Estimation system, estimation method, and program

Abstract

To provide an estimation system, estimation method, and program capable of easily and correctly estimating a time required for a mobile body to arrive at a predetermined destination point.SOLUTION: An estimation system estimates a time required for a first mobile body existing on a route from a start point to a destination point to arrive at the destination point. The estimation system includes: first acquisition means 31 for acquiring information related to a movement mode of the first mobile body from the start point to a position of the first mobile body; second acquisition means 32 for acquiring information related to a movement mode of one or more second mobile bodies, among information stored in a predetermined storage device regarding movement modes of a plurality of second mobile bodies from the start point to the destination point, whose movement mode from the start point to the position of the first mobile body is similar to the movement mode of the first mobile body; and estimation means 33 for estimating a time required for the first mobile body to arrive at the destination point from the position of the first mobile body based on the acquired information related to the movement mode of the one or more second mobile bodies.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to an estimation system, an estimation method, and a program.

Background Art

[0002] Conventionally, a technique for predicting the time required for a moving object to reach a predetermined destination has been known (for example, Patent Document 1). In the technique described in Patent Document 1, using the current position information of a bus specified by GPS (Global Positioning System) and traffic information provided from VICS (Vehicle Information and Communication System) (registered trademark), the time required for the bus to reach the destination is predicted.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, for example, there is also known a method of predicting the time required for a moving object to reach a destination based on the speed of the moving object measured by sensors installed on the route from the starting point to the destination. However, when the moving object moves on a route where no sensor is installed, it has been difficult to predict the time required for the moving object to reach the destination. Further, in order to improve the prediction accuracy of the required time, it is necessary to install more sensors on the route, which may increase the equipment cost. Furthermore, the time required for the moving object to reach the destination varies depending on, for example, the speed of the moving object moving on the route, and the speed of the moving object can vary depending on various factors such as the personality of the operator who operates the moving object (e.g., driving speed) and the traffic congestion situation of the route. Therefore, it has been difficult to easily and accurately predict the required time in consideration of these factors.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide an estimation system, an estimation method, and a program capable of easily and accurately estimating the time required for a moving object to reach a predetermined destination.

Means for Solving the Problems

[0006] In order to solve the above problems, first, the present invention provides an estimation system for estimating the time required for a first moving object existing on a route from a starting point to a destination to reach the destination, the estimation system including: a first acquisition means for acquiring information regarding the movement mode of the first moving object from the starting point to the position of the first moving object; a second acquisition means for acquiring information regarding the movement modes of one or more second moving objects, among the information regarding the movement modes of a plurality of second moving objects from the starting point to the destination stored in a predetermined storage device, whose movement modes from the starting point to the position of the first moving object are similar to the movement mode of the first moving object; and an estimation means for estimating the time required for the first moving object to reach the destination from the position of the first moving object based on the acquired information regarding the movement modes of the one or more second moving objects (Invention 1).

[0007] According to such an invention (Invention 1), among the information on the movement modes of a plurality of second moving bodies from a starting point stored in a predetermined storage device to a destination point, information on the movement modes of one or more second moving bodies in which the movement mode of the second moving body from the starting point to the position (current position) of the first moving body is similar to the movement mode of the first moving body is acquired (extracted). Based on the acquired information on the movement modes of one or more second moving bodies, the time required for the first moving body to reach the destination point from the current position is estimated. Therefore, for example, among the information on the movement modes (for example, movement speed, etc.) of a plurality of second moving bodies that vary depending on various factors (for example, the personality of the operator who operates the second moving body, the congestion status of the route, etc.), only the information on the movement mode of the second moving body in which the movement mode from the starting point to the current position of the first moving body is similar to the movement mode of the first moving body is used to estimate the time required for the first moving body to reach the destination point. Thereby, it is possible to easily and accurately estimate the time required for the first moving body to reach the destination point while considering various factors (for example, the personality of the operator, the congestion status of the route, etc.). Further, according to such an invention (Invention 1), since it is not necessary to install sensors on the route from the starting point to the destination point, the equipment cost for predicting the time required for the first moving body to reach the destination point can be reduced.

[0008] In the above invention (Invention 1), the information on the movement mode may include the movement speed at each of one or more points existing on the route from the starting point to the destination point (Invention 2).

[0009] According to such an invention (Invention 2), it is possible to estimate the time required for the first moving body to reach the destination point by using the information on the movement mode of the second moving body in which the movement speed at each of one or more points from the starting point to the position of the first moving body is similar to the movement speed of the first moving body.

[0010] In the above inventions (Inventions 1 to 2), the second acquisition means may acquire the information on the movement modes of the one or more second moving bodies by using the k-nearest neighbor method (Invention 3).

[0011] According to such an invention (Invention 3), by using the k-nearest neighbor method, information on the movement patterns of one or more second moving objects classified into the same class as the information on the movement pattern of the first moving object from the starting point to the position of the first moving object can be easily obtained (extracted) as information on the movement pattern of a second moving object whose movement pattern from the starting point to the position of the first moving object is similar to the movement pattern of the first moving object.

[0012] In the above invention (Invention 3), the second acquisition means may execute the k-nearest neighbor method using, as a feature quantity, the moving speed at each of one or more points existing on the path from the starting point to the destination point (Invention 4).

[0013] According to such an invention (Invention 4), based on the moving speed of the moving object at each of one or more points existing on the path from the starting point to the destination point, it becomes possible to easily perform class classification of the information on the movement pattern of each of the first moving object and the second moving object.

[0014] In the above invention (Invention 4), the second acquisition means may use the forward method to determine the moving speed used for executing the k-nearest neighbor method among the moving speeds at each of the one or more points (Invention 5).

[0015] According to such an invention (Invention 5), by using the forward method, among the moving speeds at each of one or more points, the moving speed of a point that can contribute to improving the accuracy of class classification is extracted, and class classification is performed using the extracted moving speed of the point. Thereby, for example, it is possible to suppress class classification from being performed using the moving speed at a point where the moving speed of the moving object varies greatly (for example, a point where a signal is installed or a point where traffic congestion is likely to occur).

[0016] In the above invention (Invention 3), the second acquisition means may use N-fold cross-validation (where N is an integer of 2 or more) to determine the value of k of the k-nearest neighbor method (Invention 6).

[0017] According to such an invention (Invention 6), by using N-fold cross-validation, it becomes possible to easily determine the value of k in the k-nearest neighbor method.

[0018] In the above invention (Invention 1), the estimation means may estimate, as the required time for the first moving body to reach the destination point from the position of the first moving body, the average value of the required time for the second moving body to reach the destination point from the position of the first moving body, obtained based on the information on the movement mode of one or more acquired second moving bodies (Invention 7).

[0019] According to such an invention (Invention 7), based on the average value of the required time for the second moving body to reach the destination point from the current position of the first moving body, which is acquired (extracted), it becomes possible to easily estimate the required time for the first moving body to reach the destination point from the current position.

[0020] In the above invention (Invention 1), the first acquisition means may acquire the information on the movement mode of the first moving body transmitted from the first moving body (Invention 8).

[0021] According to such an invention (Invention 8), it becomes possible to easily acquire the information on the movement mode of the first moving body from the first moving body.

[0022] In the above invention (Invention 1), a presentation means for presenting information on the estimated required time may be provided (Invention 9).

[0023] According to such an invention (Invention 9), the user of the estimation system can easily know the information on the estimated required time.

[0024] In the above invention (Invention 1), the estimation system may be provided at the destination point (Invention 10).

[0025] According to such an invention (Invention 10), it becomes possible to estimate the required time for the first moving body to reach the destination point from the current position at the destination point.

[0026] In the above invention (Invention 1), the first moving body and the second moving body may be vehicles (Invention 11).

[0027] According to such an invention (Invention 11), among the information on the movement modes (e.g., moving speed, etc.) of a plurality of second vehicles (second moving bodies), only the information on the movement modes of the second vehicles whose movement modes from the departure point to the current position of the first vehicle (first moving body) are similar to the movement mode of the first vehicle is used to easily and accurately estimate the time required for the first vehicle to reach the destination point from the current position.

[0028] Second, the present invention provides an estimation method for a computer to estimate the time required for a first moving body existing on the route from a departure point to a destination point to reach the destination point. The computer includes steps of: acquiring information on the movement mode of the first moving body from the departure point to the position of the first moving body; acquiring, from the information on the movement modes of a plurality of second moving bodies from the departure point to the destination point stored in a predetermined storage device, information on the movement modes of one or more second moving bodies whose movement modes from the departure point to the position of the first moving body are similar to the movement mode of the first moving body; and estimating, based on the acquired information on the movement modes of the one or more second moving bodies, the time required for the first moving body to reach the destination point from the position of the first moving body. (Invention 12)

[0029] Thirdly, the present invention provides a program for causing a computer to estimate the time required for a first moving body existing on a path from a starting point to a destination point to reach the destination point, the program causing the computer to: acquire information regarding the movement mode of the first moving body from the starting point to the position of the first moving body; acquire information regarding the movement modes of one or more second moving bodies, out of information regarding the movement modes of a plurality of second moving bodies from the starting point to the destination point stored in a predetermined storage device, whose movement modes from the starting point to the position of the first moving body are similar to the movement mode of the first moving body; and estimate the time required for the first moving body to reach the destination point from the position of the first moving body based on the acquired information regarding the movement modes of the one or more second moving bodies (Invention 13).

Effect of the Invention

[0030] According to the estimation system, estimation method, and program of the present invention, it is possible to easily and accurately estimate the time required for a moving body to reach a predetermined destination point.

Brief Description of the Drawings

[0031]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0032] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. However, this embodiment is an example, and the present invention is not limited thereto.

[0033] (1) Basic configuration of the estimation system FIG. 1 is a diagram schematically showing the basic configuration of an estimation system according to an embodiment of the present invention. As shown in FIG. 1, in the estimation system according to this embodiment, it is configured to estimate the time required for the first moving body A existing on the route from the starting point S to the destination point G to reach the destination point G. More specifically, in the estimation system according to this embodiment, information regarding the movement mode of the first moving body A wirelessly transmitted from the communication device 10 provided in the first moving body A is acquired by the estimation device 20 existing at the destination point G. Further, the estimation device 20 acquires (extracts) information regarding the movement modes of one or more second moving bodies B (shown in FIG. 6(a)) from the starting point S to the destination point G stored in a predetermined storage device, among which the movement mode of the second moving body B from the starting point S to the position (current position) of the first moving body A is similar to the movement mode of the first moving body A, and is configured to estimate the time required for the first moving body A to reach the destination point G from the position of the first moving body A based on the acquired information regarding the movement modes of the one or more second moving bodies B.

[0034] Here, the first moving body A and the second moving body B may be vehicles. Further, this vehicle may be, for example, a vehicle operated by a driver or an autonomous vehicle.

[0035] The communication device 10 may be a device (for example, a car navigation system) that can be mounted on the first moving body A. Further, when the first moving body A is a moving body capable of autonomous driving (for example, an autonomous vehicle or the like), the communication device 10 may be a control device for controlling the autonomous driving of the first moving body A. Furthermore, the communication device 10 may be a device held and operated by a user (including a driver) riding on the first moving body A. Moreover, the communication device 10 may be mounted on the second moving body B.

[0036] The estimation device 20 may be a device held and operated by a user existing at the destination point G (for example, a user (including a driver) riding on a moving body existing at the destination point G), such as a mobile terminal, a smartphone, a PDA (Personal Digital Assistant), a personal computer, a television receiver having a two-way communication function (including a so-called multifunctional smart TV).

[0037] In the present embodiment, each of the communication device 10 and the estimation device 20 is configured to be able to communicate with each other using a predetermined communication method. Here, examples of the communication method include communication methods that do not require a license, such as LPWA (Low Power Wide Area) (920 MHz), IEEE.802.11n (2.4 GHz), IEEE.802.11ac (5.6 GHz), IEEE.802.11ad (60 GHz).

[0038] (2) Configuration of the communication device The configuration of the communication device 10 will be described with reference to FIG. 2. FIG. 2 is a block diagram showing the internal configuration of the communication device 10. As shown in FIG. 3, the communication device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage device 14, a display processing unit 15, a display unit 16, an input unit 17, a measurement device 18, and a communication interface unit 19, and a bus 10a is provided for transmitting control signals or data signals between the respective units. In the present embodiment, the case where the communication device 10 includes the storage device 14, the display processing unit 15, the display unit 16, and the input unit 17 is described as an example, but at least one of the storage device 14, the display processing unit 15, the display unit 16, and the input unit 17 may not be provided in the communication device 10.

[0039] When power is supplied to the communication device 10, the CPU 11 loads various programs stored in the ROM 12 or the storage device 14 into the RAM 13 and executes them.

[0040] The storage device 14 may be, for example, a non-volatile storage device such as a flash memory, an SSD, a magnetic storage device (e.g., HDD, floppy disk (registered trademark), magnetic tape, etc.), an optical disk, etc., or a volatile storage device such as a RAM, and stores programs executed by the CPU 11 and data referred to by the CPU 11.

[0041] The display processing unit 15 displays the display data given from the CPU 11 on the display unit 16. The display unit 16 is, for example, an LCD (Liquid Crystal Display) monitor including thin film transistors arranged in a matrix in pixel units, and drives the thin film transistors based on the display data to display the displayed data on the display screen.

[0042] When the communication device 10 is a device with a button input method, the input unit 17 includes a button group including a plurality of instruction input buttons such as a direction instruction button and a determination button for receiving a user's operation input, and a button group including a plurality of instruction input buttons such as a numeric keypad, and includes an interface circuit for recognizing a press (operation) input of each button and outputting it to the CPU 11.

[0043] When the communication device 10 is a device with a touch panel input method, the input unit 17 mainly receives touch panel input by touching the display screen with a fingertip or a pen. The touch panel input method may be a known method such as a capacitance method.

[0044] Also, when the communication device 10 is a device capable of voice input, the input unit 17 may be configured to include a microphone for voice input, or may be provided with an interface circuit for outputting voice data input via an external microphone to the CPU 11. Further, when the communication device 10 is a device capable of inputting moving images and / or still images, the input unit 17 may be configured to include a digital camera or a digital video camera for image input, or may be provided with an interface circuit for receiving image data captured by an external digital camera or digital video camera and outputting it to the CPU 11.

[0045] The measuring device 18 is configured to measure the position (for example, at least one of latitude, longitude, and altitude) and the moving speed (speed) of the communication device 10 (that is, the first moving body A provided with the communication device 10). For example, the measuring device 18 may measure the position of the communication device 10 using a well-known position measurement technique such as GPS. Also, the measuring device 18 may measure the speed of the communication device 10 using a speed sensor (for example, a vehicle speed sensor, etc.) provided in the first moving body A. Further, the measuring device 18 may measure the position and speed of the communication device 10 every time a predetermined time (for example, 1 second, etc.) elapses.

[0046] The communication interface unit 19 includes an interface circuit for performing wireless communication with another device (for example, the estimation device 20).

[0047] (3) Configuration of the estimation device The configuration of the estimation device 20 will be described with reference to FIG. 3. FIG. 3 is a block diagram showing the internal configuration of the estimation device 20. As shown in FIG. 3, the estimation device 20 includes a CPU 21, a ROM 22, a RAM 23, a storage device 24, a display processing unit 25, a display unit 26, an input unit 27, and a communication interface unit 28, and a bus 20a is provided for transmitting control signals or data signals between the respective units.

[0048] When the power is turned on to the estimation device 20, the CPU 21 loads various programs stored in the ROM 22 or the storage device 24 into the RAM 23 and executes them. In the present embodiment, the CPU 21 reads and executes the programs stored in the ROM 22 or the storage device 24 to realize the functions of the first acquisition means 31, the second acquisition means 32, the estimation means 33, and the presentation means 34 (shown in FIG. 4), which will be described later.

[0049] The storage device 24 may be, for example, a non-volatile storage device such as a flash memory, an SSD, a magnetic storage device (e.g., HDD, floppy disk (registered trademark), magnetic tape, etc.), an optical disk, or a volatile storage device such as a RAM, and stores programs executed by the CPU 21 and data referred to by the CPU 21. Further, acquisition data (shown in FIG. 5(b)) and history data (shown in FIG. 6(b)), which will be described later, are stored in the storage device 24.

[0050] The communication interface unit 28 includes an interface circuit for performing wireless communication with other devices (e.g., the communication device 10 of the first moving body A).

[0051] Note that the details of the other units (here, the display processing unit 25, the display unit 26, and the input unit 27) in the estimation device 20 may be the same as those of the communication device 10.

[0052] (4) Outline of each function in the estimation system The functions realized by the estimation system of this embodiment will be described with reference to FIG. 4. FIG. 4 is a functional block diagram for explaining the functions that play a major role in the estimation system of this embodiment. In the functional block diagram of FIG. 4, the first acquisition means 31, the second acquisition means 32, and the estimation means 33 correspond to the main configurations of the estimation system of the present invention. Other means (presentation means 34) are not necessarily essential configurations, but are components for further improving the present invention.

[0053] The first acquisition means 31 has a function of acquiring information regarding the movement mode of the first moving body A from the departure point S to the position of the first moving body A. Here, the information regarding the movement mode may include the movement speed at each of one or more points existing on the route from the departure point S to the destination point G. Thereby, as will be described later, using the information regarding the movement mode of the second moving body B in which the movement speed at each of one or more points from the departure point S to the position of the first moving body A is similar to the movement speed of the first moving body A, it becomes possible to estimate the time required for the first moving body A to reach the destination point G.

[0054] Also, the first acquisition means 31 may acquire information regarding the movement mode of the first moving body A transmitted from the first moving body A. Thereby, it becomes possible to easily acquire the information regarding the movement mode of the first moving body A from the first moving body A.

[0055] Furthermore, the estimation device 20 constituting the estimation system may be provided (exist) at the destination point G. Thereby, at the destination point G, it becomes possible to estimate the time required for the first moving body A to reach the destination point G from the current position.

[0056] Furthermore, the first moving body A and the second moving body B may be vehicles. Thereby, as will be described later, among the information regarding the moving modes (e.g., moving speed, etc.) of a plurality of second vehicles (second moving bodies B), only the information regarding the moving mode of the second vehicle whose moving mode from the departure point S to the current position of the first vehicle (first moving body A) is similar to the moving mode of the first vehicle is used, and the time required for the first vehicle to reach the destination point G from the current position can be easily and accurately estimated.

[0057] The function of the first acquisition means 31 is realized, for example, as follows. Here, as shown in FIG. 5(a), it is assumed that the first moving body A has already passed one or more points (here, points P1, P2, etc.) on the route from the departure point S to the destination point G and is currently located at the point Px. First, the CPU 11 of the communication device 10 provided in the first moving body A controls the measuring device 18 to measure the position and speed of the communication device 10, for example, every time a predetermined time (e.g., 1 second, etc.) elapses. Every time the measuring device 18 measures the position and speed of the communication device 10, the information regarding the measured position and speed is transmitted to the estimating device 20 via the communication interface unit 19. Here, the information regarding the measured position and speed may be transmitted to the estimating device 20 in a state associated with the measurement date and time and the identification information of the communication device 10 (e.g., the serial number or MAC (Media Access Control) address of the communication device 10, etc.).

[0058] On the other hand, every time the CPU 21 of the estimation device 20 receives (acquires) information regarding the position and speed of the communication device 10 (i.e., the first moving body A) transmitted from the communication device 10 via the communication interface unit 28, the received information is stored in the acquisition data shown in, for example, FIG. 5(b) in a state associated with the reception date and time (acquisition date and time) of the information. Here, the acquisition data describes, for the identification information of the first moving body A (moving body ID) (i.e., the identification information of the communication device 10 provided in the first moving body A (communication device ID)), the position (location) of the measured communication device 10 (i.e., the first moving body A), the speed (passing speed) of the measured communication device 10 (i.e., the first moving body A), the measurement date and time (passing date and time), and the reception date and time (acquisition date and time) of these pieces of information, in a state where they are associated with each other. In this way, the first acquisition means 31 can acquire information regarding the movement pattern of the first moving body A from the starting point S to the position (current position) of the first moving body A from the first moving body A.

[0059] The second acquisition means 32 has a function of acquiring information regarding the movement patterns of one or more second moving bodies B whose movement patterns from the starting point S to the position of the first moving body A are similar to the movement pattern of the first moving body A, from among the information regarding the movement patterns of a plurality of second moving bodies B from the starting point S to the destination point G stored in a predetermined storage device (here, the storage device 24).

[0060] Here, the second acquisition means 32 may acquire information regarding the movement patterns of one or more second moving bodies B using the k-nearest neighbor method. In this case, by using the k-nearest neighbor method, it becomes possible to easily acquire (extract) information regarding the movement patterns of one or more second moving bodies B classified into the same class as the information regarding the movement pattern of the first moving body A from the starting point S to the position of the first moving body A, as information regarding the movement patterns of the second moving bodies B whose movement patterns from the starting point S to the position of the first moving body A are similar to the movement pattern of the first moving body A.

[0061] Further, the second acquisition means 32 may execute the k-nearest neighbor method using the moving speed at each of one or more points existing on the path from the starting point S to the destination point G as a feature amount. Thereby, based on the moving speed of each of the first moving body A and the second moving body B at each of one or more points existing on the path from the starting point S to the destination point G, it becomes possible to easily perform class classification of information regarding the moving modes of each of the first moving body A and the second moving body B.

[0062] Furthermore, the second acquisition means 32 may use the forward method to determine the moving speed used for executing the k-nearest neighbor method among the moving speeds at each of the one or more points. In this case, by using the forward method, it is possible to extract the moving speed of a point that can contribute to improving the accuracy of class classification among the moving speeds at each of the one or more points, and perform class classification using the extracted moving speed of the point. Thereby, for example, it is possible to suppress performing class classification using the moving speed at a point where the moving speeds of each of the first moving body A and the second moving body B vary greatly (for example, a point where a signal is installed or a point where traffic congestion is likely to occur).

[0063] Furthermore, the second acquisition means 32 may use N-fold cross-validation (where N is an integer of 2 or more) to determine the value of k in the k-nearest neighbor method. In this case, by using N-fold cross-validation, it becomes possible to easily determine the value of k in the k-nearest neighbor method.

[0064] The function of the second acquisition means 32 is realized as follows, for example. Here, as shown in Fig. 6(a), it is assumed that the second moving body B has passed through all the points (here, points P1, P2, Px, etc.) on the path from the starting point S to the destination point G and has already arrived at the destination point G. Also, it is assumed that the second moving body B is provided with the communication device 10 in the same manner as the first moving body A. Here, the second moving body B may be the same moving body as the first moving body A (that is, the second moving body B may be the first moving body A that has reached the destination point G in the past), or may be a moving body different from the first moving body A. First, the CPU 11 of the communication device 10 provided in the second moving body B controls the measuring device 18 to measure the position and speed of the communication device 10, for example, every time a predetermined time (for example, 1 second, etc.) elapses. Every time the measuring device 18 measures the position and speed of the communication device 10, information regarding the measured position and speed is transmitted to the estimating device 20 via the communication interface unit 19.

[0065] On the other hand, every time the CPU 21 of the estimation device 20 receives (acquires) information regarding the position and speed of the communication device 10 (i.e., the second moving body B) transmitted from the communication device 10 via the communication interface unit 28, the received information is stored in, for example, the history data shown in FIG. 6(b) in a state associated with the reception date and time (acquisition date and time) of the information. Here, the history data is for each identification information (mobile body ID) of the second moving body B (i.e., the identification information (communication device ID) of the communication device 10 provided in the second moving body B), and includes the measured position (location) of the communication device 10 (i.e., the second moving body B), the measured speed (passing speed) of the communication device 10 (i.e., the second moving body B), the measurement date and time (passing date and time), and the reception date and time (acquisition date and time) of these information, which are described in a state where they are associated with each other. Note that a plurality of different measurement data may be recorded for the same second moving body B, or one or more measurement data may be recorded for each of a plurality of different second moving bodies B. In the present embodiment, a case where the history data is stored in the storage device 24 is described as an example, but the history data may be stored in, for example, the RAM 23, or may be stored in another storage device that is communicably connected to the estimation device 20 via a communication network (e.g., the Internet or a LAN (Local Area Network), etc.). Further, in order to adapt to the congestion situation of the most recent route, the CPU 21 may set a predetermined threshold value (reference date and time) for the measurement date and time (passing date and time) in the history data, and delete (forget) the data in the history data whose measurement date and time (passing date and time) is before the threshold value (reference date and time).

[0066] Next, the CPU 21 uses the k-nearest neighbor method to obtain information regarding the movement patterns of a plurality of second moving bodies B stored in the history data (here, the moving speed at each of one or more points), among which the movement pattern of the second moving body B from the starting point S to the position of the first moving body A is similar to the movement pattern of the first moving body A. Here, a case will be described in which the CPU 21 determines the moving speed (feature amount) used to execute the k-nearest neighbor method among the moving speeds at each of one or more points using the forward method, and determines the value of k for the k-nearest neighbor method using 4 (N = 4) fold cross-validation.

[0067] In this case, the CPU 21 uses the information regarding the movement patterns of a plurality of second moving bodies B stored in the history data to obtain the classification accuracy when the moving speed at each of one or more points from the starting point S to the destination point G is used as a single feature amount. Then, the CPU 21 determines the ranking of the feature amounts in descending order of the classification accuracy. Here, using the example shown in FIG. 7 for explanation, the classification accuracy is the highest when the moving speed at the point P4 is used as the feature amount, and then, in descending order of the classification accuracy, it is determined as the point P2, the point P1, the starting point S, the point P3, and the point P5.

[0068] Next, the CPU 21 sequentially combines the feature amount with the second highest classification accuracy for the feature amount with the highest classification accuracy until the classification accuracy reaches a predetermined value (for example, 100%). For example, in the example shown in FIG. 7, first, when the moving speed at point P4 and the moving speed at point P2 are used as feature amounts, the classification accuracy is 91.7%. Next, when the moving speed at point P4, the moving speed at point P2, and the moving speed at point P1 are used as feature amounts, the classification accuracy is also 91.7%. And when the moving speed at point P4, the moving speed at point P2, the moving speed at point P1, and the moving speed at the starting point S are used as feature amounts, the classification accuracy reaches 100%. Therefore, in this case, by using the four moving speeds of the moving speed at point P4, the moving speed at point P2, the moving speed at point P1, and the moving speed at the starting point S as feature amounts, it becomes possible to improve the classification accuracy.

[0069] Also, the CPU 21 uses 4-fold cross-validation to determine the value of k in the k-nearest neighbor method. In this case, the CPU 21 may determine the value of k according to the following procedures (1) to (5). (1) The CPU 21 randomly divides the moving speed of each of one or more points of all the second moving bodies B stored in the history data into four groups. (2) The CPU 21 performs a combination in which one of the four groups is used as verification data (test data) and the remaining three groups are used as training data (learning data). Then, first, the CPU 21 learns the classification model by this combination. Next, the CPU 21 replaces the verification data from the group used as the verification data for the first time with another group. Further, the CPU 21 combines the replaced verification data with the group used as the verification data for the first time as training data and learns the classification model by this combination. In this way, the CPU 21 learns the classification model by swapping the group used as the training data and the group used as the verification data each time so that each of the four groups becomes the verification data once. (3) The CPU 21 generates four classification models based on the results of this learning, and averages the four generated classification models. (4) The CPU 21 changes the value of k in the k-nearest neighbor method and repeats the procedures in (1) to (3) above. (5) The CPU 21 determines the value of k with the highest average classification accuracy among a plurality of values of k.

[0070] Fig. 8 shows an example of the relationship between a plurality of values of k (in the example in the figure, k = 1, 2, 3, 4, 5) and the classification accuracy at each value of k. In the example shown in Fig. 8, when the value of k is 2, 3, 4, or 5, the classification accuracy is the highest (100%). In this case, the CPU 21 may determine the value of k to be any one of 2, 3, 4, or 5. Further, from viewpoints such as, for example, setting the value of k to an odd number (for performing classification by majority vote) and setting the value of k to a relatively small number (for making the class boundary clearer), in the example of Fig. 8, the CPU 21 may determine the value of k to be 3.

[0071] Then, when the CPU 21 acquires information regarding the movement pattern of the first moving body A from the starting point S to the position of the first moving body A based on the function of the first acquisition means 31, the CPU 21 executes the k-nearest neighbor method using the feature amount (movement speed at one or more points) determined by the forward method and the value of k determined by four-fold cross-validation. As a result, among the information regarding the movement patterns of a plurality of second moving bodies B stored in the history data, the CPU 21 can acquire (extract) the information regarding the movement patterns of one or more second moving bodies B classified into the same class as the information regarding the movement pattern of the first moving body A from the starting point S to the position of the first moving body A as the information regarding the movement pattern of the second moving body B whose movement pattern from the starting point S to the position of the first moving body A is similar to the movement pattern of the first moving body A.

[0072] Here, the case of using four-fold cross-validation (that is, the case where N = 4) has been described as an example, but the value of N may be set to a value other than 4.

[0073] The estimation means 33 has a function of estimating the time required for the first moving body A to reach the destination point G from the position of the first moving body based on the information regarding the moving modes of one or more acquired second moving bodies B.

[0074] Here, the estimation means 33 may estimate, as the time required for the first moving body A to reach the destination point G from the position of the first moving body A, the average value of the time required for the second moving body B to reach the destination point G from the position of the first moving body A, which is obtained based on the information regarding the moving modes of one or more acquired second moving bodies B. Thereby, based on the average value of the time required for the acquired (extracted) second moving body B to reach the destination point G from the current position of the first moving body A, it becomes possible to easily estimate the time required for the first moving body A to reach the destination point G from the current position.

[0075] The function of the estimation means 33 is realized, for example, as follows. When the CPU 21 of the estimation device 20 acquires (extracts) the information regarding the moving modes of one or more second moving bodies B based on the function of the second acquisition means 32, it determines the time required for each of the one or more second moving bodies B to reach the destination point G from the current position of the first moving body A based on the acquired (extracted) information regarding the moving modes of the second moving body B. For example, the CPU 21 may determine the time required by obtaining the difference between the passing date and time of the position corresponding to the current position of the first moving body A (point Px in the example of FIG. 5(a)) stored in the history data and the passing date and time of the destination point G for each of the one or more acquired second moving bodies B. Then, the CPU 21 may estimate the calculated average value as the time required for the first moving body A to reach the destination point G from the current position (here, point Px).

[0076] Here, as an example, a case where the average value of the required time for each of the one or more second moving bodies B obtained (extracted) is estimated as the required time for the first moving body A to reach the destination point G from the current position has been described. However, the present invention is not limited to this case. For example, the CPU 21 may estimate the median value of the required time for each of the one or more second moving bodies B obtained (extracted) as the required time for the first moving body A to reach the destination point G from the current position. Further, the CPU 21 may estimate, as the required time for the first moving body A to reach the destination point G from the current position, a value obtained by substituting the required time for each of the one or more second moving bodies B obtained (extracted) into a predetermined calculation formula.

[0077] The presentation means 34 has a function of presenting information regarding the estimated required time. Thereby, the user of the estimation system can easily know the information regarding the estimated required time.

[0078] The function of the presentation means 34 is realized, for example, as follows. When the CPU 21 of the estimation device 20 estimates the required time for the first moving body A to reach the destination point G from the current position based on the function of the estimation means 33, the information regarding the determined required time may be displayed, for example, on the display unit 26. Here, the information regarding the required time may be composed of text data or may be composed of image data or the like. Further, when the information regarding the required time is composed of voice data, the CPU 21 may output the information regarding the required time from a voice output device such as a speaker. Furthermore, the CPU 21 may transmit the information regarding the required time to another computer (for example, a server or a terminal device) connected to the estimation device 20 via a communication network such as the Internet or a LAN.

[0079] (5) Flow of the main process of the estimation system of the present embodiment Next, an example of the flow of the main process performed by the estimation system of the present embodiment will be described with reference to the flowchart of FIG. 9.

[0080] First, based on the function of the first acquisition means 31, the CPU 21 of the estimation device 20 acquires information regarding the movement mode of the first moving body A from the starting point S to the position of the first moving body A (step S100). Here, the CPU 21 may acquire information regarding the movement mode of the first moving body A transmitted from the first moving body A.

[0081] Next, based on the function of the second acquisition means 32, the CPU 21 of the estimation device 20 acquires information regarding the movement modes of one or more second moving bodies B whose movement modes from the starting point S to the position of the first moving body A are similar to the movement mode of the first moving body A, from among the information regarding the movement modes of a plurality of second moving bodies B from the starting point S to the destination point G stored in a predetermined storage device (for example, the storage device 24) (step S102). Here, the CPU 21 may acquire information regarding the movement modes of one or more second moving bodies B using the k-nearest neighbor method.

[0082] Next, based on the function of the estimation means 33, the CPU 21 of the estimation device 20 estimates the required time until the first moving body A arrives at the destination point G from the position of the first moving body A, based on the information regarding the movement modes of the one or more second moving bodies B acquired (step S104).

[0083] Although not shown in the flowchart of FIG. 9, the CPU 21 of the estimation device 20 may present information regarding the estimated required time, based on the function of the presentation means 34.

[0084] As described above, according to the estimation system, estimation method, and program of the present embodiment, among the information on the movement modes of a plurality of second moving bodies B from the starting point S to the destination point G stored in the storage device 24, the information on the movement modes of the second moving bodies B from the starting point S to the position (current position) of the first moving body A is obtained (extracted) as one or more movement modes of the second moving bodies B that are similar to the movement mode of the first moving body A. Based on the obtained information on the movement modes of one or more second moving bodies B, the time required for the first moving body A to reach the destination point G from the current position is estimated. Therefore, for example, among the information on the movement modes (e.g., movement speed, etc.) of a plurality of second moving bodies B that differ due to various factors (e.g., the personality of the operator who operates the second moving body B, the congestion status of the route, etc.), only the information on the movement mode of the second moving body B from the starting point S to the current position of the first moving body A that is similar to the movement mode of the first moving body A is used to estimate the time required for the first moving body A to reach the destination point G. As a result, it becomes possible to easily and accurately estimate the time required for the first moving body A to reach the destination point G while considering various factors (e.g., the personality of the operator, the congestion status of the route, etc.). Further, according to the estimation system, estimation method, and program of the present embodiment, since it is not necessary to install sensors on the route from the starting point S to the destination point G, the equipment cost for predicting the time required for the first moving body A to reach the destination point G can be reduced.

[0085] Note that the program of the present invention may be stored in a computer-readable storage medium. The storage medium storing this program may be the ROM 12, RAM 13, or storage device 14 of the communication device 10 shown in FIG. 2, or the ROM 22, RAM 23, or storage device 24 of the estimation device 20 shown in FIG. 3. Further, the storage medium may be, for example, a CD-ROM or the like that can be read by being inserted into a program reading device such as a CD-ROM drive. Furthermore, the storage medium may be a magnetic tape, cassette tape, flexible disk, MO / MD / DVD, etc., or a semiconductor memory.

[0086] The embodiments described above are provided to facilitate the understanding of the present invention and are not provided to limit the present invention. Therefore, each element disclosed in the above embodiments is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

[0087] For example, in the above-described embodiment, the case where the first moving body A and the second moving body B are vehicles (four-wheeled vehicles) has been described as an example. However, the present invention is not limited to this case. The first moving body A and the second moving body B may be other moving bodies (for example, living organisms such as humans and animals, two-wheeled vehicles, ships, aircraft, drones (multicopters), robots, etc.).

[0088] Also, in the above-described embodiment, the case where the estimation device 20 is provided at the destination point G has been described as an example. However, the present invention is not limited to this case. For example, the estimation device 20 may be provided at a location other than the destination point G. In this case, the CPU 21 of the estimation device 20 may transmit, for example, the estimated required time of the first moving body A to each of one or more terminal devices (not shown) existing at the destination point G, or to each of one or more terminal devices (not shown) existing at a location different from the destination point G.

[0089] Furthermore, in the above-described embodiment, the case where the second acquisition means 32 acquires (extracts) information regarding the movement patterns of one or more second moving bodies B using the k-nearest neighbor method has been described as an example. However, the present invention is not limited to this case. The second acquisition means 32 may acquire (extract) information regarding the movement patterns of one or more second moving bodies B using, for example, other classification techniques.

[0090] Also, in the above-described embodiment, the case where one estimation device 20 is provided has been described as an example. However, the present invention is not limited to this case. For example, a plurality of estimation devices 20 may be provided. In this case, the operation content and processing results, etc. on any one of the estimation devices 20 may be presented in real time on other estimation devices 20, or the processing results, etc. on any one of the estimation devices 20 may be shared among the plurality of estimation devices 20.

[0091] Furthermore, in the above-described embodiment, the estimation apparatus 20 is configured to realize the functions of the first acquisition means 31, the second acquisition means 32, the estimation means 33, and the presentation means 34. However, the present invention is not limited to this configuration. For example, a computer or the like (e.g., a general-purpose personal computer or a server) communicably connected to the estimation apparatus 20 via a communication network such as the Internet or a LAN may be configured to realize the function of at least one of the above-described means 31 to 34. Further, as shown in FIGS. 10(a) and 10(b), each function of the functional block diagram shown in FIG. 4 may be arbitrarily shared between the estimation apparatus 20 and a management server, which is an example of a computer communicably connected to the estimation apparatus 20.

[0092] Furthermore, the communication apparatus 10 may be configured to realize the function of at least one of the above-described means 31 to 34.

Industrial Applicability

[0093] The estimation system, estimation method, and program of the present invention as described above can be suitably used, for example, for traffic control services at the arrival point of a moving body or information providing services that provide information regarding the scheduled arrival time of a moving body. Therefore, its industrial applicability is extremely large.

Explanation of Reference Numerals

[0094] 10... Communication apparatus 20... Estimation apparatus 31... First acquisition means 32... Second acquisition means 33... Estimation means 34... Presentation means A... First moving body B... Second moving body G... Destination P1, P2, P3, P4, P5, Px... Locations S... Departure point

Claims

1. An estimation system for estimating the time required until a first moving object existing on the route from a starting point to a destination point arrives at the destination point, comprising: a first acquisition means for acquiring information on the movement mode of the first moving object from the starting point to the position of the first moving object; a second acquisition means for acquiring information on the movement modes of one or more second moving objects from the starting point to the destination point stored in a predetermined storage device, wherein the movement mode of the second moving object from the starting point to the position of the first moving object is similar to the movement mode of the first moving object; an estimation means for estimating the time required for the first moving object to arrive at the destination point from the position of the first moving object based on the acquired information on the movement modes of the one or more second moving objects. The estimation system.

2. The information on the movement mode includes the movement speed at each of one or more points existing on the route from the starting point to the destination point. The estimation system according to claim 1.

3. The second acquisition means acquires information on the movement modes of the one or more second moving objects using the k-nearest neighbor method. The estimation system according to claim 1 or 2.

4. The second acquisition means executes the k-nearest neighbor method using the movement speed at each of one or more points existing on the route from the starting point to the destination point as a feature amount. The estimation system according to claim 3.

5. The second acquisition means determines, using the forward selection method, the movement speed among the movement speeds at each of the one or more points that is used to execute the k-nearest neighbor method. The estimation system according to claim 4.

6. The second acquisition means determines the value of k of the k-nearest neighbor method using N-fold cross-validation (where N is an integer of 2 or more). The estimation system according to claim 3.

7. The estimation means estimates, as the time required for the first moving object to arrive at the destination point from the position of the first moving object, the average value of the time required for the second moving object to arrive at the destination point from the position of the first moving object, obtained based on the acquired information on the movement modes of the one or more second moving objects. The estimation system according to claim 1.

8. The first acquisition means acquires information on the movement mode of the first moving object transmitted from the first moving object. The estimation system according to claim 1.

9. Comprising presentation means for presenting information regarding the estimated required time The estimation system according to claim 1

10. The said estimation system is provided at the said destination The estimation system according to claim 1

11. The said first moving body and the said second moving body are vehicles The estimation system according to claim 1

12. An estimation method in which a computer estimates the required time until a first moving body existing on the route from the departure point to the destination point arrives at the destination point, wherein the computer acquires information regarding the movement mode of the first moving body from the departure point to the position of the first moving body; acquires information regarding the movement modes of one or more second moving bodies among the information regarding the movement modes of a plurality of second moving bodies from the departure point to the destination point stored in a predetermined storage device, wherein the movement mode of the second moving body from the departure point to the position of the first moving body is similar to the movement mode of the first moving body; estimates the required time until the first moving body arrives at the destination point from the position of the first moving body based on the acquired information regarding the movement modes of the one or more second moving bodies; executes each of the steps of the estimation method

13. A program for causing a computer to estimate the required time until a first moving body existing on the route from the departure point to the destination point arrives at the destination point, wherein the computer has a function of acquiring information regarding the movement mode of the first moving body from the departure point to the position of the first moving body; has a function of acquiring information regarding the movement modes of one or more second moving bodies among the information regarding the movement modes of a plurality of second moving bodies from the departure point to the destination point stored in a predetermined storage device, wherein the movement mode of the second moving body from the departure point to the position of the first moving body is similar to the movement mode of the first moving body; has a function of estimating the required time until the first moving body arrives at the destination point from the position of the first moving body based on the acquired information regarding the movement modes of the one or more second moving bodies; a program for realizing the above

Images