Information processing device, terminal device, and information processing method

Abstract

To provide a mechanism that can estimate communication characteristics in the real space with higher accuracy.SOLUTION: An information processing device of the present disclosure includes a control unit. The control unit generates estimated data in a calculation area using an estimation model of communication characteristics generated from multiple pieces of first actual measurement data in an estimation area. The control unit corrects the estimated data using second actual measurement data in the calculation area, the second actual measurement data being less in number than the first actual measurement data.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, a terminal device, and an information processing method. [Background technology]

[0002] In wireless communication, there is known a technique for realizing more suitable communication by appropriately controlling wireless resources and communication parameters. For example, suitable communication can be realized by adaptively controlling communication parameters according to the state of a propagation path between a base station and a terminal device.

[0003] For example, a base station transmits a known signal and a terminal device receives the known signal, whereby the terminal device can estimate the state of a propagation path. Furthermore, the terminal device feeds back the estimated state of the propagation path to the base station, whereby the base station can set suitable communication parameters for the terminal device.

[0004] In addition, if there is no feedback from the terminal device regarding the conditions of the propagation path, the base station can recognize the average conditions of the propagation path by using a statistical propagation model (e.g., a path loss model, an interference model, etc.) according to the distance from the terminal device. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2021-108459 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, radio wave propagation in wireless communication varies greatly depending on, for example, the presence or absence of obstacles between a base station, which is a transmitting point, and a terminal device, which is a receiving point. In addition, when considering interference with adjacent cells and surrounding base stations, the base station determines communication parameters so as to minimize the interference.

[0007] Therefore, when communication is performed using communication parameters determined by the base station, there is a risk that suitable wireless communication cannot be performed depending on obstacles that exist in the space where the base station and the terminal device actually perform wireless communication (hereinafter also referred to as real space).For example, when the base station determines the minimum transmission power to minimize interference, if an obstacle exists between the base station and the terminal device, there is a risk that the signal transmitted by the base station will not reach the terminal device due to the obstacle.

[0008] Therefore, it is desirable to estimate communication characteristics in the real space, such as the presence or absence of obstacles, with higher accuracy.

[0009] Therefore, the present disclosure provides a mechanism that can estimate communication characteristics in the real space with higher accuracy.

[0010] It should be noted that the above problem or objective is merely one of several problems or objectives that can be solved or achieved by several embodiments disclosed in this specification. [Means for solving the problem]

[0011] The information processing device of the present disclosure includes a control unit. The control unit generates estimated data for a calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data for the estimation area. The control unit corrects the estimated data using second actual measurement data for the calculation area, the second actual measurement data being smaller in number than the first actual measurement data. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of radio wave propagation according to a proposed technique of the present disclosure. [Diagram 2] FIG. 11 is a diagram illustrating an example of a communication process according to an embodiment of the present disclosure. [Diagram 3] FIG. 11 is a diagram illustrating an example of statistical processing according to an embodiment of the present disclosure. [Figure 4]FIG. 1 is a diagram illustrating a configuration example of a communication system according to an embodiment of the present disclosure. [Diagram 5] FIG. 2 is a diagram illustrating a configuration example of a control station according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a block diagram illustrating a configuration example of a base station according to an embodiment of the present disclosure. [Figure 7] FIG. 2 is a block diagram illustrating a configuration example of a terminal device according to an embodiment of the present disclosure. [Figure 8] FIG. 13 is a diagram illustrating an example of completion by interpolation according to an embodiment of the present disclosure. [Figure 9] FIG. 13 illustrates an example of nearest neighbor interpolation according to an embodiment of the present disclosure. [Figure 10] FIG. 13 is a diagram illustrating an example of completion by extrapolation according to an embodiment of the present disclosure. [Figure 11] FIG. 13 is a diagram illustrating an example of complementation by a control station according to an embodiment of the present disclosure. [Figure 12] FIG. 13 is a diagram illustrating an example of estimated data according to an embodiment of the present disclosure. [Figure 13] FIG. 11 is a diagram illustrating an example of actual communication characteristics in a calculation area according to an embodiment of the present disclosure. [Figure 14] FIG. 13 is a diagram illustrating an example of correction using complementary data by a control station according to an embodiment of the present disclosure. [Figure 15] FIG. 13 is a diagram illustrating an example of completion using estimated data according to an embodiment of the present disclosure. [Figure 16] FIG. 13 is a diagram illustrating an example of correction of an arbitrary coefficient by a control station according to an embodiment of the present disclosure. [Figure 17] FIG. 11 is a sequence diagram illustrating an example of a flow of a communication process according to an embodiment of the present disclosure. [Figure 18] 11 is a flowchart showing an example (part 1) of a flow of a control information generation process according to an embodiment of the present disclosure. [Figure 19] 11 is a flowchart showing an example (part 2) of the flow of a control information generation process according to an embodiment of the present disclosure. [Figure 20] 13 is a flowchart showing an example (part 3) of the flow of a control information generation process according to an embodiment of the present disclosure. [Figure 21] 11 is a flowchart showing an example (part 4) of the flow of a control information generation process according to an embodiment of the present disclosure. [Figure 22] 11 is a flowchart illustrating an example of a flow of a generation process according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0014] In addition, in this specification and drawings, similar components of the embodiments may be distinguished by adding at least one of different alphabets and numbers after the same reference numeral. However, when there is no need to particularly distinguish between similar components, only the same reference numerals are used. For example, multiple components having substantially the same functional configurations are distinguished as necessary, such as terminal device 400_1 and terminal device 400_2. For example, when there is no need to particularly distinguish between terminal device 400_1 and terminal device 400_2, they are simply referred to as terminal device 400.

[0015] One or more embodiments (including examples, modifications, and application examples) described below can be implemented independently. Meanwhile, at least a part of the embodiments described below may be implemented in appropriate combination with at least a part of another embodiment. These embodiments may include novel features different from each other. Thus, these embodiments may contribute to solving different purposes or problems and may provide different effects.

[0016] <<1. Introduction>> <1.1.Background> In wireless communication, communication quality characteristics such as received power, throughput, interference power, SIR (Signal-to-Interference power ratio), and SINR (Signal-to-Interference and Noise power Ratio) are strongly dependent on the radio wave propagation characteristics between the base station and the terminal device. The base station is required to adaptively design communication parameters such as modulation method and coding rate according to the radio wave propagation characteristics.

[0017] For example, when the received power of a terminal device is high, the base station can improve the transmission efficiency by using a higher-order modulation scheme. On the other hand, when the received power of a terminal device is low, the base station can suppress an increase in the bit error rate, symbol error rate, etc. by using a lower-order modulation scheme.

[0018] Originally, propagation models (statistical path loss models) such as the Okumura-Hata model have been used to estimate radio wave propagation characteristics. Statistical path loss models are used to estimate the global characteristics of radio wave propagation using information such as the distance between the transmitter and receiver.

[0019] It is also possible for the base station to transmit a pilot signal for estimating radio wave propagation characteristics to the terminal device, and for the terminal device to observe the signal, thereby estimating the radio wave propagation characteristics between the base station and the terminal device.

[0020] <1.2.Challenges> However, radio wave propagation characteristics in wireless communication vary greatly depending on the presence or absence of obstacles between a base station (transmission point) and a terminal device (reception point). This point will be explained with reference to FIG.

[0021] Fig. 1 is a diagram showing an example of radio wave propagation according to the proposed technique of the present disclosure. Fig. 1(a) is a diagram showing an example of radio wave propagation when there is no obstacle 600. Fig. 1(b) is a diagram showing an example of radio wave propagation when there is an obstacle 600.

[0022] For example, when the base station 300 transmits txIf there is no obstacle 600 (see FIG. 1(a)), the radio waves will reach a greater distance than if there is an obstacle 600 (see FIG. 1(b)).

[0023] It is known that the amount of radio wave attenuation caused by such an obstacle 600 varies in a complex manner depending on the density and height of the structure (hereinafter also referred to as the structure characteristics), the positional relationship between the base station, the structure, and the terminal device, and the like.

[0024] Therefore, if the structural characteristics in the area used to generate the propagation model and the area in which the radio wave propagation characteristics (communication characteristics) are estimated are significantly different, the propagation model may not be able to accurately estimate the communication characteristics. This problem may become more serious if the propagation model is generated using machine learning such as an AI model. As a result, the base station 300 may not be able to accurately design its own communication parameters, which may lead to a significant decrease in communication efficiency.

[0025] In addition, by having the terminal device estimate the state of the propagation path and provide feedback, it is possible to determine more accurate communication parameters. However, with this method, the base station 300 can only grasp the state of the propagation path at the location where the terminal device is located.

[0026] Therefore, when a terminal device moves, it is difficult for the base station 300 to grasp the propagation path conditions at the destination more accurately. Also, when many terminal devices feed back the propagation path conditions, the communication resources for the feedback become overhead, which is a factor in reducing the utilization efficiency of radio resources in the entire communication system.

[0027] Depending on the use case, there may be cases where the feedback of the channel conditions from the terminal device is insufficient (not obtained at all or only a small amount). In such a situation (environment, location, area), it is required to estimate the channel conditions (including communication characteristics and wireless communication environment) of the terminal device and / or the base station 300 with high accuracy.

[0028] <1.3. Overview of proposed technology> Fig. 2 is a diagram showing an example of communication processing according to an embodiment of the present disclosure. The communication processing shown in Fig. 2 is executed in a communication system. The communication system includes a control station 100, a base station 300, and terminal devices 400_1 to 400_3.

[0029] First, the base station 300 transmits a signal to the terminal devices 400_1 to 400_3 (step S1). This signal is, for example, a reference signal for measuring communication characteristics.

[0030] The terminal devices 400_1 to 400_3 measure signals to generate measured data, and transmit the generated measured data to the control station 100 (step S2). The measured data includes, for example, information on communication characteristics.

[0031] At this time, the terminal device 400 may transmit the actual measurement data to the control station 100 via the base station 300, or may transmit the actual measurement data to the control station 100 without passing through the base station 300. That is, the terminal device 400 may transmit the actual measurement data to the control station 100 via a cellular network. Alternatively, the terminal device 400 may transmit the actual measurement data to the control station 100 via Wi-Fi (registered trademark), the Internet, or the like. Alternatively, the terminal device 400 may transmit the actual measurement data to the control station 100 by being directly connected to the control station 100 via a cable.

[0032] The control station 100 executes statistical processing using the acquired measured data (step S3). The statistical processing will be described later with reference to FIG.

[0033] The control station 100 notifies the base station 300 and / or the terminal device 400_1 of statistical information related to the result of the statistical processing (step S4). Note that, although the control station 100 notifies the terminal device 400_1 of the statistical information here, it may be configured to notify the terminal devices 400_2 and 400_3 in the same manner.

[0034] Here, the statistical processing is processing using at least actual measurement data. For example, the statistical processing according to this embodiment includes processing for estimating radio wave propagation characteristics between the base station 300 and the terminal device 400.

[0035] The control station 100 may notify the base station 300 and / or the terminal device 400 of the estimated radio wave propagation characteristics as statistical information. Alternatively, the control station 100 may notify the base station 300 and / or the terminal device 400 of communication parameters (e.g., control information for communication between the base station 300 and the terminal device 400) calculated based on the estimated radio wave propagation characteristics as statistical information.

[0036] 3 is a diagram illustrating an example of statistical processing according to an embodiment of the present disclosure. The statistical processing illustrated in FIG.

[0037] The control station 100 generates an estimation model based on actual measurement data (first data) in at least one estimation area R (step S11). This estimation model is, for example, a communication characteristics estimation model used to estimate communication characteristics (radio wave propagation environment).

[0038] The control station 100 generates an estimation model from actual measurement data of the estimation area R_1 by, for example, machine learning. In Fig. 3, the number of the estimation areas R_1 used to generate the estimation model is three or more (estimated areas R_11, R_12, R_13, etc.), but the number of the estimation areas R_1 is not limited to this. The number of the estimation areas R_1 may be two or less.

[0039] Next, the control station 100 estimates the estimation data in the calculation area R_0 by using the estimation model (step S12). The calculation area R_0 is an area (real space) where the base station 300 and the terminal device 400 actually communicate with each other. The estimation data is information that represents the communication characteristics of the calculation area R_0.

[0040] The control station 100 corrects the estimated data using the actual measurement data (second data) in the calculation area R_0 (step S13). For example, the control station 100 corrects the estimated data calculated in step S12 using the actual measurement data. Alternatively, the control station 100 may correct the estimation model using the actual measurement data.

[0041] Here, the number of actual measurement data used for correction is less than the number of actual measurement data (first data, hereinafter also referred to as actual measurement data for estimation) used to generate the estimation model. The actual measurement data used for correction is data acquired from the terminal device 400. The control station 100 corrects the information on the estimation model, for example, by using at least a part of the actual measurement data (first data, hereinafter also simply referred to as actual measurement data) acquired from the terminal device 400. Alternatively, the control station 100 may correct the information on the estimation model by using simulation data in the calculation area R_0.

[0042] The control station 100 generates corrected estimated data using the result of correcting the estimated data (step S14). For example, when the estimated data is corrected with the actual measurement data, the control station 100 sets the corrected estimated data to the estimated data after correction. Alternatively, when the estimation model is corrected, the control station 100 sets the estimated data generated using the corrected estimation model to the corrected estimated data.

[0043] The control station 100 uses the corrected estimated data to generate statistical information as a result of statistical processing (step S15). For example, the control station 100 may use the corrected estimated data as the statistical information. Alternatively, the control station 100 may calculate communication parameters in the calculation area R_0 based on the corrected estimated data, and use the calculated communication parameters as the statistical information. The statistical information is transmitted to the base station 300 and / or the terminal device 400 as described above.

[0044] In this way, the control station 100 according to the proposed technology corrects information about the estimation model to generate corrected estimation data, which enables the control station 100 to estimate the radio wave propagation environment of the calculation area R_0 (real space) with higher accuracy.

[0045] Note that the correction by the control station 100 is applied not only to the estimation of the calculation area R_0, but also to the estimation of the environment of the calculation area R_0 when the antenna direction, transmission power, and transmission frequency of the base station 300 are changed.

[0046] In addition, although the control station 100 generates an estimation model as the statistical processing here, the control station 100 may generate an estimation model before starting the statistical processing. That is, the statistical processing does not have to include the generation of an estimation model. Also, the estimation model may be generated by a device other than the control station 100. In this case, the control station 100 acquires the estimation model from, for example, a device that generated the estimation model.

[0047] The control station 100 may also calculate an error between the estimated data based on the estimation model and the actual measured data in the calculation area R_0. The control station 100 determines whether to correct the estimated data, for example, depending on the magnitude of the error. Examples of the correction of the estimated data include weighted averaging, simple averaging, and substitution of a single value using the actual measured data in the calculation area R_0.

[0048] The control station 100 may use the actual measurement data in the calculation area R_0 to complement communication characteristics (actual measurement data) at points in the calculation area R_0 where there is no actual measurement data (hereinafter, also referred to as unobserved points). After that, the control station 100 corrects the estimated data by the estimation model, for example, by using the complementation result.

[0049] The control station 100 may estimate communication characteristics using machine learning, artificial intelligence, or deep learning (hereinafter, simply referred to as AI (Artificial Intelligence)). In this case, the control station 100 may set various parameters in the input data (explanatory variables) of the AI. For example, the parameters include the standard deviation of shadowing.

[0050] The control station 100 may correct, for example, any coefficient of the estimation model as a correction of the estimation model. In this case, the control station 100 corrects, for example, any coefficient of the estimation model so that an error between the estimated data by the estimation model and the actual measurement data is minimized.

[0051] The estimation accuracy of the corrected estimated data, i.e., the estimation accuracy of the communication characteristics in the calculation area R_0 that is finally estimated, is determined according to the number of actually measured data. The control station 100 may change the number of actually measured data according to the required estimation accuracy. Furthermore, the estimation accuracy of the corrected estimated data is determined according to the observation accuracy (standard deviation) of the actually measured data. The control station 100 may select the actually measured data according to the required estimation accuracy.

[0052] Furthermore, the estimation accuracy of the corrected estimation data varies depending on the correction method, and the control station 100 can select a correction method depending on the required estimation accuracy.

[0053] The estimation accuracy of the corrected estimation data is determined according to the type of AI used, the type of input data to the AI, the observation accuracy of the input data, and the estimation accuracy of the estimation model. The control station 100 can select the type of AI used, the type of input data to the AI, the input data, etc., according to the required estimation accuracy.

[0054] When correcting estimated data based on the allowable estimation error standard, it is desirable that the statistical properties of the measured data group (such as the mean, median, mode, and standard deviation) match or are similar to the statistical properties of the true predicted value.

[0055] When correcting estimated data based on complementary estimation, it is desirable that actual measurement data used for the correction is acquired near and far from base station 300. In this case, it is desirable that the actual measurement data used for the correction is acquired at points in both a Line Of Sight (LOS) environment and a Non Line Of Sight (NLOS) environment.

[0056] The estimation model may be estimated using linear regression analysis, multiple regression analysis, etc., with actual measurement data as a response variable and information on the distance between the transmitter and receiver as an explanatory variable. The control station 100 may generate the estimation model using simulation data in the estimation area R_1 and the calculation area R_0.

[0057] The estimation model can be generated by machine learning or deep learning using actual measurement data as a response variable and at least simulation data as an explanatory variable.

[0058] The estimation accuracy of the communication characteristics in the calculation area R_0 is determined based on the number of estimation areas R_1 in generating an estimation model. The control station 100 can select the number of calculation areas R_0 according to the required estimation accuracy, for example.

[0059] The estimation accuracy of the communication characteristics in the calculation area R_0 is determined according to the number of actually measured data, the observation accuracy, etc. The control station 100 can select the number of actually measured data and the actually measured data to be used according to the required estimation accuracy, for example.

[0060] When an estimation model is generated by AI using simulation data, the estimation accuracy of the communication characteristics in the calculation area R_0 is determined based on at least the accuracy of the simulation data. The control station 100 can select a simulation method or the like according to the required estimation accuracy, for example.

[0061] When an estimation model is generated using AI, the estimation accuracy of the communication characteristics in the calculation area R_0 is determined by parameters used during machine learning or deep learning. The control station 100 may select the parameters to be used depending on the required estimation accuracy, for example.

[0062] The communication characteristics are characteristics based on radio wave propagation from a transmitting point to a receiving point, and include characteristics related to received power, interference power, communication speed (throughput), or delay. The communication characteristics may also include other characteristics such as SNR, SIR, SINR, and INR.

[0063] In principle, it is desirable that the radio wave propagation characteristics in the estimated area R_1 and the radio wave propagation characteristics in the calculated area R_0 are the same or similar. When the radio wave propagation characteristics in the estimated area R_1 and the radio wave propagation characteristics in the calculated area R_0 are different, it is desirable that there is a correlation of a predetermined value or more between the radio wave propagation characteristics in both areas. The control station 100 may select the estimated area R_1 according to the radio wave propagation characteristics in the calculated area R_0.

[0064] The above-mentioned simulation data is data (virtual space estimated information) obtained by a simulation performed based on at least the communication environment information related to the estimated area R_1 and / or the calculated area R_0.

[0065] When there are multiple estimation areas R_1, the simulation data and / or the actual measurement data for estimation in the estimation area R_1 may be normalized (for example, an offset is applied to these data) by a predetermined method.

[0066] The control station 100 according to the proposed technique of the present disclosure can further improve the estimation accuracy of communication characteristics even if the amount of actual measurement data acquired in the calculation area R_0 is insufficient.

[0067] <<2. Example of communication system configuration>> <2.1. Example of overall configuration of communication system> 4 is a diagram illustrating a configuration example of a communication system according to an embodiment of the present disclosure. As illustrated in FIG. 4, the communication system includes a control station 100, a base station 300, and a terminal device 400.

[0068] The control station 100 is a cloud server that is connected to the base stations 300 via a network (not shown). The number of base stations 300 connected to the control station 100 is not limited to one, and may be two or more.

[0069] The control station 100 controls communication between the base station 300 and the terminal device 400, for example, by notifying the base station 300 of communication parameters.

[0070] For example, the control station 100 may be an information processing device that controls a dynamic spectrum access (DSA) system. In this case, the control station 100 may control radio resources and communication parameters for each base station 300 connected to the DSA. Here, the radio resources refer to resources in at least one of time, frequency, MIMO layer, and spatial domain used for wireless communication.

[0071] Alternatively, the control station 100 may be a database device having an information processing function.

[0072] The base station 300 is connected to the terminal device 400 via wireless communication. The number of terminal devices 400 connected to the base station 300 is not limited to one, and may be two or more.

[0073] The communication system may include components other than the above-mentioned control station 100, base station 300, and terminal device 400. For example, the communication system may include a core network.

[0074] In addition, examples of radio access technologies (RATs) used for radio communication between the base station 300 and the terminal device 400 include cellular communication systems such as 4G systems, 5G systems, 6G systems, LTE (Long Term Evolution), and NR (New Radio). In addition, the radio access technologies are not limited to cellular communication systems. For example, examples of the radio access technologies include various radio communication systems such as wireless LAN, Bluetooth (registered trademark), and LPWA (Low Power Wide Area) systems.

[0075] <2.2. Example of control station configuration> 5 is a diagram illustrating a configuration example of a control station 100 according to an embodiment of the present disclosure. As described above, the control station 100 is, for example, an information processing device that estimates communication characteristics of a communication system. As illustrated in FIG. 5, the control station 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0076] (Communication unit 110) The communication unit 110 is a communication interface for communicating with other devices (e.g., the base station 300). The communication unit 110 may be a network interface or a device connection interface. For example, the communication unit 110 may be a LAN (Local Area Network) interface such as a NIC (Network Interface Card), or a Universal Serial Bus (USB) interface configured with a USB host controller, a USB port, and the like. The communication unit 110 may be a wired interface or a wireless interface. The communication unit 110 functions as a communication means of the control station 100. The communication unit 110 communicates with the base station 300 under the control of the control unit 130.

[0077] (Storage unit 120) The storage unit 120 is a data readable / writable storage device such as a dynamic random access memory (DRAM), a static random access memory (SRAM), a flash memory, a hard disk, etc. The storage unit 120 functions as a storage unit of the control station 100.

[0078] (Control unit 130) The control unit 130 is a controller that controls each unit of the control station 100. The control unit 130 is realized by a processor such as a central processing unit (CPU), a micro processing unit (MPU), or a graphics processing unit (GPU).

[0079] For example, the control unit 130 is realized by a processor executing various programs stored in a storage device inside the control station 100 using a RAM (Random Access Memory) or the like as a working area. The control unit 130 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The CPU, MPU, GPU, ASIC, and FPGA can all be considered as controllers.

[0080] <2.3. Example of base station configuration> Next, the base station 300 will be described. The base station 300 is a communication device that operates a cell and provides wireless communication services to one or more terminal devices 400 located within the coverage of the cell. The cell is operated according to any wireless communication method such as LTE or NR. The base station 300 is connected to a core network. The core network is connected to a packet data network (not shown) via a gateway device (not shown). The base station 300 also operates a beam that can be identified by an SSB (Synchronization Signal / PBCH Block), and can transmit and receive data to and from one or more terminal devices 400 via one or more beams.

[0081] In addition, the base station 300 may be configured with a set of multiple physical or logical devices. For example, in the embodiment of the present disclosure, the base station 300 may be divided into multiple devices, a BBU (Baseband Unit) and a RU, and may be interpreted as a set of these multiple devices. Additionally or alternatively, in the embodiment of the present disclosure, the base station 300 may be either or both of a BBU and a RU. The BBU and the RU may be connected by a predetermined interface (e.g., eCPRI). Additionally or alternatively, the RU may be called a Remote Radio Unit (RRU) or a Radio DoT (RD). Additionally or alternatively, the RU may be compatible with a gNB-DU, which will be described later. Additionally or alternatively, the BBU may be compatible with a gNB-CU, which will be described later. Alternatively, the RU may be connected to a gNB-DU, which will be described later. Furthermore, the BBU may be compatible with a combination of a gNB-CU and a gNB-DU, which will be described later. Additionally or alternatively, the RU may be a device formed integrally with an antenna. The antenna of base station 300 (e.g., an antenna formed integrally with an RU) may employ an advanced antenna system and support MIMO (e.g., FD-MIMO) and beamforming. In the advanced antenna system, the antenna of base station 300 (e.g., an antenna formed integrally with an RU) may include, for example, 64 transmitting antenna ports and 64 receiving antenna ports.

[0082] Also, a plurality of base stations 300 may be connected to each other. One or more base stations 300 may be included in a radio access network (RAN). That is, the base station 300 may simply be referred to as a RAN, a RAN node, an AN (Access Network), or an AN node. The RAN in LTE is called EUTRAN (Enhanced Universal Terrestrial RAN). The RAN in NR is called NGRAN. The RAN in W-CDMA (UMTS) is called UTRAN. The LTE base station 300 is called eNodeB (Evolved Node B) or eNB. That is, the EUTRAN includes one or more eNodeBs (eNBs). Also, the NR base station 300 is called gNodeB or gNB. That is, the NGRAN includes one or more gNBs. Furthermore, the EUTRAN may include a gNB (en-gNB) connected to a core network (EPC) in an LTE communication system (EPS). Similarly, the NGRAN may include an ng-eNB connected to a core network 5GC in a 5G communication system (5GS). Additionally or alternatively, when the base station 300 is an eNB, gNB, etc., it may be referred to as 3GPP Access. Additionally or alternatively, when the base station 300 is a wireless access point (Access Point) (e.g., a WiFi (registered trademark) access point), it may be referred to as Non-3GPP Access. Additionally or alternatively, the base station 300 may be a radio extension device called an RRH (Remote Radio Head). Additionally or alternatively, when the base station 300 is a gNB, the base station 300 may be referred to as a combination of the gNB CU (Central Unit) and gNB DU (Distributed Unit) described above, or any of them. The gNB CU hosts multiple upper layers (e.g., RRC, SDAP, PDCP) of the Access Stratum for communication with the UE. On the other hand, the gNB-DU hosts multiple lower layers (e.g., RLC, MAC, PHY) of the Access Stratum.That is, among the message information described later, RRC signaling (e.g., MIB, various SIBs including SIB1, RRCSetup message, RRCReconfiguration message) may be generated by the gNB CU, while DCI and various physical channels (e.g., PDCCH, PBCH) described later may be generated by the gNB-DU. Alternatively, among the RRC signaling, some configuration (setting information), such as IE:cellGroupConfig, may be generated by the gNB-DU, and the remaining configuration may be generated by the gNB-CU. These configurations (setting information) may be transmitted and received via an F1 interface described later. The base station 300 may be configured to be able to communicate with other base stations 300. For example, when multiple base stations 300 are eNBs or a combination of an eNB and an en-gNB, the base stations 300 may be connected to each other via an X2 interface. Additionally or alternatively, when multiple base stations 300 are gNBs or a combination of a gn-eNB and a gNB, the devices may be connected to each other via an Xn interface. Additionally or alternatively, when the multiple base stations 300 are a combination of gNB CU and gNB DU, the devices may be connected via the F1 interface described above. Message information (RRC signaling or DCI information, physical channel) described below may be communicated between the multiple base stations 300 (e.g., via X2, Xn, F1 interfaces).

[0083] Furthermore, as described above, the base station 300 may be configured to manage multiple cells. A cell provided by the base station 300 is called a serving cell. The serving cell includes a PCell (Primary Cell) and an SCell (Secondary Cell). When dual connectivity (e.g., EUTRA-EUTRA Dual Connectivity, EUTRA-NR Dual Connectivity (ENDC), EUTRA-NR Dual Connectivity with 5GC, NR-EUTRA Dual Connectivity (NEDC), NR-NR Dual Connectivity) is provided to a UE (e.g., a terminal device 400), a PCell and zero or more SCell(s) provided by a MN (Master Node) are called a Master Cell Group. Furthermore, the serving cell may include a PSCell (Primary Secondary Cell or Primary SCG Cell). That is, when dual connectivity is provided to a UE, a PSCell and zero or more SCell(s) provided by a SN (Secondary Node) are called a Secondary Cell Group (SCG). Unless a special configuration (e.g., PUCCH on SCell) is made, the physical uplink control channel (PUCCH) is transmitted on the PCell and PSCell, but not on the SCell. Radio Link Failure is also detected on the PCell and PSCell, but not on the SCell (does not need to be detected). As such, the PCell and PSCell have a special role among the Serving Cell(s), and are therefore also called Special Cells (SpCells). One cell may be associated with one Downlink Component Carrier and one Uplink Component Carrier. Furthermore, the system bandwidth corresponding to one cell may be divided into multiple bandwidth parts.In this case, one or more Bandwidth Parts (BWPs) may be configured for the UE, and one Bandwidth Part may be used by the UE as an Active BWP. In addition, the radio resources (e.g., frequency band, numerology (subcarrier spacing), slot format (Slot configuration)) that the terminal device 400 can use may differ for each cell, each component carrier, or each BWP.

[0084] 6 is a block diagram showing a configuration example of a base station 300 according to an embodiment of the present disclosure. The base station 300 is a wireless communication device that wirelessly communicates with a terminal device 400. The base station 300 is a type of communication device. The base station 300 is also a type of information processing device.

[0085] The base station 300 shown in Fig. 6 includes a communication unit 310, a storage unit 320, a network communication unit 330, and a control unit 340. Note that the configuration shown in Fig. 6 is a functional configuration, and the hardware configuration may be different from this. Also, the functions of the base station 300 may be distributed and implemented in multiple physically separated configurations. For example, as described above, the functions of the base station 300 may be distributed to a CU and a DU, or a CU, a DU, and a RU.

[0086] The communication unit 310 is a signal processing unit for wireless communication with other wireless communication devices (for example, a terminal device 400 and another base station 300). The communication unit 310 operates under the control of the control unit 340. When the other wireless communication device is a terminal device 400, the communication unit 310 may be a wireless transceiver that supports one or more wireless access methods. For example, the communication unit 310 supports both NR and LTE. The communication unit 310 may support W-CDMA and cdma2000 in addition to NR and LTE. The communication unit 310 may also support communication using NOMA. When the other wireless communication device is another base station 300, the communication unit 310 may be an X2 interface, an Xn interface, or an F1 interface.

[0087] (Communication unit 310) The communication unit 310 includes a reception processing unit 311, a transmission processing unit 312, and an antenna 313. The communication unit 310 may include a plurality of reception processing units 311, a plurality of transmission processing units 312, and a plurality of antennas 313. When the communication unit 310 supports a plurality of radio access methods, each unit of the communication unit 310 may be configured separately for each radio access method. For example, the reception processing unit 311 and the transmission processing unit 312 may be configured separately for LTE and NR.

[0088] The reception processing unit 311 processes an uplink signal received via the antenna 313. The reception processing unit 311 operates as a receiving unit that receives a received signal. The reception processing unit 311 includes a radio receiving unit 311a, a demultiplexing unit 311b, a demodulating unit 311c, and a decoding unit 311d.

[0089] The radio receiving unit 311a performs down-conversion, removal of unnecessary frequency components, control of amplification level, orthogonal demodulation, conversion to a digital signal, removal of a guard interval (cyclic prefix), extraction of a frequency domain signal by fast Fourier transform, etc. on the uplink signal. The demultiplexing unit 311b separates uplink channels such as a PUSCH (Physical Uplink Shared Channel) and a PUCCH (Physical Uplink Control Channel) and an uplink reference signal from the signal output from the radio receiving unit 311a.

[0090] The demodulator 311c demodulates the received signal using a modulation method such as BPSK (Binary Phase Shift Keying) or QPSK (Quadrature Phase Shift Keying) for the modulation symbols of the uplink channel. The modulation method used by the demodulator 311c may be 16QAM (Quadrature Amplitude Modulation), 64QAM, or 256QAM. In this case, the signal points on the constellation do not necessarily have to be equidistant. The constellation may be a non-uniform constellation (NUC).

[0091] The decoder 311d performs a decoding process on the coded bits of the demodulated uplink channel. The decoded uplink data and uplink control information are output to the controller 340.

[0092] The transmission processing unit 312 performs a transmission process of the downlink control information and the downlink data. In this manner, the transmission processing unit 312 is an acquisition unit that acquires, for example, a bit sequence of the downlink control information, the downlink data, and the like from the control unit 340. The transmission processing unit 312 includes an encoding unit 312a, a modulation unit 312b, a multiplexing unit 312c, and a radio transmission unit 312d.

[0093] The encoder 312a encodes the downlink control information and downlink data input from the controller 340 using a coding method such as block coding, convolution coding, turbo coding, etc. The encoder 312a may also encode the downlink control information and downlink data using a polar code or a low density parity check code (LDPC code).

[0094] The modulation unit 312b modulates the coded bits output from the coding unit 312a using a predetermined modulation method such as BPSK, QPSK, 16QAM, 64QAM, or 256QAM. In this case, the signal points on the constellation do not necessarily have to be equidistant. The constellation may be a non-uniform constellation.

[0095] The multiplexing unit 312c multiplexes the modulation symbols of each channel and the downlink reference signal, and places the multiplexed symbols in a predetermined resource element. The radio transmitting unit 312d performs various signal processing on the signal from the multiplexing unit 312c. For example, the radio transmitting unit 312d performs processing such as conversion from the time domain to the frequency domain by fast Fourier transform, addition of a guard interval (cyclic prefix), generation of a baseband digital signal, conversion to an analog signal, quadrature modulation, up-conversion, removal of unnecessary frequency components, and power amplification. The signal generated by the transmission processing unit 312 is transmitted from the antenna 313.

[0096] (Storage unit 320) The storage unit 320 is a data readable / writable storage device such as a DRAM, an SRAM, a flash memory, a hard disk, etc. The storage unit 320 functions as a storage unit of the base station 300.

[0097] (Network communication unit 330) The network communication unit 330 is a communication interface for communicating with a node located at a higher level on the network (e.g., a core network). For example, the network communication unit 330 may be a LAN interface such as a NIC. Additionally or alternatively, the network communication unit 330 may be an S1 interface or an NG interface for connecting to a core network node. The network communication unit 330 may be a wired interface or a wireless interface. The network communication unit 330 functions as a network communication means of the base station 300.

[0098] (Control unit 340) The control unit 340 is a controller that controls each unit of the base station 300. The control unit 340 is realized by a processor (hardware processor) such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). For example, the control unit 340 is realized by the processor executing various programs stored in a storage device inside the base station 300 using a RAM (Random Access Memory) or the like as a working area. The control unit 340 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The CPU, MPU, ASIC, and FPGA can all be considered as controllers.

[0099] <2.4. Example of terminal device configuration> Next, a configuration example of the terminal device 400 according to an embodiment of the present disclosure will be described with reference to Fig. 7. Fig. 7 is a block diagram showing a configuration example of the terminal device 400 according to an embodiment of the present disclosure.

[0100] The terminal device 400 is a wireless communication device that wirelessly communicates with the base station 300. The terminal device 400 is, for example, a mobile phone, a smart device (smartphone or tablet), a PDA (Personal Digital Assistant), or a personal computer. The terminal device 400 may be a device such as a commercial camera equipped with a communication function, an M2M (Machine to Machine) device, or an IoT (Internet of Things) device.

[0101] The terminal device 400 may be capable of sidelink communication with other terminal devices 400. The terminal device 400 may be capable of using an automatic retransmission technique such as Hybrid Automatic Repeat reQuest (HARQ) when performing sidelink communication. The terminal device 400 may be capable of non-orthogonal multiple access (NOMA) communication with the base station 300. The terminal device 400 may also be capable of NOMA communication in communication (sidelink) with other terminal devices 400. The terminal device 400 may also be capable of low power wide area (LPWA) communication with other communication devices (for example, the base station 300 and other terminal devices 400). In addition, the wireless communication used by the terminal device 400 may be wireless communication using millimeter waves. The wireless communication (including sidelink communication) used by the terminal device 400 may be wireless communication using radio waves, or wireless communication using infrared rays or visible light (optical wireless).

[0102] The terminal device 400 may simultaneously connect to multiple base stations 300 or multiple cells to perform communication. For example, when one base station 300 can provide multiple cells, the terminal device 400 can perform carrier aggregation by using a certain cell as a pCell and using another cell as an sCell. Also, when multiple base stations 300 can provide one or multiple cells, the terminal device 400 can realize DC (Dual Connectivity) by using one or multiple cells managed by one base station 300 (MN (e.g., MeNB or MgNB)) as a pCell, or pCell and sCell(s), and using one or multiple cells managed by the other base station 300 (SN (e.g., SeNB or SgNB)) as a pCell (PSCell), or pCell (PSCell) and sCell(s). DC may be referred to as MC (Multi Connectivity).

[0103] When a communication area is supported via cells of different base stations 300 (multiple cells having different cell identifiers or the same cell identifier), the multiple cells can be bundled together by Carrier Aggregation (CA), Dual Connectivity (DC), or Multi-Connectivity (MC) technology to enable communication between the base station 300 and the terminal device 400. Alternatively, the terminal device 400 can communicate with the multiple base stations 300 via the cells of the different base stations 300 by Coordinated Multi-Point Transmission and Reception (CoMP) technology.

[0104] The terminal device 400 in Fig. 7 includes a communication unit 410, a storage unit 420, a network communication unit 430, an input / output unit 440, and a control unit 450. Note that the configuration shown in Fig. 7 is a functional configuration, and the hardware configuration may be different from this. Also, the functions of the terminal device 400 may be distributed and implemented in multiple physically separated configurations.

[0105] (Communication unit 410) The communication unit 410 is a signal processing unit for wireless communication with other wireless communication devices (e.g., the base station 300 and other terminal devices 400). The communication unit 410 operates under the control of the control unit 450. The communication unit 410 may be a wireless transceiver compatible with one or more wireless access methods. For example, the communication unit 410 supports both NR and LTE. The communication unit 410 may support W-CDMA and cdma2000 in addition to NR and LTE. The communication unit 410 may also support communication using NOMA.

[0106] The communication unit 410 includes a reception processing unit 411, a transmission processing unit 412, and an antenna 413. The communication unit 410 may include a plurality of reception processing units 411, a transmission processing unit 412, and an antenna 413. The configurations of the communication unit 410, the reception processing unit 411, the transmission processing unit 412, and the antenna 413 are similar to those of the communication unit 310, the reception processing unit 311, the transmission processing unit 312, and the antenna 313 of the base station 300.

[0107] The storage unit 420 is a data readable / writable storage device such as a DRAM, an SRAM, a flash memory, a hard disk, etc. The storage unit 420 functions as a storage unit of the terminal device 400.

[0108] The network communication unit 430 is a communication interface for communicating with other devices connected via a network. For example, the network communication unit 430 is a LAN interface such as a NIC. The network communication unit 430 may be a wired interface or a wireless interface. The network communication unit 430 functions as a network communication means of the terminal device 400. The network communication unit 430 communicates with other devices under the control of the control unit 450.

[0109] (Input / output section 440) The input / output unit 440 is a user interface for exchanging information with the user. For example, the input / output unit 440 is an operation device such as a keyboard, a mouse, an operation key, or a touch panel that allows the user to perform various operations. Alternatively, the input / output unit 440 is a display device such as a liquid crystal display (LCD) or an organic electroluminescence display (OLED). The input / output unit 440 may be an audio device such as a speaker or a buzzer. The input / output unit 440 may also be a lighting device such as an LED (Light Emitting Diode) lamp. The input / output unit 440 functions as an input / output means (input means, output means, operation means, or notification means) of the terminal device 400. Note that, in a case where the terminal device 400 is a sensor, at least a part of the functions (output function and / or input function) of the input / output unit 440 may be omitted.

[0110] (Control unit 450) The control unit 450 is a controller that controls each unit of the terminal device 400. The control unit 450 is realized by a processor such as a CPU, an MPU, or a GPU. For example, the control unit 450 is realized by a processor executing various programs stored in a storage device inside the terminal device 400 using a RAM or the like as a working area. The control unit 450 may be realized by an integrated circuit such as an ASIC or an FPGA. The CPU, the MPU, the GPU, the ASIC, and the FPGA can all be considered as controllers.

[0111] <<3. Technical features>> In this embodiment, the control station 100 estimates data (estimated data) of communication characteristics in a calculated area R_0 different from an estimated area R_1 based on an estimation model. At this time, the control station 100 utilizes actual measurement data in the estimated area R_1 to correct the estimated data based on the estimation model.

[0112] The estimation model is generated based on actual measurement data (first data) in at least one estimation area R_1. Also, data (estimated data) of communication characteristics in the calculation area R_0 is corrected using at least a part of actual measurement data (second data) in the calculation area R_0.

[0113] For example, the calculated area R_0 is a location X (e.g., around Tokyo Station). The estimated area R_1 is a location A (e.g., around Osaka Station), a location B (e.g., around Kawasaki Station), and a location C (e.g., around Shimbashi Station). Here, the calculated area R_0 is an area different from the estimated area R_1. Note that the areas listed here are merely examples, and areas other than these may be the calculated area R_0 or the estimated area R_1.

[0114] The estimation model is generated by a predetermined method using actual measurement data (first data) on communication characteristics (e.g., radio wave propagation characteristics) in places A / B / C. The communication characteristics in place X are corrected based on the generated estimation model and actual measurement data (second data) on communication characteristics in place X.

[0115] For example, a simple method for generating an estimation model may include linear regression analysis and multiple regression analysis. For example, an AI (artificial intelligence, machine learning, deep learning, etc.) may be used for generating an estimation model. Examples of the AI ​​include the following techniques. -Deep Learning -Multilayer Perceptron (MLP) -Convolutional Neural Networks (CNN) -Stochastic Gradient Descent -Decision Tree -Random Forest -Support Vector Machine -k-Nearest Neighbors -Naive Bayes Classifier There are many other methods besides these. It is desirable to select an appropriate method by taking into consideration the principles of each method.

[0116] When using AI, the communication characteristics to be estimated are used as the objective variable, and various parameters, data, and information (e.g., communication environment information) described below may be further used as the explanatory variables.

[0117] As described above, the control station 100 corrects the estimation data of the estimation model by using the actual measurement data of the calculation area R_0. Hereinafter, four methods (first to fourth methods) will be described as examples of this correction method.

[0118] <3.1. First method> The first method for correcting the estimated data is correction based on an allowable estimation error standard.

[0119] In this method, when the data estimated by the estimation model does not satisfy the following formula (1), the control station 100 corrects the estimated data.

[0120]

number

[0121] Here, x^ is the estimated data (predicted value) by the estimation model. x is the measured data set. e represents the error between the estimated data and the measured data set. γ represents the allowable estimation error. The measured data set x is given by the following equation (2).

[0122]

number

[0123] where x i(x_i) is the i-th measured data, and N is the number of measured data. E(·) is a function to calculate the error. Examples of this function include the root mean square error, the average error, and the signed average error.

[0124] Alternatively, in consideration of the worst case of the estimation error, the control station 100 may determine whether or not to correct the estimated data by using the maximum value of the errors between the estimated data x̂ and the N pieces of actual measurement data.

[0125] The measured data set x may be selected using various methods. For example, a set of measured data whose statistical properties match or are similar to those of the estimated data may be selected as the measured data set x. For example, when estimating radio wave strength, the radio wave strength tends to be similar at nearby receiving points due to spatial correlation of the radio wave strength. Therefore, the control station 100 may define a group of N pieces of measured data that exist within a radius r [m] centered on the predicted point as the measured data set x, and calculate the error e. Of course, the control station 100 may select a range other than the radius.

[0126] The radius r may be determined according to the similarity and correlation of the measured data group x. As an example, when estimating radio wave intensity, the correlation distance of shadowing is empirically 20 m in urban areas. Therefore, when the calculation area R_0 is an urban area, the control station 100 sets the radius r to be smaller than the distance (20 m).

[0127] The control station 100 may also extract an area similar to the structural characteristics around the prediction point from the calculation area R_0, and set the actual measurement data in the extracted area as the actual measurement data set x. Here, the prediction point is the point where the estimation of the estimated data is performed. It is desirable for the person who performs the calculation (e.g., the developer of the control station 100) to determine, for example, the definition of the error and the method of selecting the actual measurement data set x according to the communication characteristics of the prediction target.

[0128] When the above formula (1) is not satisfied, the control station 100 uses at least a part of the actual measurement data to correct the estimated data x̂. For example, the control station 100 performs the correction using a weighted average shown in the following formula (3).

[0129]

number

[0130] where x^' is the estimated data after correction, w i (w_i) is the weighting coefficient corresponding to the i-th measured data.

[0131] There are various ways to calculate the weighting coefficients. For example, when calculating radio wave strength, the control station 100 uses the inverse of the Euclidean distance between the predicted point and the point where the actual measurement data exists (hereinafter, the actual measurement point) as a weighting coefficient based on spatial correlation.

[0132] Furthermore, when the structural characteristics around the predicted point and the actual measurement point are similar, the control station 100 may set a large weighting coefficient for the actual measurement data.

[0133] In addition to the Euclidean distance and information on structure characteristics, if there is information that has a certain correlation with the communication characteristics of the prediction target, the control station 100 may use that information to determine the weighting coefficient.

[0134] Naturally, the control station 100 can correct the estimated data (predicted value, predicted data) x^ by using a maximum value, a minimum value, a median value, a mode value, or the like of the actually measured data other than the weighted average.

[0135] Furthermore, when actual measurement data with low measurement accuracy is mixed, the control station 100 sets a small weighting coefficient for the actual measurement data. For example, when the standard deviation of the actual measurement values ​​is known in advance by referring to the specifications of the observation equipment, the control station 100 adjusts the weighting coefficient according to the magnitude of the deviation.

[0136] If the observation accuracy of the actual measurement data is extremely low, the control station 100 may exclude the actual measurement data from the correction process. If an outlier is mixed in the actual measurement data, the control station 100 may exclude the outlier from the correction process. Methods for detecting outliers include the Smirnoff-Grubbs test, the interquartile range, and percentiles. The control station 100 may use these methods or other methods.

[0137] The control station 100 may correct the actual measurement data itself as a preprocessing before correcting the estimated data. For example, the i-th actual measurement data x i Frequency f of (x_i) i When (f_i) and the frequency f0 (f_0) of the estimated data x^ based on the estimation model differ, the control station 100 performs correction taking into account the difference in frequency.

[0138] When estimating radio wave intensity, the free space propagation loss varies depending on the frequency. Therefore, the control station 100 performs the process shown in the following equation (4) as pre-processing for the weighted average to correct the i-th measured data.

[0139]

number

[0140] where x^ i (x^_i) is the measured data after correction (preprocessing), Δ i (Δ_i) is the measured data x i This is a correction term for (x_i).

[0141] Actual data x i (x_i) is the radio wave strength, and the control station 100 is a frequency f i When correcting the free space path loss by the difference between (f_i) and frequency f0(f_0), Δ i (Δ_i) is given by the following equation (5).

[0142]

number

[0143] Here, L0(f0)(L_0(f_0))[dB] are the free space propagation losses of the estimated data x^ by the estimation model. L1(f1)(L_1(f_1))[dB] are the free space propagation losses of the i-th measured data x^. i is the free space path loss of (x_i).

[0144] The above describes the correction of measured data taking into account the difference in free space propagation loss due to frequency difference. Here, the control station 100 uses different parameters between the measured data and the estimated data. If the difference in parameters causes a difference in communication characteristics, the control station 100 may appropriately correct the measured data itself as a preprocessing step for correcting the estimated data.

[0145] <3.2. Second Method> A second method for correcting estimated data is correction based on imputation estimation.

[0146] In this method, the control station 100 spatially complements data (hereinafter also referred to as complement data) at unobserved points (points where the terminal device 400 has not measured actual measurement data) using at least a portion of the actual measurement data. The control station 100 reflects the complement result in the estimated data. For example, the control station 100 corrects the estimated data using the actual measurement data and the complement data.

[0147] The completion of unobserved points is generally divided into two methods: interpolation and extrapolation.

[0148] (interpolation) Fig. 8 is a diagram showing an example of completion by interpolation according to an embodiment of the present disclosure. Fig. 8 shows an example of completion in a two-dimensional space. In Fig. 8, actual measurement points where actual measurement data was measured are represented by black circles, and unobserved points where actual measurement data was not measured are represented by white circles.

[0149] 8 shows an example in which there are four actual measurement points, but the number of actual measurement points is not limited to four. The number of actual measurement points for one unobserved point may be three or less, or five or more.

[0150] Interpolation is a method of complementation when an unobserved point is within the range of actually measured points. In the example shown in Figure 8, the unobserved point is within the area with four actually measured points as vertices.

[0151] In this case, the control station 100 generates complementary data for unobserved points using, for example, nearest neighbor interpolation, inverse distance weighting, spline interpolation, Kriging, or the like.

[0152] It is desirable for a calculator (eg, a developer of the control station 100) to understand, for example, the principles of each method and the nature of the communication characteristics to be predicted, and to select an appropriate interpolation method.

[0153] Here, we will explain the complementation of radio wave strength as an example. When complementing radio wave strength, the important property is the spatial correlation of shadowing. Shadowing is radio wave attenuation caused by structures. It is known that the amount of attenuation has a strong correlation between nearby receiving points.

[0154] Therefore, the control station 100 uses Euclidean distance information between the unobserved point and the actually measured point to interpolate the shadowing at the unobserved point.

[0155] The computer is required to choose an appropriate interpolation method, the simplest of which is nearest neighbor interpolation.

[0156] 9 is a diagram illustrating an example of complementation by nearest neighbor interpolation according to an embodiment of the present disclosure. Nearest neighbor interpolation is a method of extracting an actual measurement point that is closest in Euclidean distance to an unobserved point, and using the shadowing at that point as a complement value at the unobserved point.

[0157] The control station 100 regards the shadowing at the red circle points in FIG. 9 as interpolated values ​​(complementary data) at unobserved points.

[0158] Although nearest neighbor interpolation has been given as an example of the interpolation method here, the control station 100 may generate complementary data for unobserved points using an interpolation method other than nearest neighbor interpolation.

[0159] (extrapolation) Fig. 10 is a diagram showing an example of complementation by extrapolation according to an embodiment of the present disclosure. Fig. 10 shows an example of complementation in a two-dimensional space. In Fig. 10, actual measurement points where actual measurement data is measured are represented by black circles, and unobserved points where actual measurement data is not measured are represented by white circles.

[0160] 10 shows an example in which there are four actual measurement points, but the number of actual measurement points is not limited to four. The number of actual measurement points for one unobserved point may be three or less, or five or more.

[0161] Extrapolation is a method of complementation when an unobserved point is outside the range of the actually measured points. In the example shown in Figure 10, the unobserved point is outside the area with four actually measured points as vertices.

[0162] In this case, the control station 100 generates complementary data for unobserved points using, for example, nearest neighbor extrapolation, mean value substitution, median substitution, multiple imputation, or the like.

[0163] It is desirable for a calculator (eg, a developer of the control station 100) to understand, for example, the principles of each method and the nature of the communication characteristics to be predicted, and to select an appropriate extrapolation method.

[0164] Here, the complementation of radio wave intensity will be described as an example. As described above, when complementing radio wave intensity, the important property is the spatial correlation of shadowing.

[0165] Therefore, the control station 100 extrapolates the shadowing at the unobserved point using the Euclidean distance information between the unobserved point and the measured point. The calculator is required to select an appropriate extrapolation method, and the simplest method is nearest neighbor extrapolation.

[0166] The control station 100 regards the shadowing of the actually measured point that is closest in Euclidean distance to the unobserved point as an extrapolated value (complementary data) at the unobserved point, in the same manner as the nearest neighbor interpolation.

[0167] Although nearest neighbor extrapolation has been given here as an example of an extrapolation method, the control station 100 may generate complementary data for unobserved points using an extrapolation method other than nearest neighbor extrapolation.

[0168] The control station 100 according to the present embodiment complements communication characteristics at unobserved points while taking into account the influence of structures on communication characteristics. In this respect, the complementation according to the present embodiment differs from complementation in general image processing fields.

[0169] Fig. 11 is a diagram showing an example of complementation by the control station 100 according to an embodiment of the present disclosure. The upper diagram of Fig. 11 is a diagram showing an example of actual measurement data in the calculation area R_0. The lower diagram of Fig. 11 is a diagram showing an example of complementation data.

[0170] 11, the control station 100 acquires actual measurement data in the calculation area R_0 from the terminal device 400. The amount of acquired actual measurement data is much smaller than the actual measurement data for estimation in the estimation area R_1 (see FIG. 3).

[0171] The control station 100 performs the above-described complementation at a plurality of unobserved points. The unobserved points may be selected, for example, at random by the control station 100. Alternatively, the control station 100 may set the points at which estimated data is calculated (estimated points) as unobserved points.

[0172] As shown in the lower diagram of FIG. 11, the control station 100 generates, through the complementation process, a larger amount of complement data than the amount of actual measurement data.

[0173] Finally, the control station 100 uses the complementary data to correct the data estimated by the estimation model.

[0174] Fig. 12 is a diagram illustrating an example of estimated data according to an embodiment of the present disclosure. For example, the control station 100 uses an arbitrary path loss model as an estimation model to obtain the estimated data as shown in Fig. 12.

[0175] In addition, there are various models for estimating path loss, such as a free space propagation loss model, an Okumura-Hata model, and a model obtained by linear regression of measured data (statistical path loss model). It is desirable for the calculator to select an appropriate path loss model. The calculator may select a path loss model by referring to the usage conditions of each model, for example.

[0176] The control station 100 may estimate a statistical path loss model using actual measurement data in an environment different from the calculation area R_0 (for example, actual measurement data for estimation in the estimation area R_1) and use the model as an estimation model in the calculation area R_0. Alternatively, the control station 100 may use AI or the like to construct an estimation model.

[0177] Fig. 13 is a diagram illustrating an example of actual communication characteristics in a calculation area R_0 according to an embodiment of the present disclosure. As shown in Fig. 13, in this embodiment, it is assumed that the actual communication characteristics are not accurately estimated by the path loss model.

[0178] FIG. 14 is a diagram illustrating an example of correction using complementary data by the control station 100 according to an embodiment of the present disclosure.

[0179] The control station 100 reflects the complementary data in the estimated data based on the estimation model. For example, the control station 100 corrects the estimated data based on the complementary data using the correction formula shown in the following formula (6).

[0180]

number

[0181] Here, P^(x) is the correction value of the radio wave strength at position x. P(x) [dBm] is the radio wave strength at position x when using the path loss model. S(x) [dB] is the shadowing at position x.

[0182] As shown in the lower diagram of FIG. 14, the control station 100 can obtain corrected estimated data that is close to the actual communication characteristics by correcting the estimated data using the complementary data.

[0183] Here, the control station 100 estimates the shadowing from the measured data in the calculation area R_0, but the data used for the estimation is not limited to the measured data. For example, the control station 100 may use the measured data for estimation in an estimation area R_1, which is different from the calculation area R_0, to estimate the unobserved points. In this case, the control station 100 may use the average shadowing value as S(x).

[0184] In addition, although the control station 100 corrects the estimated data of radio wave strength by using shadowing here, the estimated data corrected by the control station 100 is not limited to radio wave strength. For example, the control station 100 may correct estimated data of communication characteristics other than radio wave strength (e.g., signal-to-noise ratio, signal-to-interference ratio, delay characteristics, throughput characteristics, etc.) in the same way as the radio wave strength.

[0185] If the correction accuracy using the complementary data is poor, i.e., if the estimation accuracy of the correction estimation data is poor, the control station 100 may further correct the correction value by utilizing auxiliary information, etc. Examples of the auxiliary information include structure information, building information, topographical information, traffic volume, interference power volume, noise power level, and delay amount.

[0186] Further, in the above embodiment, the control station 100 complements the unobserved points by using the actually measured data at the observed points. However, the unobserved points may be complemented by using data other than the actually measured data.

[0187] Fig. 15 is a diagram showing an example of completion using estimated data according to an embodiment of the present disclosure. Fig. 15 shows an example of using estimated data when performing interpolation, but estimated data can also be used when performing extrapolation. In Fig. 15, estimated points are shown with white triangles.

[0188] For example, the control station 100 calculates the estimation data at the estimation point using an estimation model generated using actual measurement data for estimation in the estimation area R_1.

[0189] The control station 100 calculates data (complementary data) of unobserved points using this estimated data and actual measurement data of actual measurement points in the calculation area R_0. Except for using estimated data, the calculation method (complementary method) of the complementary data is the same as the above-mentioned method of complementing unobserved points using only actual measurement data of actual measurement points.

[0190] As described above, the control station 100 may correct the estimated data by using the complementary data. In this case, the estimated data may be data generated by using an estimation model generated by using actual measurement data for estimation in the estimation area R_1, or may be data generated by using a model different from this estimation model.

[0191] For example, the control station 100 may use an estimation model (first estimation model) for complementing data of unobserved points and an estimation model (second estimation model) for generating estimated data that is to be corrected using the complementing data.

[0192] The first estimation model and the second estimation model may be generated using data of the same estimation area R_1, or may be generated using data of different estimation areas R_1. In addition, the first estimation model and the second estimation model may be generated by the same method (e.g., AI learning, etc.) or may be generated by different methods.

[0193] The control station 100 may also correct the estimated data (hereinafter also referred to as the first estimated data) generated by the first estimation model before using it to complement the unobserved points. For example, the control station 100 may correct the first estimated data using the above-mentioned first method, and complement the unobserved points using the corrected first estimated data (hereinafter also referred to as the first corrected estimated data).

[0194] The correction of the first estimated data is not limited to the first method. The first estimated data may be corrected by a third or fourth method described later, or by another method.

[0195] Furthermore, the control station 100 may complement unobserved points by using simulation data instead of or in addition to the first estimated data.

[0196] In this way, by using the first estimated data and / or the simulation data, the control station 100 can complement the unobserved points with higher accuracy.

[0197] <3.3. The third method> A third method for correcting the estimated data is correction by adding explanatory variables of the AI ​​(estimation model). That is, in the third method, the control station 100 performs correction on the variables of the estimation model.

[0198] When estimating communication characteristics such as received power using AI, the control station 100 may use (add) the estimated data by the statistical path loss model in the estimation area R_1 and / or the calculation area R_0 as explanatory variables of the AI ​​(estimation model). In this way, the control station 100 can correct the estimated data within the AI ​​(estimation model).

[0199] In addition, in addition to the statistical path loss model, the control station 100 may input (add) building information (height, density, location information, etc.) to the AI ​​(estimation model) as explanatory variables, and correct the estimated data within the AI ​​(estimation model).

[0200] The control station 100 may input the attenuation coefficient of the path loss, the average value of the shadowing, the standard deviation, the correlation distance (for example, the distance at which the correlation value is 0.5), the standard deviation of the fading, and the like in each estimation area R_1 to the AI ​​(estimation model). This allows the control station 100 to perform estimation taking into account the location dependency of radio wave propagation.

[0201] Furthermore, the control station 100 may input at least a part of the actual measurement data in the calculation area R_0 to an AI (estimated model) to correct the estimated data. For example, the control station 100 may calculate the error between the estimated data and the actual measurement data, and generate a correction model by the AI. For example, the control station 100 generates the correction model by correcting the variables of the estimated model so that the error between the estimated data and the actual measurement data is reduced.

[0202] In this method, for example, actual measurement data is used as an input (explanatory variable) of the estimation model. The control station 100 acquires corrected estimation data by inputting at least the actual measurement data to the estimation model. Alternatively, the control station 100 may generate a correction model that receives the estimation data and the actual measurement data as input and outputs the corrected estimation data, and generate the corrected estimation data using this correction model.

[0203] <3.4. The fourth method> A fourth method for correcting the estimated data is correction based on reconstruction of the estimation model.

[0204] In this case, the control station 100 may correct any coefficient of the estimation model generated using the actual measurement data for estimation of the estimation area R_1, for example, by using the following formula (7). That is, the control station 100 may correct the coefficient for the variable of the estimation model.

[0205]

number

[0206] where x i (x_i) represents the measured data at point i. P^ i (d i , η) [dBm] represents the estimated data of the communication characteristics at point i when the estimation model is used. d i (d_i)[m] represents the Euclidean distance between the base station 300 and the point i. η is an arbitrary coefficient in the equation of the estimation model. Furthermore, M is the maximum value of the arbitrary coefficient and is freely set by the person performing the calculation.

[0207] For example, when correcting the path loss coefficient of the statistical path loss model, it is generally known that the path loss coefficient in urban areas is empirically 4-5. Therefore, the arbitrary coefficient of the estimation model can be set with reference to this value. The control station 100 uses the equation (7) to calculate the actual measurement data x i The difference between (x_i) and the estimated data using the estimation model is calculated, and an arbitrary coefficient η that minimizes this difference is searched for.

[0208] FIG. 16 illustrates an example of correction of an arbitrary coefficient by the control station 100 according to an embodiment of the present disclosure. 16. The vertical axis of Fig. 16 represents communication characteristics, and the horizontal axis represents the distance between the transmitter and the receiver. Note that the horizontal axis is not limited to the distance between the transmitter and the receiver, and may represent time, for example.

[0209] In FIG. 16, the model of the actual communication characteristics is indicated by a dotted line, and the estimated model before correction is indicated by a solid line.

[0210] The control station 100 corrects the arbitrary coefficients so that the estimated model before correction approaches the slope of the actual communication characteristics. In Fig. 16, the estimated model after correction (hereinafter, also referred to as the corrected model) is shown by a red line. This allows the control station 100 to obtain a corrected estimated model with a slope close to the model of the actual communication characteristics.

[0211] The control station 100 generates estimated data using the corrected constant model, and thereby the control station 100 can correct the estimated data using the actual measurement data to obtain corrected estimated data.

[0212] In addition, the actual measurement data x i There are several ways to select (x_i). For example, when correcting the path loss coefficient of the statistical path loss model, the control station 100 selects i The actual measurement data is used at the point where (d_i) is satisfied and in an LOS environment where the propagation characteristics fluctuate little.

[0213] Additionally, the control station 100 can obtain an average estimation model for the calculation area R_0 by using actual measurement data from a location where the fluctuation in communication characteristics is relatively small.

[0214] Although the control station 100 corrects the arbitrary coefficients in the above description, the correction target of the estimation model is not limited to the coefficients. For example, the control station 100 may correct an arbitrary constant term.

[0215] As described above, by using the corrected estimation model, the control station 100 can estimate communication characteristics with higher accuracy than the estimation model before correction. While the first and second methods are methods for correcting the predicted value by the estimation model, this method is a method for reconstructing the estimation model itself by utilizing actual measurement data.

[0216] <3.5. About the measured data> When using at least a part of the measured data, the acquisition range, the observation accuracy, and the number of pieces of data are important. In the correction using the measured data, it is desirable to use measured data with as many different characteristics as possible.

[0217] For example, when the estimated data of the received power according to the estimation model is corrected using a portion of the received power, it is desirable to have actual measurement data in which the received power is relatively high and low.

[0218] When performing correction using spatial interpolation or weighted moving average using measured data with high received power, there is a risk that a high correction value (corrected estimated data) will be output even in places where the received power is actually low.

[0219] Therefore, for example, it is desirable for the control station 100 to use actual measurement data acquired by the terminal devices 400 at some points near the base station 300 and some points far away for correction.

[0220] Furthermore, it is desirable for the control station 100 to use, for correction, actual measurement data acquired by the terminal device 400 at a point where the area between the base station 300 and the observation point is an NLOS environment in addition to the LOS environment. This is because communication characteristics tend to differ significantly between an LOS environment and an NLOS environment.

[0221] In addition, when the observation accuracy of the measured data used for correction is poor or when the number of pieces of data is small, the correction accuracy also deteriorates. However, if an attempt is made to ensure the number of pieces of data, the observation time may increase. Therefore, it is desirable for the control station 100 to perform correction using at least a part of the measured data acquired at multiple receiving points with different radio wave propagation characteristics.

[0222] <<4. Processing Example>> An example of each process executed in the communication system will be described below.

[0223] <4.1. Communication processing> Fig. 17 is a sequence diagram showing an example of a flow of communication processing according to an embodiment of the present disclosure. The communication processing shown in Fig. 17 is executed by the communication system at a predetermined interval or when a specific event occurs, for example.

[0224] First, the control station 100 generates an estimation model (step S101). The control station 100 generates at least one estimation model using, for example, actual measurement data for estimation of at least one estimation area R_1. This process may be executed as a process different from the communication process, and may be executed by a device other than the control station 100.

[0225] The base station 300 transmits a signal to the terminal device 400 (step S102). The terminal device 400 measures this signal and transmits actual measurement data, which is the measurement result, to the control station 100 (step S103).

[0226] Here, examples of information measured by the terminal device 400 include RSRP (Reference Signal Received Power), RSSI (Received Signal Strength Indicator), RSRQ (Reference Signal Received Quality), interference power, SNR, SIR, SINR, throughput, delay amount, Ping, and location information of the terminal device 400.

[0227] The control station 100 executes a control information generation process as an example of statistical processing (step S104). For example, the control station 100 predicts communication characteristics using an estimation model, and generates control information according to the predicted communication characteristics. Details of the control information generation process will be described later.

[0228] The control station 100 transmits the generated control information to the base station 300 and the terminal device 400 (step S105). Note that the control station 100 may transmit the control information to either the base station 300 or the terminal device 400.

[0229] The terminal device 400 may transmit the actual measurement data to the control station 100 via the base station 300, or may transmit the actual measurement data to the control station 100 without via the base station 300. That is, the terminal device 400 may notify the control station 100 of the actual measurement data via a cellular network, or may notify the control station 100 of the actual measurement data via a network other than the cellular network (for example, a LAN).

[0230] Furthermore, when transmitting control information to the terminal device 400, the control station 100 may transmit the control information via the base station 300, or may transmit the control information without passing through the base station 300. That is, the control station 100 may notify the terminal device 400 of the control information via a cellular network, or may notify the terminal device 400 of the control information via a network other than the cellular network (for example, a LAN).

[0231] Furthermore, the information that the control station 100 transmits to the base station 300 and / or the terminal device 400 as a result of the statistical processing is not limited to control information. The control station 100 may transmit corrected estimated data (communication characteristics) estimated using an estimation model to the base station 300 and / or the terminal device 400. In this way, the control station 100 may transmit information related to the corrected estimated data, such as control information or communication parameters generated based on the corrected estimated data, or estimated communication characteristics, to the base station 300 and / or the terminal device 400.

[0232] <4.2. Control information generation process> An example of the control information generation process executed by the control station 100 will be described below for each of the first to fourth correction methods.

[0233] (First Method) Fig. 18 is a flowchart showing an example (part 1) of the flow of the control information generation process according to the embodiment of the present disclosure. The control information generation process shown in Fig. 18 is executed by the control station 100 at a fixed interval or when a predetermined condition is satisfied, such as when predetermined actual measurement data is acquired.

[0234] First, the control station 100 calculates estimated data using an estimation model (step S201).

[0235] The control station 100 determines whether to correct the calculated estimated data (step S202). The control station 100 determines whether to correct the calculated estimated data depending on whether the error between the estimated data and the actual measurement data is equal to or smaller than the allowable estimated error, for example.

[0236] If it is determined that the estimated data is not to be corrected (step S202; No), the control station 100 proceeds to step S204.

[0237] On the other hand, when it is determined that the estimated data is to be corrected (step S202; Yes), the control station 100 corrects the estimated data using the actual measurement data (step S203). For example, the control station 100 corrects the estimated data using an average (for example, a weighted average) of the actual measurement data.

[0238] Next, the control station 100 determines whether or not correction has been determined for all of the estimated data (step S204).

[0239] If there is still estimated data for which the determination as to whether correction has been performed has not been performed, that is, if the determination as to whether correction has been performed has not been performed for all estimated data (step S204; No), the control station 100 returns to step S202.

[0240] On the other hand, if it has been determined that all the estimated data should be corrected (step S204; Yes), the control station 100 generates control information using the corrected estimated data (corrected estimated data) (step S205), and ends the process.

[0241] (Second Method) 19 is a flowchart showing an example (part 2) of the flow of the control information generation process according to the embodiment of the present disclosure. The control information generation process shown in FIG. 19 is executed by the control station 100 at a fixed cycle or when a predetermined condition is satisfied, such as when predetermined actual measurement data is acquired.

[0242] The control station 100 complements an unobserved point with actual measured data of the actual measured point (step S301). The control station 100 calculates data (complementary data) at the unobserved point by, for example, interpolation or extrapolation using the actual measured data at the actual measured point.

[0243] The control station 100 calculates estimated data from the estimation model (step S302). Next, the control station 100 reflects the complementary data in the estimated data (step S303). In this way, the control station 100 generates corrected estimated data.

[0244] The control station 100 generates control information using the corrected estimated data (step S304), and ends the process.

[0245] (Third Method) Fig. 20 is a flowchart showing an example (part 3) of the flow of the control information generation process according to the embodiment of the present disclosure. The control information generation process shown in Fig. 20 is executed by the control station 100 at a fixed cycle or when a predetermined condition is satisfied, such as when predetermined actual measurement data is acquired.

[0246] Furthermore, when this control information generation process is executed, it is assumed that the control station 100 generates an estimation model that uses actual measurement data as part of the input.

[0247] The control station 100 inputs at least the actual measurement data to the estimation model, and obtains corrected estimation data as the output of the estimation model (step S401).

[0248] The control station 100 generates control information using the corrected estimated data (step S402), and ends the process.

[0249] (Fourth Method) Fig. 21 is a flowchart showing an example (part 4) of the flow of the control information generation process according to the embodiment of the present disclosure. The control information generation process shown in Fig. 21 is executed by the control station 100 at a fixed interval or when a predetermined condition is satisfied, such as when predetermined actual measurement data is acquired.

[0250] First, the control station 100 calculates estimated data using an estimation model (step S501).

[0251] The control station 100 corrects the estimation model using the estimated data and / or the measured data (step S502). For example, the control station 100 corrects an arbitrary coefficient of the estimation model. In this way, the control station 100 generates a corrected estimation model.

[0252] The control station 100 calculates corrected estimated data from the corrected estimated model (step S503). The control station 100 generates control information using the corrected estimated data (step S504), and ends the process.

[0253] As described above, the control station 100 according to this embodiment corrects the estimated data using the actual measurement data of the calculation area R_0, thereby enabling the control station 100 to estimate communication characteristics with higher accuracy.

[0254] <<5. Definition of Terms>> Here, definitions of terms used in the above-mentioned embodiment will be described.

[0255] (Communication characteristics) For example, the communication characteristics may be any of the following or a combination thereof: -Characteristics based on radio wave propagation from the transmitting point to the receiving point (downlink, uplink, and sidelink) communication parameters at the transmission point, reception point, base station 300, terminal device 400 and / or communication node

[0256] The characteristics based on radio wave propagation from a transmission point to a reception point include at least one of a characteristic related to received power, a characteristic related to communication speed (throughput), and a characteristic related to delay.

[0257] The characteristics related to the received power include information on at least one of the received power, the interference power, the RSRP, the RSRQ, the RSSI, the SNR, the SNR, and the SINR.

[0258] The characteristics related to communication speed include information regarding at least one of a downlink throughput, an uplink throughput, and a sidelink throughput.

[0259] The delay-related characteristics include information regarding at least one of a latency, a jitter, and a ping value.

[0260] The communication parameters at the transmission point, the reception point, the base station 300, the terminal device 400 and / or the communication node include dynamically determined parameters and / or semi-statically determined parameters.

[0261] The dynamically determined parameters include at least one of the following information: -Information about MCS (Modulation and Coding Scheme) -Information about transmission power -Beam control information -Information about MIMO multiplexing

[0262] The semi-statically determined parameters include at least one of a range, a maximum value, a minimum value, an average value, and a median value of a parameter selectable (permitted to the base station 300 or the terminal device 400) by the base station 300 or the terminal device 400. An example of a semi-statically determined parameter is the maximum transmission power.

[0263] (About the area) In this embodiment, an area (a place, a base, for example, the calculated area R_0 and the estimated area R_1 described above) can be given by any one of the following or a combination thereof. -Coverage area (communication area) of a given base station 300, terminal device 400, or communication node - Site or building owned or managed by a specified business operator - Areas designated in advance by designated businesses or governments - Areas divided in a prescribed manner

[0264] A communication area includes, for example, coverage that can be connected to one communication node (such as a base station 300 or a terminal device 400). Also, for example, when multiple base stations 300 are installed in one base station, the base stations 300 are connected to one core network. In other words, a base station can be defined as a coverage area covered by at least one base station 300 connected to one core network.

[0265] For example, the base station 300 of the private network or the access point name (APN) of the core network may be set as the communication area for each base. In other words, the same access point name is set for the same base (communication area), and if the access point names are different, they are recognized as different bases (communication areas).

[0266] An example of a predetermined method for dividing areas is a method based on location information, in which areas are divided at predetermined distances based on location information such as latitude and longitude.

[0267] (About communication environment information) The communication environment information includes at least one of static or semi-static information and dynamic information. Static or semi-static information is fixed information or information that is updated infrequently. The static or semi-static information may be information in a higher communication layer (e.g., an application layer, an RRC (Radio Resource Control) layer, etc.). The dynamic information is information that is updated frequently. The dynamic information may be information in a lower communication layer (e.g., a physical layer, etc.).

[0268] The communication environment information includes, for example, at least one of the following pieces of information: -Map information -Structure information -Device information regarding the base station 300 or the terminal device 400 -Sensing information acquired through sensing devices -Radio communication information regarding wireless communications -Quality information regarding communication quality in wireless communication

[0269] (Map information) The map information here is information that allows the positions and sizes of structures, the base station 300, the terminal device 400, etc. to be recognized. The positions may be absolute position information such as latitude and longitude, or may be relative position information within an area.

[0270] The map information includes, for example, topographical information, an office layout diagram, and a floor plan.

[0271] (Structure information) The structural information here includes information that affects radio wave propagation, such as reflection, diffraction, and transmission.

[0272] Examples of structures include buildings, walls, plantations, roads, signs, traffic lights, road signs, pillars, buildings, the ground, glass, windows, desks, and cabinets.

[0273] The structure information includes, for example, the position, shape, size, and material of the structure, and parameters related to radio wave propagation in the structure (dielectric constant, conductivity, etc.).

[0274] The structure information is generated and constructed, for example, based on the above-mentioned map information, etc. In addition, the structure information may be generated and constructed based on information acquired from a sensing device, etc., which will be described later.

[0275] (Device information regarding base station 300 or terminal device 400) Here, the device information regarding the base station 300 or the terminal device 400 includes, for example, at least one of the pieces of information listed below. -Antenna information about antennas -Capability information regarding the functions and capabilities supported by wireless communication Shape information regarding the shape and weight of the base station 300 and / or the terminal device 400 Location information of fixed base stations 300 and / or fixed terminal devices 400

[0276] The antenna information here includes at least one of the following pieces of information: the antenna configuration of the base station 300 and / or the terminal device 400, the beam pattern, the number of antenna elements, and the configuration of the antenna elements.

[0277] (Sensing information obtained through sensing devices) The sensing information acquired through the sensing device here includes object information regarding an object detected through the sensing device, and / or effect information regarding fluctuations and / or effects on wireless communication caused by the detected object.

[0278] Here, the sensing device includes a camera, a sensor, etc. The sensor includes a photoelectric sensor, a fiber sensor, a laser sensor, a color sensor, a proximity sensor, an eddy current type displacement sensor, a contact type displacement sensor, an ultrasonic sensor, an image discrimination sensor, a pressure sensor, a vibration sensor, an inertial measurement sensor, etc.

[0279] Three-dimensional spatial information (e.g., the above-mentioned structure information) is generated from sensing information acquired through a sensing device. For example, when the sensing information is an image or video acquired in real time by a camera, the three-dimensional spatial information is generated in real time using, for example, a photogrammetry technique or a volumetric capture technique.

[0280] The objects detected by the sensing device include various devices such as the sensing device itself, a device other than the sensing device, and a terminal device 400 that transmits information acquired by the sensing device. In addition, the objects detected by the sensing device include the above-mentioned structures and objects other than structures.

[0281] The terminal device 400 that transmits the sensing information acquired by the sensing device may or may not be equipped with the sensing device. When the terminal device 400 and the sensing device are separate devices, it is preferable that the terminal device 400 acquires the sensing information from the sensing device, for example, by wired or wireless communication.

[0282] In addition, the sensing information acquired by sensing (the sensing information acquired through the sensing device) may include various sensing information in addition to the object detection information. For example, the sensing information acquired by sensing includes beam information (e.g., information on the beam pattern, the beam angle, etc.) regarding the beam transmitted from the base station 300 and / or the terminal device 400.

[0283] The above-mentioned sensing device can detect moving objects such as people and robots in addition to stationary objects such as structures. The sensing device transmits, for example, information on the detected moving object as sensing information via the terminal device 400.

[0284] The sensing device may transmit the sensing information when it detects a moving object and / or when it no longer detects a moving object, or may transmit the sensing information at regular intervals.

[0285] (Radio communication information regarding radio communication) The wireless communication information relating to wireless communication here includes, for example, at least one of the pieces of information listed below. -Communication information related to RAT (Radio access technology) and frequencies -Scenario information on communication environment scenarios - Information on restrictions regarding conditions and restrictions on wireless communication available on the local network -Information regarding the transmission power of the base station 300 or the terminal device 400

[0286] The communication information regarding the RAT includes, for example, information regarding LTE, NR, wireless LAN, Bluetooth (registered trademark), etc. The communication information regarding the frequency includes information regarding at least one of a frequency band, a center frequency, and a frequency bandwidth.

[0287] The information regarding the transmission power of the base station 300 or the terminal device 400 includes, for example, information (ss-PBCH-BlockPower) indicating the transmission power of an SS / PBCH (Synchronization Signal and Physical Broadcast CHannel) block included in an SS / PBCH (System information block type 1) included in SIB1 (System information block type 1), which is control information broadcast from the base station 300.

[0288] The scenario information regarding the communication environment scenario includes, for example, information regarding urban areas, suburban areas, rural areas, indoor offices, indoor factories, and the like.

[0289] The scenario information may further include information on a radio wave propagation model (e.g., a path loss model) corresponding to the communication environment scenario. The radio wave propagation model may correspond to each of a LOS environment and a NLOS environment.

[0290] The restriction information here includes information on conditions and restrictions regarding wireless communication permitted in the local network.

[0291] These conditions and constraints may include, for example, information about available RATs, areas where wireless communication is possible (geographical information (such as two-dimensional planar information and / or spatial information including three-dimensional height)), an upper limit on the amount of interference power outside the area, maximum transmit power that can be transmitted, transmittable frequency information, transmittable time information, the installation location of base station 300, and the like.

[0292] These conditions and constraints are, for example, set and defined in advance, and can be determined and / or changed based on information notified from a predetermined server or storage device (for example, a Spectrum Access System (SAS) server, etc.).

[0293] The quality information regarding the communication quality in wireless communication includes, for example, at least one of the following pieces of information measured or estimated by the terminal device 400 in wireless communication. - Received power -Interference power -RSRP -RSRQ -RSSI -SNR -Downlink throughput -Uplink throughput -Latency -jitter -Ping value

[0294] (About virtual space estimation information) The virtual space estimation information includes, for example, information on radio wave propagation of at least one of the base station 300 and the terminal device 400. The virtual space estimation information is, for example, data (information) obtained by simulation. The virtual space estimation information can be used as necessary when refining an estimation model.

[0295] The virtual space estimation information includes, for example, at least one of the pieces of information listed below. -LOS / NLOS information -Simulation information - Calculated information based on LOS / NLOS information, simulation information, etc.

[0296] (LOS / NLOS information) The LOS / NLOS information is information indicating whether the environment between the base station 300 and the terminal device 400 is an LOS environment or an NLOS environment.

[0297] The LOS environment is also called a line-of-sight environment. The LOS environment indicates a situation in which there are no obstacles 600, such as structures or people, on a straight line between the base station 300 and the terminal device 400, and the base station 300 and the terminal device 400 can transmit and receive direct waves between them. In this case, wireless communication between the base station 300 and the terminal device 400 is performed through reflected waves, diffracted waves, and the like in addition to direct waves.

[0298] The NLOS environment is also called a non-line-of-sight environment. The NLOS environment indicates a situation in which there is an obstacle 600, such as a structure or a person, on the straight line between the base station 300 and the terminal device 400, and the base station 300 and the terminal device 400 cannot transmit or receive direct waves between them. In this case, wireless communication between the base station 300 and the terminal device 400 is performed through reflected waves, diffracted waves, and the like other than direct waves.

[0299] (Simulation information) The simulation information includes information on a simulation result of radio wave propagation in wireless communication between the base station 300 and the terminal device 400. The simulation information includes, for example, path information on one or more paths (propagating waves, arriving waves, rays) acquired by a ray tracing simulation.

[0300] This path includes a direct wave, a reflected wave, a diffracted wave, a transmitted wave, and the like between the base station 300 and the terminal device 400. In general, there are various structures between the base station 300 and the terminal device 400, so a signal (radio wave) transmitted from a transmitting point (e.g., the base station 300) travels through various routes, becomes a plurality of paths, and arrives at a receiving point (e.g., the terminal device 400).

[0301] The path information regarding the path may include, for example, at least one of the following information: - Received power at the receiving point -Transmission power at the transmission point -Path loss - Propagation distance - Number of reflections - Number of diffractions - Number of passes -Phase variation - Angle of emission at the transmitting point - Angle of arrival at the receiving point - Arrival order of the pass (in what order among multiple passes the pass arrived) - Number of passes

[0302] (Calculation information) The calculated information is information that is generated and calculated based on the above-mentioned LOS / NLOS information, simulation information, etc. The calculated information may include, for example, at least one of the following pieces of information: - Path loss at the receiving point - Received power -Interference power -RSRP -RSRQ -RSSI -SNR -Downlink throughput -Uplink throughput -Latency -jitter -Ping value

[0303] Here, an example of a generation process of simulation data according to the present embodiment will be described with reference to Fig. 22. Fig. 22 is a flowchart showing an example of the flow of the generation process according to the embodiment of the present disclosure.

[0304] The generation process shown in FIG. 22 is executed by, for example, the control station 100 when generating an estimation model and / or calculating corrected estimation data.

[0305] First, the control station 100 constructs a virtual communication environment for an area (a predetermined area, an area for model generation, for example, a calculated area R_0, an estimated area R_1) (step S601).

[0306] For example, the virtual communication environment is a three-dimensional virtual space of the area. For example, the virtual communication environment is generated based on communication environment information in the area. For example, the virtual communication environment includes structures (such as buildings and the ground) in the area.

[0307] Next, the control station 100 executes a radio wave propagation simulation between the base station 300 and the terminal device 400 in a virtual communication environment (step S602). The radio wave propagation simulation may use various methods such as LOS environment / NLOS environment determination in a virtual space or ray tracing simulation.

[0308] The control station 100 generates virtual space estimation information based on the simulation results (step S603).

[0309] The generation process may be executed by a device other than the control station 100. In this case, the control station 100 acquires virtual space estimation information (simulation data) from the device that executes the generation process. The execution timing of the generation process is not limited to when the estimation model is generated and / or when the corrected estimation data is calculated. The control station 100 may execute the generation process at any timing.

[0310] (About location information) The information on the location is the location information of the base station 300 and / or the terminal device 400. The information on the location includes absolute location information such as latitude, longitude, and / or altitude acquired by, for example, a Global Positioning System (GPS) or a Global Navigation Satellite System (GNSS).

[0311] Alternatively, the information regarding the location includes relative location information obtained from a beacon, UWB (Ultra-Wide Band), or the like.

[0312] The absolute location information or relative location information may be an area separated by a predetermined distance or method.

[0313] Note that the information according to this embodiment can be information linked to location information.

[0314] (About the estimation accuracy) An estimation accuracy may be given to data estimated by the estimation model. This estimation accuracy is given to communication characteristics in the calculation area R_0. Furthermore, this estimation accuracy may be given to the estimation model.

[0315] Moreover, this estimation accuracy can be further utilized when using (exploiting) the estimated data in the estimation model.

[0316] The estimation accuracy of the data of the communication characteristics in the calculation area R_0 includes at least one of the following. - Number of estimated areas R_1 -Number of actual measurement data in each estimated area R_1 -Accuracy of simulation data in estimated area R_1 and calculated area R_0 - Measurement accuracy (observation accuracy) of actual data in the estimated area R_1 and the calculated area R_0

[0317] The accuracy of the simulation data in the estimated area R_1 and the calculated area R_0 is determined based on, for example, the accuracy (precision, accuracy) of the communication environment information in the simulation.

[0318] The measured data of the estimated area R_1 and the calculated area R_0 may include location information in addition to communication characteristics. For example, the error of the measured data may include an actual measurement error of RSRP and / or an error of location information by GPS.

[0319] Furthermore, if an observation error specific to the terminal device 400 occurs, information indicating the terminal device 400 may be further added as the estimation accuracy.

[0320] <<6. Normalization of measured data for estimation>> In this embodiment, when there are multiple estimated areas R_1, the simulation data and / or the actual measurement data in the estimated area R_1 is normalized (offset is provided) by, for example, a predetermined method.

[0321] The predetermined method may be performed based on communication environment information (eg, information on the transmission power from the base station 300) in each estimation area R_1.

[0322] Here, the communication environment information is the information described above. The communication environment information includes, for example, information on the transmission power of the base station 300, information on the frequency used in communication (carrier frequency, frequency bandwidth, etc.), information on the communication area (coverage area, indoor / outdoor information, etc.), etc.

[0323] For example, normalization is performed so that the communication environment information in each estimated area R_1 becomes the same.

[0324] Simulation data (third data) of communication characteristics in a specified area (one of the multiple estimated areas R_1) is normalized so that the communication environment information in the specified area is the same as the communication environment information in each estimated area R_1 (the remaining estimated areas R_1 other than the specified area).

[0325] Data (fourth data) of communication characteristics in a predetermined area (one of the multiple estimated areas R_1) is estimated taking into account the above-mentioned normalization.

[0326] The above-mentioned normalization is performed so that the communication environment information in each estimated area R_1 becomes the communication environment information in the above-mentioned predetermined area (one of the multiple estimated areas R_1).

[0327] The normalization is performed, for example, by a device that generates the estimated model (the control station 100 in this embodiment). Note that the device that performs the normalization and the device that generates the estimated model may be different devices.

[0328] A specific example of normalization will be described below.

[0329] For example, consider a case where the communication characteristics of the simulation data and / or the actual measurement data in the estimation area R_1 are the downlink RSRP.

[0330] Consider the case where the transmission power of the base station 300 at location A is A [dBm], the transmission power of the base station 300 at location B is B [dBm], and the transmission power of the base station 300 at location C is C [dBm].

[0331] When normalizing the transmission power of each of the data to S [dBm], the control station 100 assigns an offset of SA [dBm] to the RSRP in location A. The control station 100 assigns an offset of SB [dBm] to the RSRP in location B. The control station 100 assigns an offset of SC [dBm] to the RSRP in location C. In this manner, the control station 100 performs normalization by assigning an offset to each of the RSRPs (each data).

[0332] Here, S [dBm] may be the transmission power of the base station 300 in the calculation area R_0 (location X) where the estimation is performed.

[0333] <<7. Other embodiments>> The processing according to each of the above-described embodiments may be implemented in various different forms other than the above-described embodiments.

[0334] Data estimated by the estimation model according to the above-described embodiment (corrected estimated data) can be used in various processes, controls, use cases, and the like.

[0335] For example, data on communication characteristics estimated in the calculation area R_0 (corrected estimated data) can be used for cell design within that area (setting of the locations of transmission points, maximum transmission power of the transmission points, etc.).

[0336] This cell design may be performed based on the estimation accuracy of communication characteristics in the calculation area R_0. Also, this cell design may be performed by the control station 100 or the base station 300. Alternatively, the cell design may be performed in a core network or the like.

[0337] For example, data on communication characteristics estimated in the calculation area R_0 (corrected estimated data) can be used to control communication parameters (transmission power, MCS, beams, etc.) of transmission points and / or reception points within the area.

[0338] The control of the communication parameters may be performed based on the estimation accuracy of the communication characteristics in the calculation area R_0. Moreover, the control of the communication parameters may be performed by the control station 100 or the base station 300. Alternatively, the control of the communication parameters may be performed by a core network or the like.

[0339] In the above-described embodiment, one or more estimation models are generated using actual measurement data for estimation of one or more estimation areas R_1. In this case, the control station 100 may generate one estimation model for each estimation area R_1, or may generate one estimation model for all estimation areas R_1. When generating one estimation model for all estimation areas R_1, the control station 100 may perform the above-described normalization on the actual measurement data for estimation.

[0340] Alternatively, the control station 100 may generate a plurality of estimation models for a plurality of estimation areas R_1. In this case, the number of generated estimation models may be smaller than the number of estimation areas R_1.

[0341] For example, the control station 100 may divide a plurality of estimated areas R_1 into a plurality of groups and generate an estimation model corresponding to each group. At this time, the same estimated area R_1 may be included in the plurality of groups.

[0342] When a group includes a plurality of estimation areas R_1, the control station 100 may perform normalization on the actual measurement data for estimation in the estimation areas R_1 of the same group.

[0343] Furthermore, the control station 100 may perform grouping for each similar estimated area R_1. For example, the control station 100 divides estimated areas R_1 having the same and / or similar communication environment information into one group.

[0344] When multiple estimation models are generated, the control station 100 may calculate corrected estimation data using an estimation model generated based on an estimation area R_1 similar to the calculation area R_0.

[0345] The control station 100 may select an estimated area R_1 similar to the calculated area R_0, and generate an estimated model using actual measurement data for estimation of the selected estimated area R_1. Alternatively, the control station 100 may select an estimated model generated based on the estimated area R_1 similar to the calculated area R_0 from among a plurality of estimated models generated in advance.

[0346] In the above-described embodiment, the terminal device 400 and the base station 300 transmit various information (for example, real space measurement information, communication environment information, information used by the control station 100 for estimation, etc.) to the control station 100. Conditions regarding the transmission of information by the terminal device 400 and the base station 300 may be set or specified individually. These conditions include, for example, the timing of transmitting information, the trigger conditions for transmission, the period, etc.

[0347] For example, when the terminal device 400 transmits object detection information, the information may be transmitted at the timing when the terminal device 400 detects the object. That is, the detection of an object by the terminal device 400 is used as a trigger to cause the terminal device 400 to transmit the detection information to the control station 100. In other words, the terminal device 400 does not need to transmit the detection information to the control station 100 while it does not detect an object.

[0348] Also, for example, when the terminal device 400 transmits quality information regarding communication quality, the terminal device 400 may transmit the quality information at a constant cycle. Alternatively, the terminal device 400 may determine whether to transmit the quality information depending on the difference from the quality information transmitted previously.

[0349] Specifically, when the quality information is compared with previously transmitted quality information and is equal to or greater than a predetermined value (exceeds the predetermined value), the terminal device 400 transmits the quality information to the control station 100. In other words, when the quality information is compared with previously transmitted quality information and is less than a predetermined value (is equal to or greater than the predetermined value), the terminal device 400 does not need to transmit the quality information to the control station 100.

[0350] When transmitting quality information, the terminal device 400 may transmit to the control station 100 information indicating a difference from the previous quality information.

[0351] In the above-described embodiment, the control station 100 is a cloud server or a database device arranged on a network, but the control station 100 is not limited to this. For example, the control station 100 does not have to be arranged on a cloud. For example, the control station 100 may be an edge server. In this case, the control station 100 may be arranged near the base station 300, for example.

[0352] Alternatively, instead of the control station 100, the base station 300 and / or the terminal device 400 may calculate the corrected estimated data using the estimation model. In this case, the base station 300 and / or the terminal device 400 functions as an information processing device that calculates the corrected estimated data using the estimation model. In this manner, at least a part of the functions of the control station 100 may be executed by the base station 300 and / or the terminal device 400.

[0353] For example, the control device that controls the control station 100, the base station 300, and the terminal device 400 in the above-described embodiment may be realized by a dedicated computer system or a general-purpose computer system.

[0354] For example, a communication program for executing the above-mentioned operations is stored in a computer-readable recording medium such as an optical disk, a semiconductor memory, a magnetic tape, or a flexible disk and distributed. Then, for example, the program is installed in a computer and the above-mentioned processing is executed to configure a control device. In this case, the control device may be a device (for example, a personal computer) external to the control station 100, the base station 300, and the terminal device 400. Also, the control device may be a device (for example, the control units 130, 340, 450) internal to the control station 100, the base station 300, and the terminal device 400.

[0355] The above-mentioned communication program may also be stored in a disk device provided in a server device on a network such as the Internet, and may be made available for downloading to a computer. The above-mentioned functions may also be realized by cooperation between an OS (Operating System) and application software. In this case, the parts other than the OS may be stored on a medium and distributed, or the parts other than the OS may be stored in a server device and made available for downloading to a computer.

[0356] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0357] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0358] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0359] Furthermore, the effects described in this specification are merely examples and are not limiting, and other effects may also be obtained.

[0360] Furthermore, for example, the present embodiment can be implemented as any configuration constituting an apparatus or system, such as a processor as a system LSI (Large Scale Integration), a module using multiple processors, a unit using multiple modules, a set in which other functions are added to a unit, and the like (i.e., a configuration of a part of an apparatus).

[0361] In this embodiment, a system means a collection of multiple components (devices, modules (parts), etc.), regardless of whether all the components are in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device in which multiple modules are housed in a single housing, are both systems.

[0362] Also, for example, this embodiment can have a cloud computing configuration in which one function is shared and processed jointly by a plurality of devices via a network.

[0363] In the above-described embodiments, the control station 100 determines the control information of the base station 300 and / or the terminal device 400, but the present invention is not limited to this. Each of the above-described embodiments can be used for the purpose of determining and designing transmission parameters and / or reception parameters, the number of base stations 300 and / or the terminal devices 400 to be installed (maximum number of installations), installation locations, and / or installation directions (horizontal direction, tilt angle, etc.).

[0364] <<8. Conclusion>> Although the embodiments of the present disclosure have been described above, the technical scope of the present disclosure is not limited to the above-described embodiments, and various modifications are possible without departing from the gist of the present disclosure. In addition, components of different embodiments and modifications may be appropriately combined.

[0365] Furthermore, the effects of each embodiment described in this specification are merely examples and are not limiting, and other effects may also be provided.

[0366] The present technology can also be configured as follows. (1) generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; a control unit that corrects the estimated data by using second actual measurement data in the calculation area, the second actual measurement data being smaller in number than the first actual measurement data. An information processing device comprising: (2) The information processing device according to (1), wherein the control unit corrects the estimated data according to an error between the estimated data and the second actual measurement data. (3) The information processing device described in (2), wherein the control unit corrects the estimated data by performing at least one of calculating a weighted average of the second measured data, calculating a simple average of the second measured data, and substituting a predetermined value. (4) The information processing device according to (2) or (3), wherein the control unit corrects the estimated data by using the second measured data whose statistical properties coincide with or are similar to those of the estimated data. (5) The information processing device according to any one of (1) to (4), wherein the control unit uses the second actual measurement data to estimate data of an unmeasured point in the calculation area where the second actual measurement data has not been measured. (6) The information processing device according to (5), wherein the control unit estimates the data of the unmeasured points using the estimated data. (7) The information processing device described in (5) or (6), wherein the control unit estimates the data of the unmeasured points using at least one of the second actual measurement data acquired near and far from a base station and the second actual measurement data acquired in a LOS environment and a NLOS environment. (8) The information processing device according to any one of (1) to (7), wherein an input parameter of the estimation model includes a standard deviation of shadowing. (9) The information processing device according to (1), wherein the correction of the estimated data is a correction to at least one variable of the estimation model. (10) The information processing device according to (9), wherein the control unit corrects the variables of the estimation model so that an error between the estimated data and the second measured data is reduced. (11) The information processing device according to (9), wherein the control unit corrects a coefficient of the variable. (12) The information processing device according to any one of (1) to (11), wherein the estimation model is generated using the first measured data as a response variable and information about the first measured data as an explanatory variable. (13) The information processing device according to any one of (1) to (12), wherein the estimation model is generated using simulation data of the estimation area. (14) The information processing device according to (13), wherein the simulation data is data obtained by a simulation based on communication environment information relating to the estimated area. (15) The information processing device according to any one of (1) to (14), wherein the control unit corrects the estimated data by using simulation data of the calculation area. (16) The information processing device according to (15), wherein the simulation data is data obtained by a simulation based on communication environment information relating to the calculation area. (17) The information processing device according to any one of (1) to (16), wherein the estimation model is generated using machine learning or deep learning. (18) The information processing device according to any one of (1) to (17), wherein the first measured data, the estimated data, and the second measured data are communication characteristic information indicating communication characteristics based on radio wave propagation from a transmitting point to a receiving point. (19) The information processing device according to (18), wherein the communication characteristic information includes at least one of a received power, an interference power, a characteristic related to a communication speed, and a characteristic related to a delay. (20) The information processing device according to any one of (1) to (19), wherein the control unit generates the estimated data in the calculation area using the estimation model generated using the first actual measurement data of the estimation area similar to the calculation area. (twenty one) The information processing device according to any one of (1) to (20), wherein the control unit generates the estimated data in the calculation area using the estimation model generated using the first actual measurement data of the estimation area that has the same or similar radio wave propagation characteristics as the estimation area. (twenty two) The information processing device according to any one of (1) to (21), wherein the control unit generates the estimated data in the calculation area using the estimation model generated using the first measured data of the estimation area, the correlation with the radio wave propagation characteristics of the estimation area being equal to or greater than a predetermined value. (twenty three) The information processing device according to any one of (1) to (22), wherein one or more of the estimation models are generated using the first actual measurement data in a plurality of the estimation areas. (twenty four) The information processing device according to (23), wherein the first actual measurement data in the plurality of estimation areas is normalized and used to generate the estimation model. (twenty five) A control unit that notifies the information processing device of actual measurement data measured in the calculation area. Equipped with The information processing device includes: generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using the second actual measurement data, the second actual measurement data being smaller in number than the first actual measurement data; Terminal device. (26) generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using second actual measurement data in the calculation area, the second actual measurement data being smaller in number than the first actual measurement data; An information processing method comprising: (27) notifying the information processing device of actual measurement data measured by the terminal device in the calculation area; Including, The information processing device includes: generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using the second actual measurement data, the second actual measurement data being smaller in number than the first actual measurement data; Information processing methods. [Explanation of symbols]

[0367] 100 Control Station 110,310,410 Communications Department 120,320,420 storage section 130,340,450 Control section 300 base stations 330,430 Network Communication Department 400 Terminal Equipment 440 Input / output section

Claims

1. generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; a control unit that corrects the estimated data by using second actual measurement data in the calculation area, the second actual measurement data being smaller in number than the first actual measurement data. An information processing device comprising:

2. The information processing apparatus according to claim 1 , wherein the control unit corrects the estimated data in accordance with an error between the estimated data and the second actual measurement data.

3. The information processing apparatus according to claim 2 , wherein the control unit corrects the estimated data by using the second actual measurement data whose statistical properties match or are similar to those of the estimated data.

4. The information processing apparatus according to claim 1 , wherein the control unit estimates data of an unmeasured point in the calculation area where the second actual measurement data has not been measured, by using the second actual measurement data.

5. The information processing device according to claim 4 , wherein the control unit estimates the data of the unmeasured points by using the estimated data.

6. The information processing device according to claim 1 , wherein the correction of the estimation data is a correction of at least one variable of the estimation model.

7. The information processing apparatus according to claim 6 , wherein the control unit corrects the variables of the estimation model so that an error between the estimated data and the second measured data becomes smaller.

8. The information processing device according to claim 6 , wherein the control unit corrects a coefficient of the variable.

9. The information processing apparatus according to claim 1 , wherein the estimation model is generated using the first measured data as a response variable and information about the first measured data as an explanatory variable.

10. The information processing device according to claim 1 , wherein the estimation model is generated using simulation data of the estimation area.

11. The information processing apparatus according to claim 10 , wherein the simulation data is data obtained by a simulation based on communication environment information related to the estimated area.

12. The information processing apparatus according to claim 1 , wherein the control unit corrects the estimated data by using simulation data of the calculation area.

13. The information processing apparatus according to claim 12 , wherein the simulation data is data obtained by a simulation based on communication environment information relating to the calculation area.

14. The information processing device according to claim 1 , wherein the estimation model is generated using machine learning or deep learning.

15. The information processing device according to claim 1 , wherein the control unit generates the estimated data in the calculation area by using the estimation model generated using the first actual measurement data of the estimation area similar to the calculation area.

16. The information processing apparatus according to claim 1 , wherein one or more of the estimation models are generated using the first actual measurement data in a plurality of the estimation areas.

17. A control unit that notifies the information processing device of actual measurement data measured in the calculation area. Equipped with The information processing device includes: generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using the second actual measurement data, the second actual measurement data being actual measurement data in the calculation area and being smaller in number than the first actual measurement data; Terminal device.

18. generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using the second actual measurement data, the second actual measurement data being actual measurement data in the calculation area and being smaller in number than the first actual measurement data; An information processing method comprising:

19. notifying the information processing device of actual measurement data measured by the terminal device in the calculation area; Including, The information processing device includes: generating estimated data in the calculation area using an estimation model of communication characteristics generated from a plurality of first actual measurement data in the estimation area; correcting information about the estimation model by using the second actual measurement data, the second actual measurement data being actual measurement data in the calculation area and being smaller in number than the first actual measurement data; Information processing methods.

Images