WO2024089819A1 - Prediction device, prediction system, prediction method, and program - Google Patents

Prediction device, prediction system, prediction method, and program Download PDF

Info

Publication number
WO2024089819A1
WO2024089819A1 PCT/JP2022/039991 JP2022039991W WO2024089819A1 WO 2024089819 A1 WO2024089819 A1 WO 2024089819A1 JP 2022039991 W JP2022039991 W JP 2022039991W WO 2024089819 A1 WO2024089819 A1 WO 2024089819A1
Authority
WO
WIPO (PCT)
Prior art keywords
target terminal
prediction
speed
calculation unit
predicted value
Prior art date
Application number
PCT/JP2022/039991
Other languages
French (fr)
Japanese (ja)
Inventor
尚希 澁谷
憲一 河村
元晴 佐々木
貴庸 守山
Original Assignee
日本電信電話株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Priority to PCT/JP2022/039991 priority Critical patent/WO2024089819A1/en
Publication of WO2024089819A1 publication Critical patent/WO2024089819A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • the present invention relates to technology for predicting wireless communication quality.
  • wireless communication In applications such as remote control or remote monitoring of vehicles, robots, and other mobile objects, it is common to use wireless communication to perform remote communication between a server at a center and a terminal installed on the mobile object at the site. Furthermore, since mobile objects are mobile, high availability of wireless communication quality is required for remote communication for safety reasons. It is considered effective to estimate (predict) whether the wireless communication quality can be used stably at the mobile object's destination, and if there is a risk, to perform processing such as switching the line in advance or lowering the video transmission rate to prevent momentary interruptions in the video. Therefore, it is important to predict the communication quality at the destination.
  • Non-Patent Document 1 An example of a technology for predicting wireless communication quality at a moving destination is the technology disclosed in Non-Patent Document 1.
  • the technology disclosed in Non-Patent Document 1 uses machine learning to learn a model that calculates a predicted value of wireless communication quality at the terminal's position from past quality information. By using this model, it is possible to predict wireless communication quality at the terminal's future position.
  • the present invention has been made in consideration of the above points, and aims to provide a technology for predicting communication quality at a terminal's future location that is more accurate than conventional technology.
  • a future location information calculation unit that acquires a speed of a target terminal and calculates a range of a certain shape as an estimated movement range of the target terminal within a predetermined time based on the speed; a predicted value calculation unit that calculates a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
  • a prediction device comprising:
  • the disclosed technology provides a technology for predicting communication quality at a terminal's future location that is more accurate than conventional technology.
  • FIG. 1 is a diagram for explaining a problem.
  • FIG. 1 is a diagram for explaining a problem.
  • FIG. 1 illustrates an example of the configuration of a prediction device 100.
  • 4 is a flowchart for explaining the operation of the first embodiment.
  • FIG. 13 is a diagram showing an example of a sector-shaped range.
  • FIG. 13 is a diagram illustrating an example of sampling.
  • FIG. 11 is a diagram for explaining an example of statistical processing.
  • 10 is a flowchart for explaining the operation of the second embodiment.
  • FIG. 13 is a diagram showing an image of calculation of a future position.
  • FIG. 2 illustrates an example of a hardware configuration of a prediction device 100.
  • communication quality is assumed to refer to quality in wireless communication, but the technology according to the present invention can also be applied to the communication quality of wired communication rather than wireless.
  • the technology according to the present invention can be applied in an environment in which devices that allow terminals to connect to a network via wired communication are installed in various places (locations).
  • communication quality is assumed to be the quality of communication when a terminal performs wireless communication. Also, “communication quality” may be referred to as “quality.”
  • terminal is assumed to be mobile.
  • a “terminal” may be a smartphone carried by a person, or a communication device mounted on a mobile object such as a drone, automobile, or robot, or the mobile object itself such as a drone, automobile, or robot may be called a "terminal.”
  • the "communication quality” used below may be any of received power, throughput, delay, jitter, and packet loss, or may be a quality other than these.
  • the problem in this embodiment will be described.
  • the future location of a terminal is predicted on the assumption that the terminal moves at a constant speed and in a straight line until it reaches the future location, and the communication quality is predicted using the future location.
  • the prediction device 100 includes a position information acquisition unit 110, a position information DB (database) 120, a preset value storage DB 130, a future position information calculation unit 140, and a prediction value calculation unit 150.
  • FIG. 3 also shows a control decision unit 210 and a control unit 220.
  • the control decision unit 210 and the control unit 220 are provided in a terminal (called a target terminal) for which communication quality is to be predicted.
  • the control decision unit 210 and the control unit 220 may also be provided outside the target terminal.
  • the prediction device 100 may be provided within the target terminal or may be provided outside the target terminal.
  • the terminal When the configuration of the prediction device 100 shown in FIG. 3 is provided within a terminal, the terminal may be called a prediction device.
  • the prediction value calculation unit 150 in the prediction device 100 may be provided in a server external to the prediction device 100.
  • the "location information acquisition unit 110, location information DB 120, preset value storage DB 130, future location information calculation unit 140, control determination unit 210, and control unit 220" shown in FIG. 3 may be provided in the target terminal, and the prediction value calculation unit 150 may be provided in an external server.
  • the prediction device 100 location information acquisition unit 110, location information DB 120, pre-set value storage DB 130, future location information calculation unit 140
  • the prediction value calculation unit 150 is in a server
  • the system having the prediction device 100 (terminal) and the server may be called a prediction system.
  • the predicted value calculation unit 150 has a function of calculating a predicted value of communication quality at a location based on the location information of the target terminal.
  • the predicted value can be obtained (calculated) from the location information alone, or can be obtained (calculated) using received power information at that location or point cloud information obtained by LiDAR at that location, etc.
  • the location information acquisition unit 110 acquires location information indicating the current location of the target terminal.
  • the location information acquisition unit 110 stores the acquired location information in the location information DB 120 together with the measurement time.
  • the location information acquisition unit 110 is a GNSS receiver, and S101 corresponds to acquiring location information by GNSS (GPS, etc.).
  • S101 corresponds to, for example, receiving from the target terminal the positioning result (location information) obtained by the target terminal using GNSS.
  • future location information calculation unit 140 acquires the location information of the target terminal at the time of the previous measurement from location information DB 120, and calculates the magnitude (e.g., m/s) of the velocity vt of the target terminal from the location information and the current location information.
  • magnitude is a vector having a magnitude and a direction.
  • future position information calculation section 140 reads the position information of the target terminal for the past T dir seconds from position information DB 120, and calculates the traveling direction of the target terminal from the position information by least squares approximation or the like.
  • the future position information calculation unit 140 may use that speed vt .
  • the future location information calculation unit 140 calculates a sector-shaped range determined from the travel distance within a predetermined time (e.g., seconds) within a predetermined range of ⁇ angles (e.g., in degrees) from the travel direction calculated in S102, and estimates that range to be the movement range of the target terminal.
  • a predetermined time e.g., seconds
  • ⁇ angles e.g., in degrees
  • Fig. 5 shows an image of the sector range calculated in S103.
  • Pt is the position of the target terminal at the current time t (the position measured at the most recent time t) and is at the center of the sector.
  • vt (vector) is the speed calculated in S102.
  • this sector has an angle of ⁇ with the direction of travel as the central axis.
  • the future position information calculation unit 140 passes information indicating the sector-shaped range (e.g., Figure 5) to the prediction value calculation unit 150.
  • the predicted value calculation unit 150 stores the communication quality of each point (each position) in a storage unit 151 such as a memory included in the predicted value calculation unit 150.
  • This communication quality may be an estimated value (predicted value), may be a past actual value, or may be a statistical value calculated from the past actual value.
  • the predicted value calculation unit 150 refers to the storage unit 151, acquires the communication quality at the sampled positions within the sector-shaped range calculated in S103, and performs statistical processing on the acquired communication quality.
  • the predicted value calculation unit 150 sets the result of the statistical processing as a predicted value of the communication quality at the target terminal at the specified seconds ahead.
  • the "specified seconds ahead" is, for example, a time that is T pred ahead of the current time t.
  • the prediction value calculation unit 150 outputs the prediction value.
  • the prediction value is input to the control decision unit 210. For example, when the control decision unit 210 determines that the quality of the current line will deteriorate based on the prediction value, it determines that line switching is necessary and instructs the control unit 220 to switch lines. The control unit 220 executes control to switch the line used by the target terminal.
  • the prediction value calculation unit 150 randomly selects a plurality of points within a sector-shaped range, for example, within a range within a pre-set driving area, and acquires the communication quality of the points.
  • An image of this process is shown in FIG. 6.
  • the prediction value calculation unit 150 may acquire the communication quality of all points within the sector-shaped range.
  • the prediction value calculation unit 150 performs, for example, any one of the following processes (1) to (4). Note that (1) to (4) are just examples, and statistical processing other than (1) to (4) may be performed. Also, any two or more of (1) to (4) may be combined.
  • the prediction value calculation unit 150 uses the average value of all acquired communication qualities as the prediction value.
  • the prediction value calculation unit 150 uses the worst quality value among the acquired communication qualities as the prediction value.
  • the future location information calculation unit 150 obtains a correlation between the magnitude of the target terminal's speed
  • and the angle ⁇ at which the target terminal turns ( the angle ⁇ that determines the sector-shaped range) from the target terminal's movement history (or a preset value), and determines ⁇ according to the magnitude of the target terminal's speed
  • the future position information calculation unit 150 notifies the predicted value calculation unit 150 of the ⁇ determined by the above method and the information on the sector-shaped range using the above-mentioned dt .
  • the predicted value calculation unit 150 uses the predicted value calculated from the sector range using the method already described (average value, etc.). Note that the predicted value calculation unit 150 may perform all of the processing in (3).
  • the predicted value calculation unit 150 weights the communication qualities acquired within the sector-shaped range according to the travel distance using the magnitude of the speed
  • and the position within the sector is calculated in advance, and the weight is increased as the correlation increases.
  • the correlation can be calculated using, for example, the movement history.
  • S201 is the same as S101 in the first embodiment.
  • the location information acquisition unit 110 acquires location information indicating the current location of the target terminal.
  • the location information acquisition unit 110 stores the acquired location information in the location information DB 120 together with the measurement time.
  • S202 is the same as S102 in the embodiment 1.
  • the future position information calculation unit 140 calculates (or obtains) the velocity vt of the target terminal.
  • the moving route is a straight line at least for the period Tpred .
  • Tpred may be set as the time during which the moving route can be assumed to be a straight line even if the moving route is moving at high speed.
  • An image of the calculation of P is shown in FIG. 9.
  • steps S202 and S203 if the future position information calculation unit 140 detects that the calculated P or the past positioning position is a value that deviates from the moving route due to a positioning error or the like, it corrects the value to the value of the closest point on the moving route.
  • the future position information calculation unit 140 passes information indicating the future position P to the prediction value calculation unit 150.
  • the predicted value calculation unit 150 stores the communication quality at each point (each position) in a storage unit 151 such as a memory included in the predicted value calculation unit 150.
  • This communication quality may be an estimated value (predicted value) or a past actual value.
  • the predicted value calculation unit 150 refers to the storage unit 151 to obtain the communication quality at the future position P calculated in S203, and sets this as a predicted value of the communication quality at the target terminal at a time T pred ahead of the current time t.
  • S205 is the same as S105 in the first embodiment.
  • the prediction device 100 described in this embodiment can be realized, for example, by causing a computer to execute a program.
  • This computer may be a physical computer or a virtual machine on the cloud.
  • the prediction device 100 can be realized by executing a program corresponding to the processing performed by the prediction device 100 using hardware resources such as a CPU and memory built into a computer.
  • the above program can be recorded on a computer-readable recording medium (such as a portable memory) and stored or distributed.
  • the above program can also be provided via a network such as the Internet or email.
  • FIG. 10 is a diagram showing an example of the hardware configuration of the computer.
  • the computer in FIG. 7 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are connected to each other via a bus BS.
  • the computer may further include a GPU.
  • the program that realizes the processing on the computer is provided by a recording medium 1001, such as a CD-ROM or a memory card.
  • a recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 via the drive device 1000 into the auxiliary storage device 1002.
  • the program does not necessarily have to be installed from the recording medium 1001, but may be downloaded from another computer via a network.
  • the auxiliary storage device 1002 stores the installed program as well as necessary files, data, etc.
  • the memory device 1003 When an instruction to start a program is received, the memory device 1003 reads out and stores the program from the auxiliary storage device 1002.
  • the CPU 1004 realizes functions related to the prediction device 100 in accordance with the program stored in the memory device 1003.
  • the interface device 1005 is used as an interface for connecting to a network, etc.
  • the display device 1006 displays a GUI (Graphical User Interface) or the like according to a program.
  • the input device 1007 is composed of a keyboard and mouse, buttons, a touch panel, etc., and is used to input various operational instructions.
  • the output device 1008 outputs the results of calculations.
  • Memory at least one processor coupled to the memory; Including, The processor, Acquire a speed of the target terminal, and calculate a range of a certain shape based on the speed as an estimated movement range of the target terminal within a predetermined time period; calculating a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape; Prediction device.
  • the shape is a sector having an angle of ⁇ with the traveling direction of the target terminal as a central axis and having a travel distance at the speed in the specified time as a radius.
  • the prediction device according to claim 1 or 2, wherein the processor calculates, as the predicted value, a weighted average of the communication qualities at the plurality of positions using weights according to the positions.
  • Memory at least one processor coupled to the memory; Including, The processor, acquiring a speed of the target terminal, and calculating a future position of the target terminal on a predetermined moving path based on the speed; Calculating a predicted value of communication quality of the target terminal at the future location; Prediction device.
  • a prediction system comprising: (Additional Note 6) A prediction method executed by a prediction device, comprising: acquiring a speed of the target terminal, and calculating a range of a certain shape based on the speed as an estimated movement range of the target terminal within a predetermined time; calculating a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape; A prediction method comprising: (Additional Note 7) A prediction method executed by a prediction device, comprising: acquiring a speed of the target terminal and calculating a future position of the target terminal on a predetermined moving route based on the speed;
  • Prediction device 110 Position information acquisition unit 120 Position information DB 130 Pre-set value storage DB 140 Future position information calculation unit 150 Prediction value calculation unit 151 Storage unit 210 Control decision unit 220 Control unit 1000 Drive device 1001 Recording medium 1002 Auxiliary storage device 1003 Memory device 1004 CPU 1005 Interface device 1006 Display device 1007 Input device 1008 Output device

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

A prediction device according to the present invention comprises: a future position information calculation unit that acquires the speed of a target terminal and computes, on the basis of the speed, a range of a certain shape as an estimated movement range of the target terminal within a predetermined time; and a predicted value calculation unit that calculates a predicted value of the communication quality of the target terminal on the basis of the communication quality at a plurality of positions within the range of the shape.

Description

予測装置、予測システム、予測方法、及びプログラムPrediction device, prediction system, prediction method, and program
　本発明は、無線通信品質を予測する技術に関連するものである。 The present invention relates to technology for predicting wireless communication quality.
　車両、ロボット等の移動体に対する遠隔制御又は遠隔監視等の用途においては、無線通信によってセンターのサーバと現場の移動体に設けられた端末との間で遠隔通信を行うことが一般的である。また、移動体は移動する関係上、安全性を考慮して、遠隔通信の無線の通信品質は高い可用性が求められる。移動体の移動先において無線の通信品質が安定的に利用できるかを推定（予測）し、リスクがある場合は、事前に回線を切り替えたり、映像の瞬断がないように映像伝送のレートを落としたりする等の処理を行うことが有効だと考えられる。よって、移動先での通信品質を予測することが重要である。 In applications such as remote control or remote monitoring of vehicles, robots, and other mobile objects, it is common to use wireless communication to perform remote communication between a server at a center and a terminal installed on the mobile object at the site. Furthermore, since mobile objects are mobile, high availability of wireless communication quality is required for remote communication for safety reasons. It is considered effective to estimate (predict) whether the wireless communication quality can be used stably at the mobile object's destination, and if there is a risk, to perform processing such as switching the line in advance or lowering the video transmission rate to prevent momentary interruptions in the video. Therefore, it is important to predict the communication quality at the destination.
　移動先での無線の通信品質を予測する技術として、例えば非特許文献１に開示された技術がある。非特許文献１に開示された技術では、機械学習を用いて、過去の品質情報から、端末の位置における無線通信品質の予測値を算出するモデルを学習する。このモデルを用いることで、端末の将来位置における無線通信品質を予測できる。 An example of a technology for predicting wireless communication quality at a moving destination is the technology disclosed in Non-Patent Document 1. The technology disclosed in Non-Patent Document 1 uses machine learning to learn a model that calculates a predicted value of wireless communication quality at the terminal's position from past quality information. By using this model, it is possible to predict wireless communication quality at the terminal's future position.
　上述した将来位置の予測に関して、従来技術では、端末が将来位置に至るまで等速かつ直線的な移動をする前提で予測を行っていた。しかし、実際の端末（例：AGVや車、自動運転農機等）は、状況に応じて速度（速さ、進行方向）を変化させることがある。 　In conventional technology, predictions of future positions are made under the assumption that the terminal moves at a constant speed and in a straight line until it reaches its future position. However, actual terminals (e.g. AGVs, cars, self-driving agricultural machinery, etc.) may change their speed (speed, direction of travel) depending on the situation.
　そのため、従来技術では、端末の実際の将来位置と、予測した将来位置との間に乖離が発生することで、端末の実際の将来位置での無線通信品質と、予測した将来位置における無線通信品質の予測値との間に乖離が発生する。 As a result, in conventional technology, a discrepancy occurs between the actual future location of the terminal and the predicted future location, which causes a discrepancy between the wireless communication quality at the terminal's actual future location and the predicted value of wireless communication quality at the predicted future location.
　本発明は上記の点に鑑みてなされたものであり、端末の将来位置における通信品質を予測する技術において、従来技術よりも正確に通信品質を予測するための技術を提供することを目的とする。 The present invention has been made in consideration of the above points, and aims to provide a technology for predicting communication quality at a terminal's future location that is more accurate than conventional technology.
　開示の技術によれば、対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として算出する将来位置情報計算部と、
　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出する予測値算出部と、
　を備える予測装置が提供される。 According to the disclosed technology, a future location information calculation unit that acquires a speed of a target terminal and calculates a range of a certain shape as an estimated movement range of the target terminal within a predetermined time based on the speed;
a predicted value calculation unit that calculates a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
A prediction device is provided, comprising:
　開示の技術によれば、端末の将来位置における通信品質を予測する技術において、従来技術よりも正確に通信品質を予測するための技術が提供される。 The disclosed technology provides a technology for predicting communication quality at a terminal's future location that is more accurate than conventional technology.
課題を説明するための図である。FIG. 1 is a diagram for explaining a problem. 課題を説明するための図である。FIG. 1 is a diagram for explaining a problem. 予測装置１００の構成例を示す図である。FIG. 1 illustrates an example of the configuration of a prediction device 100. 実施例１の動作を説明するためのフローチャートである。4 is a flowchart for explaining the operation of the first embodiment. 扇形の範囲の例を示す図である。FIG. 13 is a diagram showing an example of a sector-shaped range. サンプリングの例を示す図である。FIG. 13 is a diagram illustrating an example of sampling. 統計処理の例を説明するための図である。FIG. 11 is a diagram for explaining an example of statistical processing. 実施例２の動作を説明するためのフローチャートである。10 is a flowchart for explaining the operation of the second embodiment. 将来位置の算出イメージを示す図である。FIG. 13 is a diagram showing an image of calculation of a future position. 予測装置１００のハードウェア構成例を示す図である。FIG. 2 illustrates an example of a hardware configuration of a prediction device 100.
　以下、図面を参照して本発明の実施の形態（本実施の形態）を説明する。以下で説明する実施の形態は一例に過ぎず、本発明が適用される実施の形態は、以下の実施の形態に限られるわけではない。 Below, an embodiment of the present invention (present embodiment) will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applicable is not limited to the embodiment described below.
　以下の説明において、「通信品質」は、無線通信における品質であることを想定するが、本発明に係る技術は、無線でなく有線で行われる通信の通信品質にも適用可能である。例えば、端末が有線でネットワークに接続できる装置が様々な場所（位置）に設置されているような環境において、本発明に係る技術を適用可能である。 In the following description, "communication quality" is assumed to refer to quality in wireless communication, but the technology according to the present invention can also be applied to the communication quality of wired communication rather than wireless. For example, the technology according to the present invention can be applied in an environment in which devices that allow terminals to connect to a network via wired communication are installed in various places (locations).
　また、以下の説明において、通信品質は、特に断らない限り、端末が無線通信を行う際のその通信の品質であることを想定する。また、「通信品質」を「品質」と呼ぶ場合がある。 In the following description, unless otherwise specified, communication quality is assumed to be the quality of communication when a terminal performs wireless communication. Also, "communication quality" may be referred to as "quality."
　「端末」は移動するものであることを想定する。「端末」は、人が持つスマートフォン等であってもよいし、ドローン、自動車、ロボット等の移動体に搭載される通信装置であってもよいし、ドローン、自動車、ロボット等の移動体そのものを「端末」と呼んでもよい。 The "terminal" is assumed to be mobile. A "terminal" may be a smartphone carried by a person, or a communication device mounted on a mobile object such as a drone, automobile, or robot, or the mobile object itself such as a drone, automobile, or robot may be called a "terminal."
　なお、以下で使用する「通信品質」は、受信電力、スループット、遅延、ジッタ、パケットロスのうちのいずれであってもよいし、「通信品質」がこれら以外の品質であってもよい。 Note that the "communication quality" used below may be any of received power, throughput, delay, jitter, and packet loss, or may be a quality other than these.
　（課題について）
　まず、本実施の形態における課題について説明する。従来技術では、図１に示すように、端末が将来位置に至るまで等速かつ直線的な移動をする前提で、端末の将来位置を予測し、それを用いて通信品質を予測していた。 (Regarding the issues)
First, the problem in this embodiment will be described. In the conventional technology, as shown in Fig. 1, the future location of a terminal is predicted on the assumption that the terminal moves at a constant speed and in a straight line until it reaches the future location, and the communication quality is predicted using the future location.
　しかし、実際の端末は、状況に応じて速度が変化する。そのため、例えば図２に示すように、推定した端末の将来位置と、実施の端末の位置との間に乖離が生じる。そのため、端末の実際の通信品質と、予測した将来位置で予測した通信品質との間にも乖離が生じる。 However, the speed of an actual terminal changes depending on the situation. Therefore, as shown in Figure 2, for example, a discrepancy occurs between the estimated future location of the terminal and the actual location of the terminal. Therefore, a discrepancy also occurs between the actual communication quality of the terminal and the communication quality predicted at the predicted future location.
　そこで、本実施の形態では、移動する端末の速度が変化する場合でも、精度良く将来位置の推定を行うための技術を説明する。 In this embodiment, we therefore describe a technique for estimating the future location with high accuracy even when the speed of a moving terminal changes.
　（装置構成）
　図３に、本実施の形態における予測装置１００の構成例を示す。図３に示すように、予測装置１００は、位置情報取得部１１０、位置情報ＤＢ（データベース）１２０、事前設定値保存ＤＢ１３０、将来位置情報計算部１４０、及び予測値算出部１５０を備える。 (Device configuration)
3 shows an example of the configuration of the prediction device 100 according to the present embodiment. As shown in FIG. 3, the prediction device 100 includes a position information acquisition unit 110, a position information DB (database) 120, a preset value storage DB 130, a future position information calculation unit 140, and a prediction value calculation unit 150.
　また、図３には、制御判断部２１０と制御部２２０が示されている。図３の例において、制御判断部２１０と制御部２２０は、通信品質の予測対象である端末（対象端末と呼ぶ）の中に備えられていると想定する。ただし、制御判断部２１０と制御部２２０は、対象端末の外部に備えられてもよい。 FIG. 3 also shows a control decision unit 210 and a control unit 220. In the example of FIG. 3, it is assumed that the control decision unit 210 and the control unit 220 are provided in a terminal (called a target terminal) for which communication quality is to be predicted. However, the control decision unit 210 and the control unit 220 may also be provided outside the target terminal.
　予測装置１００（位置情報取得部１１０、位置情報ＤＢ１２０、事前設定値保存ＤＢ１３０、将来位置情報計算部１４０、及び予測値算出部１５０）は、対象端末内に備えられていてもよいし、対象端末の外部に備えられていてもよい。 The prediction device 100 (location information acquisition unit 110, location information DB 120, pre-set value storage DB 130, future location information calculation unit 140, and prediction value calculation unit 150) may be provided within the target terminal or may be provided outside the target terminal.
　図３に示す予測装置１００の構成が端末内に備えられる場合において、その端末を予測装置と呼んでもよい。 When the configuration of the prediction device 100 shown in FIG. 3 is provided within a terminal, the terminal may be called a prediction device.
　また、予測装置１００における予測値算出部１５０が、予測装置１００の外部のサーバに備えられてもよい。例えば、図３に示す「位置情報取得部１１０、位置情報ＤＢ１２０、事前設定値保存ＤＢ１３０、将来位置情報計算部１４０、制御判断部２１０、制御部２２０」が対象端末内に備えられ、予測値算出部１５０が、外部のサーバに備えられてもよい。 Furthermore, the prediction value calculation unit 150 in the prediction device 100 may be provided in a server external to the prediction device 100. For example, the "location information acquisition unit 110, location information DB 120, preset value storage DB 130, future location information calculation unit 140, control determination unit 210, and control unit 220" shown in FIG. 3 may be provided in the target terminal, and the prediction value calculation unit 150 may be provided in an external server.
　予測装置１００（位置情報取得部１１０、位置情報ＤＢ１２０、事前設定値保存ＤＢ１３０、将来位置情報計算部１４０）が端末にあり、予測値算出部１５０がサーバにある場合において、予測装置１００（端末）と当該サーバとを有するシステムを予測システムと呼んでもよい。 When the prediction device 100 (location information acquisition unit 110, location information DB 120, pre-set value storage DB 130, future location information calculation unit 140) is in a terminal and the prediction value calculation unit 150 is in a server, the system having the prediction device 100 (terminal) and the server may be called a prediction system.
　予測値算出部１５０は、対象端末の位置情報に基づき、その位置での通信品質の予測値を算出する機能を有する。予測値は、位置情報のみから取得（算出）することもできるし、その位置での受信電力情報、あるいはその位置でのLiDARにより取得した点群情報等を用いて取得（算出）することもできる。 The predicted value calculation unit 150 has a function of calculating a predicted value of communication quality at a location based on the location information of the target terminal. The predicted value can be obtained (calculated) from the location information alone, or can be obtained (calculated) using received power information at that location or point cloud information obtained by LiDAR at that location, etc.
　（予測装置１００の動作例：実施例１）
　図３に示す構成を備える予測装置１００の実施例１の動作例を図４のフローチャートを参照して説明する。なお、事前設定値保存ＤＢ１３０には、計算で使用する事前設定値（後述のＴｄｉｒ、何秒先の予測をするか、など）が格納されている。 (Operation Example of Prediction Device 100: Example 1)
An operation example of the prediction device 100 having the configuration shown in Fig. 3 according to the first embodiment will be described with reference to the flowchart of Fig. 4. Note that the preset value storage DB 130 stores preset values used in calculations (such as T dir described below, how many seconds ahead to predict, etc.).
　＜Ｓ１０１＞
　Ｓ１０１において、位置情報取得部１１０は、対象端末の現在の位置を示す位置情報を取得する。位置情報取得部１１０は、取得した位置情報を、測定時刻とともに位置情報ＤＢ１２０に格納する。 <S101>
In S101, the location information acquisition unit 110 acquires location information indicating the current location of the target terminal. The location information acquisition unit 110 stores the acquired location information in the location information DB 120 together with the measurement time.
　位置情報取得部１１０が対象端末内に備えられる場合において、例えば位置情報取得部１１０はＧＮＳＳ受信機であり、Ｓ１０１は、ＧＮＳＳ（ＧＰＳ等）により位置情報を取得することに相当する。 If the location information acquisition unit 110 is provided in the target terminal, for example, the location information acquisition unit 110 is a GNSS receiver, and S101 corresponds to acquiring location information by GNSS (GPS, etc.).
　また、位置情報取得部１１０が対象端末の外部に備えられる場合において、Ｓ１０１は、例えば、対象端末によるＧＮＳＳでの測位結果（位置情報）を対象端末から受信することに相当する。 In addition, when the location information acquisition unit 110 is provided outside the target terminal, S101 corresponds to, for example, receiving from the target terminal the positioning result (location information) obtained by the target terminal using GNSS.
　＜Ｓ１０２＞
　Ｓ１０２において、将来位置情報計算部１４０は、位置情報ＤＢ１２０から対象端末の前回測定時の位置情報を取得し、当該位置情報と、現在の位置情報から、対象端末の速度ｖｔの大きさ（例：ｍ／ｓ）を算出する。なお、「速度」は、大きさと方向を持つベクトルである。 <S102>
In S102, future location information calculation unit 140 acquires the location information of the target terminal at the time of the previous measurement from location information DB 120, and calculates the magnitude (e.g., m/s) of the velocity vt of the target terminal from the location information and the current location information. Note that "velocity" is a vector having a magnitude and a direction.
　速度における進行方向については、将来位置情報計算部１４０は、過去Ｔｄｉｒ秒間の対象端末の位置情報を位置情報ＤＢ１２０から読み出し、当該位置情報から最小二乗近似等により、対象端末の進行方向を算出する。 Regarding the traveling direction at speed, future position information calculation section 140 reads the position information of the target terminal for the past T dir seconds from position information DB 120, and calculates the traveling direction of the target terminal from the position information by least squares approximation or the like.
　なお、例えば、対象端末のセンサ等から速度ｖｔを取得できる場合には、将来位置情報計算部１４０は、その速度ｖｔを使用してもよい。 For example, if the speed vt can be acquired from a sensor or the like of the target terminal, the future position information calculation unit 140 may use that speed vt .
　＜Ｓ１０３＞
　Ｓ１０３において、将来位置情報計算部１４０は、Ｓ１０２で算出した進行方向から事前に定めた±θの角度（単位は例えば度）の範囲内で、予め定めた時間（例えば秒数）以内の進行距離から定まる扇形の範囲を計算し、その範囲を対象端末の移動範囲であると推定する。 <S103>
In S103, the future location information calculation unit 140 calculates a sector-shaped range determined from the travel distance within a predetermined time (e.g., seconds) within a predetermined range of ±θ angles (e.g., in degrees) from the travel direction calculated in S102, and estimates that range to be the movement range of the target terminal.
　図５に、Ｓ１０３で計算される扇形の範囲のイメージを示す。図５において、Ｐｔは、対象端末の現在時刻ｔの位置（最も直近の時刻ｔにおいて測定された位置）であり、扇形の中心にある。ｖｔ（ベクトル）は、Ｓ１０２で算出された速度である。また、扇形の半径ｄｔは、速度の大きさと｜ｖｔ｜と上記予め定めた時間（単位は例えば秒）Ｔｐｒｅｄを用いて、ｄｔ＝｜ｖｔ｜×Ｔｐｒｅｄにより算出される。図５に示すように、この扇形は、進行方向を中心軸として±θの角度を有する扇形である。 Fig. 5 shows an image of the sector range calculated in S103. In Fig. 5, Pt is the position of the target terminal at the current time t (the position measured at the most recent time t) and is at the center of the sector. vt (vector) is the speed calculated in S102. The radius dt of the sector is calculated by dt = | vt | x Tpred using the magnitude of the speed, | vt |, and the above-mentioned predetermined time (unit: seconds, for example) Tpred . As shown in Fig. 5, this sector has an angle of ±θ with the direction of travel as the central axis.
　将来位置情報計算部１４０は、扇形の範囲（例：図５）を示す情報を予測値算出部１５０に渡す。 The future position information calculation unit 140 passes information indicating the sector-shaped range (e.g., Figure 5) to the prediction value calculation unit 150.
　上記のような扇形の範囲を採用することで、等速かつ直線的な移動をする場合以外の端末移動パターンにも対応することができる。なお、対象端末の推定移動範囲の形状を扇形とすることは一例である。扇形以外の形状の範囲を対象端末の推定移動範囲としてもよい。 By adopting a sector-shaped range as described above, it is possible to accommodate terminal movement patterns other than constant speed, linear movement. Note that using a sector shape as the estimated movement range of the target terminal is just one example. A range with a shape other than a sector may also be used as the estimated movement range of the target terminal.
　＜Ｓ１０４、Ｓ１０５＞
　予測値算出部１５０は、例えば、各地点（各位置）の通信品質を、予測値算出部１５０が有するメモリ等の記憶部１５１に保持しているとする。この通信品質は、推定値（予測値）であってもよいし、過去の実績値であってもよいし、過去の実績値から算出される統計値であってもよい。 <S104, S105>
The predicted value calculation unit 150, for example, stores the communication quality of each point (each position) in a storage unit 151 such as a memory included in the predicted value calculation unit 150. This communication quality may be an estimated value (predicted value), may be a past actual value, or may be a statistical value calculated from the past actual value.
　予測値算出部１５０は、記憶部１５１を参照して、Ｓ１０３で算出した扇形の範囲内で、サンプリングした位置における通信品質を取得し、取得した通信品質に対して統計処理を行う。予測値算出部１５０は、統計処理の結果を、対象端末における指定秒先の通信品質の予測値とする。「指定秒先」とは、例えば、現在時刻ｔから、Ｔｐｒｅｄだけ先の時刻である。 The predicted value calculation unit 150 refers to the storage unit 151, acquires the communication quality at the sampled positions within the sector-shaped range calculated in S103, and performs statistical processing on the acquired communication quality. The predicted value calculation unit 150 sets the result of the statistical processing as a predicted value of the communication quality at the target terminal at the specified seconds ahead. The "specified seconds ahead" is, for example, a time that is T pred ahead of the current time t.
　Ｓ１０５において、予測値算出部１５０は、予測値を出力する。予測値は制御判断部２１０に入力される。制御判断部２１０は、例えば、予測値により現在の回線の品質が悪くなることを把握すると、回線切替が必要であると判断し、回線切替を制御部２２０に指示する。制御部２２０は、対象端末が使用している回線を切り替える制御を実行する。 In S105, the prediction value calculation unit 150 outputs the prediction value. The prediction value is input to the control decision unit 210. For example, when the control decision unit 210 determines that the quality of the current line will deteriorate based on the prediction value, it determines that line switching is necessary and instructs the control unit 220 to switch lines. The control unit 220 executes control to switch the line used by the target terminal.
　＜サンプリングについて＞
　上述したサンプリング処理の例を説明する。サンプリング処理において、予測値算出部１５０は、例えば、扇形の範囲内で、事前に設定した走行エリア内の範囲で、複数の点をランダムに選択し、その点の通信品質を取得する。この処理のイメージを図６に示す。特に走行エリアなどのエリアが存在しない場合、予測値算出部１５０は、扇形の範囲内での全ての地点の通信品質を取得してもよい。 <About sampling>
An example of the above-mentioned sampling process will be described. In the sampling process, the prediction value calculation unit 150 randomly selects a plurality of points within a sector-shaped range, for example, within a range within a pre-set driving area, and acquires the communication quality of the points. An image of this process is shown in FIG. 6. When there is no particular area such as a driving area, the prediction value calculation unit 150 may acquire the communication quality of all points within the sector-shaped range.
　＜統計処理について＞
　上述した統計処理として、予測値算出部１５０は、例えば、下記の（１）～（４）の処理のうちのいずれかの処理を行う。なお、（１）～（４）は例であり、（１）～（４）以外の統計処理を行ってもよい。また、（１）～（４）のうちのいずれか複数を組み合わせてもよい。 <Statistical processing>
As the statistical processing described above, the prediction value calculation unit 150 performs, for example, any one of the following processes (1) to (4). Note that (1) to (4) are just examples, and statistical processing other than (1) to (4) may be performed. Also, any two or more of (1) to (4) may be combined.
　（１）予測値算出部１５０は、取得した全ての通信品質の平均値を予測値として採用する。 (1) The prediction value calculation unit 150 uses the average value of all acquired communication qualities as the prediction value.
　（２）予測値算出部１５０は、取得した通信品質のうち、最も品質が悪い値を予測値として採用する。 (2) The prediction value calculation unit 150 uses the worst quality value among the acquired communication qualities as the prediction value.
　（３）将来位置情報計算部１５０は、対象端末の移動実績（あるいは事前設定値）から、対象端末の速度の大きさ｜ｖｔ｜と対象端末が曲がる角度θ（＝扇型の範囲を決める角度θ）との相関を求め、その相関に基づいて、対象端末の速度の大きさ｜ｖｔ｜に応じたθを決定する。なお、｜ｖｔ｜が大きいほど、θが小さくなることが想定される。 (3) The future location information calculation unit 150 obtains a correlation between the magnitude of the target terminal's speed | vt | and the angle θ at which the target terminal turns (= the angle θ that determines the sector-shaped range) from the target terminal's movement history (or a preset value), and determines θ according to the magnitude of the target terminal's speed | vt | based on the correlation. Note that it is expected that the larger | vt | is, the smaller θ will be.
　将来位置情報計算部１５０は、上記の方法で決定したθと、前述したｄｔを用いた扇形の範囲の情報を予測値算出部１５０に通知する。 The future position information calculation unit 150 notifies the predicted value calculation unit 150 of the θ determined by the above method and the information on the sector-shaped range using the above-mentioned dt .
　予測値算出部１５０は、当該扇形の範囲から既に説明した手法（平均値等）で算出した予測値を採用する。なお、（３）の処理を全て予測値算出部１５０が行うこととしてもよい。 The predicted value calculation unit 150 uses the predicted value calculated from the sector range using the method already described (average value, etc.). Note that the predicted value calculation unit 150 may perform all of the processing in (3).
　（４）予測値算出部１５０は、扇形の範囲内から取得した通信品質に対して、速度の大きさ｜ｖｔ｜を用いて、進行距離に応じた重み付けを行い、加重平均を用いて予測値を算出する。例えば、取得した通信品質をｘ１，ｘ２，……，ｘＮとし、それに対応する重みをそれぞれｗ１，ｗ２，……，ｗＮで表すとき、加重平均は「（ｗ１ｘ１＋...．＋ｗＮｘＮ）／（ｗ１＋...．＋ｗＮ）」で計算される。 (4) The predicted value calculation unit 150 weights the communication qualities acquired within the sector-shaped range according to the travel distance using the magnitude of the speed | vt |, and calculates the predicted value using a weighted average. For example, when the acquired communication qualities are represented as x1, x2, ..., xN and the corresponding weights are represented as w1, w2, ..., wN, respectively, the weighted average is calculated as "(w1x1+....+wNxN)/(w1+....+wN)".
　重みに関しては、例えば、事前に速度の大きさ｜ｖｔ｜と扇形の範囲内の位置（例えば、扇形の中心からの距離）との相関を求めておき、相関が大きいほど重みを大きくする。相関の求め方については、例えば、移動実績を使用することができる。 Regarding the weight, for example, the correlation between the magnitude of the velocity |v t | and the position within the sector (for example, the distance from the center of the sector) is calculated in advance, and the weight is increased as the correlation increases. The correlation can be calculated using, for example, the movement history.
　例えば、｜ｖｔ｜が大きいほど、扇形の中心からの距離が大きい位置の重みが、扇形の中心からの距離が小さい位置の重みよりも大きくなることが想定される。このような相関（重み）のイメージを図７に示す。｜ｖｔ｜が大きいほど、将来位置が網掛けの範囲に収まる確率が高くなるため、網掛け範囲内の通信品質に対する重みを大きくし、網掛け範囲範囲外の通信品質に対する重みを小さくする。 For example, it is assumed that the larger |v t | is, the greater the weight of a position farther from the center of the sector will be than the weight of a position closer to the center of the sector. An image of such correlation (weight) is shown in Figure 7. The larger |v t | is, the higher the probability that the future position will fall within the shaded range, so the weight for communication quality within the shaded range is increased and the weight for communication quality outside the shaded range is decreased.
　（予測装置１００の動作例：実施例２）
　上述した実施例１のように扇形の範囲指定を用いない場合の処理として、移動経路（例：自動車の走行経路）が一意に決まっている場合等についての処理の例を実施例２として説明する。図８のフローチャートを参照して、実施例２における予測装置１００の動作例を説明する。なお、事前設定値保存ＤＢ１３０には、計算で使用する事前設定値（何秒先の予測をするか、など）が格納されている。また、対象端末の移動経路が事前設定値保存ＤＢ１３０に格納されている。 (Operation Example of Prediction Device 100: Example 2)
As a processing example when a sector-shaped range is not specified as in the above-mentioned embodiment 1, a processing example when a travel route (e.g., a travel route of a car) is uniquely determined will be described as embodiment 2. An operation example of the prediction device 100 in embodiment 2 will be described with reference to the flowchart of FIG. 8. Note that the preset value storage DB 130 stores preset values used in calculations (e.g., how many seconds ahead to predict). Also, the travel route of the target terminal is stored in the preset value storage DB 130.
　＜Ｓ２０１＞
　Ｓ２０１は、実施例１のＳ１０１と同じである。Ｓ２０１において、位置情報取得部１１０は、対象端末の現在の位置を示す位置情報を取得する。位置情報取得部１１０は、取得した位置情報を、測定時刻とともに位置情報ＤＢ１２０に格納する。 <S201>
S201 is the same as S101 in the first embodiment. In S201, the location information acquisition unit 110 acquires location information indicating the current location of the target terminal. The location information acquisition unit 110 stores the acquired location information in the location information DB 120 together with the measurement time.
　＜Ｓ２０２＞
　Ｓ２０２は、実施例１のＳ１０２と同じである。Ｓ２０２において、将来位置情報計算部１４０は、対象端末の速度ｖｔを算出（又は取得）する。 <S202>
S202 is the same as S102 in the embodiment 1. In S202, the future position information calculation unit 140 calculates (or obtains) the velocity vt of the target terminal.
　＜Ｓ２０３＞
　Ｓ２０３において、将来位置情報計算部１４０は、対象端末の将来位置Ｐを、移動経路上に沿うように、速度ｖｔと将来位置までの時間（例：秒数）Ｔｐｒｅｄとを用いて、Ｐ＝｜ｖｔ｜×Ｔｐｒｅｄにより算出する。ここでは、移動経路が、少なくともＴｐｒｅｄの期間において直線であると想定している。あるいは、高速で移動していても、移動経路が直線であると想定できる時間として、Ｔｐｒｅｄが設定されているとしてもよい。Ｐの算出イメージを図９に示す。 <S203>
In S203, the future location information calculation unit 140 calculates the future location P of the target terminal along the moving route by P=| vt |× Tpred using the speed vt and the time (e.g., number of seconds) Tpred to the future location. Here, it is assumed that the moving route is a straight line at least for the period Tpred . Alternatively, Tpred may be set as the time during which the moving route can be assumed to be a straight line even if the moving route is moving at high speed. An image of the calculation of P is shown in FIG. 9.
　なお、Ｓ２０２～Ｓ２０３において、将来位置情報計算部１４０は、算出されたＰや過去の測位位置が、測位誤差等から移動経路上から外れた値であることを検知すると、その値を、移動経路上で最も近い点の値に補正する。 In addition, in steps S202 and S203, if the future position information calculation unit 140 detects that the calculated P or the past positioning position is a value that deviates from the moving route due to a positioning error or the like, it corrects the value to the value of the closest point on the moving route.
　将来位置情報計算部１４０は、将来位置Ｐを示す情報を予測値算出部１５０に渡す。 The future position information calculation unit 140 passes information indicating the future position P to the prediction value calculation unit 150.
　＜Ｓ２０４、Ｓ２０５＞
　予測値算出部１５０は、各地点（各位置）の通信品質を、予測値算出部１５０が有するメモリ等の記憶部１５１に保持しているとする。この通信品質は、推定値（予測値）であってもよいし、過去の実績値であってもよい。 <S204, S205>
The predicted value calculation unit 150 stores the communication quality at each point (each position) in a storage unit 151 such as a memory included in the predicted value calculation unit 150. This communication quality may be an estimated value (predicted value) or a past actual value.
　予測値算出部１５０は、記憶部１５１を参照して、Ｓ２０３で算出した将来位置Ｐにおける通信品質を取得し、これを、対象端末における、現在時刻ｔから、Ｔｐｒｅｄだけ先の時刻の通信品質の予測値とする。Ｓ２０５は、実施例１のＳ１０５と同じである。 The predicted value calculation unit 150 refers to the storage unit 151 to obtain the communication quality at the future position P calculated in S203, and sets this as a predicted value of the communication quality at the target terminal at a time T pred ahead of the current time t. S205 is the same as S105 in the first embodiment.
　（ハードウェア構成例）
　本実施の形態で説明した予測装置１００は、例えば、コンピュータにプログラムを実行させることにより実現できる。このコンピュータは、物理的なコンピュータであってもよいし、クラウド上の仮想マシンであってもよい。 (Hardware configuration example)
The prediction device 100 described in this embodiment can be realized, for example, by causing a computer to execute a program. This computer may be a physical computer or a virtual machine on the cloud.
　すなわち、予測装置１００は、コンピュータに内蔵されるＣＰＵやメモリ等のハードウェア資源を用いて、予測装置１００で実施される処理に対応するプログラムを実行することによって実現することが可能である。上記プログラムは、コンピュータが読み取り可能な記録媒体（可搬メモリ等）に記録して、保存したり、配布したりすることが可能である。また、上記プログラムをインターネットや電子メール等、ネットワークを通して提供することも可能である。 In other words, the prediction device 100 can be realized by executing a program corresponding to the processing performed by the prediction device 100 using hardware resources such as a CPU and memory built into a computer. The above program can be recorded on a computer-readable recording medium (such as a portable memory) and stored or distributed. The above program can also be provided via a network such as the Internet or email.
　図１０は、上記コンピュータのハードウェア構成例を示す図である。図７のコンピュータは、それぞれバスＢＳで相互に接続されているドライブ装置１０００、補助記憶装置１００２、メモリ装置１００３、ＣＰＵ１００４、インタフェース装置１００５、表示装置１００６、入力装置１００７、出力装置１００８等を有する。なお、当該コンピュータは、更にＧＰＵを備えてもよい。 FIG. 10 is a diagram showing an example of the hardware configuration of the computer. The computer in FIG. 7 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are connected to each other via a bus BS. The computer may further include a GPU.
　当該コンピュータでの処理を実現するプログラムは、例えば、ＣＤ－ＲＯＭ又はメモリカード等の記録媒体１００１によって提供される。プログラムを記憶した記録媒体１００１がドライブ装置１０００にセットされると、プログラムが記録媒体１００１からドライブ装置１０００を介して補助記憶装置１００２にインストールされる。但し、プログラムのインストールは必ずしも記録媒体１００１より行う必要はなく、ネットワークを介して他のコンピュータよりダウンロードするようにしてもよい。補助記憶装置１００２は、インストールされたプログラムを格納すると共に、必要なファイルやデータ等を格納する。 The program that realizes the processing on the computer is provided by a recording medium 1001, such as a CD-ROM or a memory card. When the recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 via the drive device 1000 into the auxiliary storage device 1002. However, the program does not necessarily have to be installed from the recording medium 1001, but may be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files, data, etc.
　メモリ装置１００３は、プログラムの起動指示があった場合に、補助記憶装置１００２からプログラムを読み出して格納する。ＣＰＵ１００４は、メモリ装置１００３に格納されたプログラムに従って、予測装置１００に係る機能を実現する。インタフェース装置１００５は、ネットワーク等に接続するためのインタフェースとして用いられる。表示装置１００６はプログラムによるＧＵＩ（Ｇｒａｐｈｉｃａｌ　Ｕｓｅｒ　Ｉｎｔｅｒｆａｃｅ）等を表示する。入力装置１００７はキーボード及びマウス、ボタン、又はタッチパネル等で構成され、様々な操作指示を入力させるために用いられる。出力装置１００８は演算結果を出力する。 When an instruction to start a program is received, the memory device 1003 reads out and stores the program from the auxiliary storage device 1002. The CPU 1004 realizes functions related to the prediction device 100 in accordance with the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network, etc. The display device 1006 displays a GUI (Graphical User Interface) or the like according to a program. The input device 1007 is composed of a keyboard and mouse, buttons, a touch panel, etc., and is used to input various operational instructions. The output device 1008 outputs the results of calculations.
　（実施の形態の効果）
　本実施の形態で説明した技術により、端末の将来位置における通信品質を予測する技術において、従来技術よりも正確に通信品質を予測することが可能となる。 (Effects of the embodiment)
The technology described in this embodiment makes it possible to predict communication quality at the future location of a terminal more accurately than conventional technology.
　以上の実施形態に関し、更に以下の付記を開示する。 The following notes are further provided with respect to the above embodiment.
　＜付記＞
（付記項１）
メモリと、
　前記メモリに接続された少なくとも１つのプロセッサと、
　を含み、
　前記プロセッサは、
　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として算出し、
　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出する、
　予測装置。
（付記項２）
　前記形状は、前記対象端末の進行方向を中心軸として±θの角度を有し、前記所定時間の前記速度での移動距離を半径として有する扇形である
　付記項１に記載の予測装置。
（付記項３）
　前記プロセッサは、前記複数の位置の通信品質に対して、位置に応じた重みを用いて加重平均をとった値を前記予測値として算出する
　付記項１又は２に記載の予測装置。
（付記項４）
メモリと、
　前記メモリに接続された少なくとも１つのプロセッサと、
　を含み、
　前記プロセッサは、
　対象端末の速度を取得し、前記速度に基づいて、予め定められた移動経路上での前記対象端末の将来位置を算出し、
　前記将来位置における、前記対象端末の通信品質の予測値を算出する、
　予測装置。
（付記項５）
　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として決定する将来位置情報計算部と、
　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出する予測値算出部と、
　を備える予測システム。
（付記項６）
　予測装置が実行する予測方法であって、
　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として算出するステップと、
　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出するステップと、
　を備える予測方法。
（付記項７）
　予測装置が実行する予測方法であって、
　対象端末の速度を取得し、前記速度に基づいて、予め定められた移動経路上での前記対象端末の将来位置を算出するステップと、
　前記将来位置における、前記対象端末の通信品質の予測値を算出するステップと、
　を備える予測方法。
（付記項８）
　コンピュータを、付記項１ないし４のうちいずれか１項に記載の予測装置における各部として機能させるためのプログラムを記憶した非一時的記憶媒体。 <Additional Notes>
(Additional Note 1)
Memory,
at least one processor coupled to the memory;
Including,
The processor,
Acquire a speed of the target terminal, and calculate a range of a certain shape based on the speed as an estimated movement range of the target terminal within a predetermined time period;
calculating a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
Prediction device.
(Additional Note 2)
The prediction device according to claim 1, wherein the shape is a sector having an angle of ±θ with the traveling direction of the target terminal as a central axis and having a travel distance at the speed in the specified time as a radius.
(Additional Note 3)
The prediction device according to claim 1 or 2, wherein the processor calculates, as the predicted value, a weighted average of the communication qualities at the plurality of positions using weights according to the positions.
(Additional Note 4)
Memory,
at least one processor coupled to the memory;
Including,
The processor,
acquiring a speed of the target terminal, and calculating a future position of the target terminal on a predetermined moving path based on the speed;
Calculating a predicted value of communication quality of the target terminal at the future location;
Prediction device.
(Additional Note 5)
a future location information calculation unit that acquires a speed of the target terminal and determines a range of a certain shape as an estimated movement range of the target terminal within a predetermined time based on the speed;
a predicted value calculation unit that calculates a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
A prediction system comprising:
(Additional Note 6)
A prediction method executed by a prediction device, comprising:
acquiring a speed of the target terminal, and calculating a range of a certain shape based on the speed as an estimated movement range of the target terminal within a predetermined time;
calculating a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
A prediction method comprising:
(Additional Note 7)
A prediction method executed by a prediction device, comprising:
acquiring a speed of the target terminal and calculating a future position of the target terminal on a predetermined moving route based on the speed;
calculating a predicted value of communication quality of the target terminal at the future location;
A prediction method comprising:
(Additional Note 8)
A non-transitory storage medium storing a program for causing a computer to function as each unit in the prediction device according to any one of claims 1 to 4.
　以上、本実施の形態について説明したが、本発明はかかる特定の実施形態に限定されるものではなく、特許請求の範囲に記載された本発明の要旨の範囲内において、種々の変形・変更が可能である。 The present embodiment has been described above, but the present invention is not limited to this specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention as described in the claims.
１００　予測装置
１１０　位置情報取得部
１２０　位置情報ＤＢ
１３０　事前設定値保存ＤＢ
１４０　将来位置情報計算部
１５０　予測値算出部
１５１　記憶部
２１０　制御判断部
２２０　制御部
１０００　ドライブ装置
１００１　記録媒体
１００２　補助記憶装置
１００３　メモリ装置
１００４　ＣＰＵ
１００５　インタフェース装置
１００６　表示装置
１００７　入力装置
１００８　出力装置 100 Prediction device 110 Position information acquisition unit 120 Position information DB
130 Pre-set value storage DB
140 Future position information calculation unit 150 Prediction value calculation unit 151 Storage unit 210 Control decision unit 220 Control unit 1000 Drive device 1001 Recording medium 1002 Auxiliary storage device 1003 Memory device 1004 CPU
1005 Interface device 1006 Display device 1007 Input device 1008 Output device

Claims (8)

  1. 　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として算出する将来位置情報計算部と、
    　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出する予測値算出部と、
    　を備える予測装置。     a future location information calculation unit that acquires a speed of the target terminal and calculates a certain shaped range as an estimated movement range of the target terminal within a predetermined time based on the speed;
    a predicted value calculation unit that calculates a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
    A prediction device comprising:
  2. 　前記形状は、前記対象端末の進行方向を中心軸として±θの角度を有し、前記所定時間の前記速度での移動距離を半径として有する扇形である
    　請求項１に記載の予測装置。     The prediction device according to claim 1 , wherein the shape is a sector having an angle of ±θ with a central axis corresponding to a traveling direction of the target terminal and a radius corresponding to a travel distance at the speed in the predetermined time.
  3. 　前記予測値算出部は、前記複数の位置の通信品質に対して、位置に応じた重みを用いて加重平均をとった値を前記予測値として算出する
    　請求項１に記載の予測装置。     The prediction device according to claim 1 , wherein the predicted value calculation unit calculates, as the predicted value, a weighted average of the communication qualities at the plurality of positions using weights according to the positions.
  4. 　対象端末の速度を取得し、前記速度に基づいて、予め定められた移動経路上での前記対象端末の将来位置を算出する将来位置情報計算部と、
    　前記将来位置における、前記対象端末の通信品質の予測値を算出する予測値算出部と、
    　を備える予測装置。     a future position information calculation unit that acquires a speed of a target terminal and calculates a future position of the target terminal on a predetermined moving route based on the speed;
    a prediction value calculation unit that calculates a prediction value of communication quality of the target terminal at the future position;
    A prediction device comprising:
  5. 　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として決定する将来位置情報計算部と、
    　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出する予測値算出部と、
    　を備える予測システム。     a future location information calculation unit that acquires a speed of the target terminal and determines a certain shaped range as an estimated movement range of the target terminal within a predetermined time based on the speed;
    a predicted value calculation unit that calculates a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
    A prediction system comprising:
  6. 　予測装置が実行する予測方法であって、
    　対象端末の速度を取得し、前記速度に基づいて、ある形状の範囲を、前記対象端末の所定時間以内の推定移動範囲として算出するステップと、
    　前記形状の範囲内における複数の位置の通信品質に基づいて、前記対象端末の通信品質の予測値を算出するステップと、
    　を備える予測方法。     A prediction method executed by a prediction device, comprising:
    acquiring a speed of the target terminal, and calculating a range of a certain shape based on the speed as an estimated movement range of the target terminal within a predetermined time;
    calculating a predicted value of communication quality of the target terminal based on communication qualities at a plurality of positions within the range of the shape;
    A prediction method comprising:
  7. 　予測装置が実行する予測方法であって、
    　対象端末の速度を取得し、前記速度に基づいて、予め定められた移動経路上での前記対象端末の将来位置を算出するステップと、
    　前記将来位置における、前記対象端末の通信品質の予測値を算出するステップと、
    　を備える予測方法。     A prediction method executed by a prediction device, comprising:
    acquiring a speed of the target terminal, and calculating a future position of the target terminal on a predetermined moving route based on the speed;
    calculating a predicted value of communication quality of the target terminal at the future location;
    A prediction method comprising:
  8. 　コンピュータを、請求項１ないし４のうちいずれか１項に記載の予測装置における各部として機能させるためのプログラム。 A program for causing a computer to function as each part of a prediction device according to any one of claims 1 to 4.
PCT/JP2022/039991 2022-10-26 2022-10-26 Prediction device, prediction system, prediction method, and program WO2024089819A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/039991 WO2024089819A1 (en) 2022-10-26 2022-10-26 Prediction device, prediction system, prediction method, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/039991 WO2024089819A1 (en) 2022-10-26 2022-10-26 Prediction device, prediction system, prediction method, and program

Publications (1)

Publication Number Publication Date
WO2024089819A1 true WO2024089819A1 (en) 2024-05-02

Family

ID=90830266

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/039991 WO2024089819A1 (en) 2022-10-26 2022-10-26 Prediction device, prediction system, prediction method, and program

Country Status (1)

Country Link
WO (1) WO2024089819A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012029021A (en) * 2010-07-23 2012-02-09 Ntt Docomo Inc Control device and radio communication method
JP2012065138A (en) * 2010-09-16 2012-03-29 Toshiba Corp Radio communication apparatus and radio communication method
JP2019140563A (en) * 2018-02-13 2019-08-22 株式会社デンソー Mobile system communication device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012029021A (en) * 2010-07-23 2012-02-09 Ntt Docomo Inc Control device and radio communication method
JP2012065138A (en) * 2010-09-16 2012-03-29 Toshiba Corp Radio communication apparatus and radio communication method
JP2019140563A (en) * 2018-02-13 2019-08-22 株式会社デンソー Mobile system communication device

Similar Documents

Publication Publication Date Title
JP6462146B2 (en) Moving body moving system and moving path selection method
JP5306389B2 (en) Target tracking device
US9475195B2 (en) Anticipatory robot navigation
EP3004800B1 (en) Method and apparatus for offboard navigation of a robotic device
US11300663B2 (en) Method for predicting a motion of an object
WO2014196925A1 (en) Method and apparatus for offboard navigation of a robotic device
JP4348535B2 (en) Target tracking device
CN113715814A (en) Collision detection method, collision detection device, electronic apparatus, medium, and autonomous vehicle
CN112393732B (en) Unmanned aerial vehicle obstacle avoidance method and device, readable storage medium and electronic equipment
CN111279209A (en) Fingerprint data preprocessing method for improving positioning model
Adiththan et al. Cloud-assisted control of ground vehicles using adaptive computation offloading techniques
CN110377031B (en) Motion model updating method and device, electronic equipment and storage medium
WO2024089819A1 (en) Prediction device, prediction system, prediction method, and program
US20220017106A1 (en) Moving object control device, moving object control learning device, and moving object control method
JP2019175287A (en) Evading navigation decision method of moving entity, evading navigation decision system, and evading navigation decision program
JP7480975B2 (en) Travel route generation device, travel device, travel route generation method, and program
CN111045428A (en) Obstacle avoidance method, mobile robot and computer-readable storage medium
KR20220169877A (en) Method, apparatus and computer program for revising curvature error of automatic driving vehicle
WO2024089856A1 (en) Estimation device, learning device, estimation method, learning method, and program
CN115129065A (en) Robot moving speed determining method and device
JP2009295103A (en) Motion planning device, method, and program for autonomously moving robot, recording medium, and motion control device and method for autonomously moving robot
WO2024089820A1 (en) Information distribution device, prediction system, information distribution method, and program
CN112264997A (en) Method, device and equipment for determining origin of robot and storage medium
WO2023233485A1 (en) Wireless quality prediction system, wireless quality prediction device, wireless quality prediction method, and program
JP4714258B2 (en) Device, method and program for selecting route

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22963468

Country of ref document: EP

Kind code of ref document: A1