WO2024038556A1

WO2024038556A1 - Information processing device, information processing method, information processing system, computer-readable medium, and generation method

Info

Publication number: WO2024038556A1
Application number: PCT/JP2022/031253
Authority: WO
Inventors: 健夫大西; 英士高橋; 由明西川; 研次川口; 吉則渡辺; 雅之上田; 英城小塚; 瑠美松村; 克紀伊達
Original assignee: 日本電気株式会社
Priority date: 2022-08-18
Filing date: 2022-08-18
Publication date: 2024-02-22

Abstract

Provided is an information processing device (20) provided with: an acquisition unit (21) for acquiring values indicating the wireless state with respect to a plurality of user terminals that are present in the same base station area; a pre-processing unit (22) for adding the values indicating the wireless state of the respective user terminals acquired by the acquisition unit; and an identification unit (23) for identifying a setting of wireless communication with respect to a specific user terminal included in the plurality of user terminals, on the basis of the sum calculated by the pre-processing unit and the value which is acquired by the acquisition unit and which indicates the wireless state of the specific user terminal.

Description

Information processing device, information processing method, information processing system, computer readable medium, and generation method

The present disclosure relates to an information processing device, an information processing method, an information processing system, a computer-readable medium, and a generation method.

Determining various parameters related to wireless communication between a base station and a user terminal using machine learning (AI/ML) is being considered (for example, Patent Document 1).

Japanese Patent Application Publication No. 2022-105306

However, with the technology described in Patent Document 1, for example, various parameters related to wireless communication between a base station and a user terminal may not be appropriately determined.

In view of the above-mentioned problems, one of the purposes of the present disclosure is to provide a technology that can appropriately determine various parameters regarding wireless communication between a base station and a user terminal.

In a first aspect according to the present disclosure, there is provided an acquisition unit that acquires a value indicating a wireless state with each of a plurality of user terminals located in the same base station, and a wireless communication status of each user terminal acquired by the acquisition unit. a preprocessing unit that adds values indicating a state; an added value calculated by the preprocessing unit; and a value indicating a wireless state of a specific user terminal included in the plurality of user terminals acquired by the acquisition unit; Based on the above, there is provided an information processing apparatus including a specifying section that specifies wireless communication settings for the specific user terminal.

Further, in the second aspect of the present disclosure, a value indicating the wireless status with each of a plurality of user terminals located in the same base station is acquired, and the acquired value indicating the wireless status of each user terminal is added. and an information processing method for performing a process of specifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals. provided.

Further, a third aspect of the present disclosure includes a specific user terminal and an information processing device, and the information processing device monitors the wireless state of each of the plurality of user terminals located in the same base station. an acquisition unit that acquires a value indicating the wireless status of each user terminal; a preprocessing unit that adds the values indicating the wireless status of each user terminal acquired by the acquisition unit; and an additional value calculated by the preprocessing unit; provided is an information processing system, comprising: a value indicating a wireless state of the specific user terminal included in the plurality of user terminals; and a specifying unit that specifies wireless communication settings for the specific user terminal based on the be done.

Further, in a fourth aspect of the present disclosure, a value indicating the wireless status with each of a plurality of user terminals located in the same base station is acquired, and the acquired value indicating the wireless status of each user terminal is added. and a program that causes a computer to execute a process of specifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals. A non-transitory computer readable medium stored thereon is provided.

Further, in a fifth aspect of the present disclosure, a value indicating a wireless state with each of the first plurality of user terminals located in the first base station, and a value indicating the wireless state with each of the first plurality of user terminals located in the first base station, an acquisition unit that acquires a data set associated with information regarding wireless communication settings for one user terminal; a preprocessing unit that adds a value indicating the wireless state of each user terminal acquired by the acquisition unit; an additional value calculated by a preprocessing unit, a value indicating a wireless state of the first user terminal acquired by the acquisition unit, and information regarding wireless communication settings for the first user terminal acquired by the acquisition unit. Based on the sum of the values indicating the wireless state with each of the second plurality of user terminals located in the second base station, and the second user terminal included in the second plurality of user terminals. An information processing apparatus is provided that includes a value indicating a wireless state, and a generation unit that generates a learned model that specifies information regarding wireless communication settings for the second user terminal according to the value.

Further, in a sixth aspect of the present disclosure, a value indicating a wireless state with each of the first plurality of user terminals located in the first base station, and a value indicating the wireless state with each of the first plurality of user terminals located in the first base station, Obtain a dataset in which information related to wireless communication settings for one user terminal is associated, add the obtained values indicating the wireless status of each user terminal, and calculate the added value and the wireless status of the first user terminal. an added value of a value indicating a wireless state with each of a second plurality of user terminals located in the second base station, based on the value indicated and information regarding wireless communication settings for the first user terminal; generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to a value indicating a wireless state of a second user terminal included in the second plurality of user terminals; A method is provided.

Further, in a seventh aspect according to the present disclosure, a value indicating a wireless state with each of the first plurality of user terminals located in the first base station, and a value indicating the wireless state with each of the first plurality of user terminals located in the first base station, Obtain a dataset in which information related to wireless communication settings for one user terminal is associated, add the obtained values indicating the wireless status of each user terminal, and calculate the added value and the wireless status of the first user terminal. an added value of a value indicating a wireless state with each of a second plurality of user terminals located in the second base station, based on the value indicated and information regarding wireless communication settings for the first user terminal; a value indicating a wireless state of a second user terminal included in the second plurality of user terminals, and a process of generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to the second user terminal. A non-transitory computer-readable medium is provided that stores a program that causes a computer to execute the program.

According to one aspect, various parameters regarding wireless communication between a base station and a user terminal can be appropriately determined.

FIG. 1 is a diagram illustrating an example of the configuration of an information processing device that performs learning processing according to an embodiment. FIG. 1 is a diagram illustrating an example of the configuration of an information processing device that performs specific processing according to an embodiment. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. 1 is a diagram illustrating an example of the hardware configuration of each information processing device according to an embodiment. FIG. 5 is a flowchart illustrating an example of learning processing of the information processing device according to the embodiment. It is a diagram showing an example of a wireless communication DB according to the embodiment. It is a figure showing an example of post-preprocessing DB concerning an embodiment. 7 is a flowchart illustrating an example of identification processing of the information processing apparatus according to the embodiment.

The principles of the present disclosure are explained with reference to several exemplary embodiments. It is to be understood that these embodiments are described for illustrative purposes only and do not suggest limitations as to the scope of the disclosure, and to assist those skilled in the art in understanding and practicing the disclosure. The disclosure described herein may be implemented in a variety of ways other than those described below.
In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. has.
Embodiments of the present disclosure will be described below with reference to the drawings.

(Embodiment 1)
<Configuration>
<<Configuration of information processing device 10 that performs learning processing>>
With reference to FIG. 1, the configuration of an information processing apparatus 10 that performs learning processing according to an embodiment will be described. FIG. 1 is a diagram illustrating an example of the configuration of an information processing device 10 that performs learning processing according to an embodiment. The information processing device 10 includes an acquisition section 11, a preprocessing section 12, and a generation section 13. Each of these units may be realized by cooperation between one or more programs installed in the information processing device 10 and hardware such as a processor and a memory of the information processing device 10.

The acquisition unit 11 obtains a value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and wireless communication settings for the first user terminal included in the first plurality of user terminals. Get information about and associated datasets. The preprocessing unit 12 adds the values indicating the wireless state of each user terminal acquired by the acquisition unit 11. Note that the value indicating the wireless state may be, for example, a vector, an array, or a tensor composed of a plurality of values.

The generation unit 13 uses the added value calculated by the preprocessing unit 12 and the value indicating the wireless state of the first user terminal acquired by the acquisition unit 11 as explanatory variables, and generates the first user terminal acquired by the acquisition unit 11. A function (model) with information regarding wireless communication settings for the terminal as an objective variable is generated. Thereby, the generation unit 13 generates the sum of the values indicating the wireless state with each of the second plurality of user terminals located in the second base station and the second user included in the second plurality of user terminals. A model is generated that specifies information regarding wireless communication settings for the second user terminal according to a value indicating a wireless state of the terminal.

<<Configuration of information processing device 20 that performs identification (determination, inference, estimation, prediction, prediction) processing>>
Next, with reference to FIG. 2, the configuration of the information processing device 20 that performs the specific processing according to the embodiment will be described. FIG. 2 is a diagram illustrating an example of the configuration of an information processing device 20 that performs specific processing according to the embodiment. The information processing device 20 includes an acquisition section 21, a preprocessing section 22, and a specifying section 23. Each of these units may be realized by cooperation between one or more programs installed in the information processing device 20 and hardware such as a processor and a memory of the information processing device 20.

The acquisition unit 21 acquires a value indicating the wireless status with each of a plurality of user terminals located in the same base station. The preprocessing unit 22 adds the values indicating the wireless state of each user terminal acquired by the acquisition unit 21. The identifying unit 23 determines the wireless status of the specific user terminal based on the added value calculated by the preprocessing unit 22 and the value indicating the wireless state of the specific user terminal included in the plurality of user terminals acquired by the acquiring unit 21. Identify wireless communication settings.
(Embodiment 2)

Next, with reference to FIG. 3, the configuration of the information processing system 1 according to the embodiment will be described.
<System configuration>
FIG. 3 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. In the example of FIG. 3, the information processing system 1 includes an information processing device 10 and an information processing device 20. Note that the number of information processing devices 10 and information processing devices 20 is not limited to the example in FIG. 3. In addition, the information processing system 1 includes base stations 30-1, 30-2, . ). Note that N may be any natural number. In addition, the information processing system 1 includes user terminals 40-1, 40-2, . ). Note that M may be any natural number.

In the example of FIG. 3, the information processing device 10, the information processing device 20, and the base station 30 are connected to be able to communicate via the network N. Examples of the network N include, for example, a backhaul link, a core network, a LAN (Local Area Network), a bus, and the like.

Furthermore, the base station 30 and the user terminal 40 are connected so that they can communicate via wireless communication (access link) of the mobile communication system. Examples of mobile communication systems include 5th generation mobile communication system (5G), 6th generation mobile communication system (6G, Beyond 5G), 4th generation mobile communication system (4G), and 3rd generation mobile communication system ( 3G), wireless LAN, etc.

The information processing system 1 may be compliant with the specifications of the O-RAN (Open Radio Access Network) Alliance, for example. In this case, the information processing device 10 and the information processing device 20 may be included in a RIC (RAN (Radio Access Network) Intelligent Controller). In addition, RIC uses AI/ML (Artificial Intelligence/Machine Learning), for example, to identify RU (Radio Unit, radio equipment), DU (Distributed Unit, distributed station), and CU (Central Unit), which constitute the RAN. It may also be a controller that manages/controls nodes such as stations.

The RIC may, for example, provide wireless connections with different required quality for each user (for example, for each terminal, each bearer, or each session). In addition, the RIC can, for example, optimize RAN processing resources (for example, radio resources such as PRB (Physical Resource Block)) and wireless connection control (Beamforming, etc.) using multiple antennas (MIMO: Multi Input and Multi Output). good. Further, the RIC may optimize communication for each network slice (set of virtualized network resources), for example.

In this case, the information processing device 10 that performs the learning process is installed in a Non-RT-RIC (Non Real-time RIC) that is placed together with or near a central cloud station such as an OSS (Operation Support System). May be included. Further, the information processing device 20 that performs inference processing may be included in a Near-RT RIC (Near Realtime RIC) that is placed together with or near a node such as a CU, for example.

The base station 30 is a base station that has nodes such as RU, DU, and CU, and provides access links to the user terminals 40. The base station 30 may be configured as an integrated device including an RU, DU, and CU in the same housing.

Furthermore, the base station 30 may be, for example, a virtualized base station. In this case, the base station 30 may be configured as a separate device that includes at least one of the RU, DU, and CU in a separate housing, for example. In this case, the functions of at least one of the DU and CU may be realized by a server (computer) installed near the RU or by a program (software) running on a server on the cloud. Note that the base station 30 may be referred to as, for example, gNB (gNodeB, next Generation NodeB), eNB (eNodeB, evolved Node B), or the like.

The user terminal 40 is, for example, a smartphone, a tablet, an IoT (Internet of Things) device, a mobile object having a wireless communication function (for example, a vehicle, a drone, an airplane), a robot having a wireless communication function (for example, a factory robot, a home robot, etc.). robots) etc. The user terminal 40 may be referred to as, for example, UE (User Equipment).

<Hardware configuration>
FIG. 4 is a diagram showing an example of the hardware configuration of the information processing device 10 and the information processing device 20 according to the embodiment. Although the information processing device 10 will be described below as an example, the hardware configuration of the information processing device 20 may be the same as that of the information processing device 10. In the example of FIG. 4, the information processing device 10 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. These parts may be connected by a bus or the like. Memory 102 stores at least a portion of program 104. Communication interface 103 includes interfaces necessary for communication with other network elements.

When the program 104 is executed by the cooperation of the processor 101, the memory 102, etc., the computer 100 performs at least part of the processing of the embodiment of the present disclosure. Memory 102 may be of any type. Memory 102 may be, by way of non-limiting example, a non-transitory computer-readable storage medium. Memory 102 may also be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. Although only one memory 102 is shown in computer 100, there may be several physically different memory modules present in computer 100. Processor 101 may be of any type. Processor 101 may include one or more of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, by way of non-limiting example. Computer 100 may have multiple processors, such as application specific integrated circuit chips, that are time dependent on a clock that synchronizes the main processors.

Embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device.

The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. A computer program product includes computer-executable instructions, such as instructions contained in program modules, that are executed on a device on a target real or virtual processor to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or divided among program modules as desired in various embodiments. Machine-executable instructions of program modules can be executed locally or within distributed devices. In distributed devices, program modules can be located in both local and remote storage media.

Program code for implementing the methods of this disclosure may be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing device. When the program code is executed by a processor or controller, the functions/acts illustrated in the flowcharts and/or implementing block diagrams are performed. Program code can run entirely on a machine, partially on a machine, as a standalone software package, partially on a machine, partially on a remote machine, or entirely on a remote machine or server. Ru.

The program can be stored and provided to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media includes various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disk media, semiconductor memory, and the like. Magnetic recording media include, for example, flexible disks, magnetic tapes, hard disk drives, and the like. The magneto-optical recording medium includes, for example, a magneto-optical disk. Optical disc media include, for example, Blu-ray discs, CDs (Compact Discs)-ROMs (Read Only Memory), CD-Rs (Recordables), CD-RWs (ReWritables), and the like. Semiconductor memories include, for example, solid state drives, mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, RAMs (Random Access Memory), and the like. The program may also be provided to the computer on various types of temporary computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can provide the program to the computer via wired communication channels, such as electrical wires and fiber optics, or wireless communication channels.

<Processing>
＜＜Learning process＞＞
Next, with reference to FIGS. 5 to 8, an example of a learning process (a process for generating a learned model) of the information processing apparatus 10 according to the embodiment will be described. FIG. 5 is a flowchart illustrating an example of the learning process of the information processing device 10 according to the embodiment. FIG. 6 is a diagram showing an example of a wireless communication DB (Data Base) 601 according to the embodiment. FIG. 7 is a diagram showing an example of the preprocessed DB 401 according to the embodiment. The process in FIG. 5 may be executed, for example, when instructed by the administrator of the information processing device 10 or at a predetermined timing such as periodically. Note that the process in FIG. 5 may be executed for each of the uplink and downlink, for example. In this case, a trained model for uplink is generated and distributed by the process shown in FIG. 5 for uplink, and a trained model for downlink is generated and distributed by the process shown in FIG. 5 for downlink.

In step S101, the acquisition unit 11 acquires a data set for machine learning from the wireless communication DB 601. The wireless communication DB 601 may be recorded in a storage device inside the information processing device 10 or may be recorded in a storage device outside the information processing device 10.

In the example of FIG. 6, the wireless communication DB 601 includes values indicating the wireless status (wireless communication status) and wireless communication for a certain user terminal 40 (hereinafter also referred to as "learning target user terminal 40"). Contains a data set (collection) of configuration information and combinations (records). In the example of FIG. 6, the value indicating the radio state includes a value indicating the radio state of one base station 30 (first base station 30), which is the serving cell, and each of the plurality of user terminals 40. Note that the plurality of user terminals 40 include a user terminal 40 that is a learning target. Further, the value indicating the radio state includes a value indicating the radio state of each adjacent cell and a value indicating the radio state of the serving cell. The value indicating the wireless state may be information acquired (measured, calculated) by each base station 30 at a certain point in time. Note that the serving cell may be the base station 30 in which the user terminal 40 to be studied resides (registers its location). Further, the adjacent cell (neighbor cell) may be, for example, the base station 30 that may interfere with the serving cell.

The value indicating the wireless state of the user terminal 40 may be a vector value having multiple elements. Values indicating the wireless state of the user terminal 40 include, for example, changes in CQI (Channel Quality Indicator) at the user terminal 40, changes in retransmission rate for each MCS (Modulation and Coding Scheme), PRB utilization rate, At least one of information indicating values of various indicators such as radio wave quality indicators (for example, RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), etc.) and the amount of transmitted data may be included in the adjacent cell. Changes in CQI and changes in retransmission rate for each MCS may be, for example, time series data at specific time intervals (for example, tens of milliseconds to hundreds of milliseconds). The value indicating the wireless state of the user terminal 40 includes at least one of the values of various indicators such as CQI change, retransmission rate change for each MCS, PRB utilization rate, radio wave quality index of adjacent cells, and amount of transmitted data; A value calculated as a feature amount based on a learned model such as a neural network (NN) may be included. In this case, the trained model may be generated, for example, by supervised learning, or by unsupervised learning such as an autoencoder for dimension compression.

The value indicating the wireless state of the adjacent cell may include, for example, information indicating the PRB (Physical Resource Block) utilization rate at the base station 30, which is the adjacent cell. The value indicating the radio state of the serving cell includes, for example, information indicating at least one of the PRB utilization rate at the base station 30, which is the serving cell, and the number of active UEs (the number of user terminals 40 communicating using the serving cell). may be included.

The information on the wireless communication settings for the learning target user terminal 40 is the correct label (correct value) in the machine learning record. The information on the wireless communication settings for the user terminal 40 to be learned may be based on wireless communication quality requirements such as delay ( The configuration information that actually satisfies the communication requirements) may be determined. In this case, the log data may include information indicating the buffer queuing amount and retransmission rate in at least one of the learning target user terminal 40 and the serving cell base station 30. Alternatively, an index value indicating the quality of the settings may be calculated based on the log data, and learning (reinforcement learning) may be performed to select an action that increases the index value. In this case, the index value may be given a larger value, for example, as the queuing amount or retransmission rate is smaller. Further, the information on the wireless communication settings for the user terminal 40 to be learned may be determined to be a setting that theoretically satisfies the requirements for wireless communication quality such as delay, for example, based on a simulation or the like. Further, the information on the wireless communication settings for the user terminal 40 to be learned may be manually determined (assigned, registered, set) by, for example, the administrator of the information processing device 10.

The wireless communication settings for the learning target user terminal 40 may include, for example, an MCS setting value that indicates the number of useful bits that can be transmitted with one symbol. In this case, the set value may be, for example, an offset value with respect to a normally used value. In this case, for example, MCS Index 15 is normally used, and if the set offset value is 3, it is set to MCS Index 12 (=15-3).

Furthermore, the wireless communication settings for the learning target user terminal 40 may include, for example, a wireless communication scheduler parameter indicating at least one of the ratio of the amount of wireless resources and the amount of allocation of transmission opportunities. Furthermore, the wireless communication settings for the learning target user terminal 40 may include, for example, setting the upper limit of the spatial multiplexing number of MIMO (Multiple-Input and Multiple-Output).

Next, the preprocessing unit 12 divides (classifies) the values of at least some data items included in each record for machine learning acquired by the acquisition unit 11 into groups (step S102).

(Division of user terminals 40 into groups)
Here, the preprocessing unit 12 may, for example, form a group of values indicating the wireless state of each of the plurality of user terminals 40 into one group, or may divide (classify) each group of user terminals 40. . Specifically, when dividing the user terminals 40 into groups, the preprocessing unit 12 calculates, for example, the communication requirements of the user terminals 40, the magnitude of wireless quality fluctuation, and the received radio field strength (hereinafter referred to as "communication requirements etc." as appropriate). ) may identify the group to which each user terminal 40 belongs.

The communication requirements may include, for example, requirements such as delay, throughput, and packet loss rate. Further, the communication requirements may be determined (specified, estimated) based on the type of application that communicates with the user terminal 40, for example. In this case, the types of applications include, for example, real-time video, real-time audio, non-real-time video, non-real-time audio, notification of status information of IoT devices, etc., and usage of wireless communication on the user terminal 40, such as control of IoT devices, etc. The type may be included depending on the type.

Furthermore, the communication requirements may be determined (specified, estimated) based on, for example, 5QI (5G QoS (Quality of Service) Identifier). Note that the 5QI may include, for example, values indicating QoS characteristics such as priority level, packet delay, and packet error rate.

The magnitude of wireless quality fluctuation may be, for example, the variance of an index such as CQI that indicates the quality of wireless communication. The received radio field intensity may be, for example, the average value of the received radio field strengths at the user terminal 40.

Information such as communication requirements may be obtained from an external application server, for example. In this case, the information processing device 10 may obtain information from the external application server via the Internet or the like, for example. Further, the external application server may be included in a Non-RT-RIC or a Near-RT RIC.

Additionally, information such as communication requirements may be analyzed based on communication packets of the user terminal 40. In this case, for example, the type of application of the user terminal 40 that performs periodic communication may be determined to be notification of status information of an IoT device or the like. Alternatively, the communication requirements may be determined based on the communication cycle. Furthermore, it may be determined that the type of application is real-time video or the like based on the header of the communication packet. Further, information such as communication requirements may be notified from the user terminal 40.

(dividing adjacent cells into groups)
Further, the preprocessing unit 12 may, for example, form a group of values indicating the radio state of each adjacent cell into one group, or may divide (classify) the value group for each group of adjacent cells. Specifically, when dividing into groups of neighboring cells, the preprocessing unit 12 may specify the group to which each neighboring cell belongs, for example, depending on the magnitude of interference with the serving cell.

Next, the preprocessing unit 12 of the information processing device 10 performs preprocessing to aggregate the plurality of values of the data items divided into groups for each group, and stores the preprocessed machine learning data in the preprocessed DB 701. A data set is recorded (step S103). Note that the preprocessed DB 701 may be recorded in a storage device inside the information processing device 10 or may be recorded in a storage device outside the information processing device 10.

Here, for example, the preprocessing unit 12 may aggregate the data included in each record by adding (eg, totaling) the data of each group divided in step S102 for each group. In the example of FIG. 7, the preprocessed DB 701 contains values indicating the radio status aggregated for each group, values indicating the radio status of the serving cell, and information on the wireless communication settings for the user terminal 40 to be learned. Contains a dataset (collection) of records containing combinations of .

In the example of FIG. 7, the value indicating the wireless status aggregated for each group includes the total value of the values indicating the wireless status of each user terminal 40 included in the first group, and the total value of the values indicating the wireless status of each user terminal 40 included in the second group. The total value of the values indicating the radio status of 40 cells and the total value of the values indicating the radio status of each adjacent cell are included.

In the example of FIG. 7, the user terminals 40 are divided into a first group and a second group, and adjacent cells are considered to be one group. The first group may be a group that has a relatively large influence (compared to the second group) on the wireless communication settings for the user terminal 40 to be learned. In this case, the first group may be, for example, a group with relatively strict communication requirements (eg, requiring at least one of low delay and high throughput). Further, the first group may be, for example, a group in which the magnitude of wireless quality fluctuation is relatively large. Further, the first group may be, for example, a group whose radio field intensity is relatively low. Further, the first group may be a group of user terminals 40 whose score is higher than a threshold value, for example, as the communication requirements are relatively strict, the magnitude of wireless quality fluctuation is large, and the radio field intensity is small.

The preprocessing unit 12 may use the sum of the values indicating the wireless status of the first granularity of each user terminal 40 included in the first group as the value indicating the wireless status aggregated in the first group. Further, the preprocessing unit 12 calculates the sum of the values indicating the wireless state of the second granularity coarser than the first granularity of each user terminal included in the second group, which indicates the wireless state aggregated in the second group. May be used as a value. Here, coarse granularity includes, for example, a small number of data elements (dimensions). In this case, the preprocessing unit 12 uses time-series data obtained by adding values indicating the wireless status of each user terminal 40 included in the first group at each time point as a value indicating the wireless status aggregated in the first group. Good too. In this case, the preprocessing unit 12 generates, for example, time-series data obtained by adding the CQI values of each user terminal 40 included in the first group at each time point, and the retransmission rate for each MCS at each time point. At least one of the time series data obtained by adding the values at each time point may be calculated.

Furthermore, the preprocessing unit 12 may use the sum of the average values of the values indicating the wireless status of each user terminal included in the second group as a value indicating the wireless status aggregated in the second group. In this case, the preprocessing unit 12 calculates, for example, the sum of the average values of the CQI of each user terminal 40 included in the second group at each point in time, and the value of the retransmission rate at each point in time for each MCS. At least one of the values obtained by adding the average values may be calculated. This makes it possible to speed up the learning process.

Next, the generation unit 13 of the information processing device 10 generates a learned model by performing learning based on the preprocessed machine learning data set recorded in the preprocessed DB 701 (step S104). . Here, the generation unit 13 may perform supervised learning for at least one of the classification problem and the regression problem. In this case, the generation unit 13 uses a value indicating the radio state aggregated for each group and a value indicating the radio state of the serving cell as explanatory variables (input variables, independent variables), and uses the radio Machine learning is performed using information regarding communication settings as objective variables (correct label, response variable, dependent variable).

When performing supervised learning on a classification problem, the information processing device 10 may perform machine learning using, for example, a neural network (NN), a decision tree, a support vector machine (SVM), or logistic regression. good.

When performing supervised learning for a regression problem, the information processing device 10 uses, for example, a neural network (NN), a recurrent neural network (RNN), or a general regression neural network (General Regression Neural Network). , Random Forest, or machine learning using linear regression such as the least squares method.

Next, the generation unit 13 transmits (distributes) the generated trained model to the information processing device 20 (step S105). As a result, the learned model is recorded (installed) in the information processing device 20.

(others)
A case will be considered in which machine learning is performed based on information recorded in the wireless communication DB 601 without performing the preprocessing in step S103. In this case, for example, a value indicating the wireless status of each user terminal 40 and a value indicating the wireless status of each adjacent cell are also used as explanatory variables. Here, due to the structure of a model such as a neural network, the learning results will differ depending on the order of data input during learning.

For example, different learning may occur when the user terminals 40-1, 40-2, . . . A completed model is generated. Regarding the wireless communication settings for the user terminals 40 to be learned, it is considered that there is no particular significance in the order in which the information of each user terminal 40 is input. Therefore, the fact that the results of machine learning differ depending on the input order suggests that the inference accuracy may be relatively low, and it is possible that appropriate wireless settings may not be possible depending on the input order. Conceivable. Furthermore, since the number of input data when performing inference processing is a variable number (not a fixed number), it is relatively difficult to handle with a normal machine learning model.

On the other hand, in the embodiment of the present disclosure described above, since the added values for each group of one or more are input to a neural network, etc., it is possible to eliminate differences in calculation results caused by differences in the input order as in the comparative example. can. Therefore, for example, the learning time can be shortened compared to the case where learning is performed for each input order. Furthermore, the inference time can be reduced compared to the case where inference is made using the average of the results of inference for each input order. Furthermore, inference can be made with relatively high accuracy using a model with a relatively small number of parameters. Furthermore, since the number of parameters can be reduced, the processing load for learning and inference can be reduced.

<<Specific phase>>
Next, with reference to FIG. 8, an example of the identification process of the information processing apparatus 20 according to the embodiment will be described. FIG. 8 is a flowchart illustrating an example of the identification process of the information processing device 20 according to the embodiment. The process in FIG. 8 may be executed, for example, at a predetermined timing such as periodically (for example, every second), or at a timing such as when at least a part of the explanatory variables changes. In the following, an example of determining the wireless communication settings for the user terminal 40 (hereinafter also referred to as "user terminal 40 to be configured" as appropriate) located within the range (location registration) of the base station 30-1 (serving cell) I will explain about it. In addition, user terminals 40-1 to 40-K (K is a natural number smaller than M) are located (location registered) to base station 30-1, and base stations 30-2 to L (L is smaller than N) are located in base station 30-1. An example will be explained in which a small natural number) is a neighboring cell of the base station 30-1. Note that the process in FIG. 8 may be executed for each of the uplink and downlink, for example. Further, the process in FIG. 8 may be executed for each user terminal 40 residing in the serving cell, for example.

In step S201, the acquisition unit 21 acquires a value indicating the wireless state. The value indicating the radio state includes a value indicating the radio state of each of the plurality of user terminals 40 including the user terminal 40 to be configured, a value indicating the radio state of each adjacent cell, and a value indicating the radio state of the serving cell. It may be The value indicating the wireless state may be information acquired (measured, calculated) by each base station 30 at a certain point in time.

Subsequently, the preprocessing unit 22 divides (classifies) the information acquired by the acquisition unit 21 into groups (step S202). Here, the preprocessing unit 22 may divide at least one of the user terminal 40 and the adjacent cell into groups, for example, by a process similar to the process of step S102 in FIG. 5.

In this case, the preprocessing unit 22 may, for example, form a group of values indicating the wireless state of each of the plurality of user terminals 40 into one group, or may divide it into each group of user terminals 40. Further, the preprocessing unit 22 may, for example, form a group of values indicating the radio state of each adjacent cell into one group, or may divide the value group into each group of adjacent cells.

Next, the preprocessing unit 22 of the information processing device 20 performs preprocessing to aggregate the values indicating the wireless state divided into groups for each group (step S203). Here, the preprocessing unit 22 may aggregate the data of each divided group by adding (for example, summing) the data of each divided group, for example, by a process similar to the process of step S103 in FIG.

The preprocessing unit 22 may use the sum of the values indicating the wireless status of the first granularity of each user terminal 40 included in the first group as the value indicating the wireless status aggregated in the first group. Further, the preprocessing unit 12 calculates the sum of the values indicating the wireless state of the second granularity coarser than the first granularity of each user terminal included in the second group, which indicates the wireless state aggregated in the second group. May be used as a value. In this case, the preprocessing unit 22 uses time-series data obtained by adding values indicating the wireless status of each user terminal 40 included in the first group at each time point as a value indicating the wireless status aggregated in the first group. Good too. In this case, the preprocessing unit 22 calculates, for example, the value of the CQI of each user terminal 40 included in the first group at each point in time, or the value of the retransmission rate for each MCS at each point of time. The series data may be a value indicating the wireless state aggregated into the first group. In this case, the preprocessing unit 22 may use the sum of the average values of the values indicating the wireless status of each user terminal included in the second group as a value indicating the wireless status aggregated in the second group. The preprocessing unit 22 adds the average value of the CQI of each user terminal 40 included in the second group at each point in time, or adds the average value of the retransmission rate for each MCS at each point in time. The value may be a value indicating the wireless state aggregated into the second group. This makes it possible to speed up inference processing. Note that the wireless status of each user terminal 40 included in the second group may be acquired (measured) at coarser intervals than the wireless status of each user terminal 40 included in the first group.

Next, the specifying unit 23 determines the wireless settings for the user terminal 40 to be configured, based on the preprocessed inference data set and the trained model generated by the information processing device 10 in the process shown in FIG. Communication settings are specified (determined, inferred, estimated, predicted, predicted) (step S204).

Subsequently, the specifying unit 23 transmits information indicating the wireless communication settings for the specified user terminal 40 to be set to the base station 30-1 (step S205). Note that, based on the information received from the information processing device 20, the base station 30-1 transmits wireless communication to the user terminal 40 to be configured and at least one of the base station 30-1 to the user terminal 40 to be configured. You may also make settings related to this.

(Example of speeding up processing of common parts)
After the information processing apparatus 20 executes the processes from step S201 to step S203 in FIG. 8, the information processing apparatus 20 may record the execution results of each process. Then, the processes from step S204 to step S205 in FIG. 8 may be executed for each of the user terminals 40-1 to 40-K, which are the user terminals 40 to be set. Thereby, the processing speed can be increased compared to the case where the processing from step S201 to step S205 in FIG. 8 is performed for each user terminal 40, respectively.

<Modified example>
Although each of the information processing device 10 and the information processing device 20 may be included in one housing, the information processing device 10 and the information processing device 20 of the present disclosure are not limited to this. Each section of the information processing device 10 and the information processing device 20 may be realized by cloud computing configured by, for example, one or more computers. Further, at least a portion of the information processing device 10, the information processing device 20, and the base station 30 may be realized by an integrated device. Each of the information processing device 10 and the information processing device 20 as described above is also included in an example of the “information processing device” of the present disclosure.

Note that the present disclosure is not limited to the above embodiments, and can be modified as appropriate without departing from the spirit.

Part or all of the above embodiments may be described as in the following additional notes, but are not limited to the following.
(Additional note 1)
an acquisition unit that acquires a value indicating a wireless state with each of a plurality of user terminals located in the same base station;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
Based on the added value calculated by the preprocessing unit and the value indicating the wireless state of the specific user terminal included in the plurality of user terminals acquired by the acquisition unit, wireless communication to the specific user terminal is performed. A specific part that specifies settings;
An information processing device having:
(Additional note 2)
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculating the sum of values indicating the wireless state of a first granularity of each user terminal included in the second group, and calculating the sum of the values indicating the radio state of a second granularity coarser than the first granularity of each user terminal included in the second group;
The information processing device according to supplementary note 1.
(Additional note 3)
The preprocessing unit generates time-series data obtained by adding the CQI (Channel Quality Indicator) values of each user terminal included in the first group at each time point, and retransmissions for each MCS (Modulation and Coding Scheme). a value obtained by adding at least one of the time-series data obtained by adding the values of the CQI at each point in time for each point in time, and adding the average value of the CQI values at each point in time of each user terminal included in the second group; Calculating at least one of the sums of the average values of the retransmission rates for each MCS at each point in time;
The information processing device according to supplementary note 2.
(Additional note 4)
The acquisition unit acquires a value indicating a wireless state of each of a plurality of neighboring cells with respect to the base station,
The preprocessing unit adds values indicating the wireless state of each adjacent cell acquired by the acquisition unit.
The information processing device according to supplementary note 1 or 2.
(Appendix 5)
The value indicating the radio state of each of the plurality of neighboring cells includes information indicating a PRB (Physical Resource Block) utilization rate in each neighboring cell.
The information processing device according to appendix 4.
(Appendix 6)
The identifying unit identifies wireless communication settings for the specific user terminal based on at least one of a PRB (Physical Resource Block) utilization rate at the base station and the number of user terminals communicating at the base station. ,
The information processing device according to supplementary note 1 or 2.
(Appendix 7)
The wireless communication settings for the specific user terminal include MCS (Modulation and Coding Scheme) settings, wireless communication scheduler parameters, and MIMO (Multiple-Input and Multiple-Output) spatial multiplexing upper limit settings. contains at least one
The information processing device according to supplementary note 1.
(Appendix 8)
Obtain a value indicating the wireless status with each of multiple user terminals located in the same base station,
Add the obtained values indicating the wireless status of each user terminal,
identifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals;
An information processing method for performing processing.
(Appendix 9)
It has a specific user terminal and an information processing device,
The information processing device includes:
an acquisition unit that acquires a value indicating a wireless state with each of a plurality of user terminals located in the same base station;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
Wireless communication to the specific user terminal based on the added value calculated by the preprocessing unit and the value indicating the wireless state of the specific user terminal included in the plurality of user terminals acquired by the acquisition unit. a specific part that specifies the settings of the
has,
Information processing system.
(Appendix 10)
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculating time-series data in which values indicating the wireless state of each user terminal included in the second group are added at each time point, and calculating an added value of the average value of the values indicating the wireless state of each user terminal included in the second group;
The information processing system described in Appendix 9.
(Appendix 11)
Obtain a value indicating the wireless status with each of multiple user terminals located in the same base station,
Add the obtained values indicating the wireless status of each user terminal,
identifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals;
A non-transitory computer-readable medium that stores a program that causes a computer to perform a process.
(Appendix 12)
A value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. an acquisition unit that acquires the associated dataset;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
The additional value calculated by the preprocessing unit, the value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the wireless communication settings for the first user terminal acquired by the acquisition unit. Based on the information and
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and a generation unit that generates a trained model that specifies information regarding wireless communication settings for the second user terminal according to the above.
An information processing device having:
(Appendix 13)
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculate the sum of values indicating the wireless state of a first granularity of each user terminal included in the second group;
The generation unit generates each additional value calculated by the preprocessing unit, a value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the first user terminal acquired by the acquisition unit. Based on the information regarding the wireless communication settings for
A sum of values indicating the wireless state of each user terminal included in the first group among the second plurality of user terminals, and each user included in the second group among the second plurality of user terminals. Regarding the setting of wireless communication for the second user terminal according to the sum of the values indicating the wireless state of the first granularity of the terminal and the value indicating the wireless state of the second user terminal of the second granularity. Generate a trained model that identifies information,
The information processing device according to appendix 12.
(Appendix 14)
The preprocessing unit generates time-series data obtained by adding the CQI (Channel Quality Indicator) values of each user terminal included in the first group at each time point, and retransmissions for each MCS (Modulation and Coding Scheme). a value obtained by adding at least one of the time-series data obtained by adding the values of the CQI at each point in time for each point in time, and adding the average value of the CQI values at each point in time of each user terminal included in the second group; Calculating at least one of the sums of the average values of the retransmission rates for each MCS at each point in time;
The information processing device according to appendix 13.
(Appendix 15)
The acquisition unit acquires a value indicating a wireless state of each of a plurality of neighboring cells with respect to the first base station,
The preprocessing unit adds values indicating the wireless state of each adjacent cell acquired by the acquisition unit,
The generation unit generates each additional value calculated by the preprocessing unit, a value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the first user terminal acquired by the acquisition unit. Based on the information regarding the wireless communication settings for
an added value of 1 or more of the values indicating the wireless state of the second plurality of user terminals; an added value of the values indicating the wireless state of each of the plurality of neighboring cells with respect to the second base station; and the second generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to a value indicating a wireless state of the user terminal;
The information processing device according to

appendix

12 or 13.
(Appendix 16)
The value indicating the radio state of each of the plurality of neighboring cells includes information indicating a PRB (Physical Resource Block) utilization rate in each neighboring cell.
The information processing device according to appendix 15.
(Appendix 17)
The generation unit generates the learned model based on at least one of a PRB (Physical Resource Block) utilization rate at the first base station and the number of user terminals communicating with the first base station.
The information processing device according to

appendix

12 or 13.
(Appendix 18)
The wireless communication settings for the first user terminal include MCS (Modulation and Coding Scheme) setting values, wireless communication scheduler parameters, and MIMO (Multiple-Input and Multiple-Output) spatial multiplexing upper limit settings. Contains at least one of
The information processing device according to appendix 12.
(Appendix 19)
A value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. Get the associated dataset,
Add the obtained values indicating the wireless status of each user terminal,
Based on the added value, a value indicating the wireless state of the first user terminal, and information regarding wireless communication settings for the first user terminal,
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to
Generation method.
(Additional note 20)
A value indicating the wireless status with each of the first plurality of user terminals located in the area of the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. Get the associated dataset,
Add the obtained values indicating the wireless status of each user terminal,
Based on the added value, a value indicating the wireless state of the first user terminal, and information regarding wireless communication settings for the first user terminal,
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to
A non-transitory computer-readable medium that stores a program that causes a computer to perform a process.

1 Information processing system 10 Information processing device 11 Acquisition unit 12 Preprocessing unit 13 Generation unit 20 Information processing device 21 Acquisition unit 22 Preprocessing unit 23 Identification unit 30 Base station 40 User terminal

Claims

an acquisition unit that acquires a value indicating a wireless state with each of a plurality of user terminals located in the same base station;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
Based on the added value calculated by the preprocessing unit and the value indicating the wireless state of the specific user terminal included in the plurality of user terminals acquired by the acquisition unit, wireless communication to the specific user terminal is performed. A specific part that specifies settings;
An information processing device having:
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculating the sum of values indicating the wireless state of a first granularity of each user terminal included in the second group, and calculating the sum of the values indicating the radio state of a second granularity coarser than the first granularity of each user terminal included in the second group;
The information processing device according to claim 1.
The preprocessing unit generates time-series data obtained by adding the CQI (Channel Quality Indicator) values of each user terminal included in the first group at each time point, and retransmissions for each MCS (Modulation and Coding Scheme). a value obtained by adding at least one of the time-series data obtained by adding the values of the CQI at each point in time for each point in time, and adding the average value of the CQI values at each point in time of each user terminal included in the second group; Calculating at least one of the sums of the average values of the retransmission rates for each MCS at each point in time;
The information processing device according to claim 2.
The acquisition unit acquires a value indicating a wireless state of each of a plurality of neighboring cells with respect to the base station,
The preprocessing unit adds values indicating the wireless state of each adjacent cell acquired by the acquisition unit.
The information processing device according to claim 1 or 2.
The value indicating the radio state of each of the plurality of neighboring cells includes information indicating a PRB (Physical Resource Block) utilization rate in each neighboring cell.
The information processing device according to claim 4.
The identifying unit identifies wireless communication settings for the specific user terminal based on at least one of a PRB (Physical Resource Block) utilization rate at the base station and the number of user terminals communicating at the base station. ,
The information processing device according to claim 1 or 2.
The wireless communication settings for the specific user terminal include MCS (Modulation and Coding Scheme) settings, wireless communication scheduler parameters, and MIMO (Multiple-Input and Multiple-Output) spatial multiplexing upper limit settings. contains at least one
The information processing device according to claim 1.
Obtain a value indicating the wireless status with each of multiple user terminals located in the same base station,
Add the obtained values indicating the wireless status of each user terminal,
identifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals;
An information processing method for performing processing.
It has a specific user terminal and an information processing device,
The information processing device includes:
an acquisition unit that acquires a value indicating a wireless state with each of a plurality of user terminals located in the same base station;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
Wireless communication to the specific user terminal based on the added value calculated by the preprocessing unit and the value indicating the wireless state of the specific user terminal included in the plurality of user terminals acquired by the acquisition unit. a specific part that specifies the settings of the
has,
Information processing system.
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculating time-series data in which values indicating the wireless state of each user terminal included in the second group are added at each time point, and calculating an added value of the average value of the values indicating the wireless state of each user terminal included in the second group;
The information processing system according to claim 9.
Obtain a value indicating the wireless status with each of multiple user terminals located in the same base station,
Add the obtained values indicating the wireless status of each user terminal,
identifying wireless communication settings for the specific user terminal based on the added value and a value indicating a wireless state of the specific user terminal included in the plurality of user terminals;
A non-transitory computer-readable medium that stores a program that causes a computer to perform a process.
A value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. an acquisition unit that acquires the associated dataset;
a preprocessing unit that adds values indicating the wireless state of each user terminal acquired by the acquisition unit;
The additional value calculated by the preprocessing unit, the value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the wireless communication settings for the first user terminal acquired by the acquisition unit. Based on the information and
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and a generation unit that generates a trained model that specifies information regarding wireless communication settings for the second user terminal according to the above.
An information processing device having:
The preprocessing unit identifies a group to which each user terminal belongs based on at least one of the communication requirements of each user terminal, the magnitude of wireless quality fluctuation, and the received radio field strength, and identifies each user terminal included in the first group. calculate the sum of values indicating the wireless state of a first granularity of each user terminal included in the second group;
The generation unit generates each additional value calculated by the preprocessing unit, a value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the first user terminal acquired by the acquisition unit. Based on the information regarding the wireless communication settings for
A sum of values indicating the wireless state of each user terminal included in the first group among the second plurality of user terminals, and each user included in the second group among the second plurality of user terminals. Regarding the setting of wireless communication for the second user terminal according to the sum of the values indicating the wireless state of the first granularity of the terminal and the value indicating the wireless state of the second user terminal of the second granularity. Generate a trained model that identifies information,
The information processing device according to claim 12.
The preprocessing unit generates time-series data obtained by adding the CQI (Channel Quality Indicator) values of each user terminal included in the first group at each time point, and retransmissions for each MCS (Modulation and Coding Scheme). a value obtained by adding at least one of the time-series data obtained by adding the values of the CQI at each point in time for each point in time, and adding the average value of the CQI values at each point in time of each user terminal included in the second group; Calculating at least one of the sums of the average values of the retransmission rates for each MCS at each point in time;
The information processing device according to claim 13.
The acquisition unit acquires a value indicating a wireless state of each of a plurality of neighboring cells with respect to the first base station,
The preprocessing unit adds values indicating the wireless state of each adjacent cell acquired by the acquisition unit,
The generation unit generates each additional value calculated by the preprocessing unit, a value indicating the wireless state of the first user terminal acquired by the acquisition unit, and the first user terminal acquired by the acquisition unit. Based on the information regarding the wireless communication settings for
an added value of 1 or more of the values indicating the wireless state of the second plurality of user terminals; an added value of the values indicating the wireless state of each of the plurality of neighboring cells with respect to the second base station; and the second generating a trained model that specifies information regarding wireless communication settings for the second user terminal according to a value indicating a wireless state of the user terminal;
The information processing device according to claim 12 or 13.
The value indicating the radio state of each of the plurality of neighboring cells includes information indicating a PRB (Physical Resource Block) utilization rate in each neighboring cell.
The information processing device according to claim 15.
The generation unit generates the learned model based on at least one of a PRB (Physical Resource Block) utilization rate at the first base station and the number of user terminals communicating with the first base station.
The information processing device according to claim 12 or 13.
The wireless communication settings for the first user terminal include MCS (Modulation and Coding Scheme) setting values, wireless communication scheduler parameters, and MIMO (Multiple-Input and Multiple-Output) spatial multiplexing upper limit settings. Contains at least one of
The information processing device according to claim 12.
A value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. Get the associated dataset,
Add the obtained values indicating the wireless status of each user terminal,
Based on the added value, a value indicating the wireless state of the first user terminal, and information regarding wireless communication settings for the first user terminal,
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and generating a trained model that specifies information regarding wireless communication settings for the second user terminal in accordance with.
Generation method.
A value indicating the wireless status with each of the first plurality of user terminals located in the first base station, and information regarding wireless communication settings for the first user terminal included in the first plurality of user terminals. Get the associated dataset,
Add the obtained values indicating the wireless status of each user terminal,
Based on the added value, a value indicating the wireless state of the first user terminal, and information regarding wireless communication settings for the first user terminal,
The sum of the values indicating the wireless status with each of the second plurality of user terminals located in the second base station, and the value indicating the wireless status of the second user terminal included in the second plurality of user terminals. and generating a trained model that specifies information regarding wireless communication settings for the second user terminal in accordance with.
A non-transitory computer-readable medium that stores a program that causes a computer to perform a process.