Communication management device, communication management method, and communication management system

Abstract

The aim is to manage the wireless resources used in MIMO communication for each of multiple communication terminals that share common wireless communication requirements, using a simpler configuration. [Solution] The system includes a learning unit 13 configured to learn the relationship between wireless communication requests and the wireless resource allocation information to respond to those requests using a machine learning model, with the allocation information of wireless resources in a MIMO transmission system used as training data for assigning wireless communication requests to multiple communication terminals 2 to which wireless communication requests are commonly applied, and a setting unit 15 configured to set communication management information, including the trained machine learning model constructed by the learning unit 13, to the multiple communication terminals 2.

Description

[Technical Field]

[0001] The present invention relates to a communication management device, a communication management method, and a communication management system, and more particularly to wireless resource management technology. [Background technology]

[0002] Conventional technologies for managing wireless resources used in MIMO (Multiple Input Multiple Output) communication have been known. For example, Patent Document 1 discloses a method for managing wireless resources in MIMO communication in which a communication terminal notifies the base station of its communication capabilities, such as the number of antennas and frequency bands, and service requests, and the base station then allocates an appropriate number of antennas, frequency bands, and element carriers to the communication terminal.

[0003] In the technology described in Patent Document 1, the management of appropriate wireless resource allocation for service requests is performed individually between each communication terminal and the base station, and as a result, the overall management of wireless resources for multiple communication terminals becomes complicated. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2015-065656 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] With conventional technologies, it was difficult to manage the wireless resources used in MIMO communication for each of multiple communication terminals with common wireless communication requirements, using a simpler configuration.

[0006] This invention was made to solve the above-mentioned problems, and aims to manage the wireless resources used in MIMO communication for each of multiple communication terminals that share common wireless communication requirements, using a simpler configuration. [Means for solving the problem]

[0007] To solve the above-mentioned problems, the communication management device according to the present invention comprises a learning unit configured to learn the relationship between a request for wireless communication and the allocation information of wireless resources to respond to the request for wireless communication, using the allocation information of wireless resources in a MIMO transmission system as training data, which is assigned to a plurality of communication terminals to which a request for wireless communication commonly applies; and a setting unit configured to set communication management information, including the learned machine learning model constructed by the learning unit, to the plurality of communication terminals.

[0008] Furthermore, in the communication management device according to the present invention, the allocation information for the wireless resource includes the number of transmitting and receiving antennas and the frequency band used in the MIMO transmission method, and the frequency band may be one or more frequency bands.

[0009] To solve the above-mentioned problems, the communication management device according to the present invention may have the wireless communication requirements applied according to the type of application executed by the plurality of communication terminals.

[0010] To solve the above-mentioned problems, the communication management method according to the present invention comprises a learning step in which a machine learning model learns the relationship between a request for wireless communication and the allocation information of wireless resources to respond to the request for wireless communication, using the allocation information of wireless resources in a MIMO transmission system as training data, which is assigned to a plurality of communication terminals to which a request for wireless communication commonly applies; and a setting step in which the plurality of communication terminals are configured to receive communication management information including the trained machine learning model constructed in the learning step.

[0011] Furthermore, in the communication management method according to the present invention, the allocation information for the wireless resource includes the number of transmitting and receiving antennas and the frequency band used in the MIMO transmission system, and the frequency band may be one or more frequency bands.

[0012] Furthermore, in the communication management method according to the present invention, the request relating to wireless communication may be a request that is applied according to the type of application executed by the plurality of communication terminals.

[0013] Furthermore, the communication management method according to the present invention may also include, for each of the plurality of communication terminals, a first acquisition step of acquiring a request for wireless communication applicable to its own terminal; a second acquisition step of acquiring the trained machine learning model included in the communication management information set in the setting step; a calculation step of providing the request for wireless communication applicable to its own terminal acquired in the first acquisition step as an unknown input to the trained machine learning model, performing calculations on the trained machine learning model, and outputting allocation information of the wireless resource to be assigned to the own terminal; and a communication management step of performing communication using the MIMO transmission method based on the allocation information of the wireless resource output in the calculation step.

[0014] To solve the above-mentioned problems, the communication management system according to the present invention is a communication management system comprising the above-mentioned communication management device and the plurality of communication terminals, wherein each of the plurality of communication terminals comprises: a first acquisition unit configured to acquire a request relating to the wireless communication applied to its own terminal; a second acquisition unit configured to acquire the trained machine learning model included in the communication management information set by the communication management device; a calculation unit configured to provide the request relating to the wireless communication applied to its own terminal acquired by the first acquisition unit as an unknown input to the trained machine learning model, perform calculations on the trained machine learning model, and output wireless resource allocation information to be assigned to its own terminal; and a communication management unit configured to perform communication using the MIMO transmission method based on the wireless resource allocation information output by the calculation unit. [Effects of the Invention]

[0015] According to the present invention, the relationship between wireless communication requests and the wireless resource allocation information for responding to those requests is learned using a machine learning model, with the allocation information of wireless resources in a MIMO transmission system used as training data for assigning wireless communication requests to multiple communication terminals to which wireless communication requests commonly apply. Therefore, with a simpler configuration, the management of wireless resources used in MIMO communication can be performed for each of the multiple communication terminals that share common wireless communication requests. [Brief explanation of the drawing]

[0016] [Figure 1] Figure 1 is a block diagram showing the configuration of a communication management system comprising a communication management device and a communication terminal according to an embodiment of the present invention. [Figure 2] Figure 2 is a block diagram showing the configuration of a communication terminal according to this embodiment. [Figure 3] Figure 3 is a diagram illustrating the overview of the communication management system according to this embodiment. [Figure 4]FIG. 4 is a diagram for explaining the configuration of the management table of the communication management device according to the present embodiment. [Figure 5] FIG. 5 is a diagram for explaining the configuration of the learning unit included in the communication management device according to the present embodiment. [Figure 6] FIG. 6 is a block diagram showing the hardware configuration of the communication management device according to the present embodiment. [Figure 7] FIG. 7 is a block diagram showing the hardware configuration of the communication terminal according to the present embodiment. [Figure 8] FIG. 8 is a sequence showing the operation of the communication management system according to the present embodiment. Embodiments for Carrying Out the Invention

[0017] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to FIGS. 1 to 8.

[0018] [Configuration of Communication Management System] FIG. 1 is a block diagram showing the configuration of a communication management system including a communication management device 1 and a communication terminal 2 according to an embodiment of the present invention. The communication management system according to the present embodiment includes a communication management device 1, a communication terminal 2, a base station 3, and a core network 4 corresponding to a 5G wireless communication system. The communication management system manages wireless resources of the MIMO transmission method in units of a plurality of communication terminals 2 to which requirements related to wireless communication are commonly applied.

[0019] The communication management device 1 and the core network 4 are connected via a network NW such as a LAN, a WAN, or the Internet. Also, the base station 3 and the core network 4 are connected via a backhaul link.

[0020] The communication terminal 2 is implemented by mobile communication terminals such as smartphones, tablet computers, and laptop computers, as well as IoT terminals that use a 5G mobile communication network, such as smart meters, wearable devices, and industrial sensors. In this embodiment, the communication terminal 2 is equipped with a SIM card and has a unique IP address that allows it to connect to the internet. In this embodiment, the communication terminal 2 is equipped with multiple antennas 208 and performs MIMO communication with the base station 3.

[0021] Multiple communication terminals 2 exist, and each communication terminal 2 is subject to wireless communication requirements. These requirements include those applicable depending on the type of application running on the communication terminal 2. For example, smart meters require low power consumption but do not need high bandwidth, and low latency is only required when necessary. On the other hand, streaming media such as video distribution require high bandwidth, low latency, and stable high throughput. Allocating the optimal number of MIMO communication antennas and frequency band to each communication terminal 2 according to the requirements of their respective applications and services leads to efficient use of wireless resources.

[0022] In this embodiment, communication terminals 2 that share common wireless communication requirements are grouped together to manage optimal wireless resources. As shown in Figure 1, Group 1 consists of n communication terminals 2 with IP addresses IP01 to IP0n. These communication terminals 2 are a group of terminals that share common requirements such as bandwidth and latency, as required by applications and services. In the example in Figure 1, m groups (where m is an integer greater than or equal to 1) that share common wireless communication requirements are configured. Details regarding the functional blocks and hardware configuration of the communication terminals 2 will be described later.

[0023] Base station 3 is a wireless base station compatible with the 5G system and relays communication between the communication terminal 2 located within the service area and the core network 4. Base station 3 can be realized, for example, by a computer equipped with a processor, main memory, communication interface, auxiliary storage, and input / output I / O connected via a bus, and a program that controls these hardware resources.

[0024] Base station 3 is further equipped with multiple antennas and communicates wirelessly with communication terminal 2 using MIMO communication. In this embodiment, MIMO communication is realized based on the number of MIMO communication antennas and frequency band allocated to communication terminal 2. Base station 3 performs more detailed resource management of frequency and time according to the channel state and works in cooperation with communication terminal 2 to realize MIMO communication that simultaneously transmits and receives multiple data streams.

[0025] The core network 4 authenticates when the communication terminal 2 connects to the mobile communication network and manages that connection. The core network 4 also controls the initiation, maintenance, and termination of data sessions for the communication terminal 2 to connect to a data network such as the Internet via a user plane function (UPF) (not shown) using allocated radio resources and perform data communication.

[0026] Figure 3 is a diagram illustrating the overview of the communication management system according to this embodiment. Figure 3 shows a two-dimensional plane in which radio resources are defined by the time axis and the frequency axis, and a spatial axis (number of antennas). As shown in Figure 3, the radio resources are further divided into resource blocks consisting of time slots and subcarriers. For example, if a 2x2 MIMO is configured with two transmitting antennas and two receiving antennas, spatial streams s1 and s2 are provided along the spatial axis in Figure 3. For simplicity of explanation, in Figure 3, the number of transmitting and receiving antennas is assumed to be the same as the number of spatial streams, and spatial streams s1 and s2 represent the two antennas in the 2x2 MIMO configuration.

[0027] The communication management system assigns to the communication terminal 2 a number of antennas N (where N is a positive integer greater than or equal to 1) and one or more frequency bands suitable for the wireless communication requirements applied to the communication terminal 2. For example, if the number of antennas N=4 and frequency bands f1 and f3 are assigned in a 4x4 MIMO configuration, the communication terminal 2 and base station 3 will each use their four antennas to send and receive four data streams in parallel on frequency bands f1 and f3.

[0028] [Functional blocks of the communication management device] As shown in Figure 1, the communication management device 1 comprises a third acquisition unit 10, a group management unit 11, a first storage unit 12, a learning unit 13, a second storage unit 14, and a setting unit 15.

[0029] The third acquisition unit 10 acquires requests related to wireless communication as a grouping criterion for grouping communication terminals 2 that use the same number of antennas and frequency band. The third acquisition unit 10 can acquire the type of application that each of the multiple communication terminals 2 runs as a grouping criterion. For example, the third acquisition unit 10 accepts and acquires input of grouping criteria from an administrator.

[0030] The group management unit 11 assigns a group ID to the wireless communication request information acquired by the third acquisition unit 10 to create grouping information, and further groups the multiple communication terminals 2. The group management unit 11 can, for example, assign a group ID to each type of application to create grouping information.

[0031] The group management unit 11 obtains information about wireless communication requests and the IP addresses of the communication terminals 2 from each managed communication terminal 2 via the core network 4. Then, the group management unit 11 issues a group ID to each of the IP addresses of the multiple communication terminals 2 based on the grouping information.

[0032] Figure 4 shows the configuration of the management table 110 managed by the group management unit 11. First, the group management unit 11 stores the "group ID" information assigned to the "application type" in the management table 110 as grouping information. Then, for example, when "application 1" is launched by the communication terminal 2, information indicating the wireless communication request "application 1" is generated within the dedicated application and sent to the communication management device 1 along with the IP address "IP01" of the communication terminal 2. In this case, the group management unit 11 issues group ID "1" to the IP address "IP01" of the communication terminal 2 based on the information indicating "application 1" received from the communication terminal 2.

[0033] The first storage unit 12 stores the management table 110.

[0034] The learning unit 13 uses a machine learning model to learn the relationship between wireless communication requests and the wireless resource allocation information for responding to those requests, using training data which is the allocation information for wireless resources in a MIMO transmission system that is assigned to multiple communication terminals 2 to which wireless communication requests are commonly applied. The wireless resource allocation information consists of the number of antennas and the frequency band for MIMO communication.

[0035] The learning unit 13 uses a set of training data in which each of the multiple group IDs has a correct label to learn the number of antennas and frequency bands necessary to respond to the wireless communication requirements of each group ID using a machine learning model.

[0036] FIG. 5 shows a neural network structure adopted as an example of a machine learning model for learning by the learning unit 13. The neural network includes an input layer x, a hidden layer h, and an output layer y. The input nodes of the input layer x are given the values of the group IDs issued to the communication terminal 2 by the group management unit 11. Depending on the application executed by the communication terminal 2, different group IDs are given to each communication terminal 2, and a common number of MIMO communication antennas and frequency bands are assigned to each group ID. The number of antennas and frequency bands assigned to each group ID are the optimal number of antennas and frequency bands for meeting the requirements of the application associated with the group ID. Therefore, a correlation can be found between the group ID and the number of antennas and frequency bands that a plurality of communication terminals 2 with the same group ID are assigned.

[0037] Each output node y1 to y N , o1 to o M of the output layer y is a predicted value of the neural network for the value of the group ID that is the input value. The output nodes y1 to y N output the predicted value of the number of antennas. The indices 1 to N of the output nodes y1 to y N represent the number of antennas. The output nodes o1 to o M output the predicted value of the frequency band. The indices 1 to M of the output nodes o1 to o M correspond to the frequency bands f1 to f M (M ≤ k). Specifically, as the predicted value of the number of transmit / receive antennas of the output nodes y1 to y N , when the number of transmit / receive antennas N = 2, the predicted value of (y1, y2, y3, ···, y N ) = (0, 1, 0, ···, 0) is output.

[0038] As described above, in this embodiment, since one or more frequency bands can be assigned to the communication terminals 2 sharing the group ID, the output nodes o1 to o M may take the value of "1" for a plurality of predicted output values. For example, when the frequency bands f1 and f3 are assigned, (o1, o2, o3, ···, oM The predicted value )=(1,0,1,···,0) is output.

[0039] The learning unit 13 learns the parameters of the neural network model by introducing the objective function E shown in equation (1) below, so that the predicted values ​​of the number of antennas and frequency band from the neural network model for the group ID of the communication terminal 2 become the values ​​of the correct labels in the training data. The correct labels in the training data are the optimal values ​​of the number of antennas and frequency band assigned to the group ID.

[0040]

number

[0041] In equation (1) above, y1, y2, ..., y N ,o1,o2,···,o M The predicted output values ​​for each output node are shown. Also, Y1, Y2, ..., Y N ,O1,O2,···,O M is the correct label for the training data, which is prepared separately in advance. The learning unit 13 adjusts the weight parameters of the neural network so that the objective function E in equation (1) above is minimized, i.e., becomes 0. The learning unit 13 can optimize the objective function E using methods such as backpropagation.

[0042] The second memory unit 14 stores the trained machine learning model constructed by the learning unit 13.

[0043] The configuration unit 15 configures communication management information, including the trained machine learning model constructed by the learning unit 13, on the communication terminal 2. Specifically, the configuration unit 15 can configure the communication terminal 2 to be managed by sending the communication management information via the network NW.

[0044] [Communication terminal function blocks] Next, the configuration of the communication terminal 2 will be described with reference to the block diagram in Figure 2. As shown in Figure 2, the communication terminal 2 comprises a third storage unit 20, a first acquisition unit 21, a second acquisition unit 22, a calculation unit 23, and a communication management unit 24. Each of the multiple communication terminals 2 has the same configuration.

[0045] The third storage unit 20 stores the communication management information set by the setting unit 15 of the communication management device 1.

[0046] The first acquisition unit 21 acquires requests related to wireless communication applicable to its own terminal. Specifically, the first acquisition unit 21 can acquire the group ID of its own terminal, which is issued by the group management unit 11 of the communication management device 1, from the communication management device 1.

[0047] The second acquisition unit 22 acquires the trained machine learning model included in the communication management information set by the communication management device 1. Specifically, the second acquisition unit 22 reads the trained machine learning model stored in the third storage unit 20.

[0048] The calculation unit 23 provides the wireless communication request applicable to the terminal, acquired by the first acquisition unit 21, as an unknown input to a trained machine learning model, performs calculations on the trained machine learning model, and outputs wireless resource allocation information to be assigned to the terminal. More specifically, the calculation unit 23 provides the group ID of the terminal, acquired by the first acquisition unit 21, to the trained machine learning model, performs calculations, and outputs the optimal number of antennas and frequency band.

[0049] The communication management unit 24 performs communication using the MIMO transmission method based on the wireless resource allocation information output by the calculation unit 23. More specifically, the communication management unit 24 acquires channel status information based on the number of antennas and frequency band allocated to its terminal and transmits it to the base station 3. The base station 3 optimizes the allocation of wireless resources according to the channel status information. The communication management unit 24 uses the allocated number of antennas 208 to establish MIMO communication with the base station 3.

[0050] [Hardware configuration of the communication management device] Next, an example of a hardware configuration for realizing the communication management device 1 having the functions described above will be explained using Figure 6.

[0051] As shown in Figure 6, the communication management device 1 can be implemented, for example, by a computer equipped with a processor 102, main memory 103, communication interface 104, auxiliary storage 105, and input / output I / O 106 connected via a bus 101, and a program to control these hardware resources. Furthermore, the communication management device 1 may include a display device 107 connected via the bus 101.

[0052] Processor 102 is implemented using CPUs, GPUs, FPGAs, ASICs, etc.

[0053] The main memory 103 contains pre-stored programs for the processor 102 to perform various controls and calculations. The processor 102 and the main memory 103 work together to realize the various functions of the communication management device 1, such as the third acquisition unit 10, group management unit 11, learning unit 13, and setting unit 15 shown in Figure 1.

[0054] The communication interface 104 is an interface circuit for networking the communication management device 1 with various external electronic devices.

[0055] The auxiliary storage device 105 consists of a read / write storage medium and a drive device for reading and writing various information such as programs and data to the storage medium. The auxiliary storage device 105 can use semiconductor memory such as a hard disk or flash memory as the storage medium.

[0056] The auxiliary storage device 105 has a program storage area for storing the communication management program executed by the communication management device 1. It also has a program storage area for storing the machine learning program executed by the communication management device 1. Furthermore, the auxiliary storage device 105 has an area for storing information related to wireless resources. The first storage unit 12 and the second storage unit 14 described in Figure 1 are realized by the auxiliary storage device 105. In addition, it may have, for example, a backup area for backing up the above-mentioned data and programs.

[0057] The I / O106 is an input / output device that accepts signals from external devices and outputs signals to external devices.

[0058] The display device 107 is composed of an organic EL display, a liquid crystal display, or the like. The display device 107 can display management information for a group of multiple communication terminals 2.

[0059] [Hardware configuration of communication terminals] Next, an example of a hardware configuration for realizing the communication terminal 2 having the functions described above will be explained using Figure 7.

[0060] As shown in Figure 7, the communication terminal 2 can be realized by a computer equipped with a processor 202, main memory 203, communication interface 204, auxiliary storage 205, and input / output I / O 206, all connected via a bus 201, and a program that controls these hardware resources. Furthermore, the communication terminal 2 may also be equipped with a display device 207 and an antenna 208, all connected via the bus 201.

[0061] The main memory 203 contains pre-stored programs for the processor 202 to perform various controls and calculations. The processor 202 and the main memory 203 work together to realize the various functions of the communication terminal 2, such as the first acquisition unit 21, the second acquisition unit 22, the calculation unit 23, and the communication management unit 24 shown in Figure 2.

[0062] The auxiliary storage device 205 has a program storage area for storing the arithmetic program executed by the communication terminal 2. It also has a program storage area for storing the communication management program executed by the communication terminal 2. The auxiliary storage device 205 realizes the third storage unit 20 described in Figure 2. Furthermore, it may have, for example, a backup area for backing up the aforementioned data and programs.

[0063] [Operation of the communication management system] Next, the operation of the communication management system having the above-described configuration will be explained with reference to the sequence shown in Figure 8.

[0064] First, the third acquisition unit 10 acquires grouping criteria for assigning a common number of transmit and receive antennas and frequency band to the communication terminal 2 (step S1). The third acquisition unit 10 can acquire the type of application executed on the communication terminal 2 as a grouping criterion. Furthermore, the group management unit 11 assigns a group ID to each application type and stores it in the management table 110.

[0065] Next, the learning unit 13 prepares the training data (step S2). The training data consists of data in which the number of antennas and frequency band are assigned as correct labels for each group ID. The learning unit 13 can receive pre-designed training data from an external source via the communication interface 104.

[0066] Next, the learning unit 13 uses the training data obtained in step S2 to learn the relationship between group IDs indicating wireless communication requests and the allocation information for the number of antennas and frequency bands required to respond to wireless communication requests, using a machine learning model (step S3). In step S3, the learning unit 13 uses the training data for each of the multiple group IDs to learn the number of antennas and frequency bands required to respond to the wireless communication requests for each group ID using a machine learning model.

[0067] The learning unit 13, for example, adopts the neural network structure model shown in Figure 5 as a machine learning model and adjusts the weight parameters of the neural network so that the objective function E, expressed by equation (1) above, is minimized, i.e., becomes 0. The learning unit 13 can optimize the objective function using gradient descent, such as by using backpropagation. The trained machine learning model constructed by the learning unit 13 is stored in the first storage unit 12 (step S4).

[0068] Subsequently, the group management unit 11 issues a push notification to the managed communication terminal 2, instructing it to send the type of application launched and the IP address of the communication terminal 2 (step S5). For example, the push notification can be sent triggered by the launch of an application on the communication terminal 2.

[0069] Next, in response to the instructions in step S5, the communication terminal 2 notifies the communication management device 1 of its own IP address (IP01) and the type of application launched (Application 1) (step S6). The communication terminal 2 performs the processing in step S6 within the dedicated communication management application. After that, the group management unit 11 of the communication management device 1 refers to the grouping information in the management table 110 and issues a group ID to the IP address of the communication terminal 2 based on the received application type (step S7). In the example in Figure 8, group ID "1" is issued.

[0070] Next, the setting unit 15 of the communication management device 1 sets the communication management information, including the trained machine learning model constructed in the learning process of step S3, in the communication terminal 2 (step S8). In step S8, the communication management information is transmitted to the communication terminal 2 via the network NW.

[0071] Subsequently, the third storage unit 20 of the communication terminal 2 stores the trained machine learning model included in the communication management information (step S9). Next, the first acquisition unit 21 of the communication terminal 2 acquires the trained machine learning model by loading it from the third storage unit 20 (step S10). Next, the second acquisition unit 22 acquires the group ID of its own terminal (step S11). Specifically, it acquires the group ID received from the communication management device 1 in step S7.

[0072] Next, the arithmetic unit 23 provides the group ID of the local terminal obtained in step S11 as an unknown input to the trained machine learning model, performs calculations on the trained machine learning model, and outputs the number of MIMO communication antennas and frequency band allocation information assigned to the local terminal (step S12).

[0073] Subsequently, the communication management unit 24 performs MIMO communication (step S13) based on the antenna count and frequency band allocation information output in step S12. In step S13, the communication management unit 24 acquires channel status information based on the antenna count and frequency band allocated to its terminal and transmits it to the base station 3. The base station 3 optimizes the allocation of radio resources according to the channel status information. Then, the communication management unit 24 uses the antenna 208 allocated to it to establish MIMO communication with the base station 3.

[0074] Similarly, steps S9 to S13 are performed for each of the other managed communication terminals 2 (IP02~IP0n) with group ID "1".

[0075] As described above, the communication management device 1 according to this embodiment uses a machine learning model to learn the relationship between wireless communication requests and the information on the number of antennas and frequency bands to respond to those requests, using the allocation information of the number of antennas and frequency bands in the MIMO transmission system, which is assigned to multiple communication terminals 2 to which wireless communication requests are commonly applied, as training data. Therefore, with a simpler configuration, wireless resources used in MIMO communication can be managed for each of the multiple communication terminals 2 that share common wireless communication requests.

[0076] Furthermore, according to the communication management system of this embodiment, the communication management device 1 sets communication management information, including a trained machine learning model, to the communication terminal 2 via the network NW. Therefore, it is possible to centrally control and manage MIMO communication of multiple communication terminals 2.

[0077] In the embodiments described, a neural network model was used as an example of a machine learning model. However, other machine learning models such as logistic regression, random forests, decision trees, and even deep learning with multiple layers of neural networks may be used.

[0078] Furthermore, while the above-described embodiment illustrates a communication management system compliant with 5G, it may also be a communication management system compliant with LTE or 6G.

[0079] While embodiments of the communication management device, communication management method, and communication management system of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications that a person skilled in the art can envision are possible within the scope of the invention described in the claims. [Explanation of Symbols]

[0080] 1...Communication management device, 10...Third acquisition unit, 11...Group management unit, 12...First memory unit, 13...Learning unit, 14...Second memory unit, 15...Setting unit, 2...Communication terminal, 3...Base station, 4...Core network, 101, 201...Bus, 102, 202...Processor, 103, 203...Main memory, 104, 204...Communication interface, 105, 205...Auxiliary memory, 106, 206...Input / output I / O, 107, 207...Display device, 208...Antenna, NW...Network.

Claims

1. A learning unit configured to learn the relationship between wireless communication requests and the wireless resource allocation information for responding to those requests using a machine learning model, with the allocation information of wireless resources in a MIMO transmission system used as training data for assigning wireless communication requests to multiple communication terminals to which wireless communication requests commonly apply. A setting unit configured to set communication management information, including a trained machine learning model constructed in the learning unit, to the plurality of communication terminals. A communication management device equipped with the following features.

2. In the communication management device according to claim 1, The allocation information for the wireless resources includes the number of transmitting and receiving antennas and the frequency band used in the MIMO transmission method. The frequency band is one or more frequency bands. A communication management device characterized by the following features.

3. In the communication management device according to claim 1, The requirements relating to wireless communication are requirements that apply depending on the type of application executed on the multiple communication terminals. A communication management device characterized by the following features.

4. A learning step in which a machine learning model learns the relationship between a wireless communication request and the wireless resource allocation information to respond to the wireless communication request, using the allocation information of wireless resources in a MIMO transmission system, which is assigned to multiple communication terminals to which wireless communication requests commonly apply, as training data. A setting step to set communication management information, including the trained machine learning model constructed in the learning step, to the plurality of communication terminals. A communication management method comprising the following features.

5. In the communication management method described in claim 4, The allocation information for the wireless resources includes the number of transmitting and receiving antennas and the frequency band used in the MIMO transmission method. The frequency band is one or more frequency bands. A communication management method characterized by the following features.

6. In the communication management method described in claim 4, The requirements relating to wireless communication are requirements that apply depending on the type of application executed on the multiple communication terminals. A communication management method characterized by the following features.

7. In the communication management method described in claim 4, Furthermore, each of the aforementioned communication terminals, A first acquisition step of acquiring a request for wireless communication applicable to the terminal, A second acquisition step involves acquiring the trained machine learning model included in the communication management information set in the above setting step, A calculation step which involves providing the wireless communication request applicable to the terminal acquired in the first acquisition step as an unknown input to the trained machine learning model, performing calculations on the trained machine learning model, and outputting the allocation information of the wireless resource to be assigned to the terminal; A communication management step which performs communication using the MIMO transmission method based on the allocation information of the wireless resources output in the calculation step. A communication management method comprising the following features.

8. A communication management device according to any one of claims 1 to 3, The aforementioned multiple communication terminals and A communication management system comprising, Each of the aforementioned communication terminals is A first acquisition unit configured to acquire requests related to the aforementioned wireless communication applicable to its own terminal, A second acquisition unit configured to acquire the trained machine learning model included in the communication management information set by the communication management device, A calculation unit configured to provide the wireless communication request applicable to the terminal acquired by the first acquisition unit as an unknown input to the trained machine learning model, perform calculations on the trained machine learning model, and output wireless resource allocation information to be assigned to the terminal, A communication management unit configured to perform communication using the MIMO transmission method based on the allocation information of the wireless resources output by the calculation unit, A communication management system equipped with the following features.

Images