System, method, and program

Abstract

Provided is a system, a method, and a program capable of acquiring desired data. The system comprises: an acquisition unit; a calculation unit; and a selection unit. The acquisition unit of the system acquires first data items related to the communication quality from a plurality of terminals. The calculation unit of the system calculates a similarity index among the first data items of the plurality of terminals on the basis of the data items acquired by the acquisition unit. The selection unit of the system selects, on the basis of the similarity index calculated by the calculation unit, a terminal from which the acquisition unit acquires second data related to the communication quality.

Description

System, method and program

[0001] The present disclosure relates to a system, a method, and a program.

[0002] There is known a technology for acquiring data from multiple terminals and performing monitoring, control, etc. based on the acquired data. For example, Patent Literature 1 describes that an O-RAN (Open Radio Access Network) RIC (RAN Intelligent Controller) acquires reception quality information from terminals and controls the bandwidth used by a base station.

[0003] JP 2023-110542 A

[0004] However, in related technologies such as Patent Document 1, no consideration is given to how to select a terminal from which data is to be acquired. Therefore, for example, when acquiring data from an arbitrary terminal, there is a possibility that desired data may not be acquired.

[0005] In view of the above problems, one of the objects of the present disclosure is to provide a system, a method, and a program that are capable of acquiring desired data.

[0006] A system according to one aspect of the present disclosure includes an acquisition unit that acquires first data related to communication quality from a plurality of terminals, a calculation unit that calculates a similarity index between the first data of the plurality of terminals, and a selection unit that selects a terminal from which to acquire second data related to communication quality based on the similarity index.

[0007] A method according to one aspect of the present disclosure involves obtaining first data regarding communication quality from a plurality of terminals, calculating a similarity index between the first data of the plurality of terminals, and selecting a terminal from which to obtain second data regarding communication quality based on the similarity index.

[0008] A program according to one aspect of the present disclosure is a program for causing a computer to execute a process of acquiring first data regarding communication quality from a plurality of terminals, calculating a similarity index between the first data of the plurality of terminals, and selecting a terminal from which to acquire second data regarding communication quality based on the similarity index.

[0009] According to the present disclosure, desired data can be obtained.

[0010] FIG. 1 is a block diagram illustrating an example configuration of a system according to some embodiments. FIG. 2 is a block diagram illustrating an example configuration of an apparatus according to some embodiments. FIG. 3 is a flowchart illustrating a method according to some embodiments. FIG. 4 is a block diagram illustrating an example configuration of a RAN system according to some embodiments. FIG. 5 is a block diagram illustrating an example configuration of each apparatus in a RAN system according to some embodiments. FIG. 6 is a block diagram illustrating an example configuration of each apparatus in a RAN system according to some embodiments. FIG. 7 is a flowchart illustrating an example operation in a RAN system according to some embodiments. FIG. 8 is a block diagram illustrating an example distance matrix according to some embodiments. FIG. 9 is a block diagram illustrating an example terminal selection according to some embodiments. FIG. 10 is a block diagram illustrating an example terminal selection according to some embodiments. FIG. 11 is a block diagram illustrating an example configuration of each apparatus in a RAN system according to some embodiments. FIG. 12 is a flowchart illustrating an example operation in a RAN system according to some embodiments. FIG. 13 is a block diagram illustrating an example of a distance matrix according to some embodiments. FIG. 14 is a flowchart illustrating an example operation in a RAN system according to some embodiments. FIG. 15 is a block diagram illustrating an overview of computer hardware according to some embodiments.

[0011] Hereinafter, embodiments will be described with reference to the drawings. In the drawings, the same elements are denoted by the same reference numerals, and redundant description will be omitted as necessary.

[0012] (Considerations leading to the embodiments) The inventors have studied data collection in an O-RAN RIC as an example. Note that the RIC is just one example, and the embodiments can be applied to other devices and systems that collect data from multiple terminals, as well as RICs, that have similar issues. The RIC can perform intelligent control by utilizing AI (Artificial Intelligence) / ML (Machine Learning). For example, the RIC is equipped with an AI / ML-based learning-type wireless analysis function, and can identify the cause of communication quality degradation occurring in a wireless section based on the radio wave quality collected from the terminal.

[0013] One possible method is to collect communication quality and other information from all terminals in the RIC. However, collecting information from all terminals places a heavy load on the system. For example, if all terminals constantly measure and report radio wave quality, the load on the terminals will be heavy. Furthermore, if there are a large number of terminals, the processing load on the RIC and the load on the interfaces between devices will be heavy.

[0014] Another method to reduce the load is to limit the number of terminals collecting data. However, simply reducing the number of terminals collecting data poses the problem of not being able to collect the desired data. For example, to identify the cause of degradation in communication quality, the overall communication quality of the wireless environment is required. Data from various locations is required to estimate the cause of degradation in communication quality that occurs depending on the terminal's movement route or location. In addition, there are cases where an operator wants to monitor the entire wireless environment or where data overlooking the entire wireless environment is required for network redesign. For this reason, if the number of terminals is limited and data is acquired from, for example, specific terminals or arbitrary terminals, the data will be biased and the desired data will not be collected.

[0015] Therefore, in the following embodiment, by appropriately selecting a terminal from which data is acquired, it is possible to collect desired data while suppressing the load of data collection.

[0016] It is also possible to use the location information of the terminal to acquire data from a terminal that is physically far away. However, there are cases where not all terminals have the location information acquisition function, or where accurate location information cannot be acquired indoors, etc. For example, in the embodiment, desired data is collected without using the location information of the terminal.

[0017] (Embodiment 1) First, embodiment 1 will be described. In this embodiment, an outline of several embodiments will be described.

[0018] 1 shows an example of the configuration of a system 10 according to some embodiments. The system 10 may be, for example, a system that controls a wireless network such as a RAN, but may also be any other system that acquires data from terminals. For example, the system 10 may include either or both of a Near-RT RIC and a Non-RT RIC.

[0019] In the example of FIG. 1 , the system 10 includes an acquisition unit 11, a calculation unit 12, and a selection unit 13. The acquisition unit 11 acquires first data related to communication quality from a plurality of terminals. For example, the communication quality may include wireless quality. The wireless quality includes an index indicating the received power or radio wave strength of radio waves, and may be, for example, RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator), SINR (Signal to Interference plus Noise power Ratio), etc. The communication quality includes an index indicating traffic quality, and may be, for example, throughput, delay time, etc.

[0020] The calculation unit 12 calculates a similarity index between the first data of the plurality of terminals. For each combination of the plurality of terminals, the calculation unit 12 calculates a similarity index between the first data acquired by the acquisition unit 11. The similarity index between the data is an index indicating the degree of similarity between two pieces of data, and may be, for example, a distance, a similarity, a correlation, etc. between the pieces of data.

[0021] The selector 13 selects terminals from which the acquirer 11 acquires second data related to communication quality based on the similarity index calculated by the calculator 12. The first data and the second data are acquired at different times. The selector 13 may select, as terminals from which the second data is acquired, terminals whose first data is less similar than terminals whose first data is more similar. For example, the acquirer 11 acquires the first data from terminals in a first group among the multiple terminals, and the selector 13 may select a first number (e.g., N) of terminals included in the first group as terminals to be excluded from acquiring the second data based on the similarity index between the first data, and select terminals from which the second data is acquired, excluding the selected first number of terminals from the terminals included in the first group, and the first number of terminals included in the second group. The second group is a set of one or more terminals other than the first group. In this case, the selection unit 13 may select a first number of terminals from among the terminals included in the first group that have a higher degree of similarity between the first data as terminals to be excluded from obtaining the second data.

[0022] The selection unit 13 may select a specific target terminal as the terminal from which the second data is to be acquired. The target terminal is a terminal that the operator desires to focus on. The system 10 may include a designation unit that designates a target terminal from among multiple terminals. The selection unit 13 may select a terminal from which the second data is to be acquired based on a similarity index between the first data acquired from the target terminal and the first data acquired from other terminals. In this case, the selection unit 13 may select a terminal from which the degree of similarity between the target terminal and the first data is higher than a predetermined value. The selection unit 13 may also select a terminal from which the second data is to be acquired based on a policy for selecting a terminal from which the second data is to be acquired. For example, the policy may include focusing on the target terminal, i.e., selecting a terminal from which the degree of similarity between the target terminal and the first data is higher than a predetermined value. The policy may include the percentage of terminals from which the degree of similarity between the target terminal and the first data is higher than a predetermined value and the percentage of other terminals.

[0023] The system 10 may be configured with one device or multiple devices. Fig. 2 shows an example configuration of a device 20 according to some embodiments. In the example of Fig. 2, the device 20 includes the acquisition unit 11, calculation unit 12, and selection unit 13 shown in Fig. 1. For example, some or all of the acquisition unit 11, calculation unit 12, and selection unit 13 may be located in either the near-RT RIC or the non-RT RIC, or in other devices.

[0024] Figure 3 illustrates a method according to some embodiments, which may be performed, for example, by system 10 of Figure 1 or device 20 of Figure 2.

[0025] In the example of FIG. 3 , the acquisition unit 11 acquires first data related to communication quality from multiple terminals (S11). Next, the calculation unit 12 calculates a similarity index between the first data of the multiple terminals (S12). For example, the calculation unit 12 may calculate the distance, similarity, correlation, etc. between the acquired first data of the terminals. Next, the selection unit 13 selects a terminal from which to acquire second data related to communication quality based on the similarity index (S13). For example, the selection unit 13 may select a terminal from which to acquire second data a terminal having a long distance between the first data, a terminal having a low similarity, or a terminal having a low correlation. Thereafter, data from the terminal selected in S11 is acquired, and S11 to S13 are repeated.

[0026] As described above, in this embodiment, in a system that acquires data related to communication quality from multiple terminals, a terminal from which new data is acquired is selected based on similarity indices such as distance, similarity, and correlation between the acquired data. This allows terminals to be appropriately selected and data to be acquired according to the degree of similarity of the data measured by the terminals. For example, by selecting a terminal whose data is less similar than a terminal whose data is more similar, and acquiring data from that terminal, it is possible to acquire data that is more balanced and provides a bird's-eye view. Therefore, it is possible to acquire desired data even when the number of terminals from which data is acquired is limited to reduce the load.

[0027] In the following embodiment, a specific example of the first embodiment will be described.

[0028] (Embodiment 2) Next, a description will be given of embodiment 2. In this embodiment, an example will be described in which a terminal from which data is to be acquired is selected based on the distance between data acquired from a plurality of terminals.

[0029] 4 shows an example of the configuration of a RAN system 1 according to some embodiments. In the example of FIG. 4, the RAN system 1 includes a Near-RT RIC 100, a Non-RT RIC 200, an O-DU 300, an O-CU 400, an external server 500, and a terminal 600.

[0030] The terminal 600 is a UE (User Equipment) that connects to a RAN including the O-DU 300 and the O-CU 400 and performs wireless communication. The terminal 600 is also an example of a device that measures wireless quality and transmits wireless quality data indicating the measured wireless quality. The terminal 600 may be a mobile phone, a smartphone, a tablet terminal, an IoT (Internet of Things) terminal, or the like. The terminal 600 may be an AGV (Automated Guided Vehicle), an AMR (Autonomous Mobile Robot), an autonomously traveling robot, a drone, a self-driving car, or the like that implements terminal functions. The terminal 600 is, for example, a mobile terminal, but may also be a terminal with a fixed location.

[0031] The terminal 600, for example, measures the received power of radio waves at its own location and transmits the measured received power as radio quality data to the RAN including the O-DU 300 and the O-CU 400. The terminal 600 measures the received power of radio waves from a transmission source. For example, the transmission source is a base station configured by the RAN, but may be other devices. The terminal 600 receives radio waves transmitted by the transmission source and measures the received power of the received radio waves. The received power is, for example, RSRP, RSRQ, RSSI, SINR, etc., and may also be other indicators indicating radio quality.

[0032] The Non-RT RIC 200 and the Near-RT RIC 100 are communicatively connected via the O1 interface. The Non-RT RIC 200 and the E2 node including the O-DU 300 and the O-CU 400 are also communicatively connected via the O1 interface. The O1 interface is an interface primarily for sending and receiving data and messages required for operation and management. Note that an interface is a connection interface defined by a communication protocol for sending and receiving data and messages, and includes logical transmission paths and networks, as well as physical transmission paths and networks.

[0033] Furthermore, the Non-RT RIC 200 and the Near-RT RIC 100 are communicatively connected via an A1 interface. The Near-RT RIC 100 and the E2 node including the O-DU 300 and the O-CU 400 are connected via an E2 interface. The A1 interface and the E2 interface are interfaces primarily for transmitting and receiving data and messages required for control. The O-DU 300 and the O-CU 400 are communicatively connected via an F1 interface.

[0034] The Non-RT RIC 200 and the external server 500 are connected to each other via any interface that is not defined in the O-RAN. The interface between the Non-RT RIC 200 and the external server 500 may be an interface that allows a general application server to provide data. For example, HTTP (Hypertext Transfer Protocol) for a web server or another API (Application Programming Interface) may be used.

[0035] The O-DU 300 and the O-CU 400 are nodes that constitute the RAN, and are also called E2 nodes. Note that the E2 node may include either or both of the O-DU 300 and the O-CU 400. The RAN is a wireless network accessed by the terminal 600, and is connected to a core network such as a 5G Core network (5GC) or an Evolved Packet Core (EPC). The RAN may include an O-RAN Remote Unit (O-RU) that constitutes an antenna.

[0036] The O-DU 300 and the O-CU 400 provide base station functions. For example, the O-DU 300 and the O-CU 400 receive radio quality data transmitted from the terminal 600 as a base station function and transmit the received radio quality data to the Near-RT RIC 100. The base station is, for example, a gNB (next generation Node B) or an eNB (evolved Node B), but is not limited to these. The O-DU 300 and the O-CU 400 are examples of nodes that provide base station functions, and may be other network nodes.

[0037] The O-DU 300 is a logical node that provides the radio signal control function and Layer 2 control function of the base station. The O-DU 300 accommodates the O-RU, controls the radio signal or beam of the antenna in the accommodated O-RU, and performs protocol processing such as MAC (Media Access Control) and RLC (Radio Link Control) required between the O-RU and the O-CU 400.

[0038] The O-CU 400 is a logical node that provides the radio resource control function of the base station and data processing functions higher than Layer 2. The O-CU 400 accommodates the O-DU 300 and performs data transmission and reception via the accommodated O-DU 300, QoS (Quality of Service) control, cell / UE management, handover control, and protocol processing such as PDCP (Packet Data Convergence Protocol), SDAP (Service Data Adaptation Protocol), and RRC (Radio Resource Control) required between the O-DU 300 and the core network.

[0039] The RAN system 1 may include any number of O-DUs 300 and O-CUs 400, one or more, as E2 nodes. That is, the RAN system 1 may include multiple base stations. The number of O-DUs 300 and O-CUs 400 does not necessarily have to be the same. The O-DUs 300 and O-CUs 400 may be located in different locations or in the same location. Furthermore, the O-DUs 300 and O-CUs 400 may be implemented by different virtual machines operating on an edge virtualization platform, or by the same virtual machine. The O-DUs 300 and O-CUs 400 may be virtualized distributed units (vDUs) and virtualized central units (vCUs), and may constitute virtual base stations. The O-DUs 300 and O-CUs 400 may also be physical DUs and CUs. The E2 node may also be a base station device that includes the functions of O-DU300 and O-CU400.

[0040] The external server 500 is an external application server. For example, the external server 500 is a server external to the RAN including the O-DU 300 and the O-CU 400. The external server 500 can also be said to be a server external to a system including the O-DU 300, the O-CU 400, the Non-RT RIC 200, and the Near-RT RIC 100. The external server 500 may be, for example, a server on the Internet. The external server 500 may be a physical server or a virtual server on the cloud. The external server 500 executes applications related to the RAN and the terminal 600. For example, the external server 500 may be a monitoring server that monitors the wireless communication environment of the RAN. The external server 500 may acquire wireless quality data, factors of degradation of communication quality, etc. from the Non-RT RIC 200, and display the acquired data.

[0041] The Near-RT RIC 100 is a logic function that controls and optimizes the RAN in near real time. The Near-RT RIC 100 controls the RAN in a short control period, for example, of 10 ms (milliseconds; the same applies hereinafter) or more and less than 1 s (seconds; the same applies hereinafter). The Near-RT RIC 100 collects wireless quality data for each terminal 600 from an E2 node including either or both of the O-DU 300 and the O-CU 400 via the E2 interface. The Near-RT RIC 100 may transmit the collected wireless quality data to the Non-RT RIC 200, or may analyze the collected wireless quality data to control the E2 node. The wireless quality data may be RSRP, RSRQ, RSSI, SINR, etc. measured by the terminal 600. The Near-RT RIC 100 may acquire communication quality data such as throughput and delay time for each terminal 600, in addition to the wireless quality data. The processing for wireless quality data in this embodiment can be similarly applied to communication quality data.

[0042] For example, the Near-RT RIC 100 performs control according to radio quality data in accordance with a control policy acquired from the Non-RT RIC 200 via the A1 interface. The control policy is a policy related to RAN control, such as the A1 policy. The A1 policy is guidance for RAN optimization defined in the A1 interface. The Near-RT RIC 100 is located in the same location as either or both of the O-DU 300 and the O-CU 400, or in a location close to either or both of the O-DU 300 and the O-CU 400. For example, the Near-RT RIC 100 may be implemented in the same edge virtual machine as either or both of the O-DU 300 and the O-CU 400.

[0043] The Non-RT RIC 200 is a logic function that controls and optimizes the RAN in non-real time. The Non-RT RIC 200 controls the RAN with a long control period of, for example, 1 second or more. The Non-RT RIC 200 manages control policies, manages the operation of the E2 nodes including the O-DU 300 and O-CU 400 and the Near-RT RIC 100, and learns and updates learning models used in the Near-RT RIC 100 or the Non-RT RIC 200. For example, the Non-RT RIC 200 generates a control policy and notifies the Near-RT RIC 100 of the generated control policy via the A1 interface. The Non-RT RIC 200 also manages and sets the configuration information (Configuration) of the E2 node based on data acquired from the E2 node and the Near-RT RIC 100 via the O1 interface. For example, the Non-RT RIC 200 acquires wireless quality data from the Near-RT RIC 100 via the O1 interface, and analyzes factors of degradation of communication quality, etc. based on the acquired wireless quality data. The Non-RT RIC 200 transmits the acquired wireless quality data, factors of degradation of communication quality, etc. to the external server 500.

[0044] The Non-RT RIC 200 is arranged in a Service Management and Orchestration (SMO) that manages and orchestrates the RAN. The SMO is arranged in a location, for example, on a cloud, away from the E2 node including the O-DU 300 and the O-CU 400 and the Near-RT RIC 100. The Non-RT RIC 200 may include the functionality of the SMO.

[0045] 5 shows an example configuration of each device in the RAN system 1 according to some embodiments. Note that this configuration is just an example, and other configurations may be used as long as the operations according to some embodiments are possible. For example, the Non-RT RIC 200 and the Near-RT RIC 100 may include other configurations necessary to realize the functions of the Non-RT RIC and the Near-RT RIC.

[0046] In the example of FIG. 5, the Near-RT RIC 100 includes a data collection unit 110, a data storage unit 120, a distance calculation unit 130, a terminal selection unit 140, and a data transmission unit 150.

[0047] The data collection unit 110 collects wireless quality data via the E2 interface from either or both of the O-DU 300 and the O-CU 400. The data collection unit 110 instructs either or both of the O-DU 300 and the O-CU 400 to acquire data on the terminal 600 selected by the terminal selection unit 140, and collects the data on the specified terminal 600.

[0048] The data accumulation unit 120 is a database that accumulates the wireless quality data collected by the data collection unit 110. The data accumulation unit 120 accumulates the wireless quality data acquired from each terminal 600 as time-series data. Note that the data collection unit 110 may output the received wireless quality data to the distance calculation unit 130 or the data transmission unit 150.

[0049] The distance calculation unit 130 calculates the distance between the wireless quality data for each terminal 600 collected by the data collection unit 110. The distance between data is an example of an index indicating the degree of similarity between two pieces of data, and other indexes may also be calculated. The distance is not limited to the distance between the terminals that transmitted the data, and similarity or cross-correlation between the data may also be calculated. The distance calculation unit 130 calculates the distance between the time-series data of wireless quality for each terminal 600 stored in the data storage unit 120. The distance calculation unit 130 calculates the distance between the time-series data for all combinations of terminals 600 from which data has been acquired. The distance between the data may be Euclidean distance, sum of squared errors, Mahalanobis distance, or a distance using the center of gravity of the data. The distance may be calculated using the data as is, or may be calculated using values ​​transformed using Fourier transform or support vectors.

[0050] In the case of distance between data, the more similar the two data are, the closer, i.e., the lower the value. In the case of correlation or similarity between data, the more similar the two data are, the higher the value. Therefore, expressions such as close (or low) / far (or high) distance can be interpreted as high / low correlation or similarity.

[0051] The terminal selection unit 140 selects the terminal 600 from which the data collection unit 110 acquires data, based on the distance between the data calculated by the distance calculation unit 130. The terminal selection unit 140 compares the time-series data of the calculated wireless quality for all combinations of terminals 600, and selects the terminal 600 from which data is to be acquired based on the comparison result.

[0052] For example, the terminal selection unit 140 excludes terminals 600 in the first group that are paired together with a short distance between their data sets, and selects a terminal 600 from among the other terminals 600 outside the first group to acquire new data. The other terminals 600 are terminals in the second group. When the distance between the time-series data sets is short, i.e., the characteristics of the time-series data sets are similar, it can be estimated that the environments, such as the locations and directions of movement, of the terminals 600 are close. Conversely, when the distance between the time-series data sets is long, i.e., the characteristics of the time-series data sets are different, it can be estimated that the environments, such as the locations and directions of movement of the terminals 600, are far apart. Therefore, by leaving the terminals 600 with a long distance between their data sets and excluding the terminals 600 with a short distance between their data sets and selecting the other terminals 600 as data acquisition targets, it is possible to acquire data from terminals 600 with different environments, such as locations and directions of movement.

[0053] The data transmitting unit 150 transmits the wireless quality data for each terminal 600 collected by the data collecting unit 110 to the Non-RT RIC 200 via the O1 interface. That is, the data transmitting unit 150 transmits time-series data of the wireless quality data for each terminal stored in the data storing unit 120 to the Non-RT RIC 200. Note that the data transmitting unit 150 may also transmit the wireless quality data to the Non-RT RIC 200 via the A1 interface. For example, the data transmitting unit 150 may transmit the specified data at the specified timing in accordance with an instruction from the Non-RT RIC 200.

[0054] In the example of FIG. 5, the Non-RT RIC 200 includes a data receiving unit 210 and a factor estimation learning / inference unit 220 .

[0055] The data receiving unit 210 receives time-series data on wireless quality for each terminal transmitted from the Near-RT RIC 100 via the O1 interface. The data receiving unit 210 may instruct the Near-RT RIC 100 on the data to be collected and the period. The data receiving unit 210 may also acquire wireless quality data from the Near-RT RIC 100 via the A1 interface. The data receiving unit 210 may collect data from either or both of the O-DU 300 and the O-CU 400 via the O1 interface as necessary.

[0056] The factor estimation learning / inference unit 220 estimates the factor of communication quality degradation based on the acquired time-series data of wireless quality for each terminal. Estimated factors of communication quality degradation include, for example, distance attenuation, fading, and shielding. Degradation of communication quality due to distance attenuation is degradation of communication quality caused by the distance between the transmission source and the terminal being longer than the appropriate distance for proper wireless communication. Degradation of communication quality due to fading is degradation of communication quality caused by the occurrence of at least one of coherent fading (so-called multipath fading), polarization fading, jump fading, absorption fading, selective fading, and K-type fading. Degradation of communication quality due to shielding is degradation of communication quality caused by the presence of a physical obstacle between the transmission source and the terminal that shields radio waves (i.e., hinders radio wave propagation). Other factors that may degrade communication quality include interference, congestion, handover, and the like. Degradation of communication quality due to interference is degradation of communication quality caused by radio waves from multiple transmission sources interfering with each other. Degradation of communication quality due to congestion is caused by insufficient wireless resources being allocated to a terminal, while degradation of communication quality due to handover is caused by a terminal located near the cell boundary of two adjacent base stations repeatedly performing handovers between the two base stations.

[0057] The factor estimation learning / inference unit 220 estimates the degradation factor of communication quality from wireless quality data using a degradation factor estimation model. The degradation factor estimation model is a learning model that machine-learns the degradation factors of communication quality according to the time-series data of wireless quality. The learning model may be a convolutional neural network (CNN), a recurrent neural network (RNN), a long-short term model (LSTM), or other neural networks. The learning model is not limited to a neural network, and may be other machine learning models. The factor estimation learning / inference unit 220 transmits the analyzed wireless quality data and the inferred degradation factors of communication quality to the external server 500 via any interface. Furthermore, the factor estimation learning / inference unit 220 may transmit the inferred degradation factors of communication quality to the Near-RT RIC 100, and the Near-RT RIC 100 may control the RAN based on the degradation factors of communication quality.

[0058] Note that a portion of the configuration of the Non-RT RIC 200 may be arranged in the Near-RT RIC 100, or a portion of the configuration of the Near-RT RIC 100 may be arranged in the Non-RT RIC 200. FIG. 6 shows an example configuration of each device in the RAN system 1 according to some embodiments. In the example of FIG. 6, the Non-RT RIC 200 includes a distance calculation unit 130 and a terminal selection unit 140. In this case, the distance calculation unit 130 acquires time-series data of wireless quality for each terminal 600 stored in the data storage unit 120 via the O1 interface. The terminal selection unit 140 notifies the data collection unit 110 of the Near-RT RIC 100 of information on the selected terminal 600 via the O1 interface.

[0059] For example, in the example of Fig. 5, by performing distance calculation processing and terminal selection processing in the Near-RT RIC 100, it is possible to perform processing in more real time than the Non-RT RIC 200, and it is also possible to reduce the load on the O1 interface between the Near-RT RIC 100 and the Non-RT RIC 200. In the example of Fig. 6, by performing distance calculation processing and terminal selection processing in the Non-RT RIC 200, it is possible to reduce the load on the Near-RT RIC 100, and it is also possible to perform the distance calculation processing and terminal selection processing in non-real time when it is not necessary to perform them in real time.

[0060] Fig. 7 shows an example of operation in the RAN system 1 according to some embodiments. All or part of the processes in Fig. 7 may be performed by each unit of the Near-RT RIC 100 shown in Fig. 5 or by each unit of the Non-RT RIC 200 shown in Fig. 6.

[0061] In the example of FIG. 7 , first, the terminal selection unit 140 selects M arbitrary terminals 600 (S101). For example, the M terminals 600 are terminals of a first group. M is the upper limit of the number of terminals 600 from which data is collected. For example, M may be the number of terminals allowable by the E2 interface or the O1 interface, or may be the number of terminals based on the processing capabilities of the Near-RT RIC 100 or the Non-RT RIC 200. For example, the terminal selection unit 140 randomly selects M terminals 600 from all terminals 600 from which data can be acquired. The terminal selection unit 140 may select M terminals 600 or a portion of the M terminals 600 in accordance with external input from an operator or the like. For example, the terminal selection unit 140 may receive a selection of terminals 600 from an external server 500.

[0062] Next, the data collection unit 110 acquires time-series data (S102). The data collection unit 110 acquires wireless quality data from the selected M terminals 600. For example, the data collection unit 110 specifies M terminals 600 for either or both of the O-DU 300 and the O-CU 400 via the E2 interface, and acquires wireless quality data from the specified terminals 600. The data accumulation unit 120 accumulates the wireless quality data of the M terminals 600 acquired by the data collection unit 110 as time-series data for each terminal 600.

[0063] Next, the distance calculation unit 130 calculates the distance between the time series data of the terminals 600 (S103). The distance calculation unit 130 calculates the distance between the data for all combinations of the terminals 600 from which the time series data has been acquired.

[0064] FIG. 8 shows a distance matrix including distances between data for all combinations of terminals 600. When data is acquired from M terminals 600 as shown in FIG. 8, the distances for all combinations can be expressed as an M×M distance matrix. For each terminal 600, the distance calculation unit 130 calculates the distance between the data of that terminal 600 and the data of the M terminals 600. For simplicity of explanation, the terminals 600 included in the M terminals 600 may be referred to as terminal 1 to terminal M. For example, the distance calculation unit 130 calculates, as the distance for terminal 1, distances d(1,1) to d(1,M) between the data of terminal 1 and each of the data of terminals 1 to M; as the distance for terminal 2, it calculates distances d(2,1) to d(2,M) between the data of terminal 2 and each of the data of terminals 1 to M; ..., as the distance for terminal M, it calculates distances d(M,1) to d(M,M) between the data of terminal M and each of the data of terminals 1 to M.

[0065] Next, the terminal selection unit 140 selects N terminals 600 from among the M terminals 600 based on the calculated distance between the data, and excludes the selected N terminals 600 from the terminals 600 that will next acquire data (S104). The terminal selection unit 140 selects N terminals 600 in descending order of distance between the data as the terminals 600 to be excluded from the next collection. In other words, the terminal selection unit 140 selects M-N terminals 600, excluding the N terminals 600 that are closest in distance between the data from the M terminals 600 in the first group, as the terminals 600 that will next acquire data. Figures 9 to 12 show examples of selecting N terminals 600 from among M terminals 600 in descending order of distance.

[0066] FIG. 9 shows an example of selecting N out of M terminals 600 based on the average distance between data for each terminal 600. Note that other statistical values, such as the median, may be calculated instead of the average. In the example of FIG. 9, the terminal selection unit 140 calculates the average distance for each terminal 600 from each distance in the M×M distance matrix for all combinations of terminals 600. For example, based on the M×M distance matrix of FIG. 8, the terminal selection unit 140 calculates the average dave(d_1) of the distances d(1,1) to d(1,M) between the data of terminal 1 and the data of terminals 1 to M as the average distance for terminal 1, calculates the average dave(d_2) of the distances d(2,1) to d(2,M) between the data of terminal 2 and the data of terminals 1 to M as the average distance for terminal 2, and so on, and calculates the average dave(d_M) of the distances d(M,1) to d(M,M) between the data of terminal M and the data of terminals 1 to M as the average distance for terminal M. The terminal selection unit 140 sorts the calculated averages dave (d_1) to (d_M) in ascending order, selects the N lowest averages, and sets the selected N terminals 600 as terminals 600 to be excluded in the next collection.

[0067] FIG. 10 illustrates an example of selecting N out of M terminals 600 based on distance points corresponding to the distance between data for each terminal 600. The points are an example of converted values ​​obtained by converting distances based on a predetermined criterion. In the example of FIG. 10, the terminal selection unit 140 converts each distance in the M×M distance matrix for all combinations of terminals 600 into a distance point. For example, the distance may be compared with a predetermined threshold, and a distance point of "0" may be assigned if the distance is closer than the threshold, and a distance point of "1" may be assigned if the distance is farther than the threshold. For example, the terminal selection unit 140 generates an M×M distance point matrix as shown in FIG. 10 based on the M×M distance matrix of FIG. 8. The terminal selection unit 140 converts distances d(1,1) to d(M,M) in the M×M distance matrix into distance points dp(1,1) to dp(M,M) based on a threshold.

[0068] Furthermore, the terminal selection unit 140 calculates the sum of the distance points for each terminal 600 from each distance point in the M×M distance point matrix for all combinations of terminals 600. For example, based on the M×M distance point matrix in Fig. 10, the terminal selection unit 140 calculates the sum dpsum (dp_1) of the distance points dp(1,1) to dp(1,M) between terminal 1 and terminals 1 to M as the sum of the distance points for terminal 1, calculates the sum dpsum (dp_2) of the distance points dp(2,1) to dp(2,M) between terminal 2 and terminals 2 to M as the sum of the distance points for terminal 2, ... and calculates the sum dpsum (dp_M) of the distance points dp(M,1) to dp(M,M) between terminal M and terminals 1 to M as the sum of the distance points for terminal M. The terminal selection unit 140 sorts the calculated distance point totals dpsum (dp_1) to (dp_M) in ascending order, selects the N lowest-ranked terminals 600, and sets the selected N terminals 600 as terminals 600 to be excluded from the next collection.

[0069] 11 shows an example of selecting N out of M terminals 600 based on the ranking of normalized distances between data for each terminal 600. If terminals to be excluded are selected using values ​​such as distance and correlation calculated from the data as they are, there is a possibility that bias in the data will occur if there is nearby data. For this reason, by normalizing values ​​such as distance and correlation calculated from the data using ranking, it is possible to equalize the relationship between data, for example, and thereby reduce bias in the data. Note that distance normalization may be performed by other methods other than ranking.

[0070] In the example of FIG. 11 , the terminal selecting unit 140 ranks each distance in the M×M distance matrix for all combinations of terminals 600 by each column of the matrix, and selects N out of M terminals 600 based on the average ranking for each terminal 600. Ranking may also be performed by each row of the distance matrix. The terminal selecting unit 140 ranks the terminals 600 in order of closest distance in each column of the distance matrix, as 1st, 2nd, ... Mth. Ranking may also be performed in order of furthest distance in each column. For example, the terminal selecting unit 140 generates an M×M ranking matrix as shown in FIG. 11 based on the M×M distance matrix of FIG. 8 . Based on the M×M distance matrix, the terminal selection unit 140 ranks the distances d(1,1), d(2,1) ... d(M,1) in the column for terminal 1 in order of proximity and converts them into r(1,1), r(2,1) to r(M,1) indicating the rank; for the column for terminal 2, it ranks the distances d(1,2), d(2,2) ... d(M,2) in order of proximity and converts them into r(1,2), r(2,2) to r(M,2) indicating the rank; ..., for the column for terminal M, it ranks the distances d(1,M), d(2,M) ... d(M,M) in order of proximity and converts them into r(1,M), r(2,M) to r(M,M) indicating the rank.

[0071] Furthermore, the terminal selecting unit 140 calculates the average rank for each terminal 600 from each rank in the M×M rank matrix for all combinations of terminals 600. Note that if ranking is performed by column, the average rank is calculated for each row, and if ranking is performed by row, the average rank is calculated for each column. For example, based on the M×M rank matrix of FIG. 11 , the terminal selecting unit 140 calculates the average rave(r_1) of the ranks r(1,1) to r(1,M) of the distances between terminal 1 and terminals 1 to M as the average rank of terminal 1, calculates the average rave(r_2) of the ranks r(2,1) to r(2,M) of the distances between terminal 2 and terminals 1 to M as the average rank of terminal 2, ... and calculates the average rave(r_M) of the ranks r(M,1) to r(M,M) of the distances between terminal M and terminals 1 to M as the average rank of terminal M. The terminal selection unit 140 ranks the obtained average rave (r_1) to (r_M) in descending order, selects the highest N terminals, and sets the selected N terminals 600 as terminals 600 to be excluded in the next collection. Note that if the terminals are ranked in descending order of distance, the lowest N terminals are selected.

[0072] FIG. 12 shows an example of selecting N out of M terminals based on ranking points corresponding to rankings obtained by normalizing the distance between data for each terminal 600. In the example of FIG. 12, the terminal selection unit 140 converts each ranking in the M×M ranking matrix similar to that of FIG. 11 into ranking points. For example, the ranking may be compared with a predetermined threshold, and if the ranking is higher than the threshold, the ranking point may be "1," and if the ranking is lower than the threshold, the ranking point may be "2." For example, the terminal selection unit 140 generates an M×M ranking point matrix as shown in FIG. 12 based on the M×M ranking matrix of FIG. 11. The terminal selection unit 140 converts the rankings r(1,1) to r(M,M) in the M×M ranking matrix into ranking points rp(1,1) to rp(M,M) based on a threshold.

[0073] Furthermore, the terminal selection unit 140 calculates the sum of the ranking points for each terminal 600 from each ranking point in the M×M ranking point matrix for all combinations of terminals 600. For example, based on the M×M ranking point matrix in Fig. 12, the terminal selection unit 140 calculates, as the sum of the ranking points for terminal 1, rpsum (rp_1), the sum of the ranking points rp(1,1) to rd(1,M) for the distances between terminal 1 and terminals 1 to M; as the sum of the ranking points for terminal 2, it calculates rpsum (rp_2), the sum of the ranking points rp(2,1) to rp(2,M) for the distances between terminal 2 and terminals 1 to M; ..., as the sum of the ranking points for terminal M, it calculates the sum of the ranking points rp(M,1) to rp(M,M) for the distances between terminal M and terminals 1 to M, rpsum (rp_M). The terminal selection unit 140 sorts the calculated ranking point totals rpsum (rp_1) to (rp_M) in descending order, selects the highest N terminals 600, and sets the selected N terminals 600 as terminals 600 to be excluded in the next collection.

[0074] 9 to 12, terminals 600 including a distance other than the distance between the terminals themselves that is less than the threshold may be excluded in advance. For example, the terminal selection unit 140 excludes terminals 600 including a distance other than the distance between the terminals themselves that is less than the threshold from the M×M distance matrix of all combinations of terminals 600. If there is one terminal 600 including a distance other than the distance between the terminals themselves that is less than the threshold, N-1 terminals may be selected and excluded from the M-1×M-1 distance matrix excluding that terminal using the same method as in FIGS. 9 to 12. When points are assigned to distances, high points may be assigned to terminals 600 with a distance less than the threshold so that they are more likely to be deleted.

[0075] Next, the terminal selection unit 140 selects N new terminals 600 (S105). The terminal selection unit 140 selects N new terminals 600 to replace the excluded N terminals 600. That is, the terminal selection unit 140 selects N new terminals 600, for example, randomly, from among the terminals 600 excluding the M terminals 600 from which data was previously obtained, and sets these as targets for the next data collection. For example, the terminals 600 excluding the M terminals 600 from which data was previously obtained are the terminals 600 of the second group. In other words, the terminal selection unit 140 selects N terminals 600 from the second group of terminals 600 in addition to the M-N terminals 600 as the terminals 600 from which data will be next obtained. Thereafter, the process returns to S102, where time-series data is obtained from the M terminals 600 including the newly selected N terminals 600, and S102 to S105 are repeated. The newly selected N terminals 600 may include terminals 600 whose data are close to each other, and the distance between the data may change as the terminals 600 move. Therefore, by repeating steps S102 to S105, the N terminals whose data are always close to each other are excluded.

[0076] As described above, in this embodiment, the distance between data collected from multiple terminals is calculated, and the calculated distance between data is considered to be the difference in the environment in which the terminals are located. In this embodiment, by excluding terminals with combinations where the distance between data is close from the data collection terminals and continuing to select other terminals, data can be collected from combinations of terminals in different environments. In other words, by leaving terminals with long distances between data and continuing to switch terminals with short distances between data to other unselected terminals, data can be acquired from terminals with as many different locations and movement directions as possible within the allowable number of terminals. Therefore, when it is necessary to acquire a variety of data for estimating the causes of degradation in communication quality, etc., desired data can be acquired.

[0077] (Embodiment 3) Next, a description will be given of embodiment 3. In this embodiment, an example will be described in which a terminal from which data is acquired is selected based on a terminal of interest.

[0078] Fig. 13 shows an example of the configuration of each device in a RAN system 1 according to some embodiments. Note that Fig. 13 shows an example in which this embodiment is applied to the example of the configuration in Fig. 6, but this embodiment may also be applied to the example of the configuration in Fig. 5.

[0079] 13, the external server 500 includes a target terminal input unit 510. The non-RT RIC 200 includes a terminal designation unit 230. The other configurations are the same as those in FIG.

[0080] The attention terminal input unit 510 accepts input of an attention terminal from the operator. The attention terminal is a terminal 600 that the operator wants to focus on among all the terminals 600. For example, an attention terminal is a terminal 600 that is more important than the other terminals 600, or a newly introduced terminal 600. The attention terminal input unit 510 transmits the input information of the attention terminal to the Non-RT RIC 200 via an arbitrary interface. The terminal designation unit 230 receives the information of the attention terminal from the attention terminal input unit 510 via an arbitrary interface, and designates the attention terminal to the terminal selection unit 140.

[0081] Fig. 14 shows an example of operation in the RAN system 1 according to some embodiments. Fig. 14 is different from Fig. 7 in steps S201 and S202, but is otherwise similar to Fig. 7.

[0082] In the example of FIG. 14 , the terminal designation unit 230 designates a target terminal (S201). For example, when an operator inputs a target terminal to the external server 500, the target terminal input unit 510 transmits information indicating the input target terminal to the terminal designation unit 230 of the non-RT RIC 200. For example, the operator may select a target terminal from multiple terminals 600 via a GUI (Graphical User Interface) or the like. The target terminal input unit 510 may automatically select a newly added terminal 600, etc. as a target terminal from the list of terminals 600. The terminal designation unit 230 receives information indicating the target terminal from the target terminal input unit 510 and designates the target terminal to the terminal selection unit 140 based on the received information indicating the target terminal.

[0083] Furthermore, after acquiring time series data of wireless quality from M terminals 600 in S102 and calculating the distance between the time series data in S103, the terminal selection unit 140 selects N terminals 600 other than the target terminal from among the M terminals 600 based on the calculated distance between the data, and excludes the selected N terminals 600 from the terminals 600 from which data will be acquired next (S202).

[0084] FIG. 15 shows an example of a distance matrix excluding the target terminal. When a target terminal is specified, the terminal selection unit 140 generates a distance matrix excluding the specified target terminal from the M×M distance matrix of FIG. 8. For example, if the target terminal is one of M terminals 600, the terminal selection unit 140 generates an M-1×M-1 distance matrix as shown in FIG. 15. Note that the number of target terminals is not limited to one, and may be any number. Based on the distance matrix excluding the target terminal as shown in FIG. 15, the terminal selection unit 140 selects N terminals 600 with the shortest distance between data as terminals 600 to be excluded from the next collection. The method of selecting the N terminals 600 is the same as in embodiment 2. Thereafter, in S105, as in embodiment 2, new N terminals 600 from which data will be collected next are selected, and S102 and subsequent steps are repeated.

[0085] In addition, if the target terminal is not included in the M terminals in S202, N+target terminals 600 may be excluded from the M terminals, and the target terminal and N new terminals may be selected as the terminals from which data will be collected next.

[0086] As described above, a terminal from which data is to be collected may be selected based on the designated target terminal. For example, terminals other than the designated target terminal that are close in distance to each other may be deleted, and other terminals may be selected. This allows data to be reliably acquired from the terminal that the user wants to focus on, regardless of the distance between the data, when collecting data from terminals selected based on the distance between the data.

[0087] (Fourth Embodiment) Next, a fourth embodiment will be described. In this embodiment, an example will be described in which a terminal that acquires data is selected based on a specified policy. Note that the configuration of each device in the RAN system 1 is the same as that in the third embodiment.

[0088] Fig. 16 shows an example of operation in the RAN system 1 according to some embodiments. Fig. 16 is different from Fig. 14 in steps S301 and S302, but is otherwise similar to Fig. 14.

[0089] In the example of FIG. 16 , the terminal designation unit 230 designates a target terminal and a policy (S301). For example, when an operator inputs a target terminal and a policy to the external server 500, the target terminal input unit 510 transmits information indicating the input target terminal and policy to the terminal designation unit 230 of the non-RT RIC 200. The policy is a selection policy for selecting a terminal 600 based on the target terminal. For example, the policy may be a policy that concentrates on selecting terminals close to the target terminal, such as "focus on the area around the target terminal." Terminals around the target terminal are terminals that have data that is close to the target terminal's data. The policy may also be a policy that indicates the proportion of terminals 600 close to the target terminal and the proportion of terminals 600 far from the target terminal, such as "70% target terminal, 30% overall." The target terminal input unit 510 may automatically select a policy depending on the target terminal. For example, when a newly added terminal 600 is designated as the target terminal, "focus on the area around the target terminal" may be selected as the policy. The terminal designation unit 230 receives information indicating the target terminal and policy from the target terminal input unit 510, and designates the target terminal and policy to the terminal selection unit 140 based on the received information indicating the target terminal and policy.

[0090] Furthermore, after acquiring time series data of wireless quality from M terminals 600 in S102 and calculating the distance between the time series data in S103, the terminal selection unit 140 selects N terminals 600 from the M terminals 600 based on the calculated distance between the data in accordance with the specified target terminal and policy, and excludes the selected N terminals 600 from the terminals 600 from which data will be acquired next (S302).

[0091] FIG. 17 shows an example of a distance matrix when "focus on the vicinity of the terminal of interest" is specified as the policy. When "focus on the vicinity of the terminal of interest" is specified as the policy, the terminal selection unit 140 generates a distance matrix including distances to the terminals 600 around the terminal of interest from the M×M distance matrix of FIG. 8. For example, based on each distance in the M×M distance matrix of FIG. 8, terminals 600 within a predetermined distance range from the terminal of interest are extracted. Furthermore, the terminal selection unit 140 generates a distance matrix indicating the distances between the extracted terminals 600 around the terminal of interest and terminals 600 other than the terminals around the terminal of interest. For example, as shown in FIG. 17, assume that terminals around the terminal of interest are designated as terminal A among M-N terminals, and y terminals A are extracted, and the remaining terminals of M-N terminals are designated as terminal B, and z terminals B are extracted. The z terminals are M-N-y terminals. In this case, the distance matrix is ​​y×z, including the distances between the y terminals A around the terminal of interest and the remaining z terminals B. The terminal selection unit 140 selects N terminals 600 with the shortest distance between their data as terminals 600 to be excluded from the next collection, based on a distance matrix indicating the distances between the terminals 600 around the target terminal and the terminals 600 other than the terminals around the target terminal, as shown in Fig. 17. In this case, the terminals 600 with the shortest distance from the terminals 600 around the target terminal are selected. The method of selecting the N terminals 600 is the same as in the second embodiment.

[0092] FIG. 18 shows an example of a distance matrix when "70% of the attention terminal, 30% of the total" is specified as the policy. When "70% of the attention terminal, 30% of the total" is specified as the policy, the terminal selection unit 140 generates a distance matrix including the distances of 70% of the terminals 600 closest to the attention terminal from the M×M distance matrix of FIG. 8. 70% is 70% of the M-N terminals. For example, based on each distance in the M×M distance matrix of FIG. 8, the terminals 600 that make up 70% of the M-N terminals are extracted, starting from those closest to the attention terminal. Furthermore, the terminal selection unit 140 generates a distance matrix indicating the distances between the extracted 70% of the terminals 600 closest to the attention terminal and the terminals 600 other than the 70% closest to the attention terminal. For example, as shown in FIG. 18, 70% of the terminals closest to the attention terminal out of the M-N terminals are designated as terminal A, and y terminals A are extracted, and the remaining terminals out of the M-N terminals are designated as terminal B, and z terminals B are extracted. z terminals is M-N-y terminals. In this case, the distance matrix is ​​y x z, including the distances between y terminals A, which are 70% of the terminals closest to the terminal of interest, and the remaining z terminals B. The terminal selection unit 140 selects N terminals 600 with the closest distance between their data as terminals 600 to be excluded from the next collection, based on the distance matrix indicating the distances between the 70% of terminals 600 closest to the terminal of interest and the other 70% of terminals 600 close to the terminal of interest, as shown in FIG. 18 . In this case, the terminals 600 closest to the 70% of terminals 600 closest to the terminal of interest are selected. The method of selecting N terminals is the same as in embodiment 2.

[0093] Thereafter, in S105, similarly to the second embodiment, N new terminals 600 from which data will be collected next are selected, and S102 and subsequent steps are repeated.

[0094] As described above, terminals from which data is to be collected may be selected based on a specified policy. For example, terminals in the vicinity of a target terminal may be left and terminals to be deleted may be selected from among other terminals in accordance with the specified policy. The ratio of terminals close to the target terminal and terminals far from the target terminal may be adjusted in accordance with the policy. This allows for flexible selection of terminals from which data is to be collected in accordance with user specifications when collecting data from terminals including the target terminal.

[0095] (Fifth Embodiment) Next, a fifth embodiment will be described. In this embodiment, an example will be described in which a terminal from which data is to be collected is selected based on the result of grouping a plurality of target terminals. Note that the configuration of each device in the RAN system 1 is the same as that in the third embodiment.

[0096] Fig. 19 shows an example of operation in the RAN system 1 according to some embodiments. Fig. 19 is different from Fig. 14 in steps S401 to S403, but is otherwise similar to Fig. 14.

[0097] 19 , when a target terminal is designated in S201, the terminal selection unit 140 determines whether the number of designated target terminals is equal to or greater than a predetermined value (S401). The predetermined value for determining the number of target terminals may be a value based on the capacity of the E2 interface or the O1 interface. For example, if the number of target terminals is less than the predetermined value, the terminal selection unit 140 selects N terminals 600 other than the target terminal from among the M terminals, as in the third embodiment, and excludes the selected N terminals 600 from the terminals 600 from which data will be acquired next (S202).

[0098] On the other hand, if the number of target terminals is equal to or greater than the predetermined value, the terminal selection unit 140 groups the specified multiple target terminals by distance (S402). Based on the distance between the data of the target terminals, the terminal selection unit 140 classifies target terminals whose distance is within a predetermined range into the same group.

[0099] Next, the terminal selection unit 140 leaves one group representative terminal in each group, selects N terminals 600 other than the target terminal from the M terminals, and excludes the selected N terminals 600 from the terminals 600 from which data will be acquired next (S403). The terminal selection unit 140 leaves one group representative terminal in each group and excludes the other target terminals. That is, it removes the target terminals that are close in distance from each group. The group representative terminal may be any terminal in the group. For example, a terminal with a median or average distance within the group may be selected as the representative terminal. Note that the number of target terminals is not limited to one, and multiple group representative terminals may be selected, as long as the number of target terminals is less than a predetermined value. Furthermore, as in the third embodiment, the terminal selection unit 140 selects the N terminals 600 closest in distance from among the terminals 600 excluding the designated target terminal as terminals 600 to be excluded from the next collection. Thereafter, in S105, as in the second embodiment, new N terminals 600 from which data will be acquired next are selected, and S102 and subsequent steps are repeated.

[0100] As described above, the terminals from which data will be collected may be selected based on the results of grouping multiple target terminals. For example, if there are an unacceptable number of target terminals, the target terminals are classified by distance, and terminals in close groups are omitted, and the remaining allowable number of terminals is selected so that data can be monitored from a bird's-eye view. This makes it possible to collect desired data even when there are a large number of target terminals.

[0101] The present disclosure is not limited to the above-described embodiments and may be modified as appropriate without departing from the spirit of the present disclosure. Each component in the above-described embodiments may be configured with hardware, software, or both, and may be configured with a single piece of hardware or software, or may be configured with multiple pieces of hardware or software. The functions (processing) of each device, including the Non-RT RIC and Near-RT RIC, may be implemented by a computer 30 having a network interface 31, a processor 32 such as a CPU (Central Processing Unit), and a memory 33 serving as a storage device, as shown in FIG. 20 . The network interface 31 may include a network interface card (NIC) for communicating with devices including network nodes. For example, a program for performing the method in the embodiment may be stored in the memory 33, and each function may be implemented by executing the program stored in the memory 33 by the processor 32.

[0102] These programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0103] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0104] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0105] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A system comprising: an acquisition unit that acquires first data related to communication quality from a plurality of terminals; a calculation unit that calculates a similarity index between the first data of the plurality of terminals; and a selection unit that selects a terminal from which to acquire second data related to communication quality based on the similarity index. (Supplementary Note 2) The system described in Supplementary Note 1, wherein the selection unit selects a terminal whose first data is less similar than a terminal whose first data is more similar, according to the similarity index. (Supplementary Note 3) The system described in Supplementary Note 1 or 2, wherein the acquisition unit acquires the first data from terminals in a first group of the plurality of terminals, and the selection unit selects, based on the similarity index, a first number of terminals from the terminals included in the first group as terminals to be excluded from acquiring the second data, and selects terminals from the terminals included in the first group excluding the selected first number of terminals, and the first number of terminals included in a second group, as terminals from which to acquire the second data. (Supplementary Note 4) The system according to Supplementary Note 3, wherein the selection unit selects the first number of terminals from among the terminals included in the first group in order of the degree of similarity between the first data as terminals to be excluded from acquiring the second data. (Supplementary Note 5) The system according to Supplementary Note 1 or 2, wherein the selection unit calculates, for each terminal, a statistical value of the similarity index between the first data of the terminal and the first data of other terminals, and selects a terminal from which to acquire the second data based on the statistical value for each terminal. (Supplementary Note 6) The system according to Supplementary Note 1 or 2, wherein the selection unit converts the similarity index into a value based on a predetermined criterion, and selects a terminal from which to acquire the second data based on the converted value. (Supplementary Note 7) The system according to Supplementary Note 1 or 2, wherein the selection unit ranks the similarity index for each terminal or for each other terminal for combinations of the similarity index between the first data of the terminal and the first data of other terminals, and selects a terminal from which to acquire the second data based on the ranking.(Supplementary Note 8) The system according to Supplementary Note 1 or 2, further comprising: a designation unit that designates a noted terminal from the plurality of terminals, wherein the selection unit selects the noted terminal as the terminal from which the second data is to be acquired. (Supplementary Note 9) The system according to Supplementary Note 8, wherein the selection unit selects the terminal from which the second data is to be acquired based on the similarity index between the first data acquired from the noted terminal and the first data acquired from another terminal. (Supplementary Note 10) The system according to Supplementary Note 9, wherein the selection unit selects a terminal from which the degree of similarity between the noted terminal and the first data is higher than a predetermined value, according to the similarity index. (Supplementary Note 11) The system according to Supplementary Note 8, wherein, when the number of noted terminals is greater than a predetermined value, the selection unit selects the terminal from which the second data is to be acquired based on a result of grouping the noted terminals according to the similarity index. (Supplementary Note 12) The system according to Supplementary Note 8, wherein the designation unit designates a policy for selecting a terminal from which to acquire the second data based on the noted terminal, and the selection unit selects a terminal from which to acquire the second data based on the similarity index between the first data acquired from the noted terminal and the first data acquired from another terminal in accordance with the policy. (Supplementary Note 13) The system according to Supplementary Note 12, wherein the policy includes selecting a terminal from which the degree of similarity between the noted terminal and the first data is higher than a predetermined value. (Supplementary Note 14) The system according to Supplementary Note 12, wherein the policy includes a percentage of terminals from which the degree of similarity between the noted terminal and the first data is higher than a predetermined value, and a percentage of other terminals. (Supplementary Note 15) An apparatus comprising: an acquisition unit that acquires first data related to communication quality from a plurality of terminals; a calculation unit that calculates a similarity index between the first data of the plurality of terminals; and a selection unit that selects a terminal from which to acquire second data related to communication quality based on the similarity index. (Supplementary Note 16) A method comprising: acquiring first data related to communication quality from a plurality of terminals; calculating a similarity index between the first data of the plurality of terminals; and selecting a terminal from which second data related to communication quality is to be acquired based on the similarity index.(Supplementary Note 17) A program for causing a computer to execute a process of: acquiring first data related to communication quality from a plurality of terminals; calculating a similarity index between the first data of the plurality of terminals; and selecting a terminal from which second data related to communication quality is to be acquired based on the similarity index.

[0106] Some or all of the elements (e.g., configurations and functions) described in Supplements 2 to 14 that are dependent on Supplement 1 (system) may also be dependent on Supplement 15 (device), Supplement 16 (method), and Supplement 17 (program) in the same dependency relationship as Supplements 2 to 14. Some or all of the elements described in any Supplement may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0107] This application claims priority based on Japanese Patent Application No. 2024-056015, filed March 29, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0108] 1 RAN system 10 System 11 Acquisition unit 12 Calculation unit 13 Selection unit 20 Device 30 Computer 31 Network interface 32 Processor 33 Memory 100 Near-RT RIC 110 Data collection unit 120 Data storage unit 130 Distance calculation unit 140 Terminal selection unit 150 Data transmission unit 210 Data reception unit 220 Factor estimation learning / inference unit 230 Terminal designation unit 300 O-DU 400 O-CU 500 External server 510 Attention terminal input unit 600 Terminal

Claims

1. A system comprising: an acquisition unit that acquires first data related to communication quality from a plurality of terminals; a calculation unit that calculates a similarity index between the first data of the plurality of terminals; and a selection unit that selects a terminal from which to acquire second data related to communication quality based on the similarity index.

2. The system according to claim 1, wherein the selection unit selects a terminal with a low degree of similarity of the first data over a terminal with a high degree of similarity of the first data according to the similarity index.

3. The system described in claim 1 or 2, wherein the acquisition unit acquires the first data from terminals in a first group among the plurality of terminals, and the selection unit selects a first number of terminals from the terminals included in the first group as terminals to be excluded from acquiring the second data based on the similarity index, and selects terminals from the terminals included in the first group excluding the selected first number of terminals and the first number of terminals included in the second group as terminals from which the second data is to be acquired.

4. The system described in claim 3, wherein the selection unit selects the first number of terminals from among the terminals included in the first group that have a higher degree of similarity between the first data as terminals to be excluded from obtaining the second data.

5. The system according to claim 1 or 2, wherein the selection unit calculates, for each terminal, a statistical value of the similarity index between the first data of the terminal and the first data of other terminals, and selects a terminal from which to acquire the second data based on the statistical value for each terminal.

6. The system according to claim 1 or 2, wherein the selection unit converts the similarity index into a value based on a predetermined criterion, and selects a terminal from which to acquire the second data based on the converted value.

7. The system according to claim 1 or 2, wherein the selection unit ranks the similarity indexes for each terminal or each other terminal in combinations of the similarity indexes between the first data of the terminal and the first data of another terminal, and selects a terminal from which to acquire the second data based on the ranking.

8. The system according to claim 1 or 2, further comprising a designation unit that designates a target terminal from the plurality of terminals, wherein the selection unit selects the target terminal as the terminal from which the second data is to be acquired.

9. The system according to claim 8, wherein the selection unit selects a terminal from which to acquire the second data based on the similarity index between the first data acquired from the target terminal and the first data acquired from another terminal.

10. The system according to claim 9, wherein the selection unit selects a terminal whose degree of similarity between the target terminal and the first data is higher than a predetermined value, according to the similarity index.

11. The system according to claim 8, wherein, when the number of the target terminals is greater than a predetermined number, the selection unit selects a terminal from which to acquire the second data based on a result of grouping the target terminals according to the similarity index.

12. The system described in claim 8, wherein the designation unit designates a policy for selecting a terminal from which to acquire the second data based on the target terminal, and the selection unit selects a terminal from which to acquire the second data in accordance with the policy and based on the similarity index between the first data acquired from the target terminal and the first data acquired from another terminal.

13. The system according to claim 12, wherein the policy includes selecting a terminal having a degree of similarity between the target terminal and the first data that is higher than a predetermined value.

14. The system according to claim 12, wherein the policy includes a percentage of terminals having a degree of similarity between the target terminal and the first data higher than a predetermined value, and a percentage of other terminals.

15. A method comprising: acquiring first data related to communication quality from a plurality of terminals; calculating a similarity index between the first data of the plurality of terminals; and selecting a terminal from which to acquire second data related to communication quality based on the similarity index.

16. A program for causing a computer to execute the following process: acquiring first data related to communication quality from a plurality of terminals; calculating a similarity index between the first data of the plurality of terminals; and selecting a terminal from which second data related to communication quality is to be acquired based on the similarity index.

Images