Information processing device, information processing method, and information processing program

Abstract

Provided are an information processing device, an information processing method, and an information processing program that estimate the type of communication traffic. This information processing device comprises: a first acquisition unit that acquires a plurality of pieces of first traffic information related to communication by a base station in a simulated communication environment; a second acquisition unit that acquires, from a terminal, type information indicating the connection destination type of the communication via the base station in the simulated communication environment; an identification unit that, on the basis of the plurality of pieces of first traffic information acquired by the first acquisition unit and the type information acquired by the second acquisition unit, identifies a piece of first traffic information and type information indicating the communication connection destination type corresponding to the piece of first traffic information; and a generation unit that generates a trained model that has been trained on the piece of first traffic information identified by the identification unit and the type information corresponding to the piece of first traffic information.

Description

Information Processing Apparatus, Information Processing Method, and Information Processing Program

[0005]

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

[0002] Conventionally, time-series data of communication traffic is modeled, and an application type and state are estimated using a learned model. Based on the result of analyzing the communication traffic in this way, the communication traffic is controlled. That is, the base station performs radio scheduling such as preferentially allocating a radio channel to a terminal with a high urgency.

[0003] Japanese Patent Application Laid-Open No. 2021-168517

[0004] An information processing apparatus according to one aspect includes: a first acquisition unit that acquires a plurality of first traffic information related to communication of a base station in a simulated communication environment; a second acquisition unit that acquires type information that is the type of a connection destination of communication from a terminal via the base station in the simulated communication environment; a specifying unit that specifies the first traffic information and type information that is the type of the connection destination of the communication corresponding to the first traffic information based on the plurality of first traffic information acquired by the first acquisition unit and the type information acquired by the second acquisition unit; and a generation unit that generates a learned model by learning the first traffic information specified by the specifying unit and the type information corresponding to the first traffic information.

[0005] It is a diagram (schematic diagram) for explaining an information processing apparatus according to an embodiment. It is a block diagram for explaining an information processing apparatus according to an embodiment. It is a first flowchart for explaining an information processing method according to an embodiment. It is a second flowchart for explaining an information processing method according to an embodiment.

[0006] Hereinafter, an embodiment will be described.

[0007] [[ID=二十一]] [Outline of Information Processing Apparatus 100] First, the outline of an information processing apparatus 100 according to an embodiment will be described. FIG. 1 is a diagram (schematic diagram) for explaining an information processing apparatus 100 according to an embodiment.

[0008] Conventionally, time-series data of communication traffic is modeled, and the application type and state are estimated using a trained model. Based on the results of this analysis of communication traffic, communication traffic is controlled. That is, base stations perform wireless scheduling, such as allocating wireless channels preferentially to terminals with high urgency. However, communication traffic differs depending on whether a terminal is displaying a video or a social networking service. Conventional technology does not analyze communication traffic from this perspective.

[0009] In 5G networks (fifth-generation communication) that conform to the 3GPP (3rd Generation Partnership Project) (registered trademark) communication standard, it is possible to specify the QoS (Quality of Service) that the communicating traffic must satisfy using an ID (Identifier) ​​such as 5QI (5G network Quality of service class Identifier (5G QoS Identifier)), and in principle, it is possible to set a 5QI for each type of traffic. However, in reality, it is impossible to set a unique 5QI for all types of traffic, making identification practically impossible. On the other hand, it is also possible to make a comprehensive judgment using algorithms, but the various information used in that judgment changes depending on the surrounding environment and time of day, and it is not possible to handle all cases. As mentioned above, even with the use of algorithms, there is a challenge in that it is difficult to estimate the type of traffic based on the surrounding environment and time of day.

[0010] Therefore, the information processing device 100 of this embodiment performs AI / ML (artificial intelligence / machine learning) training in a simulator environment (under a simulated communication environment) that can simulate the environment. The information processing device 100 simulates profiles of different wireless environments, such as urban areas / residential areas and daytime / nighttime, according to the actual communication environment. The information processing device 100 generates various types of communication traffic in the simulator environment, and this communication traffic also simulates the trends in the actual communication environment. This communication traffic becomes the correct data for training. The information processing device 100 implements the AI ​​that has been trained in this way in the base station 301, or connects with the base station 301 via an external interface. The MAC (Media Access Control) scheduler of the base station 301 works in conjunction with the AI ​​to determine the behavior of the communication traffic from the results of the AI's inference (estimation), and performs scheduling according to that behavior.

[0011] Specifically, in this embodiment, when a terminal 202 connects to a communication destination 203 via a base station 201 under a simulated communication environment (for example, under a simulator environment), the information processing device 100 acquires first traffic information regarding the communication of the terminal 202 and type information that determines the type of the connection destination 203.

[0012] In other words, the information processing device 100 acquires multiple pieces of first traffic information relating to the communication of the base station 201 in a simulated communication environment (for example, a simulator environment). The information processing device 100 may, for example, acquire communication data acquired at the MAC layer (data link layer) of the base station 201 (for example, all communication data) as first traffic information. If the first traffic information is MAC layer communication data, for example, it may include information indicating the structure of the MAC frame, in addition to the destination ID, destination address, source ID, and source address.

[0013] The information processing device 100 acquires type information for the communication destination 203 via the base station 201 from the terminal 202 in a simulated communication environment. The information processing device 100 may acquire, for example, type information acquired at the MAC layer of the base station 201, or type information acquired from the communication destination 203. The type of the connection destination 203 may be, for example, the type of data (Trf type) sent from the connection destination 203 to the terminal 202, or it may be a type such as text data, image data, audio data, and video data.

[0014] The information processing device 100 matches the first traffic information with the type information to identify communication for the same terminal 202. That is, based on the multiple first traffic information and the multiple type information, the information processing device 100 identifies the first traffic information for the same terminal 202 and the type information which is the type of connection destination 203 for the communication corresponding to the first traffic information. As an example in this case, the information processing device 100 may identify the first traffic information and type information for communication for the same terminal 202 based on the information that identifies the terminal 202 (identification information) contained in the first traffic information and the type information corresponding to that first traffic information. The information processing device 100 learns the first traffic information and the type information corresponding to that first traffic information identified as described above to generate a trained model.

[0015] Next, the information processing device 100 acquires multiple pieces of second traffic information related to the communication of the base station 301 from the base station 301 in a real communication environment (actual communication network). The information processing device 100 may, for example, acquire communication data acquired at the MAC layer of the base station 301 (e.g., all communication data) as second traffic information.

[0016] The information processing device 100 estimates the type of communication destination 303 to which the second traffic information is recorded, based on the trained model generated as described above and the second traffic information. In other words, the information processing device 100 estimates the type of connection destination 303 (communication destination 303) to which the same terminal 302 connects via the base station 301 in a real communication environment (actual communication network).

[0017] As a result, the information processing device 100 of this embodiment can estimate the behavior of actual communication traffic, that is, the behavior of uplink communication from terminal 302 and downlink communication to terminal 302 (the behavior of communication according to the type of destination 303 when terminal 302 connects to destination 303), and can perform scheduling according to the estimated behavior.

[0018] Therefore, the information processing device 100 may be configured as a generation device or the like that generates a trained model. Alternatively, the information processing device 100 may be configured as an estimation device or the like that uses the trained model to estimate the type of destination 303 of the terminal 302 in a real communication environment. The information processing device 100 may also be configured as an adjustment device or the like that adjusts (schedules) communications based on the result of the estimation. The information processing device 100 is not limited to the example device described above, but may be configured as various devices or the like. The information processing device 100 may be a computer such as a server, base station, desktop, laptop, tablet, or smartphone. This disclosure relates to RIC (RAN Intelligent Controller).

[0019] [Details of the Information Processing Device 100] Next, an information processing device 100 according to one embodiment will be described in detail. Figure 2 is a block diagram illustrating the information processing device 100 according to one embodiment.

[0020] The information processing device 100 includes, for example, a communication unit 121, a storage unit 122, a display unit 123, and a control unit 110. The communication unit 121, the storage unit 122, and the display unit 123 may be an embodiment of the output unit. The control unit 110 includes, for example, a first acquisition unit 111, a second acquisition unit 112, a specific unit 113, a generation unit 114, a third acquisition unit 115, an estimation unit 116, and an adjustment unit 117. The control unit 110 may be configured by, for example, the arithmetic processing unit of the information processing device 100. The control unit 110 (for example, the arithmetic processing unit) may realize the functions of each unit (for example, the first acquisition unit 111, the second acquisition unit 112, the specific unit 113, the generation unit 114, the third acquisition unit 115, the estimation unit 116, and the adjustment unit 117) by appropriately reading and executing various programs stored in the storage unit 122, etc. In other words, the functions of each part may be realized through computer implementation.

[0021] The communication unit 121 is a communication interface that enables the transmission and reception of various types of information with, for example, an external device (external device) located outside the information processing device 100.

[0022] The storage unit 122 may store, for example, various information and programs. Examples of the storage unit 122 include memory, solid-state drives, and hard disk drives. The storage unit 122 may also be, for example, a storage area and server located in the cloud.

[0023] The display unit 123 is a display capable of displaying various characters, symbols, images, etc.

[0024] The first acquisition unit 111 acquires a plurality of first traffic information related to the communication of the base station 201 in a simulated communication environment. The first acquisition unit 111 may acquire the first traffic information from an external device (not shown) via, for example, the communication unit 121. The external device here may be, for example, a server and a simulation device that provides a simulated communication environment. Alternatively, the first acquisition unit 111 may acquire the first traffic information from an external memory (not shown) in which the first traffic information is stored, if that memory is connected to the interface (not shown) of the information processing device 100. The first acquisition unit 111 may acquire, for example, communication data (e.g., all communication data) acquired at the MAC layer of the base station 201 deployed in the simulated communication environment as the first traffic information. The first traffic information may include, for example, a destination ID, destination address, source ID, source address, and information indicating the configuration of the MAC frame when it is MAC layer communication data.

[0025] The second acquisition unit 112 acquires type information, which is the type of connection destination 203 for communication from the terminal 202 via the base station 201, under simulated communication conditions. The second acquisition unit 112 may acquire type information from an external device (not shown) via, for example, the communication unit 121. The external device here may be, for example, a server and a simulation device that provides a simulated communication environment. Alternatively, the second acquisition unit 112 may acquire type information from an external memory (not shown) in which type information is stored, if that memory is connected to the interface (not shown) of the information processing device 100.

[0026] The second acquisition unit 112 may acquire, for example, type information acquired at the MAC layer of a base station 201 deployed in the simulated communication environment, or type information acquired from the connection destination 203 of the simulated communication. The type of the connection destination 203 may be, for example, the type of data (Trf type) sent from the connection destination 203 to the terminal 202, or it may be a type such as text data, image data, voice data, and video data.

[0027] The identification unit 113 identifies the type information of the first traffic information and the type of the connection destination 203 for the communication corresponding to the first traffic information, based on the multiple first traffic information acquired by the first acquisition unit 111 and the type information acquired by the second acquisition unit 112. The identification unit 113 matches the first traffic information and the type information to identify communication (simulated communication) for the same terminal 202. That is, the identification unit 113 identifies the first traffic information and the type information of the connection destination 203 for the same terminal 202, based on the multiple first traffic information and the multiple type information. As an example in this case, the identification unit 113 may identify the first traffic information and type information for communication of the same terminal 202 based on the information that identifies the terminal 202 (identification information) contained in the first traffic information and the type information, respectively.

[0028] The generation unit 114 learns the first traffic information identified by the identification unit 113 and the type information corresponding to that first traffic information to generate a trained model. In other words, the generation unit 114 learns the first traffic information and the type information corresponding to that first traffic information in a simulated communication to generate a trained model.

[0029] The generation unit 114 may generate a trained model for each region where the base station 201 is installed in the simulated communication environment. Each region may be, for example, based on pre-defined regional attributes such as urban areas and residential areas. For example, in simulated communication in urban areas, the amount of communication traffic is relatively high during the day and relatively low at night. Similarly, as an example, in simulated communication in residential areas, the amount of communication traffic is relatively low during the day and relatively high at night. The generation unit 114 may also generate a trained model by learning first traffic information and type information corresponding to that first traffic information for each region (based on regional attributes) in the simulated communication environment.

[0030] Similarly, the generation unit 114 may generate a trained model for each time period of communication in which first traffic information is generated at the base station 201 under the simulated communication environment. Each time period of communication may be, for example, each predetermined time (time zone), such as daytime and nighttime. The generation unit 114 may also generate a trained model by learning the first traffic information and the type information corresponding to the first traffic information for each time period of communication under the simulated communication environment.

[0031] The actual base station 301 implements, for example, the trained model generated by the generation unit 114, or cooperates with the trained model generated by the generation unit 114 via an external interface. That is, the actual base station 301 (for example, the third acquisition unit 115, estimation unit 116, and adjustment unit 117, etc.) cooperates with the AI ​​(the AI ​​that uses the trained model described above), determines the behavior of the traffic from the results estimated by the AI, and performs scheduling according to that behavior. Scheduling may include, for example, determining the frequency band and communication timing to be allocated to the terminal 302, and the length of a single communication session.

[0032] The third acquisition unit 115 acquires second traffic information relating to the communication of the base station 301 under actual communication conditions. That is, the third acquisition unit 115 acquires, for example, second traffic information at the base station 301 deployed under actual communication conditions. The third acquisition unit 115 may acquire, for example, communication data acquired at the MAC layer of the actual base station 301 (e.g., all communication data) as second traffic information.

[0033] The third acquisition unit 115 may acquire the second traffic information from an external device (not shown) via, for example, the communication unit 121. The external device here may be, for example, a server and an actual base station 301. Alternatively, the third acquisition unit 115 may acquire the second traffic information from an external memory (not shown) in which the second traffic information is stored, if that memory is connected to the interface (not shown) of the information processing device 100.

[0034] The estimation unit 116 uses the trained model described above to estimate the destination 303 (the type of destination 303 to which the terminal 302 is connected) of the terminal 302 in the actual communication, based on the second traffic information (actual communication behavior) in the actual communication. In other words, the estimation unit 116 estimates the type of destination 303 (communication destination 303) to which the same terminal 302 connects via the base station 301 in a real communication environment (actual communication network). To put it another way, the estimation unit 116 estimates the type of communication destination 303 to which the second traffic information is recorded, based on the trained model generated by the generation unit 114 and the second traffic information acquired by the third acquisition unit 115.

[0035] Furthermore, the estimation unit 116 may use a trained model to estimate the type of communication destination 303 from second traffic information for each region (regional attribute) to which the actual base station 301 belongs. That is, the estimation unit 116 may, for example, classify the region where the actual base station 301 is located according to pre-set regional attributes such as urban areas and residential areas, similar to how the trained model is generated. The estimation unit 116 may, for example, use the second traffic information acquired by the actual base station 301 and a trained model generated based on the same region (regional attribute) as the region (regional attribute) to which the actual base station 301 is located to estimate the type of communication destination 303 under actual communication conditions. In other words, the estimation unit 116 may estimate the type of communication destination 303 in an actual communication environment based on second traffic information acquired at an actual base station 301 in which a region (regional attributes) has been set in advance, and a trained model generated by learning first traffic information and type information at a base station 201 in a simulated communication environment when that region (regional attributes) is set.

[0036] Furthermore, the estimation unit 116 may, for example, classify the time period during which the second traffic information is generated at the actual base station 301 (the time period when communication occurs) into pre-set time periods, such as daytime and nighttime, similar to how a trained model is generated. The estimation unit 116 may, for example, use the second traffic information acquired at the actual base station 301 and a trained model generated based on the same time period as the time period during which the second traffic information is generated (the time period when communication occurs) to estimate the type of communication destination 303 under actual communication conditions. In other words, the estimation unit 116 may estimate the type of communication destination 303 under actual communication conditions based on the second traffic information acquired at the actual base station 301 according to a pre-set time period and a trained model generated by learning the first traffic information and type information at the base station 201 under the simulated communication environment during that time period.

[0037] The adjustment unit 117 may, as a specific example, be a MAC scheduler or the like. The adjustment unit 117 adjusts the wireless communication environment of the base station 301 under actual communication conditions according to the type estimated by the estimation unit 116. The adjustment unit 117 can estimate the communication load, etc., according to the type of connection destination 303. As a specific example, the adjustment unit 117 estimates that the communication load is relatively large when the terminal 302 connects to a video viewing site and views videos. Similarly, as a specific example, the adjustment unit 117 estimates that the communication load is relatively small when the terminal 302 connects to a website and an SNS site and views web pages and SNS.

[0038] The adjustment unit 117 may, for example, adjust the wireless communication environment of the base station 301 according to the region (regional attributes) in which the base station 301 is located under actual communication conditions. Similarly, the adjustment unit 117 may, for example, adjust the actual wireless communication environment of the base station 301 according to the time of day under actual communication conditions.

[0039] The adjustment unit 117 schedules the wireless communication environment (communication resources) of the base station 301 under actual communication conditions, for example, according to the type estimated by the estimation unit 116. That is, when the communication load is relatively large, the adjustment unit 117 adjusts the communication environment (communication resources) of the base station 301 to relatively improve (make better). When the communication load is relatively small, the adjustment unit 117 adjusts the communication environment (communication resources) of the base station 301 to maintain it at the same level or to relatively reduce it. The adjustment unit 117 may adjust the wireless communication environment of the base station 301 using, for example, known technology.

[0040] The adjustment unit 117 may, for example, control the output unit to output the results of adjusting the wireless communication environment of the base station 301 as a history (log). The output unit may be, for example, a communication unit 121, a storage unit 122, and a display unit 123. That is, the adjustment unit 117 may, for example, control the communication unit 121 to transmit the history (log) information of the results of adjusting the wireless communication environment of the base station 301 to an external device (not shown). The external device here may be, for example, a server. The adjustment unit 117 may, for example, control the storage unit 122 to store the history (log) information of the results of adjusting the wireless communication environment of the base station 301. The adjustment unit 117 may, for example, control the display unit 123 to display the history (log) of the results of adjusting the wireless communication environment of the base station 301.

[0041] [Information Processing Method] Next, an information processing method according to one embodiment will be described.

[0042] First, we will explain the information processing method for generating a trained model. Figure 3 is a first flowchart illustrating the information processing method according to one embodiment.

[0043] In step ST101, the first acquisition unit 111 acquires multiple first traffic information related to the communication of the base station 201 under simulated communication conditions.

[0044] In step ST102, the second acquisition unit 112 acquires type information that is the type of the communication connection destination 203 from the terminal 202 via the base station 201 in a simulated communication environment.

[0045] In step ST103, the specifying unit 113 specifies the first traffic information and the type information that is the type of the communication connection destination 203 corresponding to the first traffic information, based on the plurality of first traffic information acquired in step ST101 and the type information acquired in step ST102.

[0046] In step ST104, the generation unit 114 learns the first traffic information specified in step ST103 and the type information corresponding to the first traffic information, and generates a learned model. The generation unit 114 may generate a learned model for each area where the base station 201 in the simulated communication environment is installed. Similarly, the generation unit 114 may generate a learned model for each time zone of the communication in which the first traffic information occurs in the base station 201 in the simulated communication environment.

[0047] Next, an information processing method for adjusting (scheduling) communication resources in the base station 301 will be described. FIG. 4 is a second flowchart for explaining an information processing method according to an embodiment.

[0048] The base station 301 implements the learned model generated in step ST104 or cooperates with the learned model.

[0049] In step ST201, the third acquisition unit 115 (for example, the base station 301 or the like) acquires second traffic information related to the communication of the base station 301 in an actual communication environment.

[0050] In step ST202, the estimation unit 116 (for example, the base station 301 or the like) estimates the type of the communication connection destination 303 that records the second traffic information, based on the learned model generated in step ST104 and the second traffic information acquired in step ST201.

[0051] In step ST203, the adjustment unit 117 adjusts (schedules) the wireless communication environment of the base station 301 under actual communication conditions according to the type estimated in step ST202.

[0052] [Functions and Circuitry] Next, the functions and circuitry of the information processing device 100 described above will be explained. Each part of the information processing device 100 may be implemented as a function of a computer's arithmetic processing unit or the like. The information processing device 100 may implement the functions of the first acquisition unit 111, the second acquisition unit 112, the identification unit 113, the generation unit 114, the third acquisition unit 115, the estimation unit 116, and the adjustment unit 117 by a single control unit 110 (for example, an arithmetic processing unit, etc.), or the functions of the first acquisition unit 111, the second acquisition unit 112, the identification unit 113, the generation unit 114, the third acquisition unit 115, the estimation unit 116, and the adjustment unit 117 may be implemented in a distributed manner by multiple different control units 110 (for example, arithmetic processing units, etc.). The first acquisition unit 111, second acquisition unit 112, identification unit 113, generation unit 114, third acquisition unit 115, estimation unit 116, and adjustment unit 117 (control unit 110) of the information processing device 100 described above may be implemented as the first acquisition function, second acquisition function, identification function, generation function, third acquisition function, estimation function, and adjustment function (control function), respectively, by the arithmetic processing unit of a computer. The information processing program can enable the computer to implement each of the above-described functions. The information processing program may be recorded on a computer-readable, non-temporary, tangible recording medium such as memory, a solid-state drive, a hard disk drive, or an optical disc. The storage medium may be rephrased as, for example, a non-temporary, tangible, computer-readable medium that stores the information processing program. The information processing program may also be transmitted online. The information processing program can be implemented as a product (computer program product) by the control unit 110 (for example, the arithmetic processing unit). Furthermore, as described above, each part of the information processing device 100 may be implemented by the arithmetic processing unit of a computer. The arithmetic processing unit, etc., is composed of, for example, an integrated circuit. Therefore, each part of the information processing device 100 may be realized as a circuit that constitutes the arithmetic processing unit, etc.In other words, the first acquisition unit 111, second acquisition unit 112, identification unit 113, generation unit 114, third acquisition unit 115, estimation unit 116, and adjustment unit 117 (control unit 110) of the information processing device 100 may be implemented as a first acquisition circuit, second acquisition circuit, identification circuit, generation circuit, third acquisition circuit, estimation circuit, and adjustment circuit (control circuit) that constitute the arithmetic processing unit of a computer. Furthermore, the communication unit 121, storage unit 122, and display unit 123 (output unit) of the information processing device 100 may be implemented as, for example, a communication function, storage function, and display function (output function) that include the functions of an arithmetic processing unit. Furthermore, the communication unit 121, storage unit 122, and display unit 123 (output unit) of the information processing device 100 may be implemented as a communication circuit, storage circuit, and display circuit (output circuit) by being constructed by, for example, an integrated circuit. Furthermore, the communication unit 121, storage unit 122, and display unit 123 (output unit) of the information processing device 100 may be configured as a communication device, storage device, and display device (output device) by being composed of multiple devices, for example.

[0053] The information processing device 100 can be configured by combining one or any multiple of the above-described parts. In this disclosure, the term "information" is used, but the term "information" can be replaced with "data," and the term "data" can be replaced with "information."

[0054] [Aspects and Effects of this Embodiment] Next, an aspect of this embodiment and the effects of each aspect will be described. Note that the aspects described below are examples as of the time of filing, and this embodiment is not limited to the aspects described below. That is, this embodiment is not limited to the aspects described below, and may be realized by appropriately combining the parts described above. Also, a lower-level aspect may be referenced in any of the higher-level aspects. Furthermore, the effects of this embodiment described below are examples, and the effects of each aspect are not limited to those described below. Also, each aspect may have at least one of the effects described below, for example.

[0055] (Aspect 1) An information processing device in one aspect includes: a first acquisition unit that acquires a plurality of first traffic information related to base station communications in a simulated communication environment; a second acquisition unit that acquires type information which is the type of connection destination for communications from a terminal via a base station in a simulated communication environment; an identification unit that identifies the first traffic information and the type information which is the type of connection destination for communications corresponding to the first traffic information based on the plurality of first traffic information acquired by the first acquisition unit and the type information acquired by the second acquisition unit; and a generation unit that learns the first traffic information identified by the identification unit and the type information corresponding to the first traffic information and generates a trained model. As a result, the information processing device can generate a trained model that estimates the behavior of actual communication traffic, that is, the behavior of uplink communications from a terminal and downlink communications to that terminal (the behavior of communications according to the type of connection destination when a terminal connects to a connection destination).

[0056] (Aspect 2) An information processing device in one aspect may include a third acquisition unit that acquires second traffic information relating to base station communications in an actual communication environment, and an estimation unit that estimates the type of communication destination to record the second traffic information based on a trained model generated by a generation unit and the second traffic information acquired by the third acquisition unit. This allows the information processing device to estimate the behavior of actual communication traffic, that is, the behavior of uplink communication from a terminal and downlink communication to that terminal (the behavior of communication according to the type of destination when a terminal connects to a destination).

[0057] (Aspect 3) An information processing device in one aspect may include an adjustment unit that adjusts the wireless communication environment of the base station under actual communication conditions according to the type estimated by the estimation unit. This allows the information processing device to estimate the behavior of actual communication traffic, that is, the behavior of uplink communication from a terminal and downlink communication to that terminal (the behavior of communication according to the type of destination when a terminal connects to a destination), and to schedule communication at the actual base station according to the estimated behavior.

[0058] (Aspect 4) In one aspect of the information processing device, the generation unit may generate a trained model for each region where base stations are installed in a simulated communication environment. This allows the information processing device to use the trained model to estimate the behavior of the communication traffic of each actual base station belonging to each region.

[0059] (Aspect 5) In one aspect of the information processing device, the generation unit may generate a trained model for each time period of communication in which first traffic information is generated at a base station under a simulated communication environment. This allows the information processing device to use the trained model to estimate the behavior of actual base station communication traffic in each time period.

[0060] (Aspect 6) In one aspect of the information processing method, the computer performs the following steps: a first acquisition step of acquiring a plurality of first traffic information relating to base station communications in a simulated communication environment; a second acquisition step of acquiring type information which is the type of connection destination for communications from a terminal via a base station in a simulated communication environment; an identification step of identifying the first traffic information and the type information which is the type of connection destination for communications corresponding to the first traffic information, based on the plurality of first traffic information acquired in the first acquisition step and the type information acquired in the second acquisition step; and a generation step of learning the first traffic information identified in the identification step and the type information corresponding to the first traffic information to generate a trained model. As a result, the information processing method can achieve the same effects as the information processing device of the aspect described above.

[0061] (Aspect 7) An information processing program in one aspect provides a computer with: a first acquisition function that acquires a plurality of first traffic information related to base station communications in a simulated communication environment; a second acquisition function that acquires type information which is the type of connection destination for communications from a terminal via a base station in a simulated communication environment; an identification function that identifies the first traffic information and the type information which is the type of connection destination for communications corresponding to that first traffic information based on the plurality of first traffic information acquired by the first acquisition function and the type information acquired by the second acquisition function; and a generation function that learns the first traffic information identified by the identification function and the type information which is corresponding to that first traffic information to generate a trained model. As a result, the information processing program can achieve the same effects as the information processing device in the aspect described above.

[0062] By using the above-mentioned disclosure, we can contribute to achieving Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0063] 100 Information processing device 110 Control unit 111 First acquisition unit 112 Second acquisition unit 113 Identification unit 114 Generation unit 115 Third acquisition unit 116 Estimation unit 117 Adjustment unit 121 Communication unit 122 Storage unit 123 Display unit 201 Base station in simulator environment (simulated communication environment) 202 Terminal in simulator environment (simulated communication environment) 203 Terminal connection destination in simulator environment (simulated communication environment) 301 Base station in actual communication environment 302 Terminal in actual communication environment 303 Terminal connection destination in actual communication environment

Claims

1. An information processing device comprising: a first acquisition unit that acquires a plurality of first traffic information related to base station communications in a simulated communication environment; a second acquisition unit that acquires type information which is the type of connection destination for the communications from a terminal via the base station in the simulated communication environment; an identification unit that identifies the first traffic information and the type information which is the type of connection destination for communications corresponding to the first traffic information based on the plurality of first traffic information acquired by the first acquisition unit and the type information acquired by the second acquisition unit; and a generation unit that learns the first traffic information identified by the identification unit and the type information corresponding to the first traffic information to generate a trained model.

2. An information processing device according to claim 1, comprising: a third acquisition unit that acquires second traffic information relating to base station communications in an actual communication environment; and an estimation unit that estimates the type of communication destination to record the second traffic information based on a trained model generated by the generation unit and the second traffic information acquired by the third acquisition unit.

3. The information processing apparatus according to claim 2, further comprising an adjustment unit that adjusts the wireless communication environment of the base station under the actual communication environment according to the type estimated by the estimation unit.

4. The information processing apparatus according to claim 1, wherein the generation unit generates the learned model for each region where the base station is installed in the simulated communication environment.

5. The information processing apparatus according to claim 1, wherein the generation unit generates the trained model for each time period of communication in which the first traffic information is generated at the base station under the simulated communication environment.

6. An information processing method comprising: a first acquisition step in which a computer acquires a plurality of first traffic information relating to base station communications in a simulated communication environment; a second acquisition step in which a computer acquires type information that is the type of connection destination for the communications from a terminal via the base station in the simulated communication environment; an identification step in which a computer identifies the first traffic information and type information that is the type of connection destination for communications corresponding to the first traffic information based on the plurality of first traffic information acquired in the first acquisition step and the type information acquired in the second acquisition step; and a generation step in which a computer learns the first traffic information identified in the identification step and the type information corresponding to the first traffic information to generate a trained model.

7. An information processing program that enables a computer to implement: a first acquisition function that acquires multiple first traffic information related to base station communications in a simulated communication environment; a second acquisition function that acquires type information which is the type of connection destination for the communications from a terminal via the base station in the simulated communication environment; an identification function that identifies the first traffic information and the type information which is the type of connection destination for the communications corresponding to the first traffic information based on the multiple first traffic information acquired by the first acquisition function and the type information acquired by the second acquisition function; and a generation function that learns the first traffic information identified by the identification function and the type information corresponding to the first traffic information and generates a trained model.

Images