Information processing device and program

Abstract

An information processing device (11) comprises: an acquisition unit (31) that acquires position information of first and second user terminals included among a plurality of user terminals; a calculation unit (32) that calculates a correlation between the first user terminal and the second user terminal; a correction unit (33) that corrects the correlation on the basis of the output of a trained model (M); and a determination unit (34) that determines whether to allocate the second user terminal to the same group as the first user terminal on the basis of the corrected correlation.

Description

Information processing device and program

[0001] The present invention relates to an information processing device and a program.

[0002] In wireless communication using a MIMO (Multiple Input Multiple Output) system, spatial multiplexing allows multiple transmission signals to be simultaneously transmitted using the same frequency band. Various documents have been conventionally known regarding spatial multiplexing of transmission signals (for example, Patent Document 1).

[0003] Japanese Patent Application Publication No. 2023-4898

[0004] In MIMO, it is known that when the distance between receiving antennas is short, the correlation between the antennas increases and communication capacity decreases. Therefore, it is desirable to pair the receiving communication devices so that the transmission signals to the receiving communication devices that are close to each other are not spatially multiplexed.

[0005] The location of a communication device such as a user terminal (UE) is acquired based on information collected using uplink (uplink) communication. In the frame configuration of communication with the user terminal, uplink communication is performed at a predetermined SRS (Sounding Reference Signal) period, and downlink (downlink) communication slots are inserted between uplink communication slots. Therefore, depending on the movement of the receiving user terminal during the uplink SRS period, there is a risk that pairing will not be performed properly.

[0006] An information processing device according to one aspect of the present invention is part of a technology for improving the efficiency and performance of a radio access network (RAN) by utilizing the technical fields of AI / ML (artificial intelligence / machine learning). The information processing device according to one aspect of the present invention aims to estimate the movement tendency of a receiving user terminal and appropriately pair the receiving user terminal. For example, a technology such as RIC (RAN Intelligent Controller) can be used to estimate the movement tendency of the receiving user terminal.

[0007] In order to solve the above problem, an information processing device according to the present invention is used in a radio access network in which, when a signal is transmitted from a base station to a plurality of user terminals connected to the base station, transmission signals to user terminals assigned to the same group among the plurality of user terminals are spatially multiplexed, and the information processing device comprises: an acquisition unit that acquires location information of a first and second user terminal included in the plurality of user terminals; a calculation unit that calculates a correlation between the first user terminal and the second user terminal; a correction unit that corrects the correlation based on the output of a trained model constructed by machine learning; and a decision unit that decides whether to assign the second user terminal to the same group as the first user terminal based on the correlation corrected by the correction unit, wherein the input of the trained model is the location information of the first and second user terminals, and the output of the trained model is information regarding the movement tendencies of the first and second user terminals.

[0008] The information processing device according to each aspect of the present invention may be realized by a computer. In this case, the information processing device program that realizes the information processing device on a computer by causing the computer to operate as each part (software element) of the information processing device, and the computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention.

[0009] According to the present invention, it is possible to properly pair a receiving user terminal.

[0010] While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments and is not to be limited to the disclosed exemplary embodiments.

[0011] (Radio Access Network) Fig. 1 is a diagram showing an example of the configuration of a radio access network according to an embodiment of the present invention. The radio access network N shown in Fig. 1 includes, for example, a base station 1 that complies with the standard of a fifth-generation or later-generation mobile communication system.

[0012] The base station 1 includes, for example, an array antenna 10 and an information processing device 11. The array antenna 10 has multiple antenna units. The base station 1 performs downlink and uplink communications with multiple user terminals 2. The user terminals 2 are, for example, smartphones, tablet PCs, navigation devices, etc., and can transmit and receive data to and from the base station 1.

[0013] In at least downlink communication, the base station 1 performs wireless communication using the multi-user MIMO system with multiple user terminals 2. In downlink communication, each user terminal 2 connected to the base station 1 is paired with another user terminal 2, and transmission signals are spatially multiplexed and simultaneously transmitted using the same frequency band.

[0014] In MIMO, it is known that when the distance between antennas is short, the correlation between the antennas increases, resulting in a decrease in communication capacity. When users carrying paired user terminals 2 approach each other, the receiving antennas also approach each other, which may result in a decrease in communication capacity. When information about the location of each user terminal 2 is acquired in an uplink SRS cycle to avoid a decrease in communication capacity due to the proximity of the user terminals 2, there is a risk that proper pairing may not be possible depending on the movement of the user terminals 2 within the SRS cycle.

[0015] The information processing device 11 is realized by the base station 1 and computational resources arranged in the vicinity of the base station 1. The information processing device 11 is, for example, a server device that functions as a RIC (RAN Intelligent Controller). The information processing device 11 estimates the movement tendency of user terminals 2 using techniques such as machine learning, corrects the correlation between multiple user terminals 2 based on the estimation results, and prevents user terminals 2 that are likely to approach each other within an SRS period from being paired. This prevents a decrease in communication capacity and achieves efficiency and high performance of the radio access network N.

[0016] The information processing device 11 may have a function other than the RIC. For example, the information processing device 11 may further have a function as an MEC (Multi Access Edge Computing, Mobile Edge Computing).

[0017] 2 is a block diagram showing an example of an information processing apparatus according to an embodiment of the present invention. The information processing apparatus 11 functions as an acquisition unit 31, a calculation unit 32, a correction unit 33, and a determination unit .

[0018] The acquisition unit 31 acquires location information relating to the location of each user terminal 2 connected to the base station 1. The location information may include at least one of the movement speed and movement method of the user terminal 2. The location information of the user terminal 2 acquired by the acquisition unit 31 is input to the calculation unit 32 and the correction unit 33.

[0019] Information regarding the location of the user terminal 2 may be acquired using any method. For example, if the user terminal 2 is equipped with a GNSS (Global Navigation Satellite System) receiver, the acquisition unit 31 may acquire, from the user terminal 2, the reception results of the GNSS receiver or location information of the user terminal 2 identified based on the reception results. The acquisition unit 31 may acquire information regarding the movement speed and movement direction based on the amount of change in the position of the user terminal 2. Furthermore, the acquisition unit 31 may acquire the location information of the user terminal 2 using a positioning technology such as AoA (Angle of Arrival).

[0020] The calculation unit 32 calculates the correlation between two different user terminals 2 out of the plurality of user terminals 2, based on the information acquired by the acquisition unit 31. Hereinafter, the two different user terminals 2 for which the correlation is calculated by the calculation unit 32 will be referred to as the first user terminal 2 and the second user terminal 2. The correlation between the first user terminal 2 and the second user terminal 2 is calculated by any method for calculating the correlation of receiving antennas, and the further apart the two different user terminals 2 are from each other, the lower the value will be.

[0021] The correction unit 33 corrects the correlation calculated by the calculation unit 32. The correction unit 33 uses the output of the trained model M to correct the correlation. The trained model M is a model that has been machine-learned in advance to determine the relationship between information on the movement of the user terminal 2 and information on the movement tendency of the user terminal 2. The trained model M may be constructed and updated by an arbitrary learning device provided outside the information processing device 11 or the wireless access network N.

[0022] The input to the learning model M is information about the positions of the first and second user terminals 2. The output from the learning model M is information about the movement tendencies of the first and second user terminals 2. The information about the movement tendencies of the first and second user terminals 2 is, for example, the routes that the first and second user terminals 2 are estimated to take, estimated values ​​of the movement speeds of the first and second user terminals 2, and the directions (horizontal / vertical) that the first and second user terminals 2 are estimated to move in.

[0023] The correction unit 33 corrects the correlation to a larger value when the first and second user terminals 2 tend to move closer to each other. The correction unit 33 corrects the correlation to a smaller value when the first and second user terminals 2 tend to move farther apart. A case in which the first and second user terminals 2 tend to move closer to each other is, for example, a case in which the first and second user terminals 2 move along an estimated route, in an estimated direction of movement, and at an estimated speed, causing the distance between the first user terminal 2 and the second user terminal 2 to be equal to or less than a predetermined threshold. Any calculation, such as arithmetic operations, can be used as the calculation used to correct the correlation.

[0024] The determination unit 34 performs pairing for a plurality of user terminals 2 connected to the base station 1 based on the correlation corrected by the correction unit 33. The determination unit 34 determines, for example, based on the correlation corrected by the correction unit 33, whether or not to assign the second user terminal 2 to the same group as the first user terminal.

[0025] 3 is a flowchart showing the flow of processing by an information processing device according to an embodiment of the present invention. When list information related to user terminals 2 to be paired is input, the information processing device 11 starts the processing shown in FIG.

[0026] It is assumed that the priority of the user terminals 2 included in the list information is set based on the number of resource blocks allocated to the transmission signal to each user terminal 2. In the following explanation, it is assumed that the first user terminal 2 is the user terminal with the highest priority, and the second user terminal 2 is the user terminal with the second highest priority.

[0027] In S100, the information processing device 11 functions as the decision unit 34 and assigns the first user terminal 2 to a predetermined group. Hereinafter, the predetermined group to which the first user terminal 2 is assigned will be referred to as the first group.

[0028] In S101, the information processing device 11 acquires the user terminal 2 with the next highest priority from the list information. Immediately after S100, the information processing device 11 acquires the second user terminal 2 with the next highest priority after the first user terminal 2 from the list information.

[0029] In the subsequent S102, the information processing device 11 functions as the calculation unit 32 and calculates the correlation between the second user terminal 2 and the first user terminal 2 that has been assigned to the first group. The information processing device 11 calculates the correlation based on information related to movement acquired by the acquisition unit 31 for the first user terminal 2 and the second user terminal 2.

[0030] In the following S103, the information processing device 11 functions as the correction unit 33 and corrects the correlation calculated in S102. The information processing device 11 inputs the location information acquired by the acquisition unit 31 for the first and second user terminals 2 to the trained model M. The trained model M outputs information related to movement tendencies for the first and second user terminals 2. The information processing device 11 corrects the correlation calculated in S102 based on the information related to movement tendencies output from the trained model M.

[0031] In the subsequent step S104, the information processing device 11 functions as the determination unit 34 and determines whether the correlation after correction satisfies a predetermined pairing condition. The predetermined condition may be, for example, that the correlation corrected in S103 is equal to or less than a predetermined threshold. If the determination in S104 is affirmative, the information processing device 11 assigns the second user terminal 2 to the same first group as the first user terminal 2 (S105), and if the determination in S104 is negative, the information processing device 11 assigns the second user terminal 2 to a group different from the first group (S106). After assigning the second user terminal 2 to one of the groups, the information processing device 11 proceeds to the processing of S107.

[0032] In S107, the information processing device 11 determines whether pairing has been completed. For example, if the information processing device 11 has completed the assignment of all user terminals 2 included in the list information to groups (S107: YES), the information processing device 11 ends the processing in FIG. 3. If the information processing device 11 has not completed the assignment of all user terminals 2 included in the list information to groups (S107: NO), the information processing device 11 proceeds to the processing in S101 and acquires information about the user terminal 2 with the next highest priority from the list information (S101). Thereafter, the processing from S103 onwards is executed for the user terminal 2 acquired in S101.

[0033] [Example of Implementation by Software] The functions of the information processing device 11 (hereinafter referred to as "device") are programs for causing a computer to function as the device, and can be realized by the programs for causing a computer to function as the information processing device 11. In this case, the information processing device 11 includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the programs. The functions described in each of the above embodiments are realized by executing the programs using the control device and storage device.

[0034] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0035] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0036] The processing of the calculation unit 32 described in the above embodiment may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device or another device (for example, an edge computer or a cloud server).

[0037] [Summary] An information processing device according to a first aspect of the present invention is used in a radio access network in which, when a signal is transmitted from a base station to a plurality of user terminals connected to the base station, transmission signals to user terminals assigned to the same group among the plurality of user terminals are spatially multiplexed, and the information processing device includes: an acquisition unit that acquires location information of a first and second user terminal included in the plurality of user terminals; a calculation unit that calculates a correlation between the first user terminal and the second user terminal; a correction unit that corrects the correlation based on an output of a trained model constructed by machine learning; and a decision unit that decides whether to assign the second user terminal to the same group as the first user terminal based on the correlation corrected by the correction unit, wherein an input of the trained model is location information of the first and second user terminals, and an output of the trained model is information regarding the movement tendencies of the first and second user terminals.

[0038] According to the above configuration, the receiving user terminals are assigned to groups based on the result of correcting the correlation between the receiving user terminals in accordance with their movement tendencies, so that appropriate pairing is possible.

[0039] In an information processing device according to aspect 2 of the present invention, in the above aspect 1, the correction unit may correct the correlation to a larger value when the first and second user terminals tend to move closer to each other, and may correct the correlation to a smaller value when the first and second user terminals tend to move farther apart.

[0040] According to the above configuration, when two user terminals tend to move closer to each other, the correlation is corrected to a larger value, thereby reducing the chances of two user terminals that tend to move closer to each other being assigned to the same group.

[0041] A program according to aspect 3 of the present invention is a program for causing a computer to function as the information processing device described in aspect 1 or 2, and may be configured to cause the computer to function as the acquisition unit, the calculation unit, the correction unit, and the determination unit.

[0042] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment.

[0043] 2 User terminal 11 Information processing device 31 Acquisition unit 32 Calculation unit 33 Correction unit 34 Determination unit M Trained model

Claims

1. An information processing device used in a radio access network in which, when signals are transmitted from a base station to a plurality of user terminals connected to the base station, transmission signals to user terminals assigned to the same group among the plurality of user terminals are spatially multiplexed, the information processing device comprising: an acquisition unit that acquires location information of a first and second user terminal included in the plurality of user terminals; a calculation unit that calculates the correlation between the first user terminal and the second user terminal; a correction unit that corrects the correlation based on the output of a trained model constructed by machine learning; and a decision unit that decides whether to assign the second user terminal to the same group as the first user terminal based on the correlation corrected by the correction unit, wherein the input of the trained model is the location information of the first and second user terminals, and the output of the trained model is information regarding the movement trends of the first and second user terminals.

2. The information processing device according to claim 1, wherein the correction unit corrects the correlation to a larger value when the first and second user terminals tend to move closer to each other, and corrects the correlation to a smaller value when the first and second user terminals tend to move farther apart.

3. A program for causing a computer to function as the information processing device according to claim 1 or 2, the program causing a computer to function as the acquisition unit, the calculation unit, the correction unit, and the determination unit.

Images