Movement path estimation device, method, and program

Abstract

When estimating movement paths of a plurality of users when the users move a course from a start point to an end point, one aspect of the present invention acquires respective movement logs of a plurality of first users, among the plurality of users, the movement logs of which can be acquired, calculates an average movement path of the plurality of first users on the basis of the plurality of acquired movement logs, and on the basis of the calculated average movement path, estimates an initial movement path of a second user, among the plurality of users, the movement log of which cannot be acquired. Further, on the basis of the movement logs of the first users, a common movement section in which the plurality of first users have moved in a group so as to be closer to each other within the range of preset time and distance is calculated, and among initial movement paths of the second user, the initial movement path in which a time corresponds to the common movement section is corrected so as to be brought closer to movement paths of the first users in the common movement section.

Description

Travel path estimation device, method, and program

[0001] One aspect of the present invention relates to a movement path estimation device, method, and program used to estimate the traveling path of each runner in a race using moving objects such as bicycles.

[0002] A technology is being considered for reproducing the movement status of a moving object in the real world in a virtual world. This technology can be realized, for example, by attaching a device for recording a history of location information, such as a Global Positioning System (GPS) logger, to a moving object in the real world, and then reflecting information representing the movement history obtained when the moving object moves in this state in the movement status of an avatar or the like in the virtual world.

[0003] Taking a bicycle race as an example, a GPS logger is attached to each bicycle of the participating athletes to acquire riding data of each bicycle during the race, and the bicycle race is then reproduced in a virtual world based on the acquired riding data.

[0004] However, if it is difficult to attach a GPS logger due to the structure of the bicycle, or if the athlete refuses to have one installed due to the increased weight that would result from installing a GPS logger, then riding data cannot be obtained, and for athletes for whom such riding data cannot be obtained, the riding conditions cannot be reproduced in virtual space.

[0005] Therefore, the following method has been considered as a conventional method for reproducing in a virtual space the riding conditions of a runner for whom riding data is unavailable. Non-Patent Document 1 describes a technique for calculating a standard course time based on the GPS logs of multiple users who go mountain climbing. The conventional reproduction method applies this technology to bicycle races, calculating an average riding line from a group of riding data of multiple participating runners, and estimating the riding lines of runners for whom riding data is unavailable along the calculated average riding line.

[0006] "We created a course time ruler based on your walking path," YAMAP, September 29, 2023, Internet <URL: https: / / note.yamap.com / n / n68295f78a326>

[0007] However, simply applying the technology described in Non-Patent Document 1 raises the following problem: In general, runners often run in groups during many sections of a race to avoid air resistance. However, if the running line of a runner for whom no running data is available is simply set based on the average running line of other runners, then when reproducing the running conditions of the runner in the virtual world, the running conditions of the runner for whom no running data is available will often include many sections in which the runner separates from the group and runs alone, resulting in an inaccurate reproduction of the actual running conditions.

[0008] The present invention has been made in light of the above circumstances, and aims to provide a technique that enables accurate estimation of the movement path of a mobile object whose movement history is not acquired.

[0009] In order to solve the above problem, one aspect of a movement path estimation device or estimation method according to the present invention, when estimating movement paths of multiple users moving along a course from a start point to an end point, acquires movement logs of multiple first users among the multiple users for which movement logs can be acquired, calculates an average movement path of the multiple first users based on the acquired movement logs, and estimates an initial movement path of a second user among the multiple users for which movement logs cannot be acquired based on the calculated average movement path. Furthermore, based on the movement logs of the first users, calculates a joint movement section in which the multiple first users moved in close proximity as a group within a predetermined time and distance range, and corrects the initial movement path of the second user that corresponds to the time of the joint movement section so as to approximate the movement path of the first user in the joint movement section.

[0010] According to one aspect of the present invention, when a joint movement section exists in which a plurality of first users are moving together as a group, the initial movement route estimated for a second user whose movement log cannot be acquired is corrected to approach the position of the first user in the joint movement section. Generally, in a joint movement section in which a large number of users are moving together as a group, there are few users who choose to move alone, and it is assumed that this is no exception for the second user. Therefore, by correcting the initial movement route of the second user as described above to approach the movement route of the first user in a section in which the first group of users are moving together as a group, it is possible to estimate the movement route of the second user to be closer to the actual route.

[0011] That is, according to one aspect of the present invention, it is possible to provide a technology that enables accurate estimation of the movement path of a moving object whose movement history is not acquired.

[0012] FIG. 1 is a diagram illustrating an example of a travel path estimation system according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of the hardware configuration of a travel path estimation device according to an embodiment of the present invention. FIG. 3 is a block diagram illustrating an example of the software configuration of a travel path estimation device according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating an example of the processing procedure and processing content of a travel path estimation process executed by a control unit of the travel path estimation device illustrated in FIG. 3. FIG. 5 is a flowchart illustrating an example of the processing procedure and processing content of a co-traveling section calculation process among the procedures of the travel path estimation process illustrated in FIG. 4. FIG. 6 is a flowchart illustrating an example of the processing procedure and processing content of an initial travel path correction process among the procedures of the travel path estimation process illustrated in FIG. 4. FIG. 7 is a flowchart illustrating an example of the processing procedure and processing content of an in-group travel position setting process among the procedures of the travel path estimation process illustrated in FIG. 4. FIG. 8 is a diagram illustrating an example of the travel path of a first group of users in a co-traveling section and an example of an initial travel path estimated for a second user. FIG. 9 is a diagram illustrating an example of a bounding box. FIG. 10 is a diagram illustrating an example of an in-group travel position setting process using a bounding box.

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] [One Embodiment] (Configuration Example) (1) System A travel path estimation system according to one embodiment collects travel data from a first group of users wearing GPS (Global Positioning System) loggers among multiple users participating as racers in a bicycle race, for example, using public roads or mountain roads. Then, based on the collected travel data of the first group of users, calculates an average normalized travel path of the first group of users and identifies a joint travel section where the first group of users travel together. Based on the average normalized travel path, estimates the travel path of a second user who is not wearing a GPS logger and corrects the travel path of the second user so that the second user travels together with the first group of users in the joint travel section.

[0015] FIG. 1 is a diagram showing an example of the configuration of a travel path estimation system according to an embodiment of the present invention.

[0016] In this system, GPS loggers LG1 to LGn attached to bicycles BT1 to BTn used by a group of users can be connected to a travel route estimation device SV via a network NW.

[0017] The GPS loggers LG1 to LGn continuously or discretely measure the traveling position, expressed for example by latitude and longitude, of the bicycles BT1 to BTn while they are traveling, and transmit traveling data including the measured traveling position and the time of measurement to the travel route estimation device SV via the network NW.

[0018] If the GPS loggers LG1 to LGn do not have a communication function, the travel data may be transmitted via a mobile terminal or the like carried by the user.

[0019] The network NW includes a wide area network with the Internet at its core, and an access network for accessing the wide area network. The access network may be, for example, a public wireless data communication network or a local area network (LAN), but is not limited to these.

[0020] (2) Travel Route Estimation Device SV The travel route estimation device SV is configured by, for example, a server computer installed on the cloud or the web. Note that the travel route estimation device SV may also be configured by, for example, a personal computer used by a system administrator.

[0021] 2 and 3 are block diagrams showing an example of the hardware configuration and software configuration of the travel path estimation device SV, respectively.

[0022] The travel path estimation device SV has a control unit 1 that uses a hardware processor such as a central processing unit (CPU), and this control unit 1 is connected via a bus 5 to a storage unit having a program storage unit 2 and a data storage unit 3, and a communication interface (hereinafter, the interface will be referred to as I / F) unit 4.

[0023] The communication I / F unit 4 receives the driving data transmitted from the GPS loggers LG1 to LGn using a communication protocol defined in the network NW. The communication I / F unit 4 is capable of performing data communication with an administrator terminal (not shown) used by a system administrator or the like.

[0024] The program storage unit 2 is configured by combining, for example, a nonvolatile memory such as a solid-state drive (SSD) as a storage medium that can be written to and read from at any time, and a nonvolatile memory such as a read-only memory (ROM), and stores middleware such as an operating system (OS), as well as application programs required to execute various controls according to an embodiment. Hereinafter, the OS and each application program will be collectively referred to as the program.

[0025] The data storage unit 3 is, for example, a combination of a non-volatile memory such as an SSD that can be written to and read from at any time as a storage medium, and a volatile memory such as a RAM (Random Access Memory), and its storage area includes a driving route storage unit 31, an average driving route storage unit 32, an initial driving route storage unit 33, a co-driving section information storage unit 34, and a bounding box pattern storage unit 35.

[0026] The running route storage unit 31 stores the running route information of multiple users who participated in the race. In addition to the running route information measured for each of multiple first users who wear GPS loggers, the running route storage unit 31 also stores estimated running route information for a second user who does not wear a GPS logger.

[0027] The average travel route storage unit 32 is used to store information representing an average normalized travel route calculated based on the travel route information of each of the plurality of first users.

[0028] The initial travel route storage unit 33 is used to store initial travel route information estimated for the second user based on the average normalized travel route information.

[0029] The co-driving section information storage unit 34 is used to store information regarding the co-driving section in which the first users drove in a group, which is calculated based on the driving route information of each of the multiple first users stored in the driving route storage unit 31.

[0030] The bounding box pattern storage unit 35 stores data representing a basic pattern of a bounding box used to enclose an area including the first group of users traveling in a group.

[0031] The control unit 1 has the processing functions necessary to implement one embodiment of the present invention, including a driving data acquisition processing unit 11, an average driving route calculation processing unit 12, an initial driving route estimation processing unit 13, a co-driving section calculation processing unit 14, a driving position setting processing unit 15 within the group, and a driving route correction processing unit 16.

[0032] The processing units 11 to 16 are all realized by causing a hardware processor in the control unit 1 to execute an application program stored in the program storage unit 2. Note that some or all of the processing units 11 to 16 may be realized using hardware such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit).

[0033] During or after the race, the travel data acquisition processing unit 11 acquires travel data from the GPS loggers LG1-LGn attached to the bicycles BT1-BTn via the network NW, respectively, and associates each of the acquired travel data with the user identification information (user ID) of the user from which the data was acquired, and stores this in the travel route storage unit 31 as travel route information for the first user.

[0034] The average driving route calculation processing unit 12 calculates an average normalized driving route based on the driving route information of multiple first users, and stores information representing the calculated average normalized driving route in the average driving route memory unit 32.

[0035] The initial driving route estimation processing unit 13 estimates the driving route of a second user for whom driving data could not be obtained based on information representing the average normalized driving routes of the above-mentioned multiple first users, and stores the estimated driving route in the initial driving route memory unit 33 as initial driving route information in association with the user ID of the second user.

[0036] The co-traveling section calculation processing unit 14 calculates the co-traveling section along which the first users traveled in a group, based on the travel route information of each of the multiple first users stored in the travel route storage unit 31. The co-traveling section calculation processing unit 14 then stores information representing the calculated co-traveling section together with the user IDs of the first users who make up the group in the co-traveling section in the co-traveling section information storage unit 34. An example of a method for calculating the co-traveling section will be described in the operation example.

[0037] The in-group running position setting processing unit 15 sets a bounding box in an area surrounding the first group of users running in the group in the above-mentioned joint running section, and determines an empty position within the group where the second user can run based on the positions of the multiple first users included in this bounding box. An example of the process of setting an empty position within the group will also be described in detail in the operation example.

[0038] The travel route correction processing unit 16 corrects the initial travel route of the second user, the route whose travel time corresponds to the co-travel section, so as to bring the route closer to the empty position set within the group of the first user in the co-travel section. Note that an example of the correction process for the initial travel route will also be described in the operation example.

[0039] (Example of Operation) Next, an example of operation of the travel route estimation device SV configured as above will be described.

[0040] FIG. 4 is a flowchart for explaining an example of the processing procedure and processing contents of the travel route estimation processing executed by the control unit 1 of the travel route estimation device SV shown in FIG.

[0041] (1) Acquisition of Driving Data During or after the race, the control unit 1 of the travel path estimation device SV acquires driving data of each user who participated in the race under the control of the driving data acquisition processing unit 11 as follows.

[0042] That is, in step S10, the running data acquisition processing unit 11 first selects one user from a list of participating users stored in advance. Then, in step S11, the running data acquisition processing unit 11 accesses the GPS logger LGi corresponding to the selected user i, receives recorded running data from the GPS logger LGi during the race via the communication I / F unit 4, associates the received running data with the user ID, and stores this as running route information for the first user in the running route storage unit 31. The running route information includes, for example, latitude and longitude measured continuously or discretely and the time of measurement.

[0043] The traveling data acquisition processing unit 11 determines whether all participating users have been selected in step S12. If there are any users left that have not yet been selected, the process returns to step S10 to select the next user, and the traveling data of the selected user is acquired in step S11. Thereafter, the traveling data acquisition process is repeated in the same manner for all participating users.

[0044] In addition, if the selected user's driving data cannot be acquired, such as when the user is not wearing a GPS logger or when the GPS logger is inaccessible even if worn, the driving data acquisition processing unit 11 stores information indicating that driving data cannot be acquired in the driving route memory unit 31, corresponding to the user ID.

[0045] It is also possible that the GPS loggers LG1 to LGn do not have a communication function. In this case, the running data acquisition processing unit 11 reads the running data from the GPS loggers LG1 to LGn after the race ends, with the GPS loggers LG1 to LGn directly connected to the travel path estimation device SV.

[0046] When the process of acquiring driving data for all participating users is completed, in step S13, the driving data acquisition processing unit 11 classifies the participating users into a first group of users from whom driving data was acquired and a second group of users from whom driving data could not be acquired, based on the driving route information stored in the driving route memory unit 31.

[0047] (2) Calculation of average normalized driving path Next, in step S14, under the control of the average driving path calculation processing unit 12, the control unit 1 of the travel path estimation device SV calculates the average normalized driving path based on each driving data acquired from the classified first user group.

[0048] For example, suppose there are m first users from whom driving data has been obtained, and the driving data of user i is measured using latitude and longitude as A_i(t) (0≦t≦g_i). Here, t represents the elapsed time from the time when user i passed the start point of the course, and g_i represents the time when user i passed the end point of the course. If the driving data is acquired discretely (for example, at 1-second intervals), the average driving path calculation processing unit 12 uses linear interpolation processing to calculate the latitude and longitude at time t based on the discrete driving data.

[0049] The average travel path calculation processing unit 12 then normalizes the travel area corresponding to time t to [0, 1] by setting the latitude and longitude data as A_i(t) = A_i(t) / g_i. The average travel path calculation processing unit 12 then calculates information representing the normalized latitude and longitude as M(t) = Σ_i A_i(t) to obtain the average normalized travel path of the first user group. The information representing this average normalized travel path is stored in the average travel path storage unit 32.

[0050] (3) Estimation of the initial driving route of the second user The control unit 1 of the travel route estimation device SV then, under the control of the initial driving route estimation processing unit 13, estimates the driving route of the second user for whom driving data could not be obtained as follows.

[0051] That is, the initial driving route estimation processing unit 13 first selects one second user to be estimated in step S15. Then, in step S16, the initial driving route estimation processing unit 13 estimates an initial normalized driving route for the selected second user based on the average normalized driving route information stored in the average driving route storage unit 32, and stores information representing the estimated initial normalized driving route in the initial driving route storage unit 33 in association with the user ID of the second user.

[0052] For example, if the elapsed time from when the second user to be estimated passed the starting point is t and the time when the second user passed the end point is g_e, the initial driving route estimation processing unit 13 estimates the initial normalized driving route of the second user as E(t) = M(t * g_e).

[0053] The initial driving route estimation processing unit 13 determines whether or not the selection of all second users has been completed in step S17. If the result of this determination indicates that there are still second users who have not yet been selected, the initial driving route estimation processing unit 13 returns to step S15 to select the next second user, and estimates an initial normalized driving route for the second user in step S16. Thereafter, the initial normalized driving route is estimated for each of all second users in the same manner.

[0054] (4) Calculation of the co-traveling section When the initial travel path estimation processing unit 13 has finished estimating the initial normalized travel paths for all second users, the control unit 1 of the travel path estimation device SV then, under the control of the co-traveling section calculation processing unit 14, executes the following process in step S18 to determine the co-traveling section along which the first group of users traveled together.

[0055] FIG. 5 is a flowchart showing an example of the processing procedure and processing content of the co-running section calculation processing executed by the co-running section calculation processing unit 14.

[0056] That is, in step S181, the co-traveling section calculation processing unit 14 first divides the first users into pairs for each time t and creates all combinations of these pairs. Next, in step S182, the co-traveling section calculation processing unit 14 selects one of the combinations, and in step S183, calculates the distance between the two users for the selected combination. The co-traveling section calculation processing unit 14 performs the above-described process of calculating the distance between users for all combinations.

[0057] In step S184, the co-traveling section calculation processor 14 determines that the calculation process for the distance between users has been completed for all combinations. Then, in step S185, the co-traveling section calculation processor 14 extracts all combinations for which the calculated distance between users is equal to or less than a threshold value. Then, in step S186, the co-traveling section calculation processor 14 generates a set of combinations of first users that commonly include the same user, based on the extracted combinations. This set is a co-traveling set that represents a state in which multiple first users are traveling in a group.

[0058] Furthermore, in step S187, the co-traveling section calculation processing unit 14 calculates the center of the traveling positions of the multiple first users that make up the generated co-traveling set, and stores the time when the co-traveling set was formed and information representing the center position of the co-traveling set in the co-traveling section information storage unit 34 as information representing the co-traveling section.

[0059] For example, the co-traveling section calculation processing unit 14 generates all combinations of two users at time t for m first users, and extracts all combinations in which the distance between the users is equal to or less than a threshold value L. Then, it generates a set S_j(t) that groups together combinations that commonly include the same user. S_j(t) represents the co-traveling set of the first group of users who are in a co-traveling state with each other at time t.

[0060] Next, the co-traveling section calculation processing unit 14 calculates the average C_j(t) of the travel positions of each user included in the co-traveling set S_j(t), and sets this C_j(t) as the center point of the co-traveling set, which means the center position of the first group of users traveling together in the co-traveling section of S_j(t).

[0061] 8 shows an example of the average normalized travel path M(t) of the first user group and the initial normalized travel path E(t) estimated for the second user. This example shows a case where multiple first users travel together at times t, t, t, t, t, and t, forming co-traveling sets P, P, P, P, P, P, and P, respectively.

[0062] For example, at time t1, three first users are riding in a group at positions P11, P12, and P13, with the center of the group being O1. At time t2, four users are riding in a group at positions P21, P22, P23, and P24, with the center of the group being O2. The same applies to times t3, t6, t7, and t8.

[0063] (5) Estimation of empty positions within the group Next, in step S20, the control unit 1 of the travel path estimation device SV, under the control of the in-group running position setting processing unit 15, estimates empty positions within the group traveling in the co-travel section.

[0064] In a co-traveling section, there is a high probability that a second user will join multiple first users in traveling in a group. Therefore, in order to more accurately correct the traveling route of the second user, it is necessary to estimate an empty position within the co-traveling group of the first users in the co-traveling section where the second user can travel. The empty position can be set, for example, by focusing on the density of first users within the co-traveling group.

[0065] FIG. 7 is a flowchart showing an example of the processing procedure and processing content of the vacant position setting processing executed by the in-pack traveling position setting processing unit 15.

[0066] That is, in step S191, the in-pack traveling position setting processing unit 15 first selects a traveling together section for each time t based on information representing the traveling together section stored in the traveling together section information storage unit 34, and then in step S192, encloses an area including the first group of users traveling together in the selected traveling together section with a bounding box. At this time, the shape of the bounding box is set based on the basic pattern stored in the bounding box pattern storage unit 35.

[0067] 9 shows an example of a rectangular basic bounding box BB pattern, with OB indicating its center. The in-group running position setting processor 15 uses this rectangular basic pattern to enclose an area including a first group of users running in a group, with the bounding box BB, as shown in FIG. 10. This example shows the running positions P31, P32, P33, and P34 of four users enclosed by the bounding box BB.

[0068] Next, in step S193, the in-group running position setting processing unit 15 estimates an area within the bounding box BB where the density of the first users is low. For example, if the center of the first group of users of the co-running set S_j(t) within the bounding box BB is C_j(t), the position where C_j(t) exists corresponds to a position where the density of the first group of users is relatively high.

[0069] Therefore, in step S194, the in-group running position setting processing unit 15 calculates a position within the bounding box BB that is point-symmetric with respect to the center C_j(t) of the user group with respect to the center B_j(t) of the bounding box BB as follows: C^_j(t) = C_j(t) + 2 * (B_j(t) - C_j(t)). The calculated C^_j(t) can be considered a position where the density of first users is relatively low, and this position is estimated to be an empty position within the co-running set of the first user group where there is a high possibility that a second user is running. The in-group running position setting processing unit 15 stores information representing the empty position estimated in this manner in the co-running section information storage unit 34, correlating it with the time t of the co-running section.

[0070] When the process of setting an empty position for one of the above-mentioned parallel running sections (time t) is completed, the in-pack running position setting processor 15 determines in step S196 whether or not the process has been completed for all of the parallel running sections. If there are any unprocessed parallel running sections remaining, the process returns to step S191, selects the next parallel running section to be processed, and executes the above-mentioned empty position setting process. Thereafter, the in-pack running position setting processor 15 similarly repeats the processes of steps S192 to S196 until the process of setting an empty position for all of the parallel running sections is completed.

[0071] In addition, vacant positions may be determined, for example, by calculating the density of users per unit area based on the driving positions of the first users that make up the co-driving set, identifying an area where the calculated density is below a threshold value, and setting the vacant position at a position within this area where no first users are present.

[0072] (6) Correction of initial normalized travel route Next, under the control of the travel route correction processing unit 16, the control unit 1 of the travel route estimation device SV executes a process of correcting the initial normalized travel route of the second user in step S20 as follows.

[0073] FIG. 7 is a flowchart showing an example of the procedure and content of the correction process executed by the travel route correction processing unit 16.

[0074] That is, the driving path correction processing unit 16 first selects one second user to be estimated in step S201. Next, in step S202, the driving path correction processing unit 16 calculates, for each time t, the distance between the initial normalized driving path of the second user and an empty position in the driving path set set by the in-group driving position setting processing unit 15 for each driving path section on the course. Then, in step S203, the driving path correction processing unit 16 selects, from the initial normalized driving path of the second user, the driving path set with the closest distance within a predetermined range based on the calculated distance.

[0075] The travel path correction processing unit 16 determines whether or not a co-traveling set with the closest distance has been found in step S204. If the closest co-traveling set has been found, the travel path correction processing unit 16 corrects the position of the initial normalized travel path of the second user in step S205 so that it becomes an empty position within the closest co-traveling set, and associates the position of the corrected travel path with the user ID of the second user and stores it in the travel path storage unit 31 in step S206.

[0076] On the other hand, if no co-traveling set is found whose distance is within the predetermined range, in step S207, the travel path correction processing unit 16 stores the initial normalized travel path of the second user in the travel path storage unit 31 without correcting the position of the initial normalized travel path of the second user, and associates the initial normalized travel path with the user ID of the second user.

[0077] 8, for example, at time t2, position P2k of the second user's initial normalized traveling path E(t) is corrected to an empty position within the co-traveling set P2i, and at time t3, position P3k of the second user's initial normalized traveling path E(t) is corrected to an empty position within the co-traveling set P3i. Similarly, at times t6, t7, and t8, positions P6k, P7k, and P8k of the second user's initial normalized traveling path E(t) are corrected to empty positions within the co-traveling sets P6i, P7i, and P8i, respectively.

[0078] In contrast, in sections where a co-traveling set of the first user group is not formed, such as at times t4 and t5, the positions P4k and P5k of the initial normalized travel route E(t) of the second user are not corrected, and the positions P4k and P5k are stored as they are in the travel route memory unit 31.

[0079] The driving route correction processing unit 16 executes the above-described correction process of the initial normalized driving route of the second user for each of the second users to be estimated. Then, when it determines in step S208 that the correction process for all of the second users has been completed, the series of route estimation processes ends and the process returns to a standby state.

[0080] (7) Use of Driving Route Information The driving route information of multiple users obtained by the series of processes described above is transferred from the travel route estimation device SV to, for example, a server computer that builds and operates the metaverse, and is used to recreate bicycle races using avatars, etc. in a virtual space.

[0081] Another possible use is to transfer the obtained driving route information to a personal computer used by the athlete or his / her team staff, for example, so that the athlete or staff can review the situation during the race after the race.

[0082] (Effects) As described above, in one embodiment, the travel path estimation device SV acquires travel data of a first group of users who are wearing GPS loggers LG1 to LGn among multiple users participating in a bicycle race, calculates an average normalized travel path of the first group of users based on each travel path represented by the acquired travel data, and estimates an initial travel path of a second user who is not wearing a GPS logger LG1 to LGn based on this average normalized travel path. At the same time, a section of joint travel in which the first group of users rode together is identified based on each travel path of the first group of users, and in this joint travel section, the initial travel path of the second user is corrected to approximate the travel path of the first group of users.

[0083] Generally, in bicycle races, few users choose to travel alone in the shared section where many users are traveling in a group, and it is assumed that this is no exception for the second user. Therefore, by correcting the initial traveling route of the second user as described above so that it approaches the traveling route of the first user in the shared section where the first group of users are traveling in a group, it is possible to estimate the traveling route of the second user as a route that is closer to the actual route.

[0084] In one embodiment, when correcting the initial travel route of the second user, the first user group is surrounded by a bounding box in the co-travel section, an empty position where the density of the first user group is low is identified within the bounding box, and the travel route of the second user is corrected to the identified empty position. This makes it possible to more accurately correct the travel route of the second user.

[0085] [Other Embodiments] (1) In one embodiment, a bicycle race has been described as an example, but the present invention is not limited to this. For example, the present invention can be applied to automobile races such as rallies, and human races such as mountain marathons, and can also be applied to walking events other than races, such as mountain climbing, trekking, and hiking.

[0086] (2) In addition, the configuration of each processing function of the travel path estimation device, the processing procedure and processing content, the configuration of travel path information and its display method, etc. can be modified and implemented in various ways without departing from the spirit of this invention.

[0087] Although the embodiments of the present invention have been described in detail above, the above description is merely an example of the present invention in every respect. It goes without saying that various improvements and modifications can be made without departing from the scope of the present invention. In other words, when implementing the present invention, specific configurations according to the embodiments may be appropriately adopted.

[0088] In short, this invention is not limited to the above-described embodiments, and in the implementation stage, the components can be modified and embodied without departing from the spirit of the invention. Furthermore, various inventions can be formed by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be omitted from all the components shown in the embodiments. Furthermore, components from different embodiments may be appropriately combined.

[0089] SV...travel path estimation device BT1 to BTn...bicycle LG1 to LGn...GPS logger BB...bounding box 1...control unit 2...program storage unit 3...data storage unit 4...communication I / F unit 5...bus 11...travel data acquisition processing unit 12...average travel path calculation processing unit 13...initial travel path estimation processing unit 14...co-travel section calculation processing unit 15...intra-group travel position setting processing unit 16...travel path correction processing unit 31...travel path storage unit 32...average travel path storage unit 33...initial travel path storage unit 34...co-travel section information storage unit 35...bounding box pattern storage unit

Claims

1. A movement path estimation device that estimates movement paths of multiple users when the users move along a course from a start point to an end point, comprising: a first processing unit that acquires movement logs of multiple first users for which movement logs can be acquired among the multiple users; a second processing unit that calculates an average movement path of the multiple first users based on the acquired movement logs; a third processing unit that estimates an initial movement path of a second user for which movement logs cannot be acquired among the multiple users based on the calculated average movement path; a fourth processing unit that calculates a joint movement section in which the multiple first users moved closely together as a group within a preset time and distance range based on the movement logs of the first users; and a fifth processing unit that corrects the initial movement path of the second user that corresponds to the time of the joint movement section so as to approximate the movement path of the first user in the joint movement section.

2. The travel path estimation device of claim 1, further comprising a sixth processing unit that calculates a density based on the positions of multiple first users in the joint travel section, and sets a position where the density is less than a threshold as a position to which the travel path of the second user is corrected by the fifth processing unit.

3. A movement path estimation method for estimating movement paths of multiple users when the users move along a course from a start point to an end point using an information processing device, the movement path estimation method comprising the steps of: acquiring movement logs of multiple first users from among the multiple users whose movement logs can be acquired; calculating an average movement path of the multiple first users based on the acquired movement logs; estimating an initial movement path of a second user from among the multiple users whose movement log cannot be acquired based on the calculated average movement path; calculating a joint movement section along which the multiple first users move closely together as a group within a preset time and distance range based on the movement logs of the first users; and correcting the initial movement path of the second user whose time corresponds to the joint movement section so as to approximate the movement path of the first user in the joint movement section.

4. A program that causes a processor included in the travel path estimation device to execute at least one of the processes executed by each processing unit included in the travel path estimation device according to claim 1 or 2.

Images