Terminal device for efficient reporting of radio quality, base station device, communication method, and program

Abstract

This terminal device, which has the function of performing an inference of radio quality in each of one or more timings a prescribed period after a prescribed timing by inputting, in a learning phase, the result of a first measurement of radio quality at a first timing with regard to a prescribed cell or beam and inputting, in an inference phase and into a trained model acquired by machine learning in which the result of a second measurement of radio quality at one or more second timings a prescribed period after the first timing serves as teaching data, the result of a measurement of radio quality at the prescribed timing with regard to the prescribed cell or beam, transmits, to a base station device connected thereto, a report including a value indicating an estimated value of radio quality as output from the trained model with regard to the prescribed cell or beam, as well as information indicating the specific timing after the prescribed timing to which the estimated value corresponds.

Description

Terminal device, base station device, communication method, and program for efficient reporting of wireless quality

[0001] The present invention relates to techniques for reporting radio quality in cellular communication systems.

[0002] In a wireless communication system conforming to the cellular communication standard of the Third Generation Partnership Project (3GPP (registered trademark)), a terminal device measures the wireless quality of surrounding cells (beams) and continues to connect to a base station device that provides a cell with good wireless quality. To this end, the terminal device reports the measurement results of the wireless quality of surrounding cells (beams) to the base station device to which it is currently connected, and the base station device transmits to the terminal device an instruction to switch the cell (beam) to which the terminal device should connect as necessary. This allows the terminal device to be provided with a continuously good-quality communication service.

[0003] In recent years, there has been an increasing demand for improved communication quality and throughput in cellular communication systems. To meet such demands, it is important to improve the measurement of wireless quality in terminal devices and the reporting of the results to base station devices.

[0004] The present invention provides a technique for enhancing reporting of wireless quality in terminal devices.

[0005] A terminal device according to one aspect of the present invention has an estimation means for inputting the result of a first measurement of wireless quality at a first timing for a specified cell or beam into a trained model obtained by machine learning in a learning phase, using as input the result of a first measurement of wireless quality at one or more second timings a specified period after the first timing, as training data, in an inference phase, thereby estimating wireless quality at each of one or more timings a specified period after the specified timing; and a transmission means for transmitting to a base station device to which it is connected a report including a value indicating an estimated value of wireless quality output from the trained model for the specified cell or beam and information indicating which timing after the specified timing the estimated value corresponds to.

[0006] A base station device according to one aspect of the present invention has a connection means for connecting to a terminal device capable of estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a first measurement of wireless quality at a first timing for a specified cell or beam into a trained model obtained by machine learning in a learning phase, using as input the result of a first measurement of wireless quality at a first timing and the result of a second measurement of wireless quality at one or more second timings after the first timing as training data, in an inference phase; and a receiving means for receiving from the terminal device a report including a value indicating an estimated value of wireless quality output from the trained model for the specified cell or beam and information indicating which timing after the predetermined timing the estimated value corresponds to.

[0007] According to the present invention, it is possible to improve the reporting of wireless quality in a terminal device.

[0008] 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.

[0009] The accompanying drawings are incorporated in and constitute a part of the specification, illustrate embodiments of the present invention, and together with the description are used to explain the principles of the present invention. Figure 1 is a diagram showing an example of the configuration of a wireless communication system. Figure 2 is a diagram showing an example of the hardware configuration of a base station device and a terminal device. Figure 3 is a diagram showing an example of the functional configuration of a terminal device. Figure 4 is a diagram showing an example of the functional configuration of a base station device. Figure 5 is a diagram showing an example of the flow of processing executed in the wireless communication system.

[0010] 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.

[0011] (System Configuration) FIG. 1 shows an example of the configuration of a communication system according to this embodiment. This communication system is, for example, a wireless communication system conforming to the Long Term Evolution (LTE) or fifth generation (5G) cellular communication standards of the Third Generation Partnership Project (3GPP (registered trademark)), or their successor standards. This wireless communication system includes a base station device 101 and a terminal device 111. The terminal device 111 establishes a connection with the base station device 101 and performs wireless communication in a cell 121 provided by the base station device 101. The terminal device 111 is assumed to be, for example, portable and mobile by a user. If the terminal device 111 moves beyond the range of the cell 121 while communicating in the cell 121, it is assumed that the terminal device 111 will perform a handover to another cell (such as cell 122 or cell 123). For such a handover, the terminal device 111 conventionally measures the wireless quality of other cells adjacent to the cell to which it is currently connected and reports the results to the base station device 101. The term "cell" used in this embodiment may be read as "beam" unless otherwise specified.

[0012] In recent years, the application of artificial intelligence (AI) / machine learning (ML) to cellular communication systems has been discussed. For example, by using AI / ML, the wireless quality of neighboring cells can be estimated based on the wireless quality of a currently connected cell. For example, a trained model can be obtained by machine learning using, as input in a learning phase, a first measurement result of the wireless quality of a first cell or beam whose wireless quality is to be measured, and as training data, a second measurement result of the wireless quality of a second cell or beam different from the first cell or beam. In this case, by inputting the measurement result of the wireless quality of the first cell or beam to this trained model in an inference phase, it becomes possible to estimate the wireless quality of the second cell or beam.

[0013] Furthermore, in the learning phase, a trained model can be acquired by machine learning using, as input, the result of a first measurement of wireless quality at a first timing for a specific cell or beam, and the result of a second measurement of wireless quality at one or more (in one example, multiple) second timings a specific period after the first timing as training data. Then, in this inference phase, by inputting the result of the measurement of wireless quality at a specific timing for the specific cell or beam to the trained model, it becomes possible to estimate wireless quality at each of multiple timings a specific period after (in the future) the specific timing.

[0014] Furthermore, in the learning phase, a trained model can be acquired by machine learning using as input a result of a first measurement of the radio quality of a first cell or beam at a first timing and as training data a result of a second measurement of the radio quality of a second cell at one or more (in one example, multiple) second timings that are a predetermined period after the first timing. Then, in the inference phase, by inputting the result of the measurement of the radio quality of the first cell or beam at a predetermined timing to the trained model, it becomes possible to estimate the radio quality of the second cell or beam at each of multiple timings that are a predetermined period after the predetermined timing (future).

[0015] Furthermore, the measurement result used as input may be a single value at one timing, or a series (time series) of measurement results at multiple timings. If measurement results at multiple timings are used as input in the learning phase, measurement results obtained at multiple timings with the same time intervals as the multiple timings in the learning phase are also used as input in the inference phase.

[0016] In this way, by utilizing AI / ML, radio quality measurements for some cells can be performed to obtain estimates of radio quality for other cells, and also estimates of radio quality at a future time for the currently connected cell or other adjacent cells.

[0017] Conventionally, the base station device 101 notifies the terminal device 111 of configuration information specifying a cell for measuring and reporting radio quality, and the terminal device 111 measures and reports radio quality based on the configuration information. The configuration information includes, for example, a measObject related to information on a carrier frequency or reference signal for specifying a measurement target, and a reportConfig that is a configuration related to reporting. This configuration information is notified from the base station device 101 to the terminal device 111 via a radio resource control (RRC) message such as an RRC Reconfiguration message. The configuration information typically includes information in which identification information (measID) of the configuration information, a measObjectID specifying the measurement configuration (measObject), and a reportConfigID specifying the reporting configuration (reportConfig) are associated with each other. That is, a separate measObjectID is assigned to one or more measurement settings (measObject), a reportConfigID is assigned to one or more report settings (reportConfig), and one measObjectID and one reportConfigID are associated with each other, thereby associating the measurement settings with the report settings. A measID is then assigned to the combination that associates the measurement settings with the report settings. Note that, conventionally, one measID is always associated with one measObjectID and one reportConfigID. That is, the measObjectID and reportConfigID are required information elements, and omission of these is not permitted. The terminal device 111 measures wireless quality based on the measurement configuration specified by the measObjectID, and reports the measurement results using the report configuration specified by the reportConfigID associated with the measObjectID.In addition, the terminal device 111 includes a measID in the measurement result report message (Measurement Report) to specify which setting the measurement result is based on. In this way, the base station device 101 can identify which setting information the measurement result information received from the terminal device 111 is based on.

[0018] On the other hand, when AI / ML is used, it is assumed that an estimated value of wireless quality for a cell that is not measured is obtained, as described above. That is, in the terminal device 111, an estimated value of wireless quality for a cell for which a measObject is not set is generated. However, since a measObject is not set for that cell, a measObjectID is not assigned, and as a result, no corresponding measID exists. For this reason, in the conventional framework, the terminal device 111 cannot report the estimated value of wireless quality to the base station device 101.

[0019] In view of the above circumstances, this embodiment provides a technique that enables the terminal device 111 to transmit an estimated value of wireless quality to the base station device 101.

[0020] In one example, in the present embodiment, similarly to the conventional technique, the base station device 101 transmits to the terminal device 111 configuration information related to measurements and reports for a cell whose wireless quality is to be measured. That is, configuration information in which a measObjectID, a reportConfigID, and a measID are associated with each other for a cell whose wireless quality is to be measured is notified from the base station device 101 to the terminal device 111. On the other hand, for a cell whose wireless quality is to be estimated by inputting measurement results of other cells into a trained model, configuration information in which a reportConfigID and a measID are associated with each other but no measObjectID is notified from the base station device 101 to the terminal device 111. That is, the measObjectID, which was previously a required information item, is made optional, and it is possible to omit this information item for cells whose wireless quality is not to be measured. This makes it possible to report an estimated value for a cell for which no measurement is performed and for which no measObject is set. Note that the cell to which the configuration information, in which the measID and the reportConfigID are associated but the measObjectID are not associated, is associated can be identified, for example, by a trained model for obtaining an estimated value of wireless quality. That is, when a target cell for wireless quality estimation using a trained model is uniquely determined, an estimated value of wireless quality for that cell is reported from the terminal device 111 to the base station device 101 based on the configuration information that is not associated with the measObjectID.

[0021] On the other hand, when estimates of wireless quality for multiple cells are reported, a separate reporting configuration may be prepared for each cell. In this case, information for identifying the cell for which wireless quality is estimated may be associated with measID and reportConfigID and notified to the terminal device 111. For example, the configuration information for the cell for which wireless quality is measured may be notified to the terminal device 111 by associating an item measObjectID with measID and reportConfigID, and the configuration information for the cell for which wireless quality is estimated may be notified to the terminal device 111 by associating an item named predictObjectID with measID and reportConfigID. The item predictObjectID may include, for example, a cell identifier (such as a physical cell identifier). Note that this item name is merely an example shown for explanation, and other item names may be used. Furthermore, for example, when multiple trained models acquire estimates of the wireless quality of different cells, information identifying the trained models may be used as information for identifying the cell for which the wireless quality is estimated. That is, when multiple trained models are each associated with one cell, identifying one trained model can identify which cell an estimate for that trained model is acquired.

[0022] For a first cell in which a measObject is set and a measObjectID associated with a measID is specified, the terminal device 111 measures radio quality by observing a reference signal (e.g., a synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB) or a channel state information-reference signal (CSI-RS)) specified in the measObject. Then, the terminal device 111 sets the (cell-level) radio quality in cellResults (resultSSB-Cell, resultCSI-RS-Cell) of MeasResults. When reporting beam-level radio quality, the terminal device 111 sets the radio quality in rsIndexResults (resultSSB-Indexes, resultCSI-RS-Indexes) of MeasResults. Then, the terminal device 111 reports the value set in MeasResults to the base station device 101 using the report setting indicated by reportConfig associated with measID.

[0023] On the other hand, the terminal device 111 does not measure the wireless quality of a second cell for which a measObject is not set and for which a measObjectID associated with a measID is not specified. The terminal device 111 inputs the wireless qualities of other cells into a trained model capable of outputting an estimated value of wireless quality for that cell. Then, the terminal device 111 obtains an estimated value of wireless quality for that second cell as an output from the trained model. The terminal device 111 then sets the (cell-level) wireless quality in the cellResults (resultSSB-Cell, resultCSI-RS-Cell) of MeasResults. When reporting beam-level radio quality, the terminal device 111 sets the radio quality in rsIndexResults (resultSSB-Indexes, resultCSI-RS-Indexes) of MeasResults. Then, the terminal device 111 uses the report setting indicated by reportConfig associated with measID to report the value set in MeasResults to the base station device 101. Note that the value of measID is stored in MeasResults to indicate which setting the report is based on.

[0024] In this way, the base station device 101 generates first information associating measID, measObjectID, and reportConfigID for a first cell for which wireless quality measurement is to be performed, and generates second information associating measID with reportConfigID but not associating measObjectID for a second cell for which an estimated value of wireless quality is to be obtained from measured values ​​of wireless quality for other cells, and notifies the terminal device 111 of configuration information including the first information and second information. Based on this configuration information, the terminal device 111 measures wireless quality based on the measObject setting for the first cell for which the first information has been notified, and estimates wireless quality using AI / ML without measuring wireless quality for the second cell for which the second information has been notified. Then, the terminal device 111 reports the measurement value of the wireless quality of the first cell to the base station device 101 based on the reportConfig associated with the first information, using MeasResults including the measID associated with the first information. Also, the terminal device 111 reports the estimated value of the wireless quality of the second cell to the base station device 101 based on the reportConfig associated with the second information, using MeasResults including the measID associated with the second information. This makes it possible to report the estimated value of the wireless quality for a cell for which no measurement target is configured, with minimal changes from conventional measurement and reporting settings.

[0025] Furthermore, when AI / ML is used, it is assumed that an estimated value of future wireless quality for a specific cell is obtained, as described above. It is also assumed that multiple estimated values ​​of wireless quality for a specific cell at multiple future timings are obtained. Meanwhile, conventionally, while it has been possible to report a wireless quality measurement value at a current timing for a single cell, there has been no provision for reporting an estimated value of wireless quality at a future time point. Therefore, in the conventional framework, the terminal device 111 cannot report one or more estimated values ​​of wireless quality at that future time point to the base station device 101.

[0026] In this embodiment, in view of such circumstances, it is possible to report an estimated value of wireless quality at a future time. For example, in MeasResults, the item MeasQuantityResults that defines the contents of ResultsSSB-Cell (ResultsSSB-Indexes) and ResultsCSI-RS-Cell (ResultsCSI-RS-Indexes) indicating measurement values ​​can be extended to include information indicating the timing at which the reported value corresponds. Note that this is just one example, and the timing at which the reported value corresponds may be indicated in an item other than MeasQuantityResults. When multiple estimates are reported, multiple ResultsSSB-Cell (ResultsSSB-Indexes) or ResultsCSI-RS-Cell (ResultsCSI-RS-Indexes) may be listed in MeasResults to indicate the respective estimates. Each of the multiple listed information elements may be used to report a single estimate, and timestamp information indicating the timing to which the estimate corresponds may be stored in the information element. In one example, MeasResults may use ResultsSSB-Cell (ResultsSSB-Indexes) or ResultsCSI-RS-Cell (ResultsCSI-RS-Indexes) that do not include timestamp information to report the actual wireless quality, rather than an estimate. In other words, when the base station device 101 receives information that does not include a timestamp, it may determine that the value indicated by the information is the actually measured wireless quality, and when it receives information that includes a timestamp, it may determine that the value indicated by the information is an estimated value of the wireless quality.

[0027] Note that, for example, when wireless quality is estimated at multiple timings, the timestamp may be indicated in units corresponding to the time intervals between the multiple timings. For example, when wireless quality is estimated based on SSB, the multiple timings may be set at SSB periods. In this case, the timestamp may be indicated by the number of SSB periods. For example, the timing at which the SSB wireless quality is measured may be set as "0," the timestamp for the estimated value of wireless quality corresponding to the next SSB may be set as "1," and the timestamp for the estimated value of wireless quality corresponding to the SSB after that may be set as "2." Furthermore, the timestamp may be specified in units of time slots. Furthermore, for example, a combination of information indicating the earliest timing among the estimated values ​​of wireless quality and the time increment width of subsequent timings may be notified. For example, information specifying multiple timings collectively may be notified, such as the first timing being 20 milliseconds (ms) after a predetermined timing at which wireless quality is measured, followed by five estimates transmitted every 10 ms.

[0028] The base station device 101 may notify the terminal device 111 in advance of information indicating the number of estimated values ​​to be reported among the estimated values ​​corresponding to different timings as configuration information. That is, configuration information specifying the number of pieces of wireless quality information to be transmitted together with information indicating future timings can be specified in, for example, ReportConfig.

[0029] In this way, it is possible to transmit to the base station device 101 an estimated value of wireless quality estimated by the terminal device 111 using AI / ML for each of one or more future timings. This enables the base station device 101 to, for example, perform control of early execution of handover using the value of future wireless quality. In the above example, an example has been described in which the terminal device 111 acquires an estimated value of wireless quality for each of one or more future timings for the currently connected cell using AI / ML, but this is not limiting. For example, an estimated value of wireless quality for one or more future timings of another cell, such as a neighboring cell, may be acquired based on a measurement value of wireless quality in the currently connected cell, or an estimated value of wireless quality for one or more future timings of another cell may be acquired based on a measurement value of wireless quality in the other cell. Furthermore, an estimated value of wireless quality for one or more future timings of the currently connected cell may be acquired based on a measurement value of wireless quality in the other cell.

[0030] The terminal device 111 can notify the base station device 101 of information indicating whether or not it is possible to estimate wireless quality using AI / ML, using information indicating its own capabilities (UE Capability). If the terminal device 111 is capable of estimating wireless quality using AI / ML, the base station device 101 can notify the above-mentioned configuration information. That is, if the terminal device 111 is not capable of estimating wireless quality using AI / ML, the base station device 101 transmits to the terminal device 111 configuration information that includes first information in which a measObjectID, a reportConfigID, and a measID are associated with each other, and does not include second information in which the reportConfigID and the measID are associated with each other but the measObjectID is not associated with each other. On the other hand, when the terminal device 111 is capable of estimating wireless quality using AI / ML, the base station device 101 transmits configuration information including first information about a cell whose wireless quality is to be measured and second information about a cell whose wireless quality is to be estimated to the terminal device 111. This enables the base station device 101 to individually transmit appropriate configuration information in an environment where terminal devices capable of estimating wireless quality using AI / ML and terminal devices whose wireless quality is not capable of this estimation coexist.

[0031] The terminal device 111 may generate a trained model by performing machine learning, or may acquire a separately generated trained model from the base station device 101. When machine learning is performed in the terminal device 111, a trained model cannot be acquired until training data has been acquired a sufficient number of times, but a trained model suitable for the terminal device 111 can be acquired. On the other hand, when a trained model is provided from the base station device 101, a large amount of training data can be obtained from communications between a large number of terminal devices previously connected to the cell 121, thereby enabling learning to be completed quickly. The base station device 101 can also perform machine learning using, for example, reports of measurement results from terminal devices that are not capable of estimating wireless quality using AI / ML. The base station device 101 may also notify the terminal device 111 of information to be input into the provided trained model and information indicating the output of the trained model at that time. In accordance with the notification, the terminal device 111 may, for example, collect information to be input into the trained model provided from the base station device 101 (the wireless quality of the currently connected cell 121 or other cells) and input it into the trained model. Then, in accordance with the notification, the terminal device 111 can identify what kind of information is output from the trained model (for example, whether it is the wireless quality of another cell or the future wireless quality of the currently connected cell 121), and transmit a measurement result report in a format suitable for that output to the base station device 101. The terminal device 111 may also perform machine learning in accordance with the notification.

[0032] Note that performance evaluation of the trained model may be performed periodically, for example. For example, the base station device 101 may notify the terminal device 111, which is capable of estimating wireless quality, of configuration information for the cell for which wireless quality is to be estimated, including both the first information and the second information described above. The terminal device 111 then measures the wireless quality of the cell and estimates the wireless quality, and reports both to the base station device 101. The base station device 101 may then calculate the difference (error) between the actual measured value and the estimated value of the wireless quality. If the error is equal to or greater than a predetermined value, the base station device 101 may evaluate the trained model as unsuitable for the real environment and decide to perform re-learning (additional learning). Furthermore, if the difference between the estimated value and the actual measured value of the wireless quality for the maximum value or a predetermined number of highest values ​​for multiple cells is equal to or greater than a predetermined value, the trained model may be evaluated as unsuitable for the real environment and re-learning may be performed. The base station device 101 then instructs, for example, a connected terminal device to measure and report the wireless quality of the cell to which the terminal device belongs and its neighboring cells, and performs re-learning of the trained model using the reported wireless quality. The base station device 101 may terminate re-learning when the error between the output of the trained model and the actually measured wireless quality becomes equal to or less than a predetermined level after re-learning. The base station device 101 may receive reports of wireless quality measurement results from terminal devices that do not estimate wireless quality, and periodically re-learn the trained model based on the measurement results. The base station device 101 notifies the terminal device 111 of the trained model after re-learning, and the terminal device 111 estimates wireless quality using the updated trained model after the notification. If the terminal device 111 has generated a trained model, it may notify the base station device 101 that it will perform this re-learning. Furthermore, the terminal device 111 may notify the base station device 101 that re-learning is necessary, and perform re-learning in response to receiving a predetermined instruction from the base station device 101. This allows the trained model to be maintained in an appropriate state, and makes it possible to execute handover processing based on predictions at appropriate timing.

[0033] (Device Configuration) FIG. 2 shows an example of the hardware configuration of the base station device 101 and the terminal device 111 according to this embodiment. In one example, the base station device 101 and the terminal device 111 are configured to include a processor 201, a ROM 202, a RAM 203, a storage device 204, and a communication circuit 205. The processor 201 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 202 or the storage device 204. The ROM 202 is a read-only memory that stores information such as programs and various parameters related to the processing performed by the base station device 101 and the terminal device 111. The RAM 203 functions as a workspace when the processor 201 executes a program and is also a random access memory that stores temporary information. The storage device 204 is configured, for example, by a removable external storage device. The communication circuit 205 is configured, for example, by a circuit for wireless communication of 5G or a successor standard. While FIG. 2 illustrates one communication circuit 205, the base station device 101 and the terminal device 111 may have multiple communication circuits. For example, the base station device 101 and the terminal device 111 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 111 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 111 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 111 may have separate communication circuits 205 for each of the multiple available frequency bands, or may have a common communication circuit 205 for at least some of the frequency bands.

[0034] FIG. 3 shows an example of the functional configuration of the terminal device 111. The terminal device 111 includes, for example, a capability information notification unit 301, a setting information receiving unit 302, a quality measurement unit 303, a quality estimation unit 304, and a reporting unit 305. The terminal device 111 may also include, as an option, a learning unit 306. Note that FIG. 3 only shows functions particularly related to this embodiment, and does not illustrate various other functions that the terminal device 111 may have. For example, the terminal device 111 naturally has other functions that terminal devices compliant with LTE, 5G, or subsequent standards generally have. The functional blocks in FIG. 3 are shown schematically, and the respective functional blocks may be realized as an integrated unit or may be further subdivided. Furthermore, the functions in FIG. 3 may be realized, for example, by the processor 201 executing a program stored in the ROM 202 or the storage device 204, or by a processor within the communication circuit 205 executing predetermined software. Since the details of the processes executed by each functional unit have been described above, only the general functions of the terminal device 111 will be outlined here.

[0035] The capability information notifying unit 301 notifies the base station device 101 of capability information possessed by the terminal device 111 as UE Capability. For example, the capability information notifying unit 301 notifies the base station device 101 of information indicating whether the terminal device 111 has the capability to estimate the wireless quality of some cells from the measured values ​​of the wireless quality of other cells using AI / ML. Furthermore, the capability information notifying unit 301 notifies the base station device 101 of information indicating whether the terminal device 111 has the capability to estimate the future wireless quality of a specific cell from the measured values ​​of the wireless quality of the specific cell using AI / ML. The setting information receiving unit 302 receives setting information related to communication from the base station device 101. As described above, the setting information includes first information in which a measObjectID, a reportConfigID, and a measID for a cell for which wireless quality measurement is to be performed are associated. In addition, when the terminal device 111 has the ability to acquire an estimated value of the wireless quality of a second cell by inputting a measured value of the wireless quality of a first cell into a trained model, the configuration information may include second information in which a reportConfigID and a measID are associated but a measObjectID is not associated. Also, when the terminal device 111 has the ability to specify the wireless quality of a specific cell at a future timing by inputting a measured value of the wireless quality of the specific cell into a trained model, the configuration information may include information for instructing notification of information associating the estimated value with the timing, and information indicating the number of estimated values ​​of the wireless quality that should be notified among the estimated values ​​of the wireless quality corresponding to each different timing.

[0036] The quality measurement unit 303 measures the wireless quality of the connected first cell, etc., in accordance with the configuration information (measObject) identified by the measObjectID specified in the first information or the predetermined information among the configuration information received by the configuration information reception unit 302. The quality estimation unit 304 inputs the wireless quality of the first cell measured by the quality measurement unit 303 into the trained model, thereby obtaining an estimate of the wireless quality of the second cell or the wireless quality of the first cell at a future timing.

[0037] The reporting unit 305 reports the measurement value and the estimated value of wireless quality to the base station device 101 based on the setting information. The reporting unit 305 uses reportConfig specified by reportConfigID associated with the first information to report information of the measurement value of wireless quality including the measID associated with the first information to the base station device 101. Furthermore, the reporting unit 305 uses reportConfig specified by reportConfigID associated with the second information to report information of the estimated value of wireless quality including the measID associated with the second information to the base station device 101. Furthermore, the reporting unit 305 reports information indicating the estimated value of wireless quality at a future timing to the base station device 101 together with information capable of identifying that timing. When the number of estimated values ​​of future wireless quality to be reported is specified by the base station device 101, the reporting unit 305 can generate MeasResults that lists the number of cellResults or rsIndexResults indicating the wireless quality of the same cell, and report the MeasResults to the base station device 101. At this time, information indicating timing can be stored in each of the cellResults or rsIndexResults.

[0038] When a trained model needs to be generated in the terminal device 111, the learning unit 306 generates the trained model by machine learning. In addition, the learning unit 306 can re-learn the trained model in response to an instruction from the base station device 101, for example.

[0039] FIG. 4 shows an example of the functional configuration of the base station device 101. The base station device 101 includes a capability information receiving unit 401, a setting information notifying unit 402, and a report receiving unit 403. The base station device 101 may also include a learning unit 404 as an option. Note that FIG. 4 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 are generally possessed by base station devices compliant with LTE, 5G, or subsequent standards. The functional blocks in FIG. 4 are shown schematically, and the respective functional blocks may be integrated or further subdivided. Each function in FIG. 4 may be realized, for example, by the processor 201 executing a program stored in the ROM 202 or the storage device 204, or by a processor within the communication circuit 205 executing predetermined software. Since the details of the processing performed by each functional unit are as described above, only the general functions of the base station device 101 will be outlined here.

[0040] The capability information receiving unit 401 receives capability information (UE Capability) from the terminal device 111, including information indicating whether the terminal device 111 has the capability to estimate radio quality using AI / ML. The configuration information notifying unit 402 can transmit information instructing whether to estimate radio quality using AI / ML, to the terminal device 111 that has the capability to estimate radio quality using AI / ML. Furthermore, the configuration information notifying unit 402 can notify the terminal device 111 that has the capability to estimate the radio quality of some cells based on measured values ​​of the radio quality of other cells using AI / ML of configuration information including the first information and second information. Furthermore, the configuration information notifying unit 402 can notify the terminal device 111 that has the capability to acquire an estimate of radio quality of a specific cell at a future timing based on measured values ​​of the radio quality of the specific cell using AI / ML of configuration information indicating the number of estimates to be reported for the specific cell. The configuration information may associate the measObjectID, reportConfigID, and measID for that particular cell, and may further include information indicating that estimates of future timing should be reported, and the number of estimates to be reported.

[0041] The report receiving unit 403 receives from the terminal device 111 a report of the measured and estimated values ​​of wireless quality based on the setting information notified to the terminal device 111 by the setting information notifying unit 402. The base station device 101 can initiate handover processing of the terminal device 111 based on the measured and estimated values.

[0042] The learning unit 404 performs machine learning to generate a trained model for estimating wireless quality. It is sufficient for either the learning unit 306 of the terminal device 111 or the learning unit 404 of the base station device 101 to perform machine learning; it is not necessary for both to perform machine learning. Furthermore, machine learning may be performed in a network node different from either the base station device 101 or the terminal device 111. The base station device 101 may transmit an instruction to the terminal device 111 to report the difference between the actual measured value and the estimated value of wireless quality to the base station device 101. Then, if the difference exceeds a predetermined value, either the learning unit 306 of the terminal device 111 or the learning unit 404 of the base station device 101 performs re-learning of the trained model. Furthermore, instead of the difference between the estimated value and the actual measured value, information indicating that re-learning is required may be notified from the terminal device 111 to the base station device 101. In addition, when machine learning is performed in a network node different from both the base station device 101 and the terminal device 111, the base station device 101 may notify the network node that re-learning should be performed.

[0043] (Processing Flow) An example of a processing flow according to this embodiment is shown in Fig. 5. Note that, since the details of the processing executed in the wireless communication system are as described above, only an overview of the processing flow will be given here, and the details will not be repeated.

[0044] First, the terminal device 111 notifies the base station device 101 of its own capability information (S501). Here, the capability information including information indicating that the terminal device 111 can estimate wireless quality using AI / ML is notified from the terminal device 111 to the base station device 101. When the base station device 101 determines from the capability information that the terminal device 111 can estimate wireless quality using AI / ML, the base station device 101 notifies the terminal device 111 of setting information for estimating and reporting wireless quality, for example, using an RRC Reconfiguration message. Thereafter, the terminal device 111 measures a reference signal transmitted from the base station device 101 (S503, S504) and inputs the measurement value into a trained model to estimate an estimate of wireless quality of another cell or an estimate of future wireless quality of the cell (S505). Then, the terminal device 111 notifies the base station device 101 of the value of the wireless quality measurement result in S504 and the value of the wireless quality estimation result in S505 (S506).

[0045] As described above, according to the present embodiment, it is possible for the terminal device 111 to notify the base station device 101 of estimated values ​​of wireless quality for cells not designated as measurement targets without significantly changing the format of reporting measurement results in the past. This makes it possible to timely set an appropriate cell or beam to which the terminal device 111 is connected. Furthermore, it is possible for the terminal device 111 to notify the base station device 101 of estimated values ​​of wireless quality for one cell at multiple timings. This allows the base station device 101 to obtain a predicted value of future wireless quality, thereby improving the reporting of wireless quality compared to the conventional case in which only one actually measured wireless quality is reported for each cell. As a result, it is possible to perform more advanced communication control of the terminal device 111. 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."

[0046] 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.

[0047] This application claims priority based on Japanese Patent Application No. 2024-131183, filed August 7, 2024, the entire contents of which are incorporated herein by reference.

Claims

1. A terminal device comprising: an estimation means for estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a first measurement of wireless quality at a first timing for a specified cell or beam in a learning phase, and a trained model obtained by machine learning using as input the result of a first measurement of wireless quality at one or more second timings after the first timing in a predetermined period as training data in an inference phase; and a transmission means for transmitting to a connected base station device a report including a value indicating an estimated value of wireless quality output from the trained model for the specified cell or beam and information indicating which timing after the predetermined timing the estimated value corresponds to.

2. The terminal device according to claim 1, wherein the transmitting means transmits to the base station device as the report MeasResults including one or more information elements each including the estimated value corresponding to one or more timings after the predetermined period from the predetermined timing and information indicating which timing after the predetermined timing the estimated value corresponds to.

3. The terminal device according to claim 1, wherein the one or more timings correspond to a period at which a synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB) is transmitted in the specified cell or beam.

4. The terminal device according to claim 1, further comprising receiving means for receiving information indicating the number of said estimates to be included in said report from said base station device.

5. A base station device comprising: a connection means for connecting to a terminal device capable of estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a first measurement of wireless quality at a first timing for a predetermined cell or beam in an inference phase to a trained model obtained by machine learning using as input the result of a first measurement of wireless quality at a first timing and the result of a second measurement of wireless quality at one or more second timings after the first timing in a learning phase; and a receiving means for receiving from the terminal device a report including a value indicating an estimated value of wireless quality output from the trained model for the predetermined cell or beam and information indicating which timing after the predetermined timing the estimated value corresponds to.

6. The base station device according to claim 5, wherein the receiving means receives from the terminal device as the report MeasResults including one or more information elements each including the estimated value corresponding to one or more timings after the predetermined time period from the predetermined timing and information indicating to which of the one or more timings after the predetermined time period from the predetermined timing the estimated value corresponds.

7. The base station device according to claim 5, wherein the one or more timings correspond to a period at which a synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB) is transmitted in the specified cell or beam.

8. A base station device as described in claim 5, further comprising a notification means for notifying the terminal device of information indicating the number of estimated values ​​of wireless quality corresponding to different timings output from the trained model to be included in the report.

9. A communications method executed by a terminal device having a function of estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a wireless quality measurement at a predetermined timing for a specified cell or beam in an inference phase into a trained model obtained by machine learning using as input the result of a first measurement of wireless quality at a first timing for the specified cell or beam and the result of a second measurement of wireless quality at one or more second timings after the first timing in a learning phase as training data, the communications method including transmitting to a connected base station device a report including a value indicating an estimated value of wireless quality output from the trained model for the specified cell or beam and information indicating which timing after the predetermined timing the estimated value corresponds to.

10. A communication method executed by a base station device, comprising: connecting to a terminal device capable of estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a first measurement of wireless quality at a first timing for a predetermined cell or beam into a trained model obtained by machine learning in a learning phase, using as input the result of a first measurement of wireless quality at a first timing and the result of a second measurement of wireless quality at one or more second timings after the first timing as training data; and receiving from the terminal device a report including a value indicating an estimated value of wireless quality output from the trained model for the predetermined cell or beam and information indicating which timing after the predetermined timing the estimated value corresponds to.

11. A program for causing a computer provided in a terminal device having the function of estimating wireless quality at each of one or more timings after a predetermined period from a predetermined timing by inputting the result of a first measurement of wireless quality at a first timing for a predetermined cell or beam in a learning phase and the result of a second measurement of wireless quality at one or more second timings after the first timing as training data to execute the communication method described in claim 9.

12. A program for causing a computer installed in a base station device to execute the communication method according to claim 10.

Images