Terminal device and communication method

Abstract

A terminal device according to an embodiment comprises a control unit. The control unit receives a downlink reference signal included in a physical downlink control channel (PDCCH). The control unit transmits reference information relating to the downlink reference signal to an information processing device. The reference information is used in order to predict channel information using an uplink reference signal.

Description

Terminal Apparatus and Communication Method

[0001] The disclosed embodiments relate to a terminal apparatus and a communication method.

[0002] Conventionally, there has been known a technique of estimating a channel between a base station and a terminal apparatus by using a reference signal, and performing beamforming in accordance with the estimated channel (see, for example, Patent Document 1).

[0003] International Publication No. 2013 / 129146

[0004] A terminal apparatus according to an embodiment includes a control unit. The control unit receives a downlink reference signal included in a PDCCH (Physical Downlink Control Channel). The control unit transmits reference information related to the downlink reference signal to an information processing apparatus. The reference information is used for prediction of channel information using an uplink reference signal.

[0005] FIG. 1 is a diagram for explaining an example of beamforming in downlink communication. FIG. 2 is a diagram for explaining an example of beamforming in downlink communication. FIG. 3 is a diagram illustrating an example of beamforming using SRS. FIG. 4 is a diagram illustrating another example of beamforming using SRS. FIG. 5 is a diagram illustrating an estimation example of channel information using an AI model. FIG. 6 is a diagram illustrating an example of a schematic configuration of a communication system according to an embodiment. FIG. 7 is a block diagram illustrating a configuration example of a storage device according to an embodiment. FIG. 8 is a diagram illustrating a configuration example of an information processing apparatus according to an embodiment. FIG. 9 is a diagram illustrating an example of a slot format in downlink communication. FIG. 10 is a diagram illustrating an example of a slot format in downlink communication. FIG. 11 is a block diagram illustrating a configuration example of a terminal apparatus according to an embodiment. FIG. 12 is a diagram for explaining a generation example of reference information according to an embodiment. FIG. 13 is a diagram for explaining an example of estimation information according to an embodiment. FIG. 14 is a sequence diagram illustrating an example of a flow of information processing according to an embodiment. FIG. 15 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

[0006] The following describes in detail, with reference to the drawings, the embodiments for implementing the terminal device and communication method according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the terminal device and communication method according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant explanations are omitted. Also, in the following, AI (artificial intelligence) model and machine learning model are treated as synonymous terms.

[0007] In mobile communications using RIC (RAN Intelligent Controller), one of the 5G wireless network technologies, AI (Artificial Intelligence) models are sometimes used to estimate received data. By using AI models to estimate received data, improvements in the performance of data estimation can be expected.

[0008] The technology disclosed herein can improve communication quality and streamline operations through the use of AI, and will serve as an innovative technological foundation in the telecommunications business, thereby contributing to the achievement of Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0009] (Embodiment) [1. Introduction] [1-1. Beamforming] Communication using beamforming is performed between a base station and a terminal device. For example, a base station performs beamforming in downlink (DL) communication to a terminal device.

[0010] For example, in TDD (Time Division Duplex), the same frequency is used for downlink and uplink (UL) communication. Therefore, the base station may, for example, estimate channel information for DL ​​communication precoding from the SRS (Sounding Reference Signal). DL communication precoding is used for beamforming in DL communication from the base station to terminal equipment (also called UE (User Equipment)).

[0011] Figures 1 and 2 illustrate an example of beamforming in downlink communication. In Figure 1, three terminal devices each transmit different SRS signals to the base station. The base station calculates the DL precoding matrix w from the received SRS signals.

[0012] As shown in Figure 2, the base station uses the calculated DL pre-recording matrix w to generate a beam directed towards each terminal device and transmits a signal to the terminal device.

[0013] Figure 3 shows an example of beamforming using SRS. The upper part of Figure 3 shows an example of a slot format in TDD. SRS is transmitted in a special slot (indicated by "S" in Figure 3).

[0014] The base station uses SRS to perform beamforming in DL communication for slots 4 and beyond, starting from the slot that receives the SRS. For example, the base station uses beam #1, generated based on SRS #1, to perform DL communication using the DL slots indicated by the arrows in the upper diagram of Figure 3 (slots indicated as "D" in Figure 3) and a portion of the special slots.

[0015] Similarly, the base station uses beams #2 to #5 based on SRS #2 to #5 to perform DL communication with the terminal device. Therefore, even if the terminal device moves, the base station can maintain good communication with the terminal device by changing the direction of the beam.

[0016] [1-2. Problems] Here, SRS is a reference signal specific to the terminal device. Also, the SRS is transmitted in a fixed slot. Therefore, there is a problem that the interval between SRS transmissions by a single terminal device may become longer, for example, if the number of terminal devices connected to the base station increases.

[0017] This is because there is a limit to the number of SRS messages that can be transmitted in a single special slot. Therefore, as the number of terminal devices connected to the base station increases, the number of SRS messages transmitted increases, resulting in a longer interval between SRS messages transmitted by a single terminal device.

[0018] If the transmission interval of SRS increases, the accuracy of DL beamforming by the base station may decrease.

[0019] Figure 4 illustrates another example of beamforming using SRS. In Figure 4, for example, the number of terminal devices connected to the base station has increased, resulting in longer intervals between SRS signals transmitted from a single terminal device. For example, compared to Figure 3, in Figure 4, SRS signals #2 to #4 are not transmitted from the terminal device.

[0020] Therefore, the base station uses beam #1, which is generated based on SRS #1, to perform DL communication with the terminal device from the time it receives SRS #1 until it receives SRS #5. In the example in Figure 4, the base station uses beam #1, which is generated from SRS #1, to perform DL communication in the slot indicated by the arrow.

[0021] For example, if the terminal device moves as shown in Figure 4, there is a risk that the terminal device may not be able to receive beam #1. In this case, the terminal device may not be able to receive the DL signal from the base station until it transmits SRS #5.

[0022] Thus, as the transmission period of the SRS lengthens, it becomes difficult for the base station to track the beam as the terminal equipment moves. Consequently, as the transmission period of the SRS lengthens, it becomes difficult for the base station to perform beamforming in response to channel fluctuations caused by the movement of the terminal equipment, which may lead to a decrease in the accuracy of DL beamforming.

[0023] Therefore, a method can be considered to prevent a decrease in DL beamforming accuracy by estimating the SRS that the base station could not receive (SRS #2 to #4 in the example in Figure 4) using an SI model. Alternatively, instead of estimating the SRS, the base station may use an AI model to estimate channel information between itself and the terminal device.

[0024] Figure 5 shows an example of channel information estimation using an AI model. For example, a base station estimates SRS (or channel information) based on AI for RAN (Radio Access Network).

[0025] Here, AI for RAN is a technology that utilizes AI, machine learning, and other technologies to improve the frequency utilization efficiency and performance of existing RANs, as well as to automate base station operations and reduce power consumption. This technology is expected to optimize processing at all layers of the RAN, such as channel estimation and scheduling, through AI, optimize inter-cell communication in the RAN, and improve the equipment utilization rate of base stations.

[0026] In the example shown in Figure 5, an AI model generated based on AI for RAN is used to estimate the SRS that the base station did not receive.

[0027] In this case, the accuracy of the SRS (or channel information) estimation by the AI ​​model affects the accuracy of DL beamforming. In other words, to prevent a decrease in the accuracy of DL beamforming, it is necessary to improve the estimation accuracy of the AI ​​model.

[0028] To improve the estimation accuracy of an AI model, it is desirable to train the AI ​​model using a large amount of training data.

[0029] For example, if the number of terminal devices connected to the base station is small, the base station can receive more SRS from a single terminal device, as shown in Figure 3. For example, if the length of one slot in Figure 3 is 1 ms, the base station will receive SRS from a single terminal device at 10 ms intervals.

[0030] In this case, the base station can secure training data (for example, SRS, or channel information calculated from SRS) to estimate channel information at times when it does not receive SRS.

[0031] On the other hand, if the number of terminal devices connected to the base station is large, the number of SRS signals that the base station receives from a single terminal device decreases, as shown in Figure 4. For example, if the length of one slot in Figure 4 is 1 ms, the base station will receive SRS signals from a single terminal device at 40 ms intervals.

[0032] In this case, it cannot be said that the base station has secured training data (for example, SRS, or channel information calculated from SRS) to estimate channel information at times when it does not receive SRS.

[0033] Therefore, it is necessary to collect more training data to be used to train the AI ​​model that estimates channel information for DL ​​beamforming.

[0034] [1-3. Proposed Technology] In this proposed technology, the terminal device collects training data used to train the AI ​​model. The terminal device collects training data using, for example, the DL reference signal contained in the PDCCH (Physical Downlink Control Channel). For example, the terminal device transmits reference information regarding the DL reference signal contained in the PDCCH to an external device (for example, an information processing device). The reference information is used for predicting channel information using the UL reference signal (for example, SRS) by the base station. For example, the reference information is used to train the AI ​​model used for prediction.

[0035] [2. Communication System] [2-1. Outline Configuration] Figure 6 is a diagram showing an example of the outline configuration of the communication system SYS1 according to the embodiment. The communication system SYS1 shown in Figure 6 comprises a terminal device 10, a RAN (Radio Access Network) 20, and a storage device 30.

[0036] For example, terminal device 10 may be a desktop PC (Personal Computer), a notebook PC, a tablet device, a mobile phone, or a PDA (Personal Digital Assistant).

[0037] RAN20, for example, operates cell C1 and performs wireless communication with terminal devices 10 within cell C1. RAN20 includes an information processing device 100 and base stations 200. The information processing device 100 is, for example, an AI-RAN having a computing infrastructure and a learning infrastructure among the functions of RAN20. The information processing device 100 may be placed, for example, one per multiple base stations 200.

[0038] The AI-RAN information processing device 100 is deployed in a distributed manner across different regions. Thus, the AI-RAN information processing device 100 may be a cloud server distributed as an edge server (also known as a MEC server) near the terminal device 10. The information processing device 100 can achieve high speed, large capacity, and low latency by utilizing a closed network isolated from the internet. On the other hand, services that utilize the data collected by the information processing devices 100 in each region (for example, large-scale computations or learning that requires a lot of power) may be executed on the public cloud (not shown) via the internet.

[0039] The base station 200 is, for example, a communication device equipped with the function of a Radio Unit (RU). The RU has the function of transmitting and receiving radio waves to and from the terminal device 10 and converting signals between analog and digital.

[0040] The base station 200 may have at least some of the functions of a DU (Distributed Unit) and a CU (Central Unit) in addition to the functions of a RU. Furthermore, the information processing device 100 may have at least some of the functions of a DU and a CU.

[0041] A DU (Digital Unit) is a network element that performs physical layer processing. For example, a DU performs signal modulation, signal demodulation, radio resource allocation, and RLC (Radio Link Control) such as retransmission control. A CU (Control Unit) performs processing such as PDCP (Packet Data Convergence Protocol), which includes packet encryption, and RRC (Radio Resource Control), which includes radio resource management.

[0042] For the sake of simplicity, in the following explanation, it will be assumed that the information processing device 100 possesses the functions of both DU and CU.

[0043] The storage device 30 is, for example, a database device that stores information transmitted by the terminal device 10. The storage device 30 acquires and stores reference information, which will be described later, from the terminal device 10. The reference information is used, for example, for channel estimation between the base station 200 and the terminal device 10.

[0044] The storage device 30 may be implemented as a cloud server via the Internet, or may be implemented as an internal device of the information processing apparatus 100 or the terminal apparatus 10. Alternatively, the storage device 30 may be implemented as an edge server arranged near the information processing apparatus 100 or the terminal apparatus 10.

[0045] The storage device 30 may acquire the reference information from the terminal apparatus 10 via, for example, a wireless LAN or a cellular network via a base station 200. Alternatively, the storage device 30 may acquire the reference information from the terminal apparatus 10 via a wired cable or a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card.

[0046] The reference information collected by the storage device 30 from the terminal apparatus 10 is used, for example, for SRS estimation by a processing apparatus (not shown) or for generating an AI model for estimating channel information based on SRS. Generation of the AI model may be performed by the information processing apparatus 100 or the terminal apparatus 10 instead of a processing apparatus (not shown).

[0047] For example, when the storage device 30 acquires reference information from many terminal apparatuses 10, a higher-precision AI model can be generated. By using this AI model, the information processing apparatus 100 can estimate channel information between the information processing apparatus 100 and the terminal apparatus 10 with higher accuracy.

[0048] [2-2. Storage Device] FIG. 7 is a block diagram showing a configuration example of the storage device 30 according to the embodiment. The storage device 30 includes a communication unit 31, a storage unit 32, and a control unit 33. Note that the storage device 30 may include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator of the storage device 30, and a display unit (e.g., a liquid crystal display, etc.) that displays various types of information.

[0049] (Communication Unit 31) The communication unit 31 is implemented by, for example, a NIC (Network Interface Card). The communication unit 31 is connected to the network by wire or wireless connection and transmits and receives information to and from the information processing device 100, terminal device 10, etc. via the network. The network is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet.

[0050] (Storage Unit 32) The storage unit 32 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 7, the storage unit 32 has a reference information storage unit 32_1.

[0051] As described above, the reference information storage unit 32_1 stores the reference information acquired by the storage device 30 from the terminal device 10.

[0052] (Control Unit 33) The control unit 33 is a controller and is realized by the execution of various programs stored in the storage unit 32 inside the storage device 30 using RAM as a working area by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc. The control unit 33 is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0053] As shown in Figure 7, the control unit 33 has an acquisition unit 33_1 and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 33 is not limited to the configuration shown in Figure 7, and other configurations are also acceptable as long as they perform the information processing described later.

[0054] (Acquisition unit 33_1) The acquisition unit 33_1 acquires reference information from the terminal device 10, for example, via the communication unit 31. The acquisition unit 33_1 stores the acquired reference information in the reference information storage unit 32_1.

[0055] [2-3. Information Processing Device] Figure 8 is a diagram showing an example of the configuration of an information processing device 100 according to an embodiment. As shown in Figure 8, the information processing device 100 comprises a communication unit 110, a storage unit 120, and a control unit 130.

[0056] (Communication Unit 110) The communication unit 110 is implemented by, for example, a NIC. The communication unit 110 is connected to a network by wire or wireless. The network is, for example, a LAN, WAN, or the Internet. That is, the communication unit 110 is connected to a terminal device 10, a base station 200, or a storage device 30 via the network.

[0057] (Storage Unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs. For example, the storage unit 120 stores information transmitted and received via the communication unit 110. The storage unit 120 may also store applications and programs for realizing the functions of the information processing device 100, or it may store AI models, etc.

[0058] (Control Unit 130) The control unit 130 is a controller and is realized by the execution of various programs stored in the storage unit 32 inside the storage device 30 using RAM as a working area by a CPU or MPU. The control unit 33 is realized by an integrated circuit such as an ASIC or FPGA.

[0059] As shown in Figure 8, the control unit 130 includes a notification unit 131 and a transmission control unit 132, and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 8, and other configurations are also acceptable as long as they perform the information processing described later.

[0060] (Notification Unit 131) The notification unit 131 notifies the terminal device 10 of notification information regarding the DL reference signal transmitted by the PDCCH. The notification information may include, for example, resource information regarding the resource that transmits the DL reference signal, and transmission information regarding the transmission of the reference information to the storage device 30.

[0061] Resource information may include, for example, at least one of frequency resources and time resources used for transmitting DL reference signals. Transmission information may also include, for example, at least one of the following: information to be included in the reference information transmitted to the terminal device 10, transmission timing (or period), and information specifying the destination storage device 30.

[0062] For example, prior to transmitting the DL reference signal, the notification unit 131 notifies the terminal device 10 of notification information via the communication unit 110.

[0063] (Transmission control unit 132) The transmission control unit 132 controls, for example, the base station 200 to transmit a DL reference signal to the terminal device 10.

[0064] Figures 9 and 10 show an example of a slot format in downlink communication. For example, in DL communication, one slot contains both a PDCCH and a PDSCH (Physical Downlink Shared Channel). The PDCCH is transmitted by the first symbol of each DL slot. In Figure 10, the 4th, 6th, 7th, 9th-11th, 13th, and 14th symbols from the beginning are assigned PDSCH Type A. In addition, the 5th, 8th, and 12th symbols from the beginning are assigned PDSCH Type B. Furthermore, among the 1st, 5th, 8th, and 12th symbols from the beginning, the resource elements (REs) indicated by diagonal lines are assigned reference signals.

[0065] For example, in 5G, a reference signal is not always assigned to the first symbol of a slot, but the transmission control unit 132 can assign a reference signal to the first symbol and transmit PDCCH depending on the settings. Therefore, for example, the transmission control unit 132 may assign a DL reference signal to the first symbol of a slot to generate reference information.

[0066] Furthermore, in LTE, PDCCH is transmitted using the entire bandwidth. In 5G, PDCCH may be transmitted using only a portion of the bandwidth, or it may be transmitted using the entire bandwidth.

[0067] The transmission control unit 132 may, for example, transmit a DL reference signal using the entire bandwidth. This allows the terminal device 10 to generate reference information for estimating the channels across the entire bandwidth using the DL reference signal.

[0068] Furthermore, for example, if the length of one slot is 1 ms, the transmission control unit 132 can transmit DL reference signals to the terminal device 10 continuously at 1 ms intervals by transmitting DL reference signals using PDCCH.

[0069] Alternatively, the transmission control unit 132 may transmit DL reference signals at intervals corresponding to the SRS transmission interval. For example, as shown in Figure 3, the terminal device 10 transmits SRS to the base station 200 at 10ms intervals. Therefore, the transmission control unit 132 may transmit DL reference signals to the terminal device 10 at 10ms intervals to generate reference information.

[0070] Alternatively, the notification unit 131 may notify the terminal device 10 to generate reference information using DL reference signals received at 10ms intervals. For example, the notification unit 131 may notify the reception period of the DL reference signals as a time resource for resource information.

[0071] Examples of DL reference signals include LTE, NR, and in 5G, DMRS (Demodulation Reference Signal) transmitted via PDCCH.

[0072] [2-4. Terminal Device] Figure 11 is a block diagram showing an example configuration of a terminal device 10 according to the embodiment. The terminal device 10 includes a wireless communication unit 11, a communication unit 12, a storage unit 13, and a control unit 14. The terminal device 10 may also have an input unit (for example, a keyboard or mouse) for receiving various operations from the administrator of the terminal device 10, and a display unit (for example, a liquid crystal display) for displaying various information.

[0073] (Wireless communication unit 11) The wireless communication unit 11, for example, applies signal processing such as down-conversion and A / D conversion to the received signal received from the base station 200 via the antenna to generate received data. The wireless communication unit 11 also applies signal processing such as D / A conversion and up-conversion to the transmitted data to generate a transmitted signal, which is then transmitted to the base station 200 via the antenna. In this way, the wireless communication unit 11 performs wireless communication with the base station 200.

[0074] (Communication Unit 12) The communication unit 12 is implemented by, for example, a NIC. The communication unit 12 is connected to a network by wire or wireless connection and transmits and receives information to and from the storage device 30, etc. via the network. The network is, for example, a LAN, WAN, or the Internet.

[0075] (Storage Unit 13) The storage unit 13 is implemented by, for example, a semiconductor memory element such as RAM or flash memory, or a storage device such as a hard disk or optical disc. As shown in Figure 11, the storage unit 13 has a reference information storage unit 13_1. The reference information storage unit 13_1 stores the reference information generated by the processing unit 14_2, which will be described later.

[0076] (Control Unit 14) The control unit 14 is a controller and is implemented by a CPU or MPU, which executes various programs stored in the memory unit 13 inside the terminal device 10 using RAM as the working area. The control unit 14 is also implemented by an integrated circuit such as an ASIC or FPGA.

[0077] As shown in Figure 11, the control unit 14 includes an acquisition unit 14_1, a processing unit 14_2, and a notification unit 14_3, and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 14 is not limited to the configuration shown in Figure 11, and other configurations are also acceptable as long as they perform the information processing described later.

[0078] (Acquisition unit 14_1) The acquisition unit 14_1 acquires notification information from the information processing device 100 via, for example, the wireless communication unit 11. The acquisition unit 14_1 receives a DL reference signal from the base station 200 at the resource specified by the resource information included in the notification information.

[0079] The acquisition unit 14_1 receives, for example, a DL reference signal from a base station 200 to which the terminal device 10 is connected. Alternatively, the acquisition unit 14_1 may receive a DL reference signal from a base station 200 to which it is not connected. For example, the acquisition unit 14_1 may receive a DL reference signal from an adjacent base station adjacent to the base station 200 to which it is connected.

[0080] Thus, the DL reference signals acquired by the acquisition unit 14_1 are not limited to the base station 200 to which the device is connected, and DL reference information may be acquired from base stations 200 to which the device is not connected.

[0081] For example, typically, the terminal device 10 acquires the portion of the DL reference signal transmitted using the entire frequency band that is necessary for its own device, and discards the rest. On the other hand, in this embodiment, the acquisition unit 14_1 may acquire the DL reference signal using the entire frequency band, including the portion that would normally be discarded.

[0082] The acquisition unit 14_1 outputs the acquired DL reference signal to the processing unit 14_2.

[0083] (Processing Unit 14_2) Processing Unit 14_2 generates reference information relating to the DL reference signal acquired by Acquisition Unit 14_1. The reference information includes, for example, channel information corresponding to the DL reference signal. The reference information may also include, for example, information relating to at least one of the DL reference signal, terminal device 10, and base station 200 (or RAN 20) (hereinafter also referred to as additional information).

[0084] Furthermore, the information included in the reference information is not limited to channel information and / or additional information. The reference information may also include information other than channel information and / or additional information.

[0085] The processing unit 14_2 may generate reference information for all DL reference signals acquired by the acquisition unit 14_1, or it may generate reference information for some of the acquired DL reference signals.

[0086] Figure 12 is a diagram illustrating an example of reference information generation according to the embodiment. Figure 12 shows an example of a slot configuration.

[0087] As mentioned above, SRS is transmitted in special slots (slots indicated by "S" in Figure 12). If the length of one slot is 1 ms, the special slots are spaced 5 ms apart. Therefore, the shortest transmission interval for SRS is 5 ms.

[0088] Therefore, the processing unit 14_2 may generate reference information for the DL reference signal received at the same 5ms interval as the SRS transmission interval. This allows the processing unit 14_2 to generate training data (i.e., reference information) for generating the AI ​​model at the shortest SRS period, regardless of the SRS transmission interval set by the information processing device 100. For example, in Figure 4, the terminal device 10 is set to transmit SRS at 40ms intervals. Even in this case, the processing unit 14_2 can generate reference information at the shortest SRS period, 5ms, as shown in Figure 12.

[0089] For example, in Figure 12, the base station 200 transmits a DL reference signal on the PDCCH of the DL slot (the slot indicated by "D" in Figure 12). The acquisition unit 14_1 acquires the DL reference signal in all D slots, for example.

[0090] The processing unit 14_2 generates reference information using DL reference signals received at intervals of 5 ms, for example, from among the DL reference signals acquired by the acquisition unit 14_1. For example, in Figure 12, the processing unit 14_2 generates reference information using DL reference signals received in the DL slots circled in the diagram.

[0091] The interval between DL reference signals that generate reference information is pre-set, for example, by notification information.

[0092] The processing unit 14_2 may generate reference information using all of the DL reference signals acquired by the acquisition unit 14_1. In this case, the amount of reference information will increase, but the learning processing unit (not shown) can use a large amount of reference information as learning data to train the AI ​​model, thereby further improving the accuracy of channel estimation by the AI ​​model.

[0093] (Channel Information) As described above, the processing unit 14_2 generates reference information related to the DL reference signal. The reference information includes channel information corresponding to the DL reference signal.

[0094] Here, the channel information may be the decoded DL reference signal itself (hereinafter also referred to as DL reference data), or it may be estimated information obtained by estimating the channel between the base station 200 and the terminal device 10 from the DL reference data. Alternatively, the channel information may include both DL reference data and estimated information. Furthermore, the channel information may include information other than DL reference data and estimated information.

[0095] If the channel information includes estimated information, the processing unit 14_2 estimates the channel between the base station 200 and the terminal device 10 from the DL reference data and generates estimated information.

[0096] Figure 13 is a diagram illustrating an example of estimation information according to the embodiment. For example, a resource block (RB) is composed of one or more resource elements (REs) separated by time (symbols) and frequency (subcarriers). A slot (DL slot indicated by "D" in Figure 13) is composed of one or more resource blocks.

[0097] Here, the DL reference signal is assigned to the first symbol of the slot, RE (shown as hatched in diagonal lines in Figure 13). The processing unit 14_2 estimates the entire channel of RB from the DL reference signal assigned to RE, for example. For example, the processing unit 14_2 calculates the propagation channel response (channel estimate). The processing unit 14_2 uses the calculated propagation channel response as estimated information, for example.

[0098] The DL reference signal is transmitted to all terminal devices 10. Therefore, the processing unit 14_2 uses this DL reference signal to generate reference information.

[0099] On the other hand, the reference signal (e.g., SRS) transmitted via UL is different for each terminal device 10. The information processing device 100 estimates the total channel of RB from the SRS assigned to RE for each terminal device 10.

[0100] (Additional Information) As mentioned above, the reference information may include additional information. The additional information may include, for example, at least one of the source information and the movement information. The information included in the additional information may also include information other than the source information and / or the movement information.

[0101] The source information includes, for example, identification information for identifying the base station 200 (and / or information processing device 100) that transmitted the DL reference signal corresponding to the reference information. The identification information may be, for example, the cell ID (IDentification) of the base station 200 that provides wireless communication services. Alternatively, the identification information may be, for example, information about the base station 200 to which the terminal device 10 is connected.

[0102] The movement information includes, for example, information about the movement of the terminal device 10. The movement information may include, for example, information about the speed and direction of movement of the terminal device 10. The processing unit 14_2 calculates information about the speed and direction of movement and generates movement information, for example, according to the sensing results of a sensor device (not shown) provided by the terminal device 10.

[0103] Examples of sensor devices include acceleration sensors, gyroscopes, internal measurement units (IMUs), and Global Navigation Satellite System (GNSS) signal receivers.

[0104] Alternatively, the movement information may be, for example, the location information of the terminal device 10. For example, the processing unit 14_2 generates movement information that associates the time and location of receiving the DL reference signal. From multiple pieces of movement information, the movement speed and direction of the terminal device 10 can be calculated.

[0105] Alternatively, the movement information may be information about the beam used by the base station 200 to transmit the DL reference signal and / or information about the reception level (received intensity) of the DL reference signal.

[0106] One example of information related to the beam is the beam ID. For instance, if the location of the base station 200 that transmitted the DL reference signal and the beam radiation direction identified by the beam ID are known, the direction of the terminal device 10 relative to the base station 200 can be calculated.

[0107] Furthermore, information regarding the reception level includes, for example, RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), SNR (Signal Noise Rate), SINR, and RSSI (Received Signal Strength Indicator). For example, based on the reception level, the distance (or change in distance) of the terminal device 10 from the base station 200 can be calculated.

[0108] The processing unit 14_2 stores the generated reference information in the reference information storage unit 13_1.

[0109] (Notification Unit 14_3) The notification unit 14_3 transmits (notifies) the reference information stored in the reference information storage unit 13_1 to the storage device 30. The notification unit 14_3 notifies the storage device 30 of the reference information, for example, via the communication unit 12.

[0110] [3. Information Processing] Figure 14 is a sequence diagram showing an example of the information processing flow according to the embodiment. The information processing shown in Figure 14 is executed by the communication system SYS1.

[0111] As shown in Figure 14, the information processing device 100 transmits notification information to the terminal device 10 via, for example, the base station 200 (step S101). The notification information includes, for example, information for the terminal device 10 to receive a DL reference signal. The notification information may also include, for example, information for the terminal device 10 to transmit reference information to the storage device 30.

[0112] The information processing device 100 transmits a DL reference signal to the terminal device 10 via the base station 200 (step S102). The information processing device 100 instructs the base station 200 to transmit a DL reference signal to the terminal device 10. The base station 200 transmits the DL reference signal to the terminal device 10 according to the instructions of the information processing device 100. The DL reference signal is transmitted using, for example, PDCCH.

[0113] The terminal device 10 generates reference information from the received DL reference signal (step S103). The reference information includes, for example, at least one of channel information and additional information. The channel information is information for estimating the channel between the terminal device 10 and the base station 200. The channel information may be the decoded DL reference signal, or it may be a channel estimate obtained using the DL reference signal.

[0114] The terminal device 10 transmits the generated reference information to the storage device 30 (step S104). The terminal device 10 may transmit the reference information to the storage device 30 via the base station 200, in other words, via the cellular network, or it may transmit the reference information to the storage device 30 via a network such as a wireless LAN.

[0115] The terminal device 10 may send the reference information to the storage device 30 each time it is generated, or it may send multiple pieces of reference information to the storage device 30 together.

[0116] The storage device 30 holds the acquired reference information (step S105). The storage device 30 may acquire and hold reference information from multiple terminal devices 10.

[0117] The storage device 30 transmits the reference information it holds to the information processing device 100 (step S106). The storage device 30 may, for example, transmit the reference information to the information processing device 100 in accordance with a request from the information processing device 100.

[0118] The information processing device 100 generates an AI model for channel estimation using SRS using the acquired reference information (step S107). The information processing device 100 may, for example, generate an AI model that estimates (supplements) the SRS during periods when it is not received from the terminal device 10. In this case, the AI ​​model outputs the SRS as the estimation result. Alternatively, the information processing device 100 may, for example, generate an AI model that estimates the channel during periods when it is not received from the terminal device 10. In this case, the AI ​​model outputs the estimated channel value as the estimation result.

[0119] The information processing device 100, for example, learns and generates an AI model using the channel information of the reference information as training data. While the information processing device 100 is shown here to perform the AI ​​model learning and generation, the AI ​​model learning and generation may be performed by a device other than the information processing device 100 (for example, a processing device not shown). In this case, for example, the information processing device 100 acquires the AI ​​model from the processing device.

[0120] The information processing device 100 uses the acquired AI model to perform channel estimation, supplementing the SRS for periods when no data was received (step S108).

[0121] Based on the channel estimation results, the information processing device 100 performs DL beamforming (step S109) and transmits a DL signal to the terminal device 10 via the base station 200 (step S110).

[0122] As described above, the terminal device 10 according to the embodiment receives the DL reference signal included in the PDCCH and transmits reference information related to the DL reference signal to the storage device 30. The reference information is used by the information processing device 100 to predict channel information using the UL reference signal (e.g., SRS). For example, the reference information is used as training data for the AI ​​model used to predict this channel information.

[0123] In this way, by having terminal devices 10 collect reference information, the storage device 30 can collect more reference information from more terminal devices 10. As a result, for example, a processing device (not shown) that generates an AI model can train the AI ​​model using more reference information as training data, and can generate a more accurate AI model. Furthermore, the information processing device 100 can predict channel information using a more accurate AI model, and therefore can perform more accurate DL communication.

[0124] [4. Effects]

[0125] As described above, the terminal device 10 according to the embodiment includes a control unit 14. The control unit 14 receives the downlink reference signal included in the PDCCH. The control unit 14 transmits reference information regarding the downlink reference signal to the storage device 30. The reference information is used for predicting channel information using the uplink reference signal.

[0126] As a result, the storage device 30 can collect reference information from more terminal devices 10, and the information processing device 100 can predict channel information using uplink reference signals with greater accuracy.

[0127] The control unit 14 transmits additional information corresponding to the downlink reference signal to the storage device 30.

[0128] This allows the storage device 30 to collect additional information corresponding to the downlink reference signal.

[0129] The additional information includes at least one of the following: information about the base station 200 that transmits the downlink reference signal, and information about the device itself.

[0130] As a result, the storage device 30 can collect at least one of the following: information about the base station 200 (or the information processing device 100 or RAN 20) that transmits the downlink reference signal, and information about the terminal device 10.

[0131] The reference information includes at least one of the decoded downlink reference signal and channel information relating to the channel estimated using the downlink reference signal.

[0132] As a result, the storage device 30 can collect at least one of the decoded downlink reference signal and channel information relating to the channel estimated using the downlink reference signal.

[0133] The control unit 14 receives a downlink reference signal in accordance with instructions from the base station 200 (or the information processing device 100 or RAN 20).

[0134] As a result, the terminal device 10 can receive downlink signals in response to instructions from the base station 200 (or the information processing device 100 or RAN 20).

[0135] The control unit 14 transmits reference information regarding the received downlink reference signal to the storage device 30 at intervals corresponding to the transmission interval of the uplink reference signal.

[0136] As a result, the storage device 30 can collect reference information to perform more accurate prediction of channel information using the uplink reference signal with fewer data points.

[0137] The reference information is used as training data for a prediction model that uses the uplink reference signal to predict channel information.

[0138] As a result, the information processing device 100 can predict channel information using the uplink reference signal from a predictive model generated using more training data.

[0139] As described above, the communication method according to the embodiment includes a receiving step of receiving a downlink reference signal included in the PDCCH, and a transmitting step of transmitting reference information relating to the downlink reference signal to the storage device 30. The reference information is used for predicting channel information using the uplink reference signal.

[0140] As a result, the storage device 30 can collect reference information from more terminal devices 10, and the information processing device 100 can predict channel information using uplink reference signals with greater accuracy.

[0141] [5. Hardware Configuration] The information processing device 100 according to the above-described embodiment is also realized by a computer 1000 having a configuration such as that shown in Figure 15. Figure 15 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0142] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls various parts. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0143] 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 predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0144] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, 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 the generated data to output devices via the input / output interface 1600.

[0145] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or 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.

[0146] For example, when the computer 1000 functions as an information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0147] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0148] [6. Others] Furthermore, among the processes described in the above embodiments and modifications, 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 by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0149] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0150] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0151] 10 Terminal device 11 Wireless communication unit 12, 31, 110 Communication unit 13, 32, 120 Storage unit 14, 33, 130 Control unit 20 RAN 30 Storage device 100 Information processing device 200 Base station

Claims

1. A terminal device comprising a control unit that receives a downlink reference signal included in a PDCCH (Physical Downlink Control Channel) and transmits reference information relating to the downlink reference signal to an information processing device, wherein the reference information is used for predicting channel information using an uplink reference signal.

2. The terminal device according to claim 1, wherein the control unit transmits additional information corresponding to the downlink reference signal to the information processing device.

3. The terminal device according to claim 2, wherein the additional information includes at least one of the following: information relating to the base station transmitting the downlink reference signal and information relating to the device itself.

4. The terminal device according to claim 1, wherein the reference information includes at least one of the decoded downlink reference signal and channel information relating to a channel estimated using the downlink reference signal.

5. The terminal device according to claim 1, wherein the control unit receives the downlink reference signal in accordance with instructions from the base station.

6. The terminal device according to claim 1, wherein the control unit transmits the reference information relating to the downlink reference signal received at intervals corresponding to the transmission interval of the uplink reference signal to the information processing device.

7. The terminal device according to claim 1, wherein the reference information is used as training data for a prediction model used to predict channel information using the uplink reference signal.

8. A communication method comprising: a receiving step of receiving a downlink reference signal included in a PDCCH (Physical Downlink Control Channel); and a transmitting step of transmitting reference information relating to the downlink reference signal to an information processing device, wherein the reference information is used for predicting channel information using an uplink reference signal.

Images