System, base station device, testing method, and program

Abstract

Provided is a system comprising a base station device which is disposed in a distributed platform, and a testing terminal which is a testing user terminal for testing mobile communication between the base station device and a user terminal, wherein the base station device has an AI model acquisition unit that acquires an AI model to be used for communication between the base station device and the user terminal, a test performance unit that performs a test of communication with the testing terminal using the AI model acquired by the AI model acquisition unit, and a result recording unit that records a test result from the test performance unit.

Description

System, base station equipment, test method, and program

[0001] This invention relates to a system, a base station device, a test method, and a program.

[0002] Patent Document 1 states that "An AI model may be deployed in at least one of the following: a core network device, an access network device, a terminal device, an OAM, etc., and the corresponding function is performed by using the AI ​​model. One or more AI models may be deployed in a CU. Alternatively, one or more AI models may be deployed in a DU. Optionally, the CU in Figure 3 may be further divided into CU-CP and CU-UP. Optionally, one or more AI models may be deployed in a CU-CP. Alternatively, one or more AI models may be deployed in a CU-UP." Patent Document 2 states that "with respect to one or more of the WTRU102a-d, base stations 114a-b, eNode-B160a-c, MME162, SGW164, PGW166, gNB180a-c, AMF182a-b, UPF184a-b, SMF183a-b, DN185a-b, and / or any other devices described herein, one or more of the functions described herein may be performed by one or more emulation devices (not shown). The emulation devices may be designed to implement testing of one or more of the other devices in a laboratory environment and / or an operator network environment. The device may be directly coupled to another device for testing purposes and / or the test may be performed using terrestrial radio communication. Model compression techniques are widely used to run DNN models only on the user device. They reduce the model memory footprint and runtime, making it possible to adapt it to a specific device. A family of flexible AI models has recently been proposed. These models can be immediately adapted to available resources, for example, by enabling early classification termination, model width adaptation (slimming), or switchable model weight quantization. [Prior Art Documents] [Patent Documents] [Patent Document 1] Japanese Patent Publication No. 2025-501292 [Patent Document 2] Japanese Patent Publication No. 2024-509670

[0003] An AI (Artificial Intelligence) model that has completed learning needs to verify its effectiveness in advance. For example, conventionally, when generating an AI model used by a base station in a mobile communication network, a virtual environment is constructed using a simulator environment or an emulator environment, and the effectiveness of the AI model is verified pseudo - experimentally by embedding the AI model into the virtual environment. For improving wireless performance, since there are specific environmental differences associated with the wireless communication area of the base station, regardless of whether the base station is a distributed base station or a centralized base station, it is necessary to verify the effectiveness of the AI model in a considerable number of virtual environment patterns. For pre - verification in a virtualized pseudo - real network environment, its operation needs to be carried out in the prepared pseudo - environment patterns, and there is a limitation that the update cycle of the AI model cannot be shortened in the short term. Also, since it is only a pseudo - environment, there is a certain deviation from the original real environment, so the effectiveness of the verification is not necessarily guaranteed.

[0004] According to an embodiment of the present invention, a system is provided. The system may include a base station device disposed within a distributed infrastructure. The system may include a test terminal that is a test user terminal for testing mobile communication between the base station device and a user terminal. The base station device may have an AI model acquisition unit that acquires an AI model used for communication between the base station device and the user terminal. The base station device may have a test execution unit that executes a communication test using the AI model acquired by the AI model acquisition unit with the test terminal. The base station device may have a result recording unit that records the test results by the test execution unit.

[0005] In the system, the AI model may include at least one of a model for channel estimation and a model for channel interpolation, and the test execution unit may execute a communication test that performs at least one of channel estimation and channel interpolation using the AI model with the test terminal.

[0006] In any of the above systems, the base station device may have a function to generate multiple cells, and the test execution unit may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal for only some of the multiple cells that can be generated.

[0007] Any of the above systems may include a plurality of base station devices located within the distributed infrastructure, and each of the plurality of base station devices' test execution units may perform communication tests with the test terminal using the AI ​​model acquired by each of the plurality of base station devices' AI model acquisition units.

[0008] Any of the above systems may include multiple types of test terminals corresponding to multiple types of user terminals that may communicate with the base station device, and the test execution unit may perform communication tests using the AI ​​model acquired by the AI ​​model acquisition unit with each of the multiple types of test terminals.

[0009] Any of the above systems may include a plurality of test terminals, and the test execution unit may use the AI ​​model acquired by the AI ​​model acquisition unit to perform multiple communication tests targeting a different number of test terminals from the plurality of test terminals.

[0010] In any of the above systems, the test terminal may be located within the distributed infrastructure, and the base station equipment may communicate wirelessly with the test terminal using an antenna unit located within the distributed infrastructure.

[0011] In any of the above systems, the base station equipment may be located in a rack within the distributed infrastructure, and the test terminal may be located in the same rack as the base station equipment.

[0012] In any of the above systems, the test terminal may be located outside the distributed infrastructure, and the base station equipment may communicate wirelessly with the test terminal using an antenna unit located outside the distributed infrastructure.

[0013] In any of the above systems, the test terminal may be located within the distributed infrastructure, and the base station equipment may communicate wirelessly with the test terminal using an antenna unit located outside the distributed infrastructure.

[0014] Any of the above systems may further include a management device for managing the base station equipment and a model management unit located within the distributed infrastructure that provides the AI ​​model to the base station equipment. The management device may also include a result acquisition unit for acquiring the test results recorded in the result recording unit and a modification instruction unit for instructing the model management unit to modify the AI ​​model if the test results indicate a problem with the use of the AI ​​model.

[0015] In any of the above systems, the base station device may have a communication control unit that communicates with a plurality of user terminals and provides mobile communication services to the plurality of user terminals, and the test execution unit may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal during a predetermined time period in which the number of user terminals communicating with the communication control unit is small.

[0016] In any of the above systems, the base station device may have a communication control unit that communicates with a plurality of user terminals and provides mobile communication services to the plurality of user terminals, and the test execution unit may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal when the number of user terminals communicating with the communication control unit is less than a predetermined number.

[0017] According to one embodiment of the present invention, a base station device is provided that is located within a distributed infrastructure. The base station device may include an implementation unit that implements a virtual test terminal, which virtually realizes a test user terminal for testing communication between the base station device and a user terminal. The base station device may include an AI model acquisition unit that acquires an AI model to be used for communication between the base station device and a user terminal. The base station device may include a test execution unit that simulates and tests communication between the base station device and the virtual test terminal using the AI ​​model acquired by the AI ​​model acquisition unit. The base station device may include a result recording unit that records the results of the test performed by the test execution unit.

[0018] According to one embodiment of the present invention, a test method is provided that is performed by a base station device located in a distributed infrastructure. The test method may include an implementation step of implementing a virtual test terminal that virtually realizes a test user terminal for testing communication between the base station device and a user terminal. The test method may include an AI model acquisition step of acquiring an AI model to be used for communication between the base station device and the user terminal. The test method may include a test execution step of testing the communication between the base station device and the virtual test terminal by simulation using the AI ​​model acquired in the AI ​​model acquisition step. The test method may include a result recording step of recording the results of the test performed by the test execution unit.

[0019] According to one embodiment of the present invention, a program is provided for executing the following steps: an implementation step of implementing a virtual test terminal in a base station device located in a distributed infrastructure, which virtually realizes a test user terminal for testing communication between the base station device and a user terminal; an AI model acquisition step of acquiring an AI model to be used for communication between the base station device and the user terminal; a test execution step of simulating and testing communication between the base station device and the virtual test terminal using the AI ​​model acquired in the AI ​​model acquisition step; and a result recording step of recording the results of the test performed by the test execution unit.

[0020] It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention.

[0021] A schematic example of system 10 is shown. A schematic example of the configuration of the distributed infrastructure 30 is shown. A schematic example of the functional configuration of the management device 200 is shown. A schematic example of the functional configuration of the base station device 310 is shown. A schematic example of the processing flow by the base station device 310 is shown. A schematic example of the processing flow by the base station device 310 is shown. A schematic example of the processing flow by the base station device 310 is shown. A schematic example of the arrangement of the test terminal 400 is shown. A schematic example of the arrangement of the test terminal 400 is shown. A schematic example of the arrangement of the test terminal 400 is shown. A schematic example of the functional configuration of the base station device 310 is shown. A schematic example of the hardware configuration of the computer 1200 that functions as the management device 200 or the base station device 310 is shown.

[0022] The present invention will be described below through embodiments, but these embodiments are not intended to limit the scope of the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0023] In the system according to this embodiment, for example, a test terminal, which is a test user terminal for testing mobile communication with a user terminal, is prepared in advance at the base station equipment, and the system is configured to perform communication tests using a new AI model via OTA (Over The Air) between the base station equipment and the test terminal, thereby enabling immediate confirmation of whether or not there are abnormalities in the new AI model in a real environment. In this system, the load on the communication environment caused by the tests may be reduced by performing communication tests with the test terminal using the new AI model during late-night or early-morning hours when there are few connected user terminals connected to the base station equipment. In this system, if there is an optimal AI model for each wireless communication area, local pre-verification may be performed at the aggregate unit of base station equipment covering that wireless communication area.

[0024] Figure 1 schematically shows an example of system 10. System 10 comprises a management infrastructure 20 and a plurality of distributed infrastructures 30. The management infrastructure 20 may include a management device 200. The distributed infrastructures 30 may include a plurality of base station devices 310. The distributed infrastructures 30 may include one or more test terminals 400. System 10 may include a plurality of antenna units 330. System 10 may include a plurality of user terminals 500.

[0025] The system 10 according to this embodiment may be applied to an AI-RAN (Radio Access Network). AI-RAN may include three types: "AI for RAN", "AI on RAN", and "AI and RAN". "AI for RAN" may be a technology that utilizes AI and machine learning techniques to improve the frequency utilization efficiency and performance of existing RANs, or to realize automation of base station operations and power saving. "AI for RAN" is expected to optimize processing at all layers, such as channel estimation and scheduling processing performed by each cell of the RAN, optimize cooperation between RAN cells, and improve the equipment utilization rate of base stations. "AI on RAN" may be a technology that utilizes the computing infrastructure of a base station to provide highly immediate services to users and devices around the base station with low latency. "AI on RAN" enables the deployment of AI and machine learning technology applications at the network edge via RAN, thereby facilitating the creation of new industries and solutions that leverage low latency and confidentiality. "AI and RAN" may be a technology for performing RAN processing and AI and machine learning technology processing that is not directly related to RAN on the same computing infrastructure. By integrating AI and RAN processing with "AI and RAN," improvements in infrastructure utilization efficiency can be expected. System 10 may be applied in particular to "AI for RAN."

[0026] The system 10 according to this embodiment may perform RAN control and AI processing.

[0027] The RAN control performed by system 10 may be vRAN (Virtual RAN). Multiple distributed infrastructures 30 may constitute a vRAN. Multiple base station devices 310 are located on each of the multiple distributed infrastructures 30, and the multiple base station devices 310 provide a mobile communication service using multiple antenna units 330 to multiple user terminals 500.

[0028] The user terminal 500 can be any terminal as long as it is capable of using mobile communication services. Examples of user terminals 500 include, but are not limited to, smartphones, tablet terminals, PCs (Personal Computers), mobile Wi-Fi (registered trademark), wearable terminals such as smartwatches and smart glasses, IoT (Internet of Things) terminals such as sensors, smart home appliances, and smart meters, in-vehicle equipment, robots, and game consoles. User terminals 500 may include any terminal that falls under the category of IoE (Internet of Everything).

[0029] The AI ​​processing performed by system 10 may include RAN control AI processing, which is AI processing related to RAN control. The AI ​​processing performed by system 10 may also include non-RAN control AI processing, which is AI processing not related to RAN control.

[0030] An example of AI-based RAN control processing is the RIC (RAN Intelligent Controller). The RIC is a technology that uses AI to optimize RAN wireless resources and automate RAN operations. The RIC includes Non-RT (Real Time) RIC and Near-RT RIC. The Non-RT RIC is sometimes called a Centralized RIC. The Non-RT RIC is located within the SMO (Service Management and Orchestration), which manages and orchestrates the RAN. The Non-RT RIC generates and notifies policies related to RAN control and transmits information to the Near-RT RIC. For example, a Non-RT RIC generates a trained model for RAN control by performing machine learning using data collected from the RAN, and sends it to a Near-RT RIC. A Near-RT RIC is sometimes called a Distributed RIC. Compared to a Non-RT RIC, a Near-RT RIC is located closer to the RAN nodes (RU (Radio Unit), DU (Distributed Unit), CU (Central Unit)) and performs control of the RAN nodes and resources. Compared to a Non-RT RIC, a Near-RT RIC performs processing with higher real-time capabilities. For example, a Near-RT RIC performs inference processing related to RAN control using the trained model obtained from a Non-RT RIC. RAN control AI processing is not limited to RICs.

[0031] Non-RAN-controlled AI processing may correspond to so-called MEC (Multi-access Edge Computing) applications. Examples of non-RAN-controlled AI processing include, but are not limited to, monitoring AI execution processing that determines the situation within the imaging range of an input image, and response AI execution processing that outputs a response to an inquiry made by a user.

[0032] The distributed infrastructure 30 may be data centers located in various locations. The distributed infrastructure 30 may have multiple types of equipment, including base station equipment 310. The management infrastructure 20 may be a data center that manages multiple distributed infrastructures 30. The management infrastructure 20 may have multiple types of equipment, including management equipment 200.

[0033] The management infrastructure 20 may be called the Core Brain, and the distributed infrastructure 30 may be called the Regional Brain. Note that Figure 1 illustrates a case where a single-layer distributed infrastructure 30 is located below the management infrastructure 20, but it is not limited to this. The distributed infrastructure 30 may have multiple layers. For example, if two layers of distributed infrastructure 30 are located below the management infrastructure 20, the management infrastructure 20 may be called the Core Brain, the distributed infrastructure 30 at the lower layer may be called the Regional Brain, and the distributed infrastructure 30 at the lower layer may be called the Sub-Regional Brain.

[0034] The base station device 310 uses one or more antenna units 330 to form one or more cells and provides mobile communication services to one or more user terminals 500 located within the cells. If the communication method that the system 10 conforms to is the 5G (5th Generation) communication method, the base station device 310 may function as a DU and a CU. The base station device 310 may function as a DU and the management device 200 may function as a CU. If the communication method that the system 10 conforms to is the LTE (Long Term Evolution) communication method, the base station device 310 may function as a BBU (Base Band Unit). A single base station device 310 may be capable of forming multiple cells, such as 20 cells or 40 cells. The base station device 310 may include one or more CPUs (Central Processing Units) and one or more GPUs (Graphics Processing Units). The base station device 310 may include one or more superchips in which the CPUs and GPUs are connected by an interconnect. The interconnect may be memory-consistent and capable of achieving high bandwidth and low latency.

[0035] Conventionally, when an AI model was generated for communication between a base station device 310 and a user terminal 500, research institutions would prepare a virtual environment using a simulator or emulator environment to conduct tests, or a tester carrying a user terminal 500 would travel to a location where communication with the target base station device 310 was possible to conduct tests. However, in the case of tests using a virtual environment, since it is only a simulated environment, there is a certain degree of discrepancy with the actual environment, and the effectiveness was not always appropriate. In addition, when a tester had to travel to the target location to conduct tests, it was difficult to conduct tests frequently.

[0036] In the system 10 shown in Figure 1, the distributed infrastructure 30 includes a test terminal 400. The test terminal 400 may be a test user terminal for testing mobile communication between the base station device 310 and a user terminal 500. The distributed infrastructure 30 may have the test terminal 400 located within the distributed infrastructure 30, or it may have the test terminal 400 located outside the distributed infrastructure 30. For example, when the base station device 310 acquires a new AI model, it performs a communication test using the AI ​​model with the test terminal 400. By having the distributed infrastructure 30 pre-equipped with the test terminal 400, the base station device 310 can immediately perform a communication test whenever a new AI model is acquired or an AI model is updated.

[0037] The AI ​​model according to this embodiment may be any model that can be used directly or indirectly by the base station device 310 for communication with the user terminal 500. For example, examples of AI models include a channel estimation model that estimates channel state information from a received signal, and a channel interpolation model that interpolates channel state information. Other examples of AI models include a transmission signal estimation model that estimates the transmission signal on the receiving side, a transmission signal restoration model that restores the transmission signal on the receiving side, a beamforming optimization model that selects or adapts to the optimal beam, a scheduling optimization model that optimizes resource allocation, and a power control model that optimizes transmission power, but these are just examples and are not limited to these.

[0038] Figure 2 schematically shows an example of the configuration of the distributed infrastructure 30. In the example shown in Figure 2, the distributed infrastructure 30 comprises a PF (PlatForm) 300, a model management unit 350, and a storage server 360.

[0039] The PF300 comprises multiple base station devices 310 and a test terminal 400. The PF300 may also include multiple test terminals 400.

[0040] The model management unit 350 provides the AI ​​model to the base station device 310. The model management unit 350 may generate an AI model. The model management unit 350 may update an AI model. For example, the model management unit 350 generates or updates an AI model using information collected while providing mobile communication services to multiple user terminals 500 as training data. The model management unit 350 may update an AI model. Examples of information used as training data include RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), SINR (Signal to Interference plus Noise Ratio), RSSI (Received Signal Strength Indicator), CQI (Channel Quality Indicator), MCS (Modulation and Coding Scheme), BLER (Block Error Rate), and PRB usage rate (Physical Resource Block). Examples include, but are not limited to, Utilization, TTI (Transmission Time Interval), HARQ (Hybrid Automatic Repeat request), ICIC (Inter-Cell Interference Coordination), PDCCH utilization (Physical Downlink Control Channel Utilization), QoE (Quality of Experience), throughput, RTT (Round Trip Time), jitter, and packet loss rate.

[0041] The storage server 360 stores various types of data. For example, the storage server 360 stores the test results of communication tests using the AI ​​model by the base station equipment 310.

[0042] The model management unit 350, for example, refers to the test results of communication tests using the AI model by the base station device 310 stored in the storage server 360, and updates the AI model or generates a new AI model.

[0043] FIG. 3 schematically shows an example of the functional configuration of the management device 200. The management device 200 may communicate with the base station device 310 via the model management unit 350. The management device 200 may also communicate with the base station device 310 without going through the model management unit 350. The management device 200 may communicate with the storage server 360 via the model management unit 350. The management device 200 may also communicate with the storage server 360 without going through the model management unit 350.

[0044] The management device 200 includes a storage unit 202, a management unit 204, a result acquisition unit 206, a determination instruction unit 208, and a correction instruction unit 210. The storage unit 202 stores various information. The storage unit 202 stores, for example, information on a plurality of base station devices 310 arranged in each of the plurality of distributed bases 30. The storage unit 202 stores information on the test terminals 400 included in each of the plurality of distributed bases 30. The information on the test terminals 400 of each of the plurality of distributed bases 30 may include the number of test terminals 400, the types of test terminals 400, and the positions of the test terminals 400.

[0045] The management unit 204 manages the plurality of distributed bases 30. The management unit 204 may manage the AI models to be used by the plurality of base station devices 310 for each of the plurality of distributed bases 30. For example, the management unit 204 may cause the model management unit 350 to generate or update an AI model. The management unit 204 may send an instruction to the model management unit 350 to provide the AI model to the base station device 310, and cause the model management unit 350 to send the AI model to the base station device 310. The base station device 310 executes a communication test using the AI model provided from the model management unit 350 with the test terminal 400 and records the test results. The base station device 310 may send the test results to the storage server 360.

[0046] The result acquisition unit 206 acquires the test results stored in the base station device 310 from the base station device 310. The result acquisition unit 206 may acquire the test results from the storage server 360.

[0047] When the test results acquired by the result acquisition unit 206 indicate that there are no problems in using the AI model, the confirmation instruction unit 208 transmits a confirmation instruction for confirming the use of the AI model to the base station device 310. After receiving the confirmation instruction, the base station device 310 uses the target AI model for communication with the user terminal 500.

[0048] When the test results acquired by the result acquisition unit 206 indicate that there are problems in using the AI model, the correction instruction unit 210 instructs the model management unit 350 to correct the AI model. The correction of the AI model may include both changing the target AI model and generating a new AI model and replacing it with the target AI model. When the test results acquired by the result acquisition unit 206 indicate that there are problems in using the AI model, the correction instruction unit 210 may transmit an instruction not to use the AI model to the base station device 310.

[0049] After instructing the model management unit 350 to correct the AI model, the correction instruction unit 210 may notify the management unit 204 that the correction of the AI model is completed in response to receiving a report of the completion of the correction from the model management unit 350. In response to receiving the notification from the correction instruction unit 210, the management unit 204 may cause the base station device 310 to test the AI model.

[0050] The existence of problems in using the AI model may mean that when the base station device 310 uses the AI model, communication with the user terminal 500 cannot be performed normally. The inability to perform communication with the user terminal 500 normally may mean that communication with the user terminal 500 cannot be established. The inability to perform communication with the user terminal 500 normally may mean that although communication with the user terminal 500 is possible, the communication quality is lower than a predetermined quality. The inability to perform communication with the user terminal 500 normally may mean that although communication with the user terminal 500 is possible, the communication speed is lower than a predetermined speed.

[0051] The correction instruction unit 210 may, for example, if the test results acquired by the result acquisition unit 206 indicate that there was a problem with the use of the AI ​​model, send at least one of the following instructions to the model management unit 350: an instruction to tune the AI ​​model; an instruction to generate an AI model using different learning data than the learning data used when the AI ​​model was generated; an instruction to generate an AI model with changed learning parameters from when the AI ​​model was generated; and an instruction to generate an AI model using a different learning algorithm than when the AI ​​model was generated.

[0052] Figure 4 schematically shows an example of the functional configuration of the base station device 310. The base station device 310 comprises a storage unit 312, a communication control unit 314, an AI model acquisition unit 316, a test execution unit 318, and a result recording unit 320.

[0053] The memory unit 312 stores various types of information. For example, the memory unit 312 stores an AI model used for communication with the user terminal 500. For example, the memory unit 312 stores information about a test terminal 400 provided on the distributed infrastructure 30 where the base station device 310 is located.

[0054] The communication control unit 314 controls the communication of the base station device 310. The communication control unit 314 may perform communication with devices on the core network side. The communication control unit 314 may perform communication with user terminals 500. The communication control unit 314 may establish communication connections with multiple user terminals 500 and provide mobile communication services to multiple user terminals 500.

[0055] The communication control unit 314 may perform communication with the user terminal 500 using the AI ​​model stored in the memory unit 312. For example, if a channel estimation model is stored in the memory unit 312, the communication control unit 314 will use the channel estimation model to estimate the channel of the user terminal 500, perform control according to the estimation result, and communicate with the user terminal 500.

[0056] The AI ​​model acquisition unit 316 acquires an AI model. The AI ​​model acquisition unit 316 acquires an AI model from, for example, the model management unit 350. The AI ​​model acquisition unit 316 acquires an AI model generated by the model management unit 350 or an AI model updated by the model management unit 350 from the model management unit 350.

[0057] The test execution unit 318 performs a communication test with the test terminal 400 using the AI ​​model acquired by the AI ​​model acquisition unit 316. For example, if the AI ​​model acquired by the AI ​​model acquisition unit 316 is a channel estimation model, the test execution unit 318 uses the channel estimation model to estimate the channel of the test terminal 400, performs control according to the estimation result, and communicates with the test terminal 400.

[0058] The test execution unit 318 may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit 316 with the test terminal 400 during a predetermined time period when the number of user terminals 500 connected to the communication control unit 314 is small. The time period when the number of user terminals 500 connected to the communication control unit 314 is small may be late at night. The time period when the number of user terminals 500 connected to the communication control unit 314 is small may be early in the morning. The time period when the number of user terminals 500 connected to the communication control unit 314 is small may be late at night or early in the morning. This reduces the adverse impact of the communication test on the mobile communication service.

[0059] The test execution unit 318 may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit 316 with the test terminal 400 when the number of user terminals 500 connected to the communication control unit 314 is less than a predetermined number. The test execution unit 318 may monitor the change in the number of user terminals 500 connected to the communication control unit 314 and perform the communication test when it determines that the number is less than a predetermined number. The test execution unit 318 may monitor the change in the number of user terminals 500 connected to the communication control unit 314 and perform the communication test when it determines that the state of being less than a predetermined number has continued for a predetermined time. This reduces the adverse impact of the communication test on the mobile communication service.

[0060] The results recording unit 320 records the test results performed by the test execution unit 318. When the test execution unit 318 performs a communication test targeting the test terminal 400, it causes the results recording unit 320 to record the test results. For example, if the test execution unit 318 performs a communication test and is able to communicate with the test terminal 400 without any problems occurring, it causes the results recording unit 320 to record a test result indicating that there were no problems with the use of the AI ​​model. For example, if the test execution unit 318 performs a communication test and a problem occurs with the test terminal 400, it causes the results recording unit 320 to record a test result indicating that there were problems with the use of the AI ​​model.

[0061] As a specific example, if the test execution unit 318 is unable to communicate with the test terminal 400, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that communication with the test terminal 400 was not possible. As a specific example, if the test execution unit 318 is able to communicate with the test terminal 400, but the communication quality is lower than a predetermined quality, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that the communication quality of communication with the test terminal 400 has deteriorated. As a specific example, if the test execution unit 318 is able to communicate with the test terminal 400, but the communication speed is lower than a predetermined speed, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that the communication speed of communication with the test terminal 400 has deteriorated.

[0062] The communication control unit 314 may transmit the test results recorded in the result recording unit 320 to the storage server 360. The communication control unit 314 may transmit the test results recorded in the result recording unit 320 to the management device 200. If the correction instruction unit 210 of the management device 200 indicates that there was a problem with the use of the AI ​​model, it instructs the model management unit 350 to correct the AI ​​model. For example, if the test results indicate that communication with the test terminal 400 could not be established, the correction instruction unit 210 transmits an instruction to the model management unit 350 to correct the AI ​​model to resolve the problem of not being able to communicate with the test terminal 400. For example, if the test results indicate that the communication quality of communication with the test terminal 400 has deteriorated, the correction instruction unit 210 transmits an instruction to the model management unit 350 to correct the AI ​​model to improve the communication quality. For example, if the test results indicate that the communication speed with the test terminal 400 has decreased, the correction instruction unit 210 sends an instruction to the model management unit 350 to modify the AI ​​model so that the communication speed improves.

[0063] In this embodiment, the base station device 310 may have a function to generate multiple cells. In this case, the test execution unit 318 may perform communication tests with the test terminal 400 using the AI ​​model acquired by the AI ​​model acquisition unit 316 for only some of the multiple cells that can be generated. For example, the test execution unit 318 may perform communication tests with the test terminal 400 using the AI ​​model acquired by the AI ​​model acquisition unit 316 for only one of the multiple cells that can be generated. Since the processing using the AI ​​model is basically software processing and does not differ from cell to cell, if it operates normally in some of the multiple cells, it is assumed that it will operate normally in the other cells as well. Therefore, by configuring the test execution unit 318 to perform communication tests on only some of the multiple cells, the load on the communication tests and the time required for the communication tests can be appropriately reduced. Alternatively, the test execution unit 318 may perform communication tests with the test terminal 400 using the AI ​​model acquired by the AI ​​model acquisition unit 316 for all of the multiple cells that can be generated.

[0064] Only one test terminal 400 may be placed within a single distributed infrastructure 30. Multiple test terminals 400 may be placed within a single distributed infrastructure 30. Multiple types of test terminals 400 that may communicate with the base station device 310 may be placed within a single distributed infrastructure 30. Examples of multiple types of test terminals 400 that may communicate with the base station device 310 include, but are not limited to, iOS (registered trademark) smartphones, Android (registered trademark) smartphones, smartphones with other operating systems, tablet devices, PCs, mobile Wi-Fi, wearable devices such as smartwatches and smart glasses, IoT devices such as sensors, smart home appliances and smart meters, in-vehicle devices, robots, and game consoles.

[0065] If only one test terminal 400 is located within the distributed infrastructure 30, multiple base station devices 310 within the distributed infrastructure 30 may share that single test terminal 400. That is, each test execution unit 318 of the multiple base station devices 310 may perform communication tests with the test terminal 400 using the AI ​​model acquired by each AI model acquisition unit 316 of the multiple base station devices 310. This reduces the number of test terminals 400 required, contributing to cost reduction.

[0066] If multiple test terminals 400 are deployed within the distributed infrastructure 30, the test execution unit 318 may use the AI ​​model acquired by the AI ​​model acquisition unit 316 to perform multiple communication tests targeting different numbers of the test terminals 400. This allows testing the impact of the AI ​​model on different numbers of terminals connected to the base station device 310, thereby enhancing security.

[0067] If multiple types of test terminals 400 that may communicate with the base station device 310 are placed within the distributed infrastructure 30, the test execution unit 318 may perform communication tests using the AI ​​model acquired by the AI ​​model acquisition unit 316 with each of the multiple types of test terminals 400. This makes it possible to test the influence of the AI ​​model when the terminal types are different, thereby increasing security.

[0068] Figure 5 schematically shows an example of the processing flow by the base station device 310. Figure 5 describes the case where one test terminal 400 is located on one distributed infrastructure 30. Here, the starting state is described as the state in which the AI ​​model acquisition unit 316 has already acquired the AI ​​model to be tested.

[0069] In step 102 (sometimes abbreviated as S), the test execution unit 318 performs a communication test using the AI ​​model with the test terminal 400.

[0070] In S104, the test execution unit 318 causes the test results from S102 to be recorded in the result recording unit 320.

[0071] Each of the multiple base station devices 310 located on the distributed infrastructure 30 may perform the processing shown in Figure 5.

[0072] Figure 6 schematically shows an example of the processing flow by the base station device 310. Figure 6 describes the case where multiple test terminals 400 are arranged on a single distributed infrastructure 30. Here, the starting state is described as the state in which the AI ​​model acquisition unit 316 has already acquired the AI ​​model to be tested.

[0073] In S202, the test execution unit 318 determines the number of test subjects. The test execution unit 318 determines the number of test subjects by referring to test plan information, for example, which shows the test plan. The test plan information may be registered in advance and stored in the storage unit 312. The test plan information may show multiple tests with varying numbers of test subjects. For example, if 10 test terminals 400 are provided, the test plan information may include patterns in the number of test subjects, such as 1st time: 1 unit, 2nd time: 5 units, 3rd time: 10 units, etc.

[0074] In S204, the test execution unit 318 performs a communication test using an AI model on the number of test terminals 400 determined in S202. In S206, the test execution unit 318 records the test results from S204 in the result recording unit 320.

[0075] If testing is completed for all patterns included in the test plan information (YES in S208), the process ends; otherwise, it returns to S202.

[0076] Each of the multiple base station devices 310 located on the distributed infrastructure 30 may perform the processing shown in Figure 6.

[0077] Figure 7 schematically shows an example of the processing flow by the base station device 310. Figure 7 illustrates the case where multiple types of test terminals 400 are arranged on a single distributed infrastructure 30. Here, the starting state is described as the state in which the AI ​​model acquisition unit 316 has already acquired the AI ​​model to be tested.

[0078] In S302, the test execution unit 318 determines the test terminal 400 of the target type. The test execution unit 318 determines the test terminal 400 of the target type by referring to the test plan information, for example. The test plan information may show the types of test terminals 400 to be tested in order, such as the first being an iOS (registered trademark) smartphone, the second being an Android (registered trademark) smartphone, the third being a mobile Wi-Fi, and so on.

[0079] In S304, the test execution unit 318 performs a communication test using an AI model on the type of test terminal 400 determined in S302. In S306, the test execution unit 318 records the test results from S304 in the result recording unit 320.

[0080] If the tests for all types included in the test plan information have been completed (YES in S308), the process ends; otherwise, the process returns to S302.

[0081] Each of the multiple base station devices 310 located on the distributed infrastructure 30 may perform the processing shown in Figure 7.

[0082] Figure 8 schematically shows an example of the arrangement of the test terminal 400. Here, we will describe an example of the arrangement of the test terminal 400 when the radio waves from the antenna unit 330 used to communicate with the user terminal 500 do not reach inside the distributed infrastructure 30. Although Figure 8 illustrates the case where one test terminal 400 is placed inside the distributed infrastructure 30, as mentioned above, multiple test terminals 400 may be placed inside the distributed infrastructure 30, and multiple types of test terminals 400 may be placed.

[0083] In the example shown in Figure 8, the test terminal 400 is located within the distributed infrastructure 30, and the base station equipment 310 communicates wirelessly with the test terminal 400 using a test antenna unit 332 located within the distributed infrastructure 30. The distributed infrastructure 30 may have only one test antenna unit 332, or it may have multiple test antenna units 332 corresponding to multiple base station equipment 310. If only one test antenna unit 332 is located within the distributed infrastructure 30, the multiple base station equipment 310 may share one test antenna unit 332, for example, by using one test antenna unit 332 sequentially.

[0084] In the example shown in Figure 8, multiple base station devices 310 are arranged in a rack 302. The rack 302 may be a so-called server rack, system rack, or 19-inch rack, and is capable of supplying power to the devices arranged therein.

[0085] The test terminal 400 may be placed in a rack 302 where multiple base station devices 310 are located. This makes it possible to efficiently secure power for the test terminal 400 and manage the test terminal 400.

[0086] One or more test antenna units 332 may be placed in a rack 302 where multiple base station devices 310 are located. This makes it possible to secure power for the test antenna units 332 and to manage the test antenna units 332 more efficiently.

[0087] Figure 9 schematically shows an example of the arrangement of the test terminal 400. Here, we will explain an example of the arrangement of the test terminal 400 when the radio waves from the antenna unit 330 used to communicate with the user terminal 500 do not reach inside the distributed infrastructure 30. We will mainly explain the differences from Figure 8.

[0088] In the example shown in Figure 9, the test terminal 400 is located outside the distributed infrastructure 30, and the base station equipment 310 communicates wirelessly with the test terminal 400 using an antenna unit 330 located outside the distributed infrastructure 30. Each of the multiple base station equipment 310 communicates wirelessly with the test terminal 400 using its corresponding antenna unit 330.

[0089] In the example shown in Figure 9, the test terminal 400 is located in the test facility 40 outside the distributed infrastructure 30.

[0090] Figure 10 schematically shows an example of the arrangement of the test terminal 400. Here, we will explain an example of the arrangement of the test terminal 400 when the radio waves from the antenna unit 330 used to communicate with the user terminal 500 reach inside the distributed infrastructure 30. Although Figure 10 illustrates the case where one test terminal 400 is arranged inside the distributed infrastructure 30, as mentioned above, multiple test terminals 400 may be arranged inside the distributed infrastructure 30, and multiple types of test terminals 400 may be arranged.

[0091] In the example shown in Figure 10, the test terminal 400 is located within the distributed infrastructure 30, and the base station equipment 310 communicates wirelessly with the test terminal 400 using an antenna unit 330 located outside the distributed infrastructure 30. Each of the multiple base station equipment 310 communicates wirelessly with the test terminal 400 using its corresponding antenna unit 330.

[0092] In the example shown in Figure 10, the multiple base station devices 310 are arranged in a rack 302. The test terminal 400 may be placed within the rack 302 where the multiple base station devices 310 are arranged.

[0093] In the embodiments described above, the case in which an actual test terminal 400 is placed on the distributed infrastructure 30 has been explained, but the invention is not limited to this. Instead of placing an actual test terminal 400 on the distributed infrastructure 30, or in addition to placing an actual test terminal 400 on the distributed infrastructure 30, the base station device 310 may be provided with a function to implement a virtual test terminal that virtually realizes a test user terminal for testing communication between the base station device 310 and the user terminal 500.

[0094] Figure 11 schematically shows an example of the functional configuration of the base station device 310. In the example shown in Figure 11, the base station device 310 includes a storage unit 312, a communication control unit 314, an AI model acquisition unit 316, a test execution unit 318, and a result recording unit 320, in addition to an implementation unit 322.

[0095] The memory unit 312 stores various types of information. For example, the memory unit 312 stores an AI model used for communication with the user terminal 500.

[0096] The communication control unit 314 controls the communication of the base station device 310. The communication control unit 314 may perform communication with devices on the core network side. The communication control unit 314 may perform communication with user terminals 500. The communication control unit 314 may establish communication connections with multiple user terminals 500 and provide mobile communication services to multiple user terminals 500.

[0097] The communication control unit 314 may perform communication with the user terminal 500 using the AI ​​model stored in the memory unit 312. For example, if a channel estimation model is stored in the memory unit 312, the communication control unit 314 will use the channel estimation model to estimate the channel of the user terminal 500, perform control according to the estimation result, and communicate with the user terminal 500.

[0098] The AI ​​model acquisition unit 316 acquires an AI model. The AI ​​model acquisition unit 316 acquires an AI model from, for example, the model management unit 350. The AI ​​model acquisition unit 316 acquires an AI model generated by the model management unit 350 or an AI model updated by the model management unit 350 from the model management unit 350.

[0099] The implementation unit 322 implements a virtual test terminal 410, which virtually realizes a test user terminal for testing communication between the base station device 310 and the user terminal 500. The implementation unit 322 may implement one virtual test terminal 410. The implementation unit 322 may implement multiple virtual test terminals 410. The implementation unit 322 may implement multiple types of virtual test terminals 410. Examples of multiple types of virtual test terminals 410 include, but are not limited to, a virtual iOS smartphone, a virtual Android smartphone, virtual smartphones with those operating systems, a virtual tablet terminal, a virtual PC, a virtual mobile Wi-Fi, virtual wearable terminals such as a virtual smartwatch and virtual smart glasses, virtual IoT terminals such as a virtual sensor, virtual smart home appliance, and virtual smart meter, virtual in-vehicle equipment, a virtual robot, and a virtual game console.

[0100] The test execution unit 318 performs a communication test with the virtual test terminal 410 using the AI ​​model acquired by the AI ​​model acquisition unit 316. The test execution unit 318 may construct a virtual wireless communication path with the virtual test terminal 410 and perform a communication test with the virtual test terminal 410 by virtually communicating using the AI ​​model through the constructed virtual wireless communication path. For example, if the AI ​​model acquired by the AI ​​model acquisition unit 316 is a channel estimation model, the test execution unit 318 estimates the channel of the virtual test terminal 410 using the channel estimation model, performs control according to the estimation result, and communicates with the virtual test terminal 410. As a result, the base station device 310 can immediately perform a communication test, albeit not in a real environment, each time a new AI model is acquired or an AI model is updated, making it possible to perform the minimum necessary verification before actually putting the AI ​​model into operation.

[0101] The test execution unit 318 may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit 316 with a virtual test terminal 410 during a predetermined time period when the number of user terminals 500 connected to the communication control unit 314 is low. The time period when the number of user terminals 500 connected to the communication control unit 314 is low may be late at night. The time period when the number of user terminals 500 connected to the communication control unit 314 is low may be early in the morning. The time period when the number of user terminals 500 connected to the communication control unit 314 is low may be late at night or early in the morning. This makes it possible to perform the communication test when the overall load on the base station device 310 is relatively low.

[0102] The test execution unit 318 may perform a communication test using the AI ​​model acquired by the AI ​​model acquisition unit 316 with the virtual test terminal 410 when the number of user terminals 500 connected to the communication control unit 314 is less than a predetermined number. The test execution unit 318 may monitor the change in the number of user terminals 500 connected to the communication control unit 314 and perform the communication test when it determines that the number is less than a predetermined number. The test execution unit 318 may monitor the change in the number of user terminals 500 connected to the communication control unit 314 and perform the communication test when it determines that the state of being less than a predetermined number has continued for a predetermined time. This makes it possible to perform the communication test when the overall load on the base station device 310 is relatively low.

[0103] The results recording unit 320 records the test results performed by the test execution unit 318. When the test execution unit 318 performs a communication test targeting the virtual test terminal 410, it causes the results to be recorded in the results recording unit 320. For example, if the test execution unit 318 performs a communication test and is able to communicate with the virtual test terminal 410 without any problems occurring, it causes the results recording unit 320 to record a test result indicating that there were no problems with the use of the AI ​​model. For example, if the test execution unit 318 performs a communication test and a problem occurs with the virtual test terminal 410, it causes the results recording unit 320 to record a test result indicating that there were problems with the use of the AI ​​model.

[0104] As a specific example, if the test execution unit 318 is unable to communicate with the virtual test terminal 410, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that communication with the virtual test terminal 410 was not possible. As a specific example, if the test execution unit 318 is able to communicate with the virtual test terminal 410, but the communication quality is lower than a predetermined quality, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that the communication quality of communication with the virtual test terminal 410 has deteriorated. As a specific example, if the test execution unit 318 is able to communicate with the virtual test terminal 410, but the communication speed is lower than a predetermined speed, it uses the AI ​​model to record a test result in the result recording unit 320 indicating that the communication speed of communication with the virtual test terminal 410 has deteriorated.

[0105] The communication control unit 314 may transmit the test results recorded in the result recording unit 320 to the storage server 360. The communication control unit 314 may transmit the test results recorded in the result recording unit 320 to the management device 200. If the correction instruction unit 210 of the management device 200 indicates that there was a problem with the use of the AI ​​model, it instructs the model management unit 350 to correct the AI ​​model. For example, if the test results indicate that communication with the virtual test terminal 410 could not be established, the correction instruction unit 210 transmits an instruction to the model management unit 350 to correct the AI ​​model to resolve the problem of not being able to communicate with the virtual test terminal 410. For example, if the test results indicate that the communication quality of communication with the virtual test terminal 410 has deteriorated, the correction instruction unit 210 transmits an instruction to the model management unit 350 to correct the AI ​​model to improve the communication quality. For example, if the test results indicate that the communication speed with the virtual test terminal 410 has decreased, the correction instruction unit 210 sends an instruction to the model management unit 350 to modify the AI ​​model so that the communication speed improves.

[0106] Figure 12 schematically shows an example of the hardware configuration of a computer 1200 that functions as a management device 200, a base station device 310, or a model management unit 350. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to this embodiment, or to cause the computer 1200 to execute operations associated with the device according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0107] The computer 1200 according to this embodiment includes a CPU 1212, a GPU 1213, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0108] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in the RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0109] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from the DVD-ROM 1227, etc., and provides them to the storage device 1224. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

[0110] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 when activated. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0111] The program is provided on a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0112] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into the RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as the RAM 1214, storage device 1224, DVD-ROM 1227, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0113] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as a storage device 1224, a DVD drive 1226 (DVD-ROM 1227), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0114] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to the RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if a plurality of entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the plurality of entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0115] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0116] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0117] A computer-readable storage medium may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disk (DVD), Blu-ray® disk, memory stick, integrated circuit card, etc.

[0118] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and conventional procedural programming languages ​​such as the C programming language or similar programming languages.

[0119] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to a processor or programmable circuit of a general-purpose computer, special-purpose computer, or other programmable data processing device, so that the processor or programmable circuit of the programmable data processing device, such as a computer, can execute the instructions to generate means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), tablet computer, smartphone, workstation, server computer, general-purpose computer, or special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by each computer executing a part of the program and passing data during program execution between computers as needed.

[0120] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasks, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0121] By using the invention according to this embodiment, it becomes possible to appropriately test AI models before applying them to mobile communication services. This contributes to the stable provision and improvement of the quality of mobile communication services, and contributes to achieving at least one of the Sustainable Development Goals (SDGs) Goal 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation," and Goal 11, "Make cities and human settlements inclusive, safe, resilient and sustainable."

[0122] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0123] It should be noted that the execution order of operations, procedures, steps, and stages in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be performed in any order unless the output of a previous operation is used in a later operation. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is mandatory to perform the operations in that order.

[0124] 10 System, 20 Management infrastructure, 30 Distributed infrastructure, 40 Test equipment, 200 Management device, 202 Storage unit, 204 Management unit, 206 Result acquisition unit, 208 Confirmation instruction unit, 210 Correction instruction unit, 300 PF, 302 Rack, 310 Base station equipment, 312 Storage unit, 314 Communication control unit, 316 AI model acquisition unit, 318 Test execution unit, 320 Result recording unit, 322 Implementation unit, 330 Antenna unit, 332 Test antenna unit, 350 Model management unit, 360 Storage server, 400 Test terminal, 410 Virtual test terminal, 500 User terminal, 1200 Computer, 1210 Host controller, 1212 CPU, 1213 GPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / Output controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 Input / Output chip

Claims

1. A system comprising a base station device located within a distributed infrastructure, and a test terminal which is a test user terminal for testing mobile communication between the base station device and a user terminal, wherein the base station device includes an AI model acquisition unit for acquiring an AI model to be used for communication between the base station device and the user terminal, a test execution unit for performing a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal, and a result recording unit for recording the test results by the test execution unit.

2. The system according to claim 1, wherein the AI ​​model includes at least one of a model for channel estimation and a model for channel interpolation, and the test execution unit performs a communication test with the test terminal that performs at least one of channel estimation and channel interpolation using the AI ​​model.

3. The system according to claim 1 or 2, wherein the base station device has a function to generate a plurality of cells, and the test execution unit performs a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal for only some of the plurality of cells that can be generated.

4. The system according to any one of claims 1 to 3, wherein the system comprises a plurality of base station devices arranged within the distributed infrastructure, and the test execution unit of each of the plurality of base station devices performs a communication test with the test terminal using the AI ​​model acquired by the AI ​​model acquisition unit of each of the plurality of base station devices.

5. The system according to any one of claims 1 to 4, wherein the system comprises a plurality of test terminals, and the test execution unit uses the AI ​​model acquired by the AI ​​model acquisition unit to perform multiple communication tests targeting a different number of test terminals among the plurality of test terminals.

6. The system according to any one of claims 1 to 4, wherein the system comprises a plurality of test terminals corresponding to a plurality of user terminals that may be connected to the base station device, and the test execution unit performs a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with each of the plurality of test terminals.

7. The system according to any one of claims 1 to 6, wherein the test terminal is located within the distributed infrastructure, and the base station device communicates wirelessly with the test terminal using an antenna unit located within the distributed infrastructure.

8. The system according to any one of claims 1 to 7, wherein the base station device is located in a rack within the distributed infrastructure, and the test terminal is located in the rack in which the base station device is located.

9. The system according to any one of claims 1 to 7, wherein the test terminal is located outside the distributed infrastructure, and the base station device communicates wirelessly with the test terminal using an antenna unit located outside the distributed infrastructure.

10. The system according to any one of claims 1 to 6, wherein the test terminal is located within the distributed infrastructure, and the base station device communicates wirelessly with the test terminal using an antenna unit located outside the distributed infrastructure.

11. The system according to any one of claims 1 to 10, wherein the base station device has a communication control unit that communicates with a plurality of user terminals and provides mobile communication services to the plurality of user terminals, and the test execution unit performs a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal during a predetermined time period in which the number of user terminals communicating with the communication control unit is small.

12. The system according to any one of claims 1 to 10, wherein the base station device has a communication control unit that communicates with a plurality of user terminals and provides mobile communication services to the plurality of user terminals, and the test execution unit performs a communication test using the AI ​​model acquired by the AI ​​model acquisition unit with the test terminal when the number of user terminals communicating with the communication control unit is less than a predetermined number.

13. The system according to any one of claims 1 to 12, further comprising: a management device for managing the base station device; and a model management unit located within the distributed infrastructure and providing the AI ​​model to the base station device, wherein the management device includes: a result acquisition unit for acquiring the test results recorded in the result recording unit; and a modification instruction unit for instructing the model management unit to modify the AI ​​model when the test results indicate a malfunction in the use of the AI ​​model.

14. A base station device located within a distributed infrastructure, comprising: an implementation unit that implements a virtual test terminal which virtually realizes a test user terminal for testing communication between the base station device and a user terminal; an AI model acquisition unit that acquires an AI model to be used for communication between the base station device and the user terminal; a test execution unit that simulates and tests communication between the base station device and the virtual test terminal using the AI ​​model acquired by the AI ​​model acquisition unit; and a result recording unit that records the results of the test performed by the test execution unit.

15. A test method performed by a base station device located in a distributed infrastructure, comprising: an implementation step of implementing a virtual test terminal that virtually realizes a test user terminal for testing communication between the base station device and a user terminal; an AI model acquisition step of acquiring an AI model to be used for communication between the base station device and the user terminal; a test execution step of simulating and testing communication between the base station device and the virtual test terminal using the AI ​​model acquired in the AI ​​model acquisition step; and a result recording step of recording the test results in the test execution step.

16. A program for executing the following steps on a base station device located within a distributed infrastructure: an implementation step of implementing a virtual test terminal that virtually realizes a test user terminal for testing communication between the base station device and a user terminal; an AI model acquisition step of acquiring an AI model to be used for communication between the base station device and the user terminal; a test execution step of simulating and testing communication between the base station device and the virtual test terminal using the AI ​​model acquired in the AI ​​model acquisition step; and a result recording step of recording the test results in the test execution step.

Images