auxiliary storage 105,205 Wireless I / F 106 Network I / F 107,207 buses 200 user devices 206 Touch Panel

Claims

1. A base station comprising a base station communication unit that transmits information to a terminal device instructing the terminal device to transition to a state in which it is possible to generate learning data, transmits a beam to the terminal device, which is a signal used by the terminal device to generate learning data, and receives the learning data transmitted from the terminal device, the learning data including a reception strength associated with a direction ID of the beam.

2. The base station according to claim 1 , wherein the training data is training data for use in AI machine learning to determine the direction of a beam to be used for communication between the base station and the terminal device.

3. The base station according to claim 1 , further comprising a decision unit that decides a communication method with the terminal device using trained AI that has performed machine learning using the training data.

4. The base station according to claim 1 , wherein the base station communication unit transmits an SIB including the information or a paging DCI including the information.

5. a terminal communication unit that receives, from a base station, information instructing the terminal to transition to a state in which training data can be generated, receives from the base station a beam that is a signal used to generate the training data, and transmits the training data; a transition unit that transitions the terminal device to a state in which the training data can be generated when the information is received; The terminal device is equipped with a generation unit that, when receiving the signal, uses the signal to associate the measured receiving strength of the beam with the direction ID of the beam, includes it in the learning data, and generates the learning data.

6. A processor provided in a base station having a communication device, A program that functions as a base station communication control unit that sends information to a terminal device instructing the terminal device to transition to a state in which learning data can be generated, sends a beam to the terminal device, which is a signal used by the terminal device to generate learning data, and controls the communication device to receive the learning data sent from the terminal device, which includes a reception strength associated with the beam direction ID.

7. A processor included in a terminal device having a communication device, a terminal communication control unit that receives, from a base station, information instructing the communication device to transition to a state in which training data can be generated, receives from the base station a beam that is a signal used to generate the training data, and controls the communication device to transmit the training data; a transition unit that transitions the terminal device to a state in which the training data can be generated when the information is received; A program that functions as a generation unit that, when the signal is received, uses the signal to associate the measured reception strength of the beam with the direction ID of the beam, includes it in the learning data, and generates the learning data.

8. A communication method in which a base station transmits information to a terminal device instructing the terminal device to transition to a state in which it is possible to generate training data, the base station transmits a beam, which is a signal used by the terminal device to generate training data, to the terminal device, and the base station receives the training data transmitted from the terminal device, the training data including a reception strength associated with a direction ID of the beam.

9. receiving information from the base station instructing the device to transition to a state in which learning data can be generated; When the information is received, the terminal device transitions to a state in which it is possible to generate learning data; receiving a beam from the base station, the beam being a signal used to generate training data; When the signal is received, the signal is used to associate the measured reception strength of the beam with the direction ID of the beam, and the received strength is included in the training data to generate the training data; A data generation method that transmits the training data.

Images