Terminal device for beam selection of wireless communication using artificial intelligence (AI) / machine learning (ML), base station device, control method, and program

Abstract

This terminal device is configured to: measure a reference signal transmitted by a base station device using each of a smaller number of second beams than a plurality of first beams capable of being formed by the base station device, where which of the plurality of first beams is to be used for communicating with the terminal device is determined by inputting at least a part of the result of the terminal device measuring a reference signal transmitted using each of the second beams into a model trained by machine learning; determine the configuration of a report of the result of measuring the reference signal; transmit a notification related to the configuration of the report to the base station device; and use the configuration of the report to transmit a report of measuring the reference signal to the base station device.

Description

Terminal device, base station device, control method, and program for beam selection in wireless communication using artificial intelligence (AI) / machine learning (ML)

[0001] The present invention relates to a beam selection technology for wireless communication using artificial intelligence (AI) / machine learning (ML).

[0002] In the standardization work of the Third Generation Partnership Project (3GPP), in a communication device capable of forming multiple beams to perform wireless communication, the use of artificial intelligence (AI) / machine learning (ML) is being considered to determine which of the multiple beams to use to communicate with a partner device. Non-Patent Document 1 describes an AI / ML model in which a terminal device measures reference signal received power (RSRP) for some beams included in multiple beams with narrow beam widths that can be formed in a network (base station device), and selects a beam to use for communication from all of the multiple beams based on the RSRP.

[0003] 3GPP (registered trademark) Contribution, R1-2203142

[0004] The beam selection method in the AI / ML model requires sufficient feedback of RSRP from the terminal device. However, if the terminal device provides excessively sufficient feedback, unnecessary overhead increases, which may cause a decrease in throughput.

[0005] The present invention provides a technique for appropriately configuring feedback from a terminal device to a base station device for a beam selection method using an AI / ML model to be used by the base station device.

[0006] A terminal device according to one aspect of the present invention is a base station device capable of forming a plurality of first beams, and at least a portion of the results of measurements by the terminal device of reference signals transmitted using each of second beams that are fewer than the plurality of first beams are input into a trained model using machine learning, thereby determining which of the plurality of first beams to use for communication with the terminal device.The base station device has: a measurement means for measuring the reference signals transmitted using each of the second beams; a determination means for determining the configuration of a report of the measurement results of the reference signals; and a transmission means for transmitting a notification regarding the configuration of the report to the base station device and transmitting a measurement report of the reference signal to the base station device based on the configuration of the report.

[0007] A base station device according to one aspect of the present invention comprises a transmitting means for transmitting a reference signal using each of a number of second beams that is less than the number of a plurality of first beams that the base station device can form; a receiving means for receiving a notification regarding the configuration of a report of measurement results of the reference signal from a terminal device that has received the reference signal, and receiving a measurement report of the reference signal based on the configuration of the report; and a determining means for determining which of the plurality of first beams to use for communication with the terminal device by inputting at least a portion of the measurement results of the reference signal included in the measurement report into a trained model using machine learning.

[0008] According to the present invention, it is possible to appropriately configure feedback from a terminal device to a base station device for a selection method using an AI / ML model for a beam used by the base station device.

[0009] Other features and advantages of the present invention will become apparent from the following description taken in conjunction with the accompanying drawings, in which the same or similar elements are designated by the same reference numerals.

[0010] The accompanying drawings are included in and constitute a part of the specification, illustrate embodiments of the present invention, and are used, together with the description, to explain the principles of the present invention. FIG. 1A is a diagram illustrating an example of a configuration of a wireless communication system. FIG. 1B is a diagram illustrating an example of a configuration of a wireless communication system. FIG. 2A is a diagram illustrating an example of machine learning for beam determination. FIG. 2B is a diagram illustrating an example of machine learning for beam determination. FIG. 3A is a diagram illustrating another example of machine learning for beam determination. FIG. 3B is a diagram illustrating another example of machine learning for beam determination. FIG. 4 is a diagram illustrating an example of the hardware configuration of a base station device and a terminal device. FIG. 5 is a diagram illustrating an example of the functional configuration of a terminal device. FIG. 6 is a diagram illustrating an example of the functional configuration of a base station device. FIG. 7 is a diagram illustrating an example of the flow of processing executed in a wireless communication system. FIG. 8 is a diagram illustrating an example of the flow of processing executed in a wireless communication system. FIG. 9A is a diagram illustrating a flow of a process for notifying condition information. FIG. 9B is a diagram illustrating a flow of a process for notifying condition information.

[0011] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be combined in any desired manner. Furthermore, the same reference numerals are used to designate identical or similar components, and redundant descriptions will be omitted.

[0012] (System Configuration) Figures 1A and 1B show an example configuration of a wireless communication system according to this embodiment. This wireless communication system is, for example, a cellular communication system conforming to the cellular communication standard of the Third Generation Partnership Project (3GPP (registered trademark)), and is configured to include a base station device 101 and a terminal device 102. The base station device 101 can form multiple first beams 111 and selectively uses one of these beams to communicate with the terminal device 102. This selection of the beam to be used is performed, for example, based on the results of measuring the reception quality of reference signals transmitted by all beams in the terminal device 102. This selection is particularly effective in the downlink where signals are transmitted from the base station device 101 to the terminal device 102. The reference signal here is, for example, a synchronization signal / physical broadcast channel (SS / PBCH) block (SSB) or a channel state information reference signal (CSI-RS). Furthermore, the reception quality may be, for example, reference signal received power (RSRP), reference signal received strength (RSRQ), signal-to-interference-and-noise ratio (SINR), etc. For example, the terminal device 102 measures the reception quality of the reference signal transmitted in each of the multiple first beams 111 and notifies the base station device 101 of the measurement results. Based on the measurement results, the base station device 101 determines, for example, a beam with high reception quality as the beam to be used for communication with the terminal device 102.

[0013] However, if the terminal device 102 measures reference signals for all of the first beams 111 to determine reception quality and notify the base station device 101 of the reception quality, the need to perform multiple measurements increases the time required to determine the beam. Furthermore, multiple notifications for multiple beams may waste radio resources. In response to this, for example, by selecting some beams that are expected to provide good quality in the terminal device 102 and having the terminal device 102 measure and report only those beams, it is possible to simplify the measurements and reduce the amount of information to be reported. However, this process does not allow for the selection of a beam to be used from all of the first beams 111. In response to this, the use of artificial intelligence (AI) / machine learning (ML) to select a beam to be used is being considered. For example, at least a portion of the measurement results by the terminal device 102 of reference signals transmitted in second beams that are fewer than the first beam 111 are input into a trained model obtained by machine learning. Then, as an output of the trained model, a small number of candidates for beams to be used by the base station device 101 for communication (e.g., downlink, and in some cases, also uplink) with the terminal device 102 may be output. After that, the terminal device 102 measures the reception quality of the reference signal for each of the small number of candidates, and the beam to be used for communication may be determined based on the measurement results. Also, the beam to be used for communication may be determined all at once, rather than the candidates, based on the output of the trained model.

[0014] The second beam, the reception quality of which is input to the trained model, may be, for example, a part of the first beam 111, as shown by beam 112 in FIG. 1A . That is, a part of the many first beams 111 that the base station device 101 can form (e.g., one beam 112 is set for each predetermined number of first beams 111) is set as the second beam, and the reception quality of the reference signal transmitted via the second beam is measured in the terminal device 102. Then, at least a part of the measurement results is input to the trained model, thereby determining the beam to be used in the base station device 101 for communication with the terminal device 102. Also, a beam with a wider beam width than the first beam 111, such as beam 113 in FIG. 1B , may be used as the second beam. For example, when SSB is transmitted by beam 113 and CSI-RS is transmitted by the first beam 111, the terminal device 102 transmits the measurement results of the SSB to the base station device 101, and the beam that the base station device 101 uses to communicate with the terminal device 102 is determined from the first beam 111 by inputting the measurement results into the trained model.

[0015] In this way, beam selection based on artificial intelligence / machine learning makes it possible to determine a beam suitable for communication between the base station device 101 and the terminal device 102 from among all of the first beams 111, without the terminal device 102 measuring and reporting the radio quality of all of the first beams 111. Note that beam selection based on artificial intelligence / machine learning can be performed in the base station device 101, but may also be performed in, for example, another network node. In that case, the base station device 101 can provide information received from the terminal device 102 to that network node and obtain information on the beam determined based on that information from the network node. In this way, beam selection does not necessarily have to be performed in the base station device 101.

[0016] An example of machine learning for beam determination will now be described with reference to Figures 2A and 2B. Figure 2A shows an example of the learning phase in machine learning, and Figure 2B shows an example after the learning phase is completed and a trained model for beam determination processing has been obtained. Note that these are merely examples, and the beams to be used may be determined by other configurations.

[0017] In the learning phase shown in the example of FIG. 2A , the terminal device 102 performs machine learning using information on the reception quality of reference signals transmitted from each of the first beams 111 as training data 203 and information on the reception quality of reference signals transmitted from each of the second beams as input 202. Here, the training data may be, for example, data on the reception quality itself corresponding to each of the first beams 111, or data identifying a beam to be selected when that reception quality is obtained. Furthermore, although the reception quality of the second beam is represented as RSRP in FIG. 2A , it may also be other index values ​​such as RSRQ, SINR, or signal-to-noise ratio (SNR). The reception quality of the second beam is input to a learning model 201, and information in a format corresponding to the training data 203 is output from that information. Then, the difference between that output and the training data 203 is fed back to the learning model 201, and the learning model 201 is updated. This process is repeated until the difference value remains sufficiently small, or until the process has been repeated a predetermined number of times, at which point the machine learning ends and the learned model at that time is output as the trained model.

[0018] 2B , an input 212 relating to the reception quality for the second beam, which is the same as the input 202 in the learning phase, is supplied to the trained model 211. Based on the input 212, the trained model 211 infers and outputs a beam (or a candidate beam in some cases) 213 to be used for communication with the terminal device 102 in the base station device 101. In this way, based on measurement results of reference signals transmitted by fewer beams than the first beam 111, a beam to be used for communication with the terminal device 102 can be determined from all of the first beams 111.

[0019] For example, the reception quality input 202 / 212 for the second beam may be adjusted to a predetermined level for values ​​below that level. For example, if the predetermined level for RSRP is set to -60 dBm, all reception quality information below -60 dBm may be input to the learning model 201 / trained model 211 as -60 dBm. In other words, reception quality values ​​low enough that they are expected to have little impact on learning and inference may all be treated as having the same quality. In the examples of Figures 2A and 2B, the input multiple reception qualities are distinguished by the input port as to which beam of the second beam each corresponds. For example, into a port labeled RSRP #1, the RSRP for one beam corresponding to that RSRP #1 is always input, and RSRPs for other beams are not input. This is because if this order is not fixed, learning will not be completed or the accuracy of inference will deteriorate.

[0020] 3A and 3B show another example of machine learning for beam determination. In the examples of FIGS. 3A and 3B, only a portion of the second beams are input to the learning model 301 and the trained model 311. For example, even if a large number of measurement results, such as measurement results for all second beams, are acquired from the terminal device 102, only a portion of the measurement results are used as input 302 to the learning model 301 to perform machine learning. Note that the teacher data 303 is the same as in the case of FIG. 2A. Similarly, only a portion of the measurement results of the second beams can be used as input 312 for the trained model 311. Note that the number of measurement results included in the input 302 and the input 312 is the same. That is, if, for example, eight measurement result values ​​are input in the input 302 in the learning phase, eight measurement result values ​​are also input in the input 312 in the inference phase. Note that if only the measurement result values ​​are used as inputs 302 and 312, it becomes unclear which of the second beams the values ​​relate to, which may result in a decrease in learning efficiency and inference performance. Therefore, inputs 302 and 312 may include information indicating which beam the values ​​relate to. That is, beam IDs for each of the second beams and the reception quality of the corresponding reference signal (RSRP in the examples of FIGS. 3A and 3B ) may be used as inputs 302 and 312.

[0021] In this way, by using artificial intelligence (AI) / machine learning (ML), it is possible to select a beam to be used for communication by taking into account all beams available at the base station device 101 based on the observation results of reference signals transmitted from a relatively small number of beams. However, as described above, for example, after a measurement report of a reference signal is fed back from the terminal device 102 to the base station device 101, it is possible that some of the measurement report will not be used as input to the trained model. Feedback of such unused information wastes radio resources and hinders improvement in the frequency utilization efficiency of the entire system. Furthermore, even if more precise reporting enables highly accurate beam selection, if the granularity (quantization level) of the reference signal reception quality report is fixed, the benefits of such highly accurate selection cannot be obtained. For this reason, this embodiment provides a technology that uses artificial intelligence (AI) / machine learning (ML) to appropriately configure feedback when determining a beam to be used at the base station device 101.

[0022] For example, the terminal device 102 is enabled to autonomously determine the report configuration. That is, the terminal device 102 measures reference signals (e.g., CSI-RS or SSB) transmitted from each of a plurality of second beams that are fewer than the above-described large number of first beams 111, and determines how to report the measurement results for each of the second beams. For example, the terminal device 102 may determine which of the measurement results for each of the second beams to report, and may decide to notify the base station device 101 of only the measurement results to be reported. Then, the terminal device 102 determines the number of beams to be reported so as to report the measurement results. That is, in a conventional CSI-RS measurement report (CSI-Report), the base station device 101 may specify the maximum number of beams to be reported, but the present embodiment enables the terminal device 102 to determine the number of beams to be reported. In one example, the terminal device 102 may measure the reception quality of the reference signal from each of the second beams and determine that the beams whose reception quality values ​​do not reach a predetermined value are not to be reported. Also, when the terminal device 102 recognizes the number of reception quality values ​​to be input to the trained model, it may determine the number of reception quality values ​​to be reported so as to report reception quality values ​​for beams that do not exceed that number.

[0023] The terminal device 102 may also determine the number of signals (messages) to transmit the measurement results. For example, in a conventional CSI report, one report includes measurement results for up to four beams, and when the number of beams to be reported is 4n-3 to 4n, the report may be transmitted using n signals. In one example, the terminal device 102 may accordingly determine to transmit a report using n signals when the determined number of beams to be reported is 4n-3 to 4n. However, this is not limited thereto, and the terminal device 102 may, for example, determine to transmit a report regarding four beams using two or more signals. In this case, the terminal device 102 may further determine the number of measurement results to be included in each report. For example, when it is necessary to increase the amount of information in the report for each beam, the terminal device 102 may reduce the number of reception qualities (the number of beams) to be included in one report.

[0024] Furthermore, the terminal device 102 may determine, for example, the content of the report for each beam. For example, the terminal device 102 may determine whether to express the reception quality of the reference signal using a differential value based on the reception quality for a specific beam, or whether to express the quality without using such a differential value. When a differential value is used, for example, if the difference between a first value indicating the reference measurement result and a second value of the measurement result is large, it is assumed that the specific value cannot be indicated. That is, if the magnitude of the difference does not exceed a predetermined value, the value can be indicated in detail. However, if the magnitude of the difference exceeds the predetermined value, a report may be made as if the differential value were the predetermined value, and the detailed value may not be reported. For this reason, the terminal device 102 may determine, for example, to use the differential value in the report when the difference between the first value indicating the reference measurement result and the second value of the measurement result is equal to or less than a predetermined value, and may determine not to use the differential value in the report when the difference exceeds the predetermined value. Furthermore, the terminal device 102 may vary the bit width indicating the reception quality. For example, the terminal device 102 can increase the bit width when more detailed information needs to be notified to the base station device 101, and can decrease the bit width when coarse information is sufficient.

[0025] If the terminal device 102 independently determines a report configuration and transmits a measurement report to the base station device 101 in accordance with that configuration, the base station device 101 will not recognize that configuration and will therefore be unable to obtain measurement result information correctly. For this reason, in this embodiment, the terminal device 102 transmits a notification regarding the determined report configuration to the base station device 101. This allows the base station device 101 to recognize the report configuration and correctly obtain reference signal measurement result information from a measurement report that uses the configuration determined by the terminal device 102.

[0026] The terminal device 102 may notify the base station device 101 of information regarding the measurement report configuration using a signal separate from the measurement report, or may notify the base station device 101 using the same signal as the measurement report. In one example, the terminal device 102 may request the base station device 101 to use the report configuration by notifying the base station device 101 of the report configuration. In this case, the base station device 101 identifies the measurement report configuration based on the request and transmits an instruction corresponding to the identified content to the terminal device 102. For example, the base station device 101 may select approval, rejection, or change in response to the request and transmit a reply including the result of the selection to the terminal device 102. For example, the base station device 101 may transmit a response indicating approval to the terminal device 102 if it approves the entire requested configuration, or may transmit a response indicating the content of the change to the terminal device 102 if the requested configuration can be accepted with some changes. Furthermore, if the base station device 101 rejects the use of the requested configuration, it transmits a response indicating rejection to the terminal device 102. According to this, for example, a report of a configuration suitable for selecting a beam using a trained model can be transmitted from the terminal device 102 to the base station device 101. Note that the terminal device 102 may notify the base station device 101 of information indicating the configuration of the measurement report, and the base station device 101 may unconditionally accept the notified configuration. For example, when a single signal including information on the configuration of the measurement report and the measurement report is transmitted, the base station device 101 may unconditionally accept the configuration and analyze the measurement report.

[0027] Furthermore, the base station device 101 may determine some of the components of the report in advance and notify the terminal device 102 of them. Then, the terminal device 102 may independently determine components of the report other than those specified by the base station device 101, generate a measurement report composed of the determined components and the components notified by the base station device 101, and transmit the measurement report to the base station device 101. In one example, the base station device 101 may notify the terminal device 102 of components related to the number of beams among the second beams for which measurement results of corresponding reference signals should be reported. In this case, the terminal device 102 transmits a measurement report of reference signals transmitted by the specified number of beams to the base station device 101, but independently determines at least one of the number of signals for which the measurement report is to be transmitted, the content of the report related to each beam to be reported, and the bit width of the information indicating the measurement results of the reference signals, and transmits a measurement report having that configuration to the base station device 101. Note that the base station device 101 may notify the terminal device 102 of, for example, information specifying at least one of the number of signals for which a measurement report is to be transmitted, the content of the report for each beam to be reported, and the bit width of the information indicating the measurement results of the reference signal, instead of the number of beams for which measurement results should be reported. The terminal device 102 may determine the configuration of the measurement report by using the elements notified by the base station device 101 and independently determining the other elements. Note that in either case, the terminal device 102 transmits information regarding the configuration of the measurement report (for example, information indicating the configuration or a request as described above) to the base station device 101. This is because the base station device 101 needs to know the elements independently determined by the terminal device 102.

[0028] As described above, the base station device 101 can recognize the format of the measurement report by receiving information regarding the configuration of the measurement report from the terminal device 102. The base station device 101 then receives the measurement report and acquires the contents of the measurement report (the reception quality of the reference signal and, if necessary, the ID of the beam corresponding to that reception quality). The base station device 101 may, for example, input at least a portion of the acquired reception quality of the reference signal into a trained model stored in the base station device 101, thereby identifying a beam to be used for communication with the terminal device 102 from among the first beams 111. The base station device 101 may also provide information on the reception quality of the acquired reference signal (and, if necessary, the ID of the beam corresponding to that reception quality) to another network node that stores the trained model. In this case, at least a portion of the reception quality of the reference signal is input into the trained model in the other network node, and the base station device 101 selects a beam from the first beams 111 to be used for communication with the terminal device 102. Information about the determined beam is then notified to the base station device 101, and the base station device 101 can determine, in accordance with the notification, which beam from among the first beams 111 to use for communication with the terminal device 102. The base station device 101 then uses the beam to communicate with the terminal device 102.

[0029] In this way, in this embodiment, the terminal device 102 determines the configuration of the measurement report, notifies information about the configuration to the base station device 101, and transmits the measurement report based on the configuration. As a result, appropriate measurement results for beam selection using artificial intelligence (AI) / machine learning (ML) can be shared between the base station device 101 and the terminal device 102 in just the right amount, depending on, for example, the reception quality of reference signals from each beam in the terminal device 102.

[0030] When the terminal device 102 determines the reporting configuration, the base station device 101 may notify the terminal device 102 in advance of conditions for determining which of the second beams to report measurement results for. For example, as the conditions, information indicating a predetermined value that the measurement result value to be reported must exceed may be notified from the base station device 101 to the terminal device 102 in advance. In this case, the terminal device 102 reports reference signals (beams) for which reception quality exceeding the notified predetermined value can be obtained, and does not report reference signals for which reception quality does not exceed the predetermined value. For example, in the learning phase of machine learning, if a learning model is generated by replacing reception quality values ​​that do not exceed a predetermined value with the predetermined value, even if a reception quality that does not exceed the predetermined value is notified, the value will not be used in the inference phase. Therefore, the base station device 101 notifies the terminal device 102 of the above-mentioned conditions so that such reception quality is not reported. When the terminal device 102 selects beams to be reported according to the above-mentioned conditions, the number of measurement results to be reported is variable. For this reason, the terminal device 102 transmits information regarding the report configuration to the base station device 101 as described above, and notifies the base station device 101 of the measurement results in accordance with that configuration.

[0031] The above-mentioned condition may also include information indicating the maximum number of reference signals (beams) to be reported. For example, if a trained model is generated using only the reception qualities for a predetermined number of reference signals during the learning phase of machine learning, the reception qualities to be input to the trained model may also be limited to the predetermined number. Therefore, even if measurement results of the reception qualities for beams exceeding the predetermined number are reported, the measurement results for the beams exceeding the predetermined number are not used for beam selection. For example, the base station device 101 may notify the terminal device 102 of a condition including the predetermined number as the maximum number of reference signals to be reported. For example, if the number of beams whose reception qualities satisfy the above-mentioned condition exceeds the predetermined number, the terminal device 102 does not report to the base station device 101 the measurement results of the reception qualities for the beams exceeding the predetermined number.

[0032] The base station device 101 may transmit the above-mentioned conditions periodically, for example. When the terminal device 102 acquires these conditions, it compares them with the conditions stored at that time. Then, when the terminal device 102 receives conditions that differ from the stored conditions, it updates the stored conditions with the received conditions. The base station device 101 may also transmit conditions each time the trained model is updated. When the terminal device 102 acquires the conditions, it updates the stored conditions with the acquired conditions. When reporting a measurement, the terminal device 102 determines the report content and report configuration based on the latest conditions, notifies the base station device 101 of information regarding the report configuration, generates a measurement report using the configuration, and transmits the measurement report to the base station device 101.

[0033] As described above, by using conditions, it is possible to prevent unnecessary feedback of information that is not input into the trained model and is not used to determine the beam to be used by the base station device 101.

[0034] (Device Configuration) FIG. 4 shows an example of the hardware configuration of the base station device 101 and the terminal device 102 according to this embodiment. In one example, the base station device 101 and the terminal device 102 are configured to include a processor 401, a ROM 402, a RAM 403, a storage device 404, and a communication circuit 405. The processor 401 is a computer configured to include one or more processing circuits, such as a general-purpose CPU (Central Processing Unit) or an ASIC (Application Specific Integrated Circuit), and performs the overall processing of the device and each of the above-mentioned processes by reading and executing programs stored in the ROM 402 or the storage device 404. The ROM 402 is a read-only memory that stores information such as programs and various parameters related to the processing executed by the base station device 101 and the terminal device 102. The RAM 403 functions as a workspace when the processor 401 executes a program and is also a random access memory that stores temporary information. The storage device 404 is configured, for example, by a removable external storage device. The communication circuit 405 is configured, for example, by a circuit for wireless communication of 5G or a successor standard. While FIG. 4 illustrates one communication circuit 405, the base station device 101 and the terminal device 102 may have multiple communication circuits. For example, the base station device 101 and the terminal device 102 may have wireless communication circuits for 5G and a successor standard, respectively, and a common antenna for these circuits. The base station device 101 and the terminal device 102 may also have separate antennas suitable for each standard. The base station device 101 may also have a wired communication circuit used when communicating with other base station devices or nodes in the core network. The terminal device 102 may also have a communication circuit compliant with a wireless communication standard other than a cellular communication standard, such as a wireless local area network (LAN) or Bluetooth (registered trademark). The base station device 101 and the terminal device 102 may have separate communication circuits 405 for each of the multiple available frequency bands, or may have a common communication circuit 405 for at least some of the frequency bands.

[0035] FIG. 5 shows an example of the functional configuration of the terminal device 102. The terminal device 102 includes, for example, a measurement unit 501, a report configuration determination unit 502, an information notification unit 503, an information receiving unit 504, and a communication unit 505. Note that FIG. 5 only shows functions particularly related to this embodiment, and various other functions that the terminal device 102 may have are omitted from the illustration. For example, the terminal device 102 naturally has other functions that terminal devices compliant with 5G or subsequent standards generally have. The functional blocks in FIG. 5 are shown schematically, and the respective functional blocks may be integrated or further subdivided. Each function in FIG. 5 may be realized, for example, by the processor 401 executing a program stored in the ROM 402 or the storage device 404, or may be realized, for example, by a processor within the communication circuit 405 executing predetermined software. The details of the processing performed by each functional unit will not be described here, and only their general functions will be outlined.

[0036] The measurement unit 501 measures the reception quality of each reference signal transmitted using a plurality of second beams that are fewer than the many first beams that the base station device 101 can form. The measurement unit 501 may measure the reception quality of each reference signal transmitted by each first beam, for example, during the learning phase of machine learning for beam determination in the base station device 101. The report configuration determination unit 502 determines the report configuration when reporting the reference signal measurement results to the base station device 101. That is, the report configuration determination unit 502 may determine, for example, at least one of the number of reference signals to be reported, the number of signals for which the report is transmitted, a format for expressing the reception quality measurement results (whether or not a differential value is used), and a bit width for expressing the reception quality measurement results. The report configuration determination unit 502 may acquire information specifying part of its configuration or information on conditions from the base station device 101, for example, via the information receiving unit 504, and determine a configuration other than that specified by the base station device 101. The report configuration determination unit 502 requests the base station device 101 to use the determined configuration, and determines the measurement report configuration to be finally used based on the response to the request. The information notification unit 503 notifies the base station device 101 of information regarding the configuration determined by the report configuration determination unit 502. The information notification unit 503 also generates a measurement report using that configuration and transmits the measurement report to the base station device 101. The information receiving unit 504 receives information specifying a part of the measurement report configuration and conditions for selecting measurement results to be reported from the base station device 101. The communication unit 505 communicates with the base station device 101 using a beam selected from the first beams that the base station device 101 can form based on the information of the measurement results notified by the information notification unit 503.

[0037] FIG. 6 shows an example of the functional configuration of the base station device 101. The base station device 101 includes, for example, a reference signal transmitter 601, an information receiver 602, a beam determiner 603, an information provider 604, and a communication unit 605. Note that FIG. 6 only shows functions particularly related to this embodiment, and does not illustrate various other functions that the base station device 101 may have. For example, the base station device 101 naturally has other functions that base station devices compliant with 5G and subsequent standards generally have. The functional blocks in FIG. 6 are shown schematically, and the respective functional blocks may be integrated or further subdivided. Each function in FIG. 6 may be realized, for example, by the processor 401 executing a program stored in the ROM 402 or the storage device 404, or by a processor within the communication circuit 405 executing predetermined software. The details of the processing performed by each functional unit will not be described here, and only their general functions will be outlined.

[0038] The reference signal transmitting unit 601 transmits reference signals (CSI-RS, SSB, etc.) in each of the first beams and each of the second beams. Note that if the second beam is part of the first beam, there is no need to separately transmit a reference signal for the second beam. The information receiving unit 602 receives information regarding the configuration of the measurement report from the terminal device 102. Furthermore, the information receiving unit 602 receives a measurement report from the terminal device 102, analyzes the measurement report using a configuration based on the received information, and acquires information on the measurement result.

[0039] The beam determination unit 603 determines which of the first beams to use for communication with the terminal device 102 as a result of inputting information on the measurement results acquired from the terminal device 102 into the trained model. In one example, a small number (two or more) of candidate beams may be designated from among a large number of first beams based on output from the trained model. In this case, the beam determination unit 603 may notify the terminal device 102 of information on the candidate beams and cause the terminal device 102 to measure reference signals transmitted from the reference signal transmission unit 601 for each of the candidate beams. The beam determination unit 603 may then acquire measurement results for the candidate beams from the terminal device 102 and ultimately determine a beam to be used in communication with the terminal device 102. Note that in another example, a beam to be ultimately used in communication with the terminal device 102 may be directly designated from among a large number of first beams based on output from the trained model. The trained model may also be stored in another external network node different from the base station device 101. In this case, the beam determination unit 603 provides information on measurement results acquired from the terminal device 102 to the other network node. The beam determination unit 603 may then acquire inference results using the trained model from the other network node and determine a beam to be used in communication with the terminal device 102 based on the results. In one example, the trained model may output the communication quality expected to be obtained for each first beam as the inference result. In this case, the beam determination unit 603 may determine the beam with the best communication quality or a beam selected randomly or according to a predetermined rule from among beams whose communication quality exceeds a predetermined value as the beam to be used in communication with the terminal device 102. The beam determination unit 603 may also select a predetermined number of beams with the best communication quality, or a predetermined number of beams selected randomly or according to a predetermined rule from among beams whose communication quality exceeds a predetermined value, as the above-mentioned candidate beams.

[0040] The information providing unit 604 provides the terminal device 102 with, for example, information specifying a part of the configuration of the measurement report and information such as conditions for the terminal device 102 to select a beam to be reported. Furthermore, if the information regarding the configuration of the measurement report received by the information receiving unit 602 is information indicating a request for use of that configuration, the information providing unit 604 determines, for example, whether to accept, modify, or reject the configuration, and transmits a reply according to the contents to the terminal device 102. The communication unit 605 communicates with the terminal device 102 using the beam determined by the beam determining unit 603.

[0041] (Processing flow) Next, an example of the processing flow executed in the wireless communication system will be described. Here, an example is shown in which CSI-RS is measured as a reference signal, but the terminal device 102 may measure other reference signals and notify the base station device 101 of the measurement results. Note that the processing flow described below is just an example, and modifications such as those described above can be made in each procedure. Furthermore, since the details of each procedure are as described above, an overview of the processing flow will be described here, and the detailed description will not be repeated.

[0042] FIG. 7 shows a first processing example of the terminal device 102. In this embodiment, for example, by machine learning, a beam to be used for communication with the terminal device 102 is selected from among the first beams based on measurement results of reference signals from a smaller number of second beams (e.g., second beams prepared as part of the first beams or separately from the first beams) among a large number of first beams that the base station device 101 can form. For this reason, the base station device 101 first performs a learning phase process with the terminal device 102 (S701) to generate a trained model. Note that the base station device 101 may perform the learning phase process with a terminal device other than the terminal device 102, or may not perform the learning phase process with the terminal device 102. In the learning phase, for example, the base station device 101 transmits reference signals using each of the first beam and the second beam, and the terminal device 102 measures the reception quality of the reference signals. The terminal device 102 then feeds back all of the reception qualities to the base station device 101, and the base station device 101 or another network node executes machine learning using the feedback regarding the second beam as input and the feedback regarding the first beam as training data. Upon completion of the learning phase, a trained model is generated.

[0043] After the learning phase is completed, the terminal device 102 measures the reception quality of the reference signal transmitted from the base station device 101 using each of the second beams (S703), and determines the configuration of a report (CSI Report) for reporting the measurement results of the reception quality (S704). Note that the base station device 101 may provide the terminal device 102 with information specifying part of the report configuration (S702). Note that the terminal device 102 may determine all of the configurations, in which case the processing of S702 is omitted.

[0044] The terminal device 102 transmits information regarding the report configuration determined in S704 to the base station device 101 (S705). Furthermore, the terminal device 102 transmits a measurement result report to the base station device 101 based on the configuration notified to the base station device 101 in S705 (S706). While FIG. 7 illustrates an example in which the information regarding the configuration and the measurement result report are transmitted separately, this is not limiting. That is, these may be transmitted to the base station device 101 via a single signal. That is, the terminal device 102 may include information indicating the configuration of the report in a report (CSI Report) including information indicating the measurement results. Furthermore, the notification of S705 may include information requesting the base station device 101 to use that configuration. In this case, a response including information indicating whether the request is approved, changed, or rejected may be transmitted from the base station device 101 to the terminal device 102 (not shown). In this case, if the terminal device 102 receives a response indicating approval, it uses the configuration notified in S705, and if it receives a response indicating a change, it uses another configuration obtained by changing the configuration notified in S705 depending on the content of the change, and transmits a report including information indicating the measurement results to the base station device 101. Also, if the terminal device 102 receives a response indicating rejection, it can execute the process of S704 again and transmit a signal to the base station device 101 requesting the use of the determined configuration again. Note that when a request is transmitted to the base station device 101, the notification of S705 and the report of S706 are transmitted by separate signals.

[0045] When the base station device 101 receives a report of the measurement results of the reception quality of the reference signal in S706, the base station device 101 inputs the information into the trained model and determines to use a beam selected from the first beams (S707). Note that if the trained model is held by a network node different from the base station device 101, information on the measurement results is transferred from the base station device 101 to the network node, and the network node determines the beam to be used. The determined beam is then notified to the base station device 101, and the base station device 101 determines to use the beam. The base station device 101 can then transmit, for example, a downlink signal (e.g., a physical downlink shared channel (PDSCH)) to the terminal device 102.

[0046] FIG. 8 illustrates an example of a processing flow in which, instead of specifying some of the configuration requirements in S702 of FIG. 7 , the base station device 101 notifies the terminal device 102 of conditions used to select beams for which measurement results should be reported. Before a measurement report is performed, the base station device 101 notifies the terminal device 102 of information indicating, for example, a predetermined value that the reception quality of a reference signal must exceed as a condition used to select a beam for which measurement results should be reported (S801). Information indicating the maximum number of beams to be reported may also be notified as a condition. The terminal device 102 measures the reception quality of a reference signal transmitted by a second beam and determines a reporting configuration so that, for example, only measurement results that satisfy the notified condition are notified to the base station device 101 (S802). Subsequent processing is similar to that of FIG. 7 . The condition information may be notified, for example, every time a trained model is updated by machine learning, as shown in FIG. 9A , or periodically, as shown in FIG. 9B . Also, for example, when the terminal device 102 connects to the base station device 101, the base station device 101 may notify the terminal device 102 of information on the conditions.

[0047] As described above, in this embodiment, it is possible to flexibly configure the feedback transmitted from the terminal device 102 to the base station device 101. This makes it possible to prevent excessive or insufficient feedback for selecting a beam to be used by the base station device 101 using artificial intelligence (AI) / machine learning (ML). This makes it possible to contribute to Goal 9 of the United Nations-led Sustainable Development Goals (SDGs), which is to "build resilient infrastructure, promote sustainable industrialization, and foster innovation."

[0048] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention.

[0049] This application claims priority based on Japanese Patent Application No. 2024-014260, filed February 1, 2024, the entire contents of which are incorporated herein by reference.

Claims

1. A terminal device comprising: a base station device capable of forming a plurality of first beams, wherein at least a portion of the results of measurements by the terminal device of reference signals transmitted using each of second beams that are fewer than the plurality of first beams are input into a trained model using machine learning, thereby determining which of the plurality of first beams to use for communication with the terminal device; a measurement means for measuring the reference signals transmitted using each of the second beams; a determination means for determining a report configuration for the measurement results of the reference signals; and a transmission means for transmitting a notification regarding the report configuration to the base station device and transmitting a measurement report of the reference signals to the base station device based on the report configuration.

2. The terminal device according to claim 1, further comprising a receiving means for receiving information on the configuration of a second report of the measurement results of the reference signal from the base station device, and the transmitting means for transmitting a measurement report of the reference signal having the configuration of the report and the configuration of the second report to the base station device.

3. The terminal device of claim 2, wherein the second report configuration includes a configuration regarding the number of beams among the plurality of second beams for reporting corresponding measurement results, and the report configuration determined by the determination means includes a configuration regarding at least one of the number of signals for reporting the measurement results, the content of the report regarding each beam, and the bit width of information indicating the measurement results of the reference signal.

4. The terminal device of claim 1, wherein the report configuration includes configuration regarding at least one of the number of beams among the plurality of second beams that report corresponding measurement results, the content of the report regarding each beam, and the bit width of information indicating the measurement results of the reference signal.

5. A terminal device according to any one of claims 1 to 4, wherein the transmitting means transmits the notification regarding the report configuration and the measurement report of the reference signal using separate signals.

6. The terminal device according to claim 5, wherein the transmitting means requests the base station device to use the configuration of the report by the notification, and transmits the measurement report of the reference signal to the base station device using the configuration determined in the base station device based on the request.

7. A terminal device according to any one of claims 1 to 4, wherein the transmitting means transmits the measurement report of the reference signal and a notification regarding the configuration of the report by a single signal.

8. A base station device comprising: a transmitting means for transmitting a reference signal using each of a number of second beams that is less than the number of a plurality of first beams that the base station device can form; a receiving means for receiving a notification regarding a report configuration of the measurement result of the reference signal from a terminal device that has received the reference signal, and receiving a measurement report of the reference signal based on the report configuration; and a determining means for determining which of the plurality of first beams to use for communication with the terminal device by inputting at least a portion of the measurement results of the reference signal included in the measurement report into a trained model using machine learning.

9. The base station device according to claim 8, further comprising a notification means for notifying the terminal device of information on the configuration of a second report of the measurement result of the reference signal, and the receiving means receives from the terminal device a measurement report of the reference signal having the configuration of the report and the configuration of the second report.

10. The base station device described in claim 9, wherein the second report configuration includes a configuration regarding the number of beams among the plurality of second beams for which corresponding measurement results are to be reported, and the report configuration included in the notification includes a configuration regarding at least one of the number of signals for reporting the measurement results, the content of the report regarding each beam, and the bit width of information indicating the measurement results of the reference signal.

11. The base station device of claim 8, wherein the report configuration includes configuration regarding at least one of the number of beams among the plurality of second beams for which corresponding measurement results are reported, the content of the report regarding each beam, and the bit width of information indicating the measurement results of the reference signal.

12. The base station device according to any one of claims 8 to 11, wherein the receiving means receives the notification regarding the report configuration and the measurement report of the reference signal by separate signals.

13. The base station device described in claim 12, wherein the receiving means receives the notification including a request to use the reporting configuration, and the base station device further has: a specifying means for specifying a configuration to be used in reporting the measurement results of the reference signal based on the request; and an instruction means for instructing the terminal device of the specified configuration, and the receiving means receives the measurement report of the reference signal transmitted by the terminal device using the specified configuration.

14. The base station device according to any one of claims 8 to 11, wherein the receiving means receives one signal including a measurement report of the reference signal and a notification regarding the configuration of the report.

15. A control method executed by a terminal device, the control method comprising: a base station device capable of forming a plurality of first beams, wherein at least a portion of the results of measurements by the terminal device of reference signals transmitted using each of second beams that are fewer than the plurality of first beams are input into a trained model using machine learning, thereby determining which of the plurality of first beams to use for communication with the terminal device; measuring the reference signals transmitted using each of the second beams; determining a report configuration for the measurement results of the reference signals; transmitting a notification regarding the report configuration to the base station device, and transmitting a measurement report of the reference signals to the base station device based on the report configuration.

16. A control method executed by a base station device, comprising: transmitting a reference signal using each of a number of second beams that is less than the number of multiple first beams that the base station device can form; receiving a notification regarding a report configuration of the measurement results of the reference signal from a terminal device that has received the reference signal, and receiving a measurement report of the reference signal based on the report configuration; and inputting at least a portion of the measurement results of the reference signal included in the measurement report into a trained model using machine learning, thereby determining which beam of the multiple first beams to use for communication with the terminal device.

17. A program for causing a computer provided in a terminal device to execute the control method according to claim 15.

18. A program for causing a computer installed in a base station device to execute the control method set forth in claim 16.

Images