Communication system, control method, and program

Abstract

Provided is a communication system that comprises: a travel situation inference unit that infers a time series of positions for an electric train that is scheduled to travel one section of a railway line that is covered by a wireless base station when the electric train is traveling the one section of the railway line and a crowdedness situation for people on the electric train when the electric train is traveling the one section of the railway line; and a base station control unit that controls the wireless base station to emit a beam to cover the electric train as traveling the one section of the railway line on the basis of the results of the inference by the travel situation inference unit. The communication system may have a RAN control function and an AI processing (RAN Intelligent Controller (RIC), etc.) function.

Description

Communication system, control method, and program

[0001] The present invention relates to a communication system, a control method, and a program.

[0002] Patent Document 1 describes a data transmission device that includes a beamforming processing unit that performs beamforming processing between a terminal installed in a mobile body, a beam angle detection unit that detects a beam angle based on the results of the beamforming processing, and a mobile body position estimation unit that estimates the position of the mobile body from the beam angle and installation location information of the data transmission device, and that determines whether the estimated position of the mobile body is within the communication range of the transmission device, and if it is within the communication range, transmits desired data to the mobile body. [Prior Art Documents] [Patent Document 1] JP 2022-028055 A

[0003] Conventionally, wireless base station schedulers have not been configured specifically for providing mobile communication services to communication terminals on trains. Instead, areas are simply divided by antenna tilt of the wireless base station, resulting in concentrated handovers when switching between areas. Furthermore, since many passengers ride on a train in a small area, a large amount of traffic is concentrated at a single wireless base station. Furthermore, in areas where multiple train lines run parallel, the line of sight is relatively wide, making radio interference between wireless base stations more likely to occur.

[0004] Since the location and speed of trains are almost fixed, their movements are easy to predict. In the communication system according to this embodiment, for example, a wireless base station for trains installed along the tracks performs beamforming for trains using predictions based on AI (Artificial Ingelligence) rather than beamforming based on feedback from communication terminals.

[0005] Ordinary beamforming is performed on communication devices that move around randomly, such as those carried by pedestrians. However, in the case of communication devices carried by train passengers, their movement is dependent on the movement of the train. In other words, in the case of communication devices on a train, by comparing the train schedule and delay status with the access status on the network side, it is possible to predict the number of people passing by and where they will pass at what time, minute, and second. In the communication system according to this embodiment, the AI ​​on the network side controls the beams of the wireless base stations based on this information in order to maximize communication capacity.

[0006] As a specific example, the communication system according to this embodiment includes a distributed infrastructure having a RAN control function for controlling a RAN (Radio Access Network) and an AI processing function for performing AI processing, and a management infrastructure for managing multiple distributed infrastructures, each of which controls beams from multiple radio base stations.

[0007] Types of AI processing include AI processing related to RAN control (sometimes referred to as RAN-controlled AI processing) and AI processing not related to RAN control (sometimes referred to as non-RAN-controlled AI processing).

[0008] An example of RAN control AI processing is RIC (RAN Intelligent Controller). RIC is a technology that uses AI to optimize RAN radio resources and automate RAN operations. RIC includes Non-RT RIC and Near-RT RIC (Near-Real Time RIC). Non-RT RIC is sometimes called Centralized RIC. Non-RT RIC is located inside SMO (Service Management and Orchestration), which manages and orchestrates the RAN. Non-RT RIC generates and notifies policies related to RAN control and sends information to Near-RT RIC. For example, the Non-RT RIC performs machine learning using data collected from the RAN to generate a trained model for RAN control and transmits it to the Near-RT RIC. The Near-RT RIC is sometimes called a Distributed RIC. Compared to the Non-RT RIC, the Near-RT RIC is located closer to the RAN nodes (RU (Radio Unit), DU (Distributed Unit), CU (Central Unit)) and controls the RAN nodes, resources, etc. The Near-RT RIC performs processing with higher real-time performance than the Non-RT RIC. The Near-RT RIC performs inference processing related to RAN control using, for example, a trained model acquired from the Non-RT RIC. RAN control AI processing is not limited to the RIC.

[0009] The non-RAN control AI processing may correspond to a so-called MEC (Multi-access Edge Computing) application. Examples of the non-RAN control AI processing include a monitoring AI execution process that determines the situation within the imaging range of an input captured image, and a response AI execution process that outputs a response to an input user inquiry. However, this is not limited to these.

[0010] According to one embodiment of the present invention, there is provided a communication system. The communication system may include a traveling condition estimation unit that estimates a time-series position of a train scheduled to travel on a section of track covered by a radio base station when the train travels on the section of track and a congestion state of people on the train when the train travels on the section of track. The communication system may include a base station control unit that controls the radio base station to irradiate a beam to cover the train traveling on the section of track based on the estimation result by the traveling condition estimation unit.

[0011] In the communication system, the running condition estimation unit may estimate the time series position of the train when it runs along the section of track and the congestion of people inside the train when it runs along the section of track based on train schedule information for the train currently in operation, train operation status information for the train, and the congestion of people on the platform of the station where the train stops before running along the section of track.

[0012] Any of the communication systems includes a train position learning model that receives train schedule information and train operation status information generated by machine learning using learning data including train schedule information from past train operations, train operation status information, and time-series positions of the train when the train traveled through the section of track, and outputs time-series positions of the train when the train traveled through the section of track; and a train position learning model that receives train schedule information and train operation status information generated by machine learning using learning data including train schedule information from past train operations, train operation status information, and time-series positions of the train when the train traveled through the section of track, and outputs time-series positions of the train when the train traveled through the section of track. and a congestion situation learning model that takes as input the congestion situation of people on the platform of a station where the train stops before running along the one section of track, and outputs the congestion situation of people inside the train when the train runs along the one section of track, the congestion situation learning model being generated by machine learning using learning data including the congestion situation of people on the platform of a station where the train stops before running along the one section of track, and the congestion situation of people inside the train when the train runs along the one section of track, and the running situation estimation unit may use the train position learning model and the congestion situation learning model to estimate the time-series position of the train when it runs along the one section of track and the congestion situation of people inside the train when it runs along the one section of track.

[0013] Any of the communication systems may include train schedule information, train operation status information, and a timeline of when the train will run on the section of track, the timeline of when the train will run on the section of track being generated by machine learning using learning data including: train schedule information for past train operations; operation status information for the train; a congestion status of people on platforms of stations where the train stopped before running on the section of track; a chronological position of the train when the train ran on the section of track; and a congestion status of people inside the train when the train ran on the section of track. The train may include a memory unit that stores a running situation learning model that takes as input the congestion of people on the platform of the station where the train previously stopped, and outputs the time-series position of the train when it travels along the one section of the track and the congestion of people inside the train when it travels along the one section of the track, and the running situation estimation unit may use the running situation learning model to estimate the time-series position of the train when it travels along the one section of the track and the congestion of people inside the train when it travels along the one section of the track.

[0014] In any of the communication systems, the running condition estimation unit may estimate the time series position of the train when it runs along the section of track and the congestion of people inside the train when it runs along the section of track based on train schedule information for the train currently in operation, train operation status information for the train, the congestion of people on the platform of a station where the train will stop before running along the section of track, and the congestion of people inside the train before it stops at the station.

[0015] In any of the communication systems, the train may have a plurality of cars, and the traveling condition estimation unit may estimate a time-series position of the train when it travels along the section of track and a pedestrian congestion state in each of the plurality of cars of the train when it travels along the section of track based on timetable information for the train during operation, operation status information for the train, and pedestrian congestion states in a plurality of sections corresponding to the plurality of cars of the train on a platform of a station where the train stops before traveling along the section of track, and the base station control unit may control the wireless base station to irradiate a plurality of beams onto the train based on an estimation result from the traveling condition estimation unit. The base station control unit may control the wireless base station to irradiate a plurality of beams onto a car determined to be in a crowded state among the plurality of cars of the train. The base station control unit may control the wireless base station to irradiate a single beam onto a plurality of consecutive cars determined to be in an unoccupied state among the plurality of cars of the train.

[0016] In any of the communication systems, the train may include a plurality of cars, and the running condition estimation unit may estimate the congestion state of people in a plurality of sections corresponding to the plurality of cars of the train on the station platform and the number of user terminals for each supported frequency, based on user terminal information including location information of the user terminal received from the user terminal within the range of the radio base station and frequency information supported by the wireless communication function of the user terminal, by a radio base station installed at a station where the train stops before traveling through the section, and the base station control unit may control the radio base station to irradiate the train with a plurality of beams of different frequencies based on the estimation results by the running condition estimation unit.

[0017] According to one embodiment of the present invention, there is provided a control method executed by a computer. The control method may include a traveling situation estimation step of estimating a time-series position of a train scheduled to travel on a section of track covered by a wireless base station when the train travels on the section of track and a congestion state of people on the train when the train travels on the section of track. The control method may include a base station control step of controlling the wireless base station to irradiate a beam to cover the train traveling on the section of track based on a result of the estimation in the traveling situation estimation step.

[0018] According to one embodiment of the present invention, there is provided a program for causing a computer to execute the control method.

[0019] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions.

[0020] FIG. 1 is a schematic diagram illustrating an example of a communication system 10. FIG. 2 is an explanatory diagram illustrating processing details of the communication system 10. FIG. 3 is an explanatory diagram illustrating beam control of a radio base station 300 by a distributed infrastructure 200. FIG. 4 is an explanatory diagram illustrating beam control of a radio base station 300 by a distributed infrastructure 200. FIG. 5 is an explanatory diagram illustrating beam control of a radio base station 300 by a distributed infrastructure 200. FIG. 6 is an explanatory diagram illustrating beam control of a radio base station 300 by a distributed infrastructure 200. FIG. 7 is an explanatory diagram illustrating beam control of a radio base station 300 by a distributed infrastructure 200. FIG. 8 is a schematic diagram illustrating an example of the functional configuration of a distributed infrastructure 200. FIG. 9 is a schematic diagram illustrating an example of the hardware configuration of a computer 1200 that functions as a management infrastructure 100 or a distributed infrastructure 200.

[0021] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0022] FIG. 1 schematically illustrates an example of a communication system 10. The communication system 10 includes a distributed infrastructure 200. The communication system 10 may include multiple distributed infrastructures 200. The communication system 10 may include a management infrastructure 100 that manages the multiple distributed infrastructures 200. In the communication system 10 according to this embodiment, for example, the management infrastructure 100 and the multiple distributed infrastructures 200 may cooperate to control the RAN 310 and perform AI processing. The RAN 310 provides mobile communication services to a UE (User Equipment) 30. The UE 30 may be an example of a user terminal.

[0023] The RAN 310 may be a virtualized vRAN (Virtual RAN), and the communication system 10 may control the vRAN. The RAN 310 may be a physical RAN, and the communication system 10 may control the physical RAN. In this embodiment, a case where the RAN 310 is a vRAN will be mainly described as an example.

[0024] The AI ​​processing performed by the communication system 10 includes RAN-controlled AI processing (sometimes referred to as RAN_AI). The AI ​​processing performed by the communication system 10 may include non-RAN-controlled AI processing (sometimes referred to as non-RAN_AI).

[0025] The distributed infrastructure 200 may be a data center located in various locations. The distributed infrastructure 200 may be configured with multiple devices. The distributed infrastructure 200 may be realized on a virtualization platform made up of multiple devices. The distributed infrastructure 200 may also be realized by a single device. In other words, the distributed infrastructure 200 may be a distributed device.

[0026] The management infrastructure 100 may be a data center that manages multiple distributed infrastructures 200. The management infrastructure 100 may be configured with multiple devices. The management infrastructure 100 may be realized on a virtualization infrastructure made up of multiple devices. The management infrastructure 100 may also be realized by a single device. In other words, the management infrastructure 100 may be a management device.

[0027] The management infrastructure 100 may be referred to as a Core Brain, and the distributed infrastructure 200 may be referred to as a Regional Brain. While FIG. 1 illustrates an example in which a single-level management infrastructure 100 is arranged below the management infrastructure 100, this is not limiting. The distributed infrastructure 200 may have multiple levels. For example, when a two-level distributed infrastructure 200 is arranged below the management infrastructure 100, the management infrastructure 100 may be referred to as a Core Brain, the distributed infrastructure 200 at the level below that may be referred to as a Regional Brain, and the distributed infrastructure 200 at the level further below that may be referred to as a Sub-Regional Brain.

[0028] The distributed infrastructure 200 may be arranged with one or more central processing units (CPUs). The distributed infrastructure 200 may be arranged with one or more graphics processing units (GPUs). The distributed infrastructure 200 may be arranged with multiple super chips, each of which has a CPU and a GPU connected via an interconnect. The interconnect may have memory consistency and may be capable of achieving high bandwidth and low latency. In this way, the distributed infrastructure 200 may have CPU resources and GPU resources as computational resources.

[0029] 2 to 6 are explanatory diagrams illustrating processing details of the communication system 10. In FIGS. 2 to 6, beam control of the radio base station 300 by the distributed infrastructure 200 will be described. The radio base station 300 may be capable of emitting multiple beams. The radio base station 300 radiates multiple beams, for example, using MU-MIMO (Multi User-Multiple Input and Multiple Output). In this example, the radio base station 300 covers a section 42 of the railway line 40. In FIGS. 2 to 6, radio base stations other than the radio base station 300 that covers the section 42 are not illustrated.

[0030] The distribution infrastructure 200 estimates the time-series position of the train 400 when the train 400, which is scheduled to run through one section 42, runs through the one section 42. The distribution infrastructure 200 may acquire and store in advance train schedule information indicating the train 400's schedule, and use the train schedule information of the train 400 to estimate the time-series position of the train 400 when it runs through the one section 42.

[0031] The distribution infrastructure 200 may acquire operation status information indicating the operation status of the train 400, and use the operation status information to estimate the time-series position of the train 400 when traveling through one section 42. The distribution infrastructure 200 may receive operation status information provided by a server of a railway management company that manages the train 400. The distribution infrastructure 200 may also receive operation status information from a server that provides information related to railways, such as transfer guides.

[0032] The operation status information may indicate whether the train 400 is running according to the train schedule. If the train 400 is not running according to the train schedule, the operation status information may indicate a delay status of the train 400.

[0033] The distribution infrastructure 200 may use the train schedule information and the operation status information to estimate the time-series position of the train 400 when it runs through one section 42. For example, if the operation status information indicates that the train 400 is running according to the train schedule, the distribution infrastructure 200 uses the train schedule information to estimate the time-series position of the train 400. For example, if the operation status information indicates that the train 400 is not running according to the train schedule, the distribution infrastructure 200 estimates the time-series position of the train 400 when it runs through one section 42 by taking into account the delay indicated by the operation status information to the time-series position of the train 400 when it runs according to the train schedule.

[0034] The distribution platform 200 may estimate the time-series position of the train 400 when it runs through one section 42 using a train position learning model that takes as input train schedule information and operation status information generated by performing machine learning using learning data including train schedule information from past train 400 operations, operation status information of the train 400, and the time-series position of the train 400 when it runs through one section 42, and outputs the time-series position of the train 400 when it runs through one section 42. The distribution platform 200 may generate and store the train position learning model in advance. The distribution platform 200 may also acquire and store a train position learning model generated by another device in advance.

[0035] The distribution infrastructure 200 estimates the congestion state of people inside the train 400 when the train 400, which is scheduled to run through the one section 42, runs through the one section 42. The distribution infrastructure 200 may estimate the congestion state of people inside the train 400 when it runs through the one section 42, based on the congestion state of people on the platform of the station 50 where the train 400 stops before running through the one section 42.

[0036] The distributed infrastructure 200 may determine the congestion status of people on the platform of the station 50 by analyzing an image captured by a camera installed on the platform of the station 50. The distributed infrastructure 200 may receive, from another device, congestion status information indicating the congestion status of people on the platform of the station 50, which the other device determined by analyzing an image captured by a camera installed on the platform of the station 50. The distributed infrastructure 200 may receive, from a location information management server, congestion status information indicating the congestion status of people on the platform of the station 50, which is specified by the location information management server that manages the location information of each UE 30. The location information management server may manage the location information of the UE 30 by receiving, from the UE 30, the location information of the UE 30 measured by the UE 30. The UE 30 may acquire its own location information by a method such as a Global Navigation Satellite System (GNSS) such as a Global Positioning System (GPS), Wi-Fi (registered trademark) (Wireless Fidelity), or cell positioning.

[0037] The distribution infrastructure 200 may acquire connected user information indicating the number of UEs 30 connected to a radio base station 300 from the radio base station 300 covering the platform of the station 50, and may determine the congestion status of people on the platform of the station 50 from the connected user information. The connected user information may include location information of each of the multiple UEs 30. The connected user information may include information indicating which frequency each of the multiple UEs 30 corresponds to. The distribution infrastructure 200 may estimate the number of people located on the platform of the station 50 from the connected user information. The distribution infrastructure 200 may estimate the number of people located in each of multiple sections on the platform of the station 50 from the connected user information. The distribution infrastructure 200 may estimate the number of users available for each supported frequency located on the platform of the station 50 from the connected user information. The distribution infrastructure 200 may estimate the number of users available for each supported frequency located in each of multiple sections on the platform of the station 50 from the connected user information.

[0038] The distribution platform 200 may estimate the congestion state of people inside the train 400 when it travels through one section 42 using a congestion state learning model that takes as input the congestion state of people on the platform of a station 50 where the train 400 stopped before traveling through one section 42 and outputs the congestion state of people inside the train 400 when it travels through one section 42, the congestion state being generated by performing machine learning using learning data including past congestion states of people on the platform of a station 50 where the train 400 stopped before traveling through one section 42 and the congestion state of people inside the train 400 when it travels through one section 42. The distribution platform 200 may generate and store the congestion state learning model in advance. The distribution platform 200 may also acquire and store in advance a congestion state learning model generated by another device.

[0039] When the distribution infrastructure 200 knows the congestion status of people on the train 400 before it stops at station 50, it may estimate the congestion status of people on the train 400 when it runs through one section 42 based on the congestion status of people on the platform at station 50 and the congestion status of people on the train 400 before it stops at station 50. For example, when the distribution infrastructure 200 is able to acquire the congestion status of people on the train 400 from the server of the railway management company that manages the train 400 between the time the train 400 departs from the previous station 50 and the time the train 400 arrives at station 50, the distribution infrastructure 200 uses the acquired congestion status. For example, the distribution infrastructure 200 uses the congestion status of people on the train 400 that was estimated one time ago as the congestion status of people on the train 400 before it stops at station 50.

[0040] The distribution platform 200 may estimate the congestion situation of people inside the train 400 when it runs through the one section 42 using a congestion situation learning model that takes as input the congestion situation of people on the platform of the station 50 where the train 400 stopped before running through the one section 42 and the congestion situation of people inside the train 400 before the train 400 stops at the station 50, and outputs the congestion situation of people inside the train 400 when it runs through the one section 42, the congestion situation of people inside the train 400 before the train 400 stops at the station 50, which have been generated by performing machine learning using learning data including the congestion situation of people on the platform of the station 50 where the train 400 stopped before running through the one section 42 in the past, the congestion situation of people inside the train 400 before the train 400 stopped at the station 50, and the congestion situation of people inside the train 400 when it runs through the one section 42. The distribution platform 200 may generate and store the congestion situation learning model in advance. The distribution platform 200 may also acquire and store a congestion situation learning model generated by another device in advance.

[0041] The distribution infrastructure 200 may estimate the congestion state of people in each of the multiple cars of the train 400 when it travels through one section 42. The distribution infrastructure 200 may estimate the congestion state of people in each of the multiple cars of the train 400 when it travels through one section 42, based on the congestion state of people in multiple sections corresponding to the multiple cars of the train 400 on the platform of the station 50 where the train 400 stops before traveling through one section 42.

[0042] The distributed infrastructure 200 may determine the congestion status of people in each of the multiple sections on the platform of the station 50 by analyzing an image captured by a camera installed on the platform of the station 50. The distributed infrastructure 200 may receive, from another device, congestion status information indicating the congestion status of people in each of the multiple sections on the platform of the station 50, which the other device determined by analyzing an image captured by a camera installed on the platform of the station 50. The distributed infrastructure 200 may receive, from a location information management server that manages the location information of each UE 30, congestion status information indicating the congestion status of people in each of the multiple sections on the platform of the station 50, which is identified by the location information management server.

[0043] The distributed base station 200 controls the radio base station 300 to emit a beam to cover the train 400 traveling through one section 42 based on the estimated results of the time-series position of the train 400 when traveling through one section 42 and the congestion status of people on the train 400.

[0044] 3 , when the distribution infrastructure 200 determines that the train 400 is not crowded, the distribution infrastructure 200 may control the radio base station 300 to cover the entire train 400 with a single beam. The distribution infrastructure 200 may control the radio base station 300 to follow the train 400 with a single beam according to the estimated time-series position of the train 400 so as to continuously cover the train 400. As illustrated in FIG. 3 , when the train 400 has three cars 410, 420, and 430, the distribution infrastructure 200 may control the radio base station 300 to cover the cars 410, 420, and 430 with a single beam 312.

[0045] 4 , when the distribution infrastructure 200 determines that the congestion state of people on board the train 400 is normal or crowded, the distribution infrastructure 200 may control the radio base station 300 to cover the entire train 400 with multiple beams. The distribution infrastructure 200 may control the radio base station 300 to follow the train 400 with multiple beams according to the estimated time-series position of the train 400 so as to continuously cover the train 400. As illustrated in FIG. 4 , when the train 400 has three cars 410, 420, and 430, the distribution infrastructure 200 may control the radio base station 300 to cover the cars 410, 420, and 430 with three beams 312, 314, and 316, respectively.

[0046] For example, the distribution infrastructure 200 estimates a so-called congestion rate as the congestion state of people on the train 400, and determines that the train is in an unoccupied state if the congestion rate is lower than a predetermined threshold. The distribution infrastructure 200 may determine that the train is in a congested state if the congestion rate is higher than the predetermined threshold. The distribution infrastructure 200 may determine that the train is in an unoccupied state if the estimated congestion rate is lower than a predetermined first threshold, determine that the train is in a congested state if the congestion rate is higher than a second threshold that is higher than the first threshold, and determine that the train is in a normal state if the congestion rate is between the first threshold and the second threshold.

[0047] The distribution infrastructure 200 may control the beam of the radio base station 300 based on the estimation result of the congestion state of people in each of the multiple cars of the train 400. For example, the distribution infrastructure 200 controls the radio base station 300 to irradiate multiple beams to cars that are determined to be in a crowded state among the multiple cars of the train 400. For example, the distribution infrastructure 200 controls the radio base station 300 to irradiate one beam to multiple consecutive cars that are determined to be in an unoccupied state among the multiple cars of the train 400.

[0048] As illustrated in Figure 5, when train 400 has three cars 410, 420, and 430, and car 410 is in a normal congestion state and cars 420 and 430 are in an uncongested state, distribution platform 200 may control radio base station 300 to cover car 410 with beam 312 and to cover cars 420 and 430 with beam 314.

[0049] As illustrated in Figure 6, when train 400 has three cars 410, 420, and 430, and the congestion situation in car 410 is congested, and the congestion situations in cars 420 and 430 are normal, distribution platform 200 may control radio base station 300 to cover car 410 with beams 312 and 313, to cover car 420 with beam 314, and to cover car 430 with beam 316.

[0050] In conventional beamforming in TDD (Time Division Duplex) communications, a radio base station receives an SRS (Sounding Reference Signal) emitted from a communication terminal, estimates the propagation channel matrix, and then calculates the inverse matrix to direct a beam toward the communication terminal. This calculation requires processing to apply beam weighting in units of several tens of milliseconds, since the beam must be continuously directed toward a moving object.

[0051] In contrast, the distribution infrastructure 200 according to this embodiment estimates the time-series position of the train 400, which moves regularly to a certain extent, and causes the radio base station 300 to emit beams to cover the train 400 based on the estimation results. This eliminates the need to calculate beam weights for each communication terminal, contributing to saving computational resources and reducing power consumption. Furthermore, the distribution infrastructure 200 estimates the congestion status of people on the train 400 and adjusts the beams as illustrated in FIGS. 3 to 6 based on the estimation results. This allows communication traffic to be distributed by emitting more beams to crowded trains 400, and the number of beams to be reduced to trains 400 that are quiet, thereby appropriately reducing the processing load of the radio base station 300. Furthermore, communication traffic can be distributed more precisely by emitting more beams to crowded trains, and the processing load of the radio base station 300 can be appropriately reduced by covering quiet trains with fewer beams.

[0052] 7 shows an example of the functional configuration of the distributed infrastructure 200. The distributed infrastructure 200 includes a memory unit 202, a RAN control unit 204, an AI management unit 206, an acquisition unit 208, a learning execution unit 210, a driving situation estimation unit 212, and a base station control unit 214.

[0053] The RAN control unit 204 executes a RAN control function that controls a RAN 302 configured by a plurality of radio base stations 300. The RAN control unit 204 may execute a function of a so-called vRAN (Virtual RAN). The RAN control unit 204 may control communications in the RAN 302 by controlling the plurality of radio base stations 300 that configure the RAN 302 and coordinating with other distributed infrastructures 200. The RAN control unit 204 may manage the base station control unit 214.

[0054] The AI ​​management unit 206 manages AI processing. For example, the AI ​​management unit 206 manages the execution of RAN-controlled AI processing. For example, the AI ​​management unit 206 manages the execution of non-RAN-controlled AI processing. The AI ​​management unit 206 may manage the acquisition unit 208, the learning execution unit 210, and the driving situation estimation unit 212.

[0055] The acquisition unit 208 acquires various data and stores the acquired data in the storage unit 202.

[0056] For example, the acquisition unit 208 acquires train schedule information that indicates the schedule of the target train 400. The acquisition unit 208 acquires the train schedule information from, for example, a server of a railway management company that manages the train 400. The acquisition unit 208 may acquire the train schedule information from any server that provides information related to railways.

[0057] For example, the acquisition unit 208 acquires operation status information indicating the operation status of the target train 400. The acquisition unit 208 may acquire operation status information provided by a server of a railway management company that manages the train 400. The distribution platform 200 may acquire operation status information from a server that provides information related to railways, such as transfer guides.

[0058] For example, the acquisition unit 208 acquires connected user information indicating the number of UEs 30 connected to the radio base station 300 from a radio base station 300 covering the platform of the station 50. The acquisition unit 208 may determine the congestion status of people on the platform of the station 50 from the connected user information. The connected user information may include location information of each of the multiple UEs 30. The connected user information may include information indicating which frequency each of the multiple UEs 30 corresponds to. The acquisition unit 208 may estimate the number of people located on the platform of the station 50 from the connected user information. The acquisition unit 208 may estimate the number of people located in each of multiple sections on the platform of the station 50 from the connected user information. The acquisition unit 208 may estimate the number of users available for each supported frequency located on the platform of the station 50 from the connected user information. The acquisition unit 208 may estimate the number of users available for each supported frequency located in each of multiple sections on the platform of the station 50 from the connected user information.

[0059] For example, the acquiring unit 208 acquires learning data.

[0060] For example, the acquisition unit 208 acquires learning data including past train schedule information when the train 400 was operating, operation status information of the train 400, and the time-series position of the train 400 when the train 400 ran through one section 42.

[0061] For example, the acquisition unit 208 acquires learning data including the past congestion status of people on the platform of the station 50 where the train 400 stopped before traveling through the section 42, and the congestion status of people inside the train 400 when the train 400 traveled through the section 42. For example, the acquisition unit 208 acquires learning data including the past congestion status of people on the platform of the station 50 where the train 400 stopped before traveling through the section 42, the congestion status of people inside the train 400 before the train 400 stopped at the station 50, and the congestion status of people inside the train 400 when the train 400 traveled through the section 42.

[0062] For example, the acquisition unit 208 acquires learning data including the past congestion status of people in each of multiple sections on the platform of the station 50 where the train 400 stopped before traveling through the section 42, and the past congestion status of people in each of the multiple cars of the train 400 when the train 400 traveled through the section 42. For example, the acquisition unit 208 acquires learning data including the past congestion status of people in each of multiple sections on the platform of the station 50 where the train 400 stopped before traveling through the section 42, the past congestion status of people in each of the multiple cars of the train 400 before stopping at the station 50, and the past congestion status of people in each of the multiple cars of the train 400 when the train 400 traveled through the section 42.

[0063] For example, the acquisition unit 208 acquires learning data including past train schedule information when the train 400 was in operation, operation status information of the train 400, the congestion status of people on the platform of the station 50 where the train 400 stopped before running through the section 42, the chronological position of the train 400 when the train 400 ran through the section 42, and the congestion status of people inside the train 400 when the train 400 ran through the section 42. For example, the acquisition unit 208 acquires learning data including past train schedule information when the train 400 was in operation, operation status information of the train 400, the congestion status of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through the section 42, the chronological position of the train 400 when the train 400 ran through the section 42, and the congestion status of people inside each of the multiple cars of the train 400 when the train 400 ran through the section 42.

[0064] For example, the acquisition unit 208 acquires a learning model generated by another device.

[0065] For example, the acquisition unit 208 acquires a train position learning model that takes as input the train schedule information and operation status information of the train 400, which are generated by machine learning using learning data including train schedule information from past train 400 operations, operation status information of the train 400, and the time-series positions of the train 400 when the train 400 travels through one section 42, and outputs the time-series positions of the train 400 when the train 400 travels through one section 42.

[0066] For example, the acquisition unit 208 acquires a congestion situation learning model that takes as input the congestion situation of people on the platform of a station 50 where the train 400 stopped before running through a section 42, and outputs the congestion situation of people inside the train 400 when it runs through a section 42, and that is generated by machine learning using learning data including the congestion situation of people on the platform of a station 50 where the train 400 stopped before running through a section 42 in the past and the congestion situation of people inside the train 400 when it runs through a section 42. For example, the acquisition unit 208 acquires a congestion situation learning model that takes as input the congestion situation on the platform of the station 50 where the train 400 stopped before running through a section 42 in the past and the congestion situation on the train 400 before stopping at the station 50, and outputs the congestion situation on the train 400 when it runs through a section 42, which model is generated by machine learning using learning data including the congestion situation on the platform of the station 50 where the train 400 stopped before running through a section 42 in the past, the congestion situation on the train 400 before stopping at the station 50, and the congestion situation on the train 400 when it runs through a section 42.

[0067] For example, the acquisition unit 208 acquires a congestion situation learning model that takes as input the congestion situations of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through one section 42, and outputs the congestion situations of people in each of the multiple cars of the train 400 when the train 400 runs through one section 42, and that is generated by machine learning using learning data including the congestion situations of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through one section 42 in the past and the congestion situations of people in each of the multiple cars of the train 400 when the train 400 runs through one section 42. For example, the acquisition unit 208 acquires a congestion situation learning model that takes as input the congestion situations of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through one section 42 in the past and the congestion situations of people in each of the multiple cars of the train 400 before stopping at the station 50, which are generated by machine learning using learning data including the congestion situations of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through one section 42, the congestion situations of people in each of the multiple cars of the train 400 before stopping at the station 50, and the congestion situations of people in each of the multiple cars of the train 400 when the train 400 runs through one section 42, and outputs the congestion situations of people in each of the multiple cars of the train 400 when the train 400 runs through one section 42.

[0068] For example, the acquisition unit 208 acquires a running situation model that takes as input the train schedule information of the train 400, the running status information of the train 400, and the congestion of people on the platform of the station 50 where the train 400 stopped before running through the one section 42, which are generated by machine learning using learning data including train schedule information from past operations of the train 400, running status information of the train 400, the congestion of people on the platform of the station 50 where the train 400 stopped before running through the one section 42, the chronological position of the train 400 when it ran through the one section 42, and the congestion of people inside the train 400 when it ran through the one section 42, and outputs the chronological position of the train 400 when it runs through the one section 42 and the congestion of people inside the train 400 when it runs through the one section 42. For example, the acquisition unit 208 acquires a running situation model that takes as input the train schedule information of the train 400, the running status information of the train 400, and the congestion status of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through the single section 42, which are generated by machine learning using learning data including: train schedule information from past operations of the train 400; running status information of the train 400; the congestion status of people in each of the multiple sections on the platform of the station 50 where the train 400 stopped before running through the single section 42; the chronological position of the train 400 when the train 400 ran through the single section 42; and the congestion status of people in each of the multiple cars of the train 400 when the train 400 ran through the single section 42.

[0069] The learning execution unit 210 generates a learning model by executing machine learning using the learning data stored in the storage unit 202. The learning execution unit 210 stores the generated learning model in the storage unit 202.

[0070] For example, the learning execution unit 210 performs machine learning using learning data including train schedule information from past train 400 operations, train operation status information for the train 400, and the time-series positions of the train 400 when the train 400 traveled through one section 42, to generate a train position learning model that takes train schedule information and train operation status information for the train 400 as input and outputs the time-series positions of the train 400 when the train 400 travels through one section 42.

[0071] For example, the learning execution unit 210 uses machine learning using learning data including the past congestion situations of people on the platform of a station 50 where the train 400 stopped before running through a section 42 and the congestion situations of people inside the train 400 when the train 400 runs through a section 42 to generate a congestion situation learning model in which the congestion situations of people on the platform of a station 50 where the train 400 stopped before running through a section 42 is used as input, and the congestion situations of people inside the train 400 when the train 400 runs through a section 42 is used as output. For example, the learning execution unit 210 performs machine learning using learning data including the past congestion situation on the platform of station 50 where train 400 stopped before running through one section 42, the congestion situation of people inside train 400 before stopping at station 50, and the congestion situation of people inside train 400 when train 400 runs through one section 42, to generate a congestion situation learning model that takes as input the congestion situation of people on the platform of station 50 where train 400 stopped before running through one section 42 and the congestion situation of people inside train 400 before stopping at station 50, and outputs the congestion situation of people inside train 400 when train 400 runs through one section 42.

[0072] For example, the learning execution unit 210 uses machine learning using learning data including the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 has stopped in the past before running through one section 42 and the congestion status of people inside each of the multiple cars of train 400 when train 400 runs through one section 42 to generate a congestion status learning model that takes as input the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 has stopped before running through one section 42 and outputs the congestion status of people inside each of the multiple cars of train 400 when train 400 runs through one section 42. For example, the learning execution unit 210 performs machine learning using learning data including the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 has stopped before running through one section 42 in the past, the congestion status of people inside each of the multiple cars of train 400 before stopping at station 50, and the congestion status of people inside each of the multiple cars of train 400 when train 400 runs through one section 42, to generate a congestion status learning model that takes as input the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 has stopped before running through one section 42 and the congestion status of people inside each of the multiple cars of train 400 before stopping at station 50, and outputs the congestion status of people inside each of the multiple cars of train 400 when train 400 runs through one section 42.

[0073] For example, the learning execution unit 210 performs machine learning using learning data including train schedule information from past train 400 operations, train operation status information for the train 400, the congestion of people on the platform of the station 50 where the train 400 stopped before running through the one section 42, the chronological position of the train 400 when the train 400 ran through the one section 42, and the congestion of people inside the train 400 when the train 400 ran through the one section 42, to generate a running status model that takes as input the train schedule information for the train 400, the operation status information for the train 400, and the congestion of people on the platform of the station 50 where the train 400 stopped before running through the one section 42, and outputs the chronological position of the train 400 when the train 400 runs through the one section 42 and the congestion of people inside the train 400 when the train 400 runs through the one section 42. For example, the learning execution unit 210 performs machine learning using learning data including train schedule information from past train 400 operations, train operation status information for the train 400, the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 stopped before running through one section 42, the chronological position of train 400 when train 400 ran through one section 42, and the congestion status of people inside each of the multiple cars of train 400 when train 400 ran through one section 42, to generate a running status model that takes as input the train schedule information for train 400, the operation status information for train 400, and the congestion status of people in each of the multiple sections on the platform of station 50 where train 400 stopped before running through one section 42, and outputs the chronological position of train 400 when train 400 runs through one section 42 and the congestion status of people inside each of the multiple cars of train 400 when train 400 runs through one section 42.

[0074] The traveling situation estimation unit 212 estimates the traveling situation of the train 400. The traveling situation estimation unit 212 may estimate a future time-series position of the train 400. The traveling situation estimation unit 212 may estimate a future time-series position of the train 400 using a train position learning model stored in the memory unit 202. The traveling situation estimation unit 212 may estimate a future congestion state of people on the train 400. The traveling situation estimation unit 212 may estimate a future congestion state of people on the train 400 using a congestion state learning model stored in the memory unit 202.

[0075] The running condition estimation unit 212 may estimate the time-series position of the train 400 when the train 400, which is scheduled to run through a section 42 of the track 40 that is covered by the radio base station 300, runs through the section 42 and the congestion state of people inside the train 400 when the train 400 runs through the section 42. The running condition estimation unit 212 may estimate the time-series position of the train 400 when the train 400 runs through the section 42 and the congestion state of people inside the train 400 when the train 400 runs through the section 42, based on the train timetable information of the train 400 currently in operation, the operation status information of the train 400, and the congestion state of people on the platform of the station 50 where the train 400 stops before running through the section 42.

[0076] The running condition estimation unit 212 may use the train schedule information acquired by the acquisition unit 208 to estimate the time-series position of the train 400 when it runs through one section 42 of the track 40. The running condition estimation unit 212 estimates the time-series position of the train 400 when it runs through one section 42, for example, from the departure time of the train 400 at a station where the train 400 stops before running through the one section 42 and the arrival time of the train 400 at a station where the train 400 stops after running through the one section 42.

[0077] The running condition estimation unit 212 may estimate the time-series position of the train 400 when it runs through one section 42, using the train schedule information and operation status information acquired by the acquisition unit 208. For example, if the operation status information indicates that the train 400 is running according to the train schedule, the running condition estimation unit 212 uses the train schedule information to estimate the time-series position of the train 400. For example, if the operation status information indicates that the train 400 is not running according to the train schedule, the distribution platform 200 estimates the time-series position of the train 400 when it runs through one section 42 by taking into account the delay indicated by the operation status information to the time-series position of the train 400 when it runs according to the train schedule.

[0078] The running condition estimation unit 212 may use the train position learning model stored in the memory unit 202 to estimate the time-series position of the train 400 when the train 400 runs through one section 42. The running condition estimation unit 212 may acquire an estimation result of the time-series position of the train 400 when it runs through one section 42 by inputting the train schedule information and operation status information acquired by the acquisition unit 208 into the train position learning model stored in the memory unit 202.

[0079] The running condition estimation unit 212 may use the congestion condition learning model stored in the memory unit 202 to estimate the congestion condition of people on board the train 400 when the train 400 travels through one section 42. The running condition estimation unit 212 may acquire an estimation result of the congestion condition of people on board the train 400 when the train 400 travels through one section 42 by inputting the congestion condition of people on the platform of the station 50 where the train 400 stopped before traveling through one section 42, which was acquired by the acquisition unit 208, into the congestion condition learning model.

[0080] The traveling situation estimation unit 212 may use the traveling situation learning model stored in the memory unit 202 to estimate the time-series position of the train 400 when the train 400 travels through the one section 42 and the congestion state of people inside the train 400 when the train 400 travels through the one section 42. The traveling situation estimation unit 212 may acquire estimated results of the time-series position of the train 400 when it travels through the one section 42 and the congestion state of people inside the train 400 when it travels through the one section 42 by inputting the train schedule information, operation status information, and the congestion state of people on the platform of the station 50 where the train 400 stopped before traveling through the one section 42 acquired by the acquisition unit 208 into the traveling situation learning model.

[0081] The traveling situation estimation unit 212 may estimate the time-series position of the train 400 when the train 400 travels through one section 42 and the congestion state of people inside the train 400 when the train 400 travels through one section 42, based on train schedule information for the train 400 currently in operation, operation status information for the train 400, the congestion state of people on the platform of a station 50 where the train 400 stops before traveling through one section 42, and the congestion state of people inside the train 400 before stopping at the station 50. The traveling situation estimation unit 212 may make the estimation using a train position learning model and a congestion state learning model. The traveling situation estimation unit 212 may make the estimation using the traveling situation learning model.

[0082] The traveling situation estimation unit 212 may estimate the congestion status of people in each of the multiple cars of the train 400. The traveling situation estimation unit 212 may estimate the time-series position of the train 400 when the train 400 travels through one section 42 and the congestion status of people in each of the multiple cars of the train 400 when the train 400 travels through one section 42, based on train schedule information for the train 400 currently in operation, operation status information for the train 400, and the congestion status of people in multiple sections corresponding to the multiple cars of the train 400 on the platform of the station 50 where the train 400 stops before traveling through one section 42. The traveling situation estimation unit 212 may make the estimation using a train position learning model and a congestion status learning model. The traveling situation estimation unit 212 may also make the estimation using the traveling situation learning model.

[0083] The traveling condition estimation unit 212 may estimate a so-called congestion rate as the congestion state of people on the train 400, and may determine that the train is in an unoccupied state if the congestion rate is lower than a predetermined threshold, and may determine that the train is in a congested state if the congestion rate is higher than the predetermined threshold. The traveling condition estimation unit 212 may determine that the train is in an unoccupied state if the estimated congestion rate is lower than a predetermined first threshold, may determine that the train is in a congested state if the congestion rate is higher than a second threshold that is higher than the first threshold, and may determine that the train is in a normal state if the congestion rate is between the first threshold and the second threshold.

[0084] The traveling condition estimation unit 212 may estimate a so-called congestion rate as the congestion state of people inside the carriages of the train 400, and may determine that the train is in an unoccupied state if the congestion rate is lower than a predetermined threshold, and may determine that the train is in a congested state if the congestion rate is higher than the predetermined threshold. The traveling condition estimation unit 212 may determine that the train is in an unoccupied state if the estimated congestion rate is lower than a predetermined first threshold, may determine that the train is in a congested state if the congestion rate is higher than a second threshold that is higher than the first threshold, and may determine that the train is in a normal state if the congestion rate is between the first threshold and the second threshold.

[0085] Based on the estimation result by the traveling condition estimation unit 212, the base station control unit 214 controls the radio base station 300 to radiate a beam to cover the train 400 traveling in one section 42. Based on the estimation result by the traveling condition estimation unit 212, the base station control unit 214 may control the radio base station 300 to radiate one beam toward the train 400. Based on the estimation result by the traveling condition estimation unit 212, the base station control unit 214 may control the radio base station 300 to radiate multiple beams toward the train 400.

[0086] When it is determined that the train 400 is not crowded, the base station control unit 214 may control the radio base station 300 to irradiate one beam onto the entire train 400. When it is determined that the train 400 is crowded, the base station control unit 214 may control the radio base station 300 to irradiate multiple beams onto the train 400.

[0087] The base station control unit 214 may control the radio base station 300 to irradiate multiple beams to a car determined to be in a crowded state among the multiple cars of the train 400. The base station control unit 214 may control the radio base station 300 to irradiate one beam to a series of multiple cars determined to be in an unoccupied state among the multiple cars of the train 400.

[0088] The traveling condition estimation unit 212 may estimate the congestion state of people in multiple sections corresponding to multiple cars of the train 400 on the platform of the station 50 and the number of user terminals for each supported frequency, based on connected user information including location information of the UE 30 received from the UE 30 within the range of the radio base station by a radio base station installed in the station 50 where the train 400 stops before traveling through one section 42 and frequency information supported by the wireless communication function of the UE 30. The base station control unit 214 may control the radio base station 300 to irradiate the train 400 with multiple beams of different frequencies, based on the estimation result by the traveling condition estimation unit 212.

[0089] 8 schematically illustrates an example of the hardware configuration of a computer 1200 that functions as the management infrastructure 100 or the distribution infrastructure 200. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or can cause the computer 1200 to execute operations associated with the apparatus according to the present embodiment or one or more "parts," and / or can cause the computer 1200 to execute a process according to the present embodiment or steps of the process. Such a program can be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0090] The computer 1200 according to this embodiment includes a CPU 1212, a GPU 1213, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communications interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes a ROM 1230 and legacy input / output units such as a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0091] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller 1216 itself, and causes the image data to be displayed on the display device 1218.

[0092] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0093] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0094] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or a method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

[0095] For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to a network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0096] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive 1226 (DVD-ROM 1227), an IC card, etc. to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0097] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0098] The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0099] The blocks in the flowcharts and block diagrams in the present embodiments may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0100] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disc read-only memories (CD-ROMs), digital versatile discs (DVDs), Blu-ray discs, memory sticks, integrated circuit cards, and the like.

[0101] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0102] The computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or another programmable data processing device processor or programmable circuit, either locally or via a local area network (LAN), a wide area network (WAN) such as the Internet, so that the processor or programmable circuit of the programmable data processing device, such as a computer, executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Here, the computer may be a personal computer (PC), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, a special-purpose computer, or the like, or may be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system, and is a broad definition of computer. In a distributed computing system, multiple computers collectively execute a program by each executing a portion of the program and passing data between the computers as needed during program execution.

[0103] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc. A computer may have one processor or multiple processors. In a multiprocessor system with multiple processors, each processor executes a portion of a program and passes data between processors as needed during program execution, allowing the multiple processors to collectively execute the program. For example, in multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which portion of a program each processor executes changes dynamically. Which portion of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0104] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0105] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order.

[0106] 10 Communication system, 30 UE, 40 Track, 42 ​​One section, 50 Station, 100 Management base station, 200 Distribution base station, 202 Memory unit, 204 RAN control unit, 206 AI management unit, 208 Acquisition unit, 210 Learning execution unit, 212 Traveling situation estimation unit, 214 Base station control unit, 300 Radio base station, 310 RAN, 312 Beam, 313 Beam, 314 Beam, 316 Beam, 400 Train, 410 Vehicle, 420 Vehicle, 430 Vehicle, 1200 Computer, 1210 Host controller, 1212 CPU, 1213 GPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / output controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 I / O chip

Claims

1. A communication system comprising: a running condition estimation unit that estimates the time-series position of a train that is scheduled to run on a section of track that is covered by a wireless base station when the train runs on the section of track and the congestion status of people on the train when the train runs on the section of track; and a base station control unit that controls the wireless base station to irradiate a beam to cover the train running on the section of track based on the estimation results by the running condition estimation unit.

2. The communication system of claim 1, wherein the running condition estimation unit estimates the time-series position of the train when it runs along the section of track and the congestion of people inside the train when it runs along the section of track based on train schedule information for the train currently in operation, train operation status information for the train, and the congestion of people on the platform of the station where the train stops before running along the section of track.

3. A memory unit for storing: a train position learning model that takes train schedule information and train operation status information as input and outputs the time-series position of the train when it runs on the one section of track, the train position learning model being generated by machine learning using learning data including train schedule information from past train operations, train operation status information of the train, and the time-series position of the train when it runs on the one section of track; and a congestion situation learning model that takes as input the congestion situation of people on the platform of a station where the train stopped before running on the one section of track in the past and outputs the congestion situation of people inside the train when it runs on the one section of track, the congestion situation being generated by machine learning using learning data including the congestion situation of people on the platform of a station where the train stopped before running on the one section of track in the past and the congestion situation of people inside the train when it runs on the one section of track; 3. The communication system according to claim 2, wherein the traveling condition estimation unit uses the train position learning model and the congestion condition learning model to estimate the time-series position of the train when it travels along the section of the track and the congestion condition of people inside the train when it travels along the section of the track.

4. A memory unit for storing a running situation learning model that takes train running schedule information, train running status information, and the congestion of people on the platform of a station where the train stopped before running on the one section of track as inputs, and outputs the position of the train in time series when the train runs on the one section of track and the congestion of people on the train when the train runs on the one section of track, the model being generated by machine learning using learning data including train running schedule information from past train operations, train running status information, the congestion of people on the platform of a station where the train stopped before running on the one section of track, the time-series position of the train when the train ran on the one section of track, and the congestion of people on the train when the train ran on the one section of track, 3. The communication system according to claim 2, wherein the traveling situation estimation unit uses the traveling situation learning model to estimate a time-series position of the train when the train travels along the section of the track and a congestion state of people inside the train when the train travels along the section of the track.

5. A communication system as described in any one of claims 2 to 4, wherein the running condition estimation unit estimates the time series position of the train when it runs along the section of track and the congestion of people inside the train when it runs along the section of track based on train schedule information for the train currently in operation, train operation status information for the train, the congestion of people on the platform of a station where the train will stop before running along the section of track, and the congestion of people inside the train before it stops at the station.

6. A communication system as described in any one of claims 2 to 4, wherein the train has a plurality of cars, the running condition estimation unit estimates the time series position of the train when it runs along the one section of track and the occupancy status of people in each of the plurality of cars of the train when it runs along the one section of track based on operation timetable information for the train while it is in operation, operation status information for the train, and the occupancy status of people in a plurality of sections corresponding to the plurality of cars of the train on the platform of a station where the train stops before running along the one section of track, and the base station control unit controls the wireless base station to irradiate a plurality of beams onto the train based on the estimation results of the running condition estimation unit.

7. The communication system according to claim 6, wherein the base station control unit controls the wireless base station to irradiate a plurality of beams onto a car determined to be in a crowded state among the plurality of cars of the train.

8. The communication system described in claim 6, wherein the base station control unit controls the radio base station to irradiate one beam to a plurality of consecutive cars among the plurality of cars of the train that are determined to be in an unoccupied state.

9. A communication system as claimed in any one of claims 2 to 4, wherein the train includes a plurality of carriages, and the running condition estimation unit estimates the congestion status of a plurality of sections corresponding to the plurality of carriages of the train on the platform of the station and the number of user terminals for each supported frequency based on user terminal information including location information of the user terminal received from the user terminal within the range of the radio base station and frequency information supported by the wireless communication function of the user terminal, and the base station control unit controls the radio base station to irradiate the train with a plurality of beams of different frequencies based on the estimation results by the running condition estimation unit.

10. A control method executed by a computer, comprising: a running condition estimation step of estimating the time-series position of a train scheduled to run on a section of track covered by a radio base station when the train runs on the section of track and the congestion status of people on the train when the train runs on the section of track; and a base station control step of controlling the radio base station to irradiate a beam to cover the train running on the section of track based on the estimation results in the running condition estimation step.

11. A program for causing a computer to execute the control method according to claim 10.

Images