Data generation system, data generation method, and program

Abstract

To provide a parking lot data generation system, a parking lot data generating method, and a program that are capable of appropriately generating parking lot data.SOLUTION: A system 100 according to an embodiment includes: a parking position acquisition unit that acquires parking position information indicating the parking positions of vehicles; a facility information acquisition unit that acquires facility information including a facility and its location information; a clustering unit that clusters the parking positions to generate clusters according to the density of parking positions; a parking lot range setting unit that sets a parking lot range based on the clusters; and a parking lot data generation unit that generates parking lot data in which the parking lot range is associated with the facility information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a data generation system, a data generation method, and a program.

Background Art

[0002] Patent Document 1 discloses a system for discriminating a facility where a vehicle can be parked. A terminal device measures the current position of the vehicle and transmits probe information including the current position to an information providing server. The information providing server discriminates a point where the vehicle stops for a predetermined time or more as a parking facility.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in Patent Document 1, there is a problem that information such as a parking lot is erroneously generated in an environment where large and small parking lots are mixed.

[0005] The present disclosure has been made in view of the above background, and provides a data generation system, a data generation method, and a program capable of appropriately generating data.

Means for Solving the Problems

[0006] The data generation system according to this embodiment may include a parking position acquisition unit that acquires moving body position information indicating the position of a moving body, a facility information acquisition unit that acquires facility information including a facility and its position information, a clustering unit that clusters the moving body positions in order to generate clusters according to the density of the moving body positions, a range setting unit that sets a range of the moving body based on the clusters, and a data generation unit that generates data in which the range is associated with the facility information.

[0007] In the above data generation system, the position acquisition unit acquires parking position information indicating the parking position of a vehicle in which the position acquisition unit is parked, the clustering unit clusters the parking positions, the range setting unit is a parking lot range setting unit that sets the parking lot range of the vehicle as the range of the vehicle, and the data generation unit is a parking lot data generation unit that generates parking lot data in which the parking lot range is associated with the facility information.

[0008] In the above data generation system, the clustering unit may generate clusters based on the density distribution of the parking positions.

[0009] In any of the above data generation systems, a location where the density of the parking positions is equal to or greater than a threshold value may be set as the parking lot range.

[0010] In any of the above data generation systems, the parking lot data generation unit may associate the parking lot range with the facility information based on the centroid of the cluster.

[0011] Any of the above data generation systems may further include a parking lot range database in which the parking lot ranges of known parking lots are registered, and the parking lot range database may be updated based on the parking lot data generated by the parking lot data generation unit.

[0012] In any of the above data generation systems, the facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time. The parking lot data generation unit may associate the parking lot range with the facility information based on the attribute information.

[0013] In any of the above data generation systems, the clustering unit may have a machine learning model that performs density-based clustering.

[0014] The data generation method according to this embodiment includes a step of acquiring moving body position information indicating the position of a moving body, a step of acquiring facility information including a facility and its position information, a step of clustering the moving body positions in order to generate clusters according to the density of the moving body positions, a step of setting a range of the moving body based on the clusters, and a step of generating data in which the range is associated with the facility information.

[0015] In the above data generation method, the moving body position information is parking position information indicating the parking position of a parked vehicle, the parking positions are clustered, a parking lot range of the vehicle is set as the range of the moving body, and parking lot data in which the parking lot range is associated with the facility information may be generated.

[0016] In the above data generation method, in the clustering, clusters may be generated based on the density distribution of the parking positions.

[0017] In any of the above data generation methods, the density of the parking positions may be set such that locations with a threshold value or higher are used as the parking lot range.

[0018] In any of the above data generation methods, the parking lot range and the facility information may be associated based on the centroid of the cluster.

[0019] In any of the above data generation methods, in any of the above programs, in the parking lot range database, the parking lot ranges of known parking lots are registered, and the parking lot range database may be updated based on the parking lot data.

[0020] In any of the above data generation methods, the facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time, and the parking lot range may be associated with the facility information based on the attribute information.

[0021] In any of the above data generation methods, the clusters may be generated using a machine learning model that performs density-based clustering.

[0022] The program according to this embodiment causes a computer to execute steps of acquiring moving body position information indicating the position of a moving body, acquiring facility information including a facility and its position information, clustering the moving body positions to generate clusters for generating a cluster corresponding to the density of the moving body positions, setting a range of the moving body based on the clusters, and generating parking lot data in which the range is associated with the facility information.

[0023] In the above program, the moving body position information is parking position information indicating the parking position of a parked vehicle, the parking positions are clustered, the parking lot range of the vehicle is set as the range of the moving body, and parking lot data in which the parking lot range is associated with the facility information may be generated.

[0024] In the above program, in the clustering, clusters may be generated based on the density distribution of the parking positions.

[0025] In any of the above programs, the parking lot range may be set at locations where the density of the parking positions is equal to or greater than a threshold value.

[0026] In any of the above programs, the parking lot range and the facility information may be associated based on the centroid of the cluster.

[0027] In any of the above programs, a parking lot range database stores the parking lot ranges of known parking lots, and the parking lot range database may be updated based on the parking lot data.

[0028] In any of the above programs, the facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time, and the parking lot range may be associated with the facility information based on the attribute information.

[0029] In any of the above programs, the cluster may be generated using a machine learning model that performs density-based clustering.

Advantages of the Invention

[0030] According to the present disclosure, it is possible to provide a data generation system, a data generation method, and a program that can appropriately generate data.

Brief Description of the Drawings

[0031]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0032] Hereinafter, the present invention will be described through embodiments of the invention. However, the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are necessarily essential as means for solving the problems. For the sake of clarity of explanation, the following description and drawings have been appropriately omitted and simplified. In each drawing, the same reference numerals are assigned to the same elements, and duplicate explanations are omitted as necessary.

[0033] Embodiment 1 FIG. 1 is a block diagram showing a system 100 according to Embodiment 1. The system 100 includes a vehicle position DB (database) 1, a facility position DB 2, a parking lot data generation device 3, and a parking lot DB 4.

[0034] The vehicle position DB 1 is a database that stores vehicle position information of a plurality of vehicles 7. The vehicle position information includes time-series data of the vehicle position indicated by latitude, longitude, etc. For example, in the vehicle position information, the vehicle position and the measurement time of the vehicle position are associated with each other. Further, the vehicle position information stores the vehicle position information for each vehicle. For example, in the vehicle position information, a vehicle ID unique to the vehicle is associated with the vehicle position. The vehicle position information may be acquired at regular time intervals for each vehicle.

[0035] For example, the vehicle 7 is provided with a probe 7a for measuring the vehicle position. As the probe 7a, for example, a positioning sensor of a global positioning system (GPS) or the like can be used. Alternatively, as a method for measuring the vehicle position, a position estimation method using a wireless device such as WiFi (registered trademark), Bluetooth (registered trademark), or a beacon may be used. In this case, the wireless device is used as the probe 7a. By combining the latitude and longitude of the wireless device and the relative vehicle position from the wireless device, the position of the vehicle can be converted into latitude and longitude. In this case, the probe 7a does not necessarily have to be mounted on the vehicle. That is, the probe 7a may be mounted on a wireless device or the like. Further, the probe 7a may detect vehicle information indicating the vehicle speed, whether the engine is on or off, and the like. That is, the vehicle position DB1 may store vehicle information indicating the vehicle type and the state of the vehicle. The probe 7a transmits vehicle position information indicating the vehicle position to the parking lot data generation device 3 or the like.

[0036] The vehicle position information may include information for specifying the vehicle position not only in a flat parking lot but also in an underground parking lot or a multi-story parking lot. For example, the altitude of the vehicle or the floor number of the parking lot may be included in the vehicle position information. Further, the acquisition frequency of the vehicle position only needs to include position information before and after parking, but may also include information during driving. If position information during driving is obtained, it can be used to correct the position at the time of parking. Of course, the positioning device such as GPS is not limited to an in-vehicle device. For example, a mobile terminal such as a smartphone possessed by a driver or a passenger may measure the vehicle position.

[0037] Note that the parking lot data generation device 3 may acquire vehicle position information from a plurality of vehicles 7 and accumulate it in the vehicle position DB1. Alternatively, a device different from the parking lot data generation device 3 may acquire the vehicle position information and accumulate it in the vehicle position DB1.

[0038] The facility location DB2 is a database that stores facility location information indicating the locations of facilities. For example, in the facility location DB2, the location of each facility is saved as a list. The facility location DB2 includes location information (coordinates) indicated by latitude, longitude, etc. for each facility. Here, examples of facilities include buildings or places with parking lots. Also, the facility may be a facility without a building, such as a park. The facility may be a public facility or a private facility. Also, the facility is not limited to a permanently installed facility and may be a facility installed for a limited period. Also, the facility is not limited to parking lots such as public parking lots and private parking lots, and may include houses, stores, offices, etc. The facility location DB2 stores information regarding facilities with attached parking lots.

[0039] The parking lot data generation device 3 generates parking lot data by referring to the vehicle location DB1 and the facility location DB2. That is, the parking lot data generation device 3 generates parking lot data based on the vehicle location information and the facility location information. The parking lot data generation device 3 records the generated parking lot data in the parking lot DB4. Therefore, the parking lot DB4 stores parking lot data that associates facilities with their parking lots.

[0040] The parking lot data generation device 3 will be described. The parking lot data generation device 3 includes a vehicle location acquisition unit 30, a parking location acquisition unit 31, a facility information acquisition unit 32, a clustering unit 33, a parking lot range setting unit 34, and a parking lot data generation unit 35.

[0041] The vehicle location acquisition unit 30 acquires vehicle location information from the vehicle location DB1. Alternatively, the vehicle location acquisition unit 30 may directly acquire the vehicle location from the probe 7a. Also, the user can specify the period, region, etc. of the vehicle location information to be acquired. For example, the user can specify the region and period for which the vehicle location information is to be acquired. The vehicle location acquisition unit 30 can extract and read the vehicle location information for the specified period in the specified region.

[0042] The parking position acquisition unit 31 acquires parking position information indicating the parking position of the vehicle 7 based on the vehicle position information acquired by the vehicle position acquisition unit 30. For example, when the vehicle 7 is at the same position for a predetermined time or longer, the parking position acquisition unit 31 sets that position as the parking position. The parking position information may include not only the parking position but also information such as the parking time, parking date and time, and vehicle type.

[0043] Alternatively, the parking position acquisition unit 31 may acquire vehicle information from the vehicle 7 and set the parking position based on the vehicle information. The parking position acquisition unit 31 extracts the parking positions of a plurality of vehicles. Thereby, information indicating a plurality of parking positions on the map is generated. That is, a distribution map in which a data distribution with one parking position as one data point is shown on the map is generated.

[0044] The vehicle information is, for example, information such as vehicle speed, engine on / off, and vehicle ID. Specifically, the parking position acquisition unit 31 can set the vehicle position when the engine is off as the parking position. Alternatively, the parking position acquisition unit 31 may set the vehicle position as the parking position when the speed is 0 km / h and a certain time has elapsed.

[0045] The facility information acquisition unit 32 reads facility position information from the facility position DB 2. The facility position information is information indicating the position of each facility.

[0046] The clustering unit 33 clusters the parking positions to generate clusters. The clustering unit 33 clusters the parking positions in order to generate clusters according to the density of the parking positions. For example, the parking positions are represented by coordinates of latitude and longitude. The clustering unit 33 performs clustering based on the density of the parking positions. The clustering unit 33 can perform clustering using a machine learning model generated by a machine learning method such as unsupervised learning. Also, the machine learning model may be generated using deep learning or the like. The clustering unit 33 may perform non-hierarchical clustering.

[0047] For example, the clustering unit 33 performs clustering based on the density of data points with the parking positions as the data points. The clustering unit 33 detects a region where areas with dense data points are separated from areas with sparse data points as one cluster. The clustering unit 33 can generate clusters based on the density distribution of parking positions. Areas with a high density of parking positions become clusters. For example, the clustering unit 33 has a machine learning model generated using an unsupervised machine learning clustering algorithm. The clustering unit 33 has a machine learning model that performs density-based clustering.

[0048] As density-based clustering, methods such as OPTICS (ordering points to identify the clustering structure) and DBSCAN (Density-based spatial clustering of applications with noise) can be used. For the clustering unit 33, the number of data points within a predetermined search distance (radius) is obtained. When the number of data points is equal to or greater than a predetermined value, the range of the cluster is expanded. As the distance used for clustering, the Euclidean distance or the like can be used. Of course, the clustering unit 33 may perform density-conforming clustering by other methods. For example, the clustering unit 33 can perform clustering using the mean-shift method. In this case, the clustering unit 33 obtains the maximum points of density. Then, the clustering unit 33 sets a range that includes the maximum points and has a density equal to or greater than a threshold value as one cluster. That is, positions with a density less than the threshold value are excluded from the cluster.

[0049] The parking lot range setting unit 34 sets the parking lot range based on the clusters. Each cluster corresponds to a parking lot, and the size of the cluster indicates the parking lot range. The parking lot range setting unit 34 sets the region defined by the cluster as the parking lot range. That is, the boundary of the cluster becomes the boundary of the parking lot range.

[0050] Specifically, an area with dense data points becomes a cluster indicating a parking available range, and an area with sparse data points indicates a non-parking available range. The parking lot range setting unit 34 sets a dense area where the density of data points is equal to or greater than a threshold value as the parking lot range. The parking lot range setting unit 34 sets a location where the density of the parking position is equal to or greater than the threshold value as the parking lot range. The parking lot range setting unit 34 sets an area defined by one cluster as one parking lot range. More specifically, the parking lot range setting unit 34 sets a continuous range where the density of data points is equal to or greater than the threshold value as one parking lot range.

[0051] The parking lot data generation unit 35 generates parking lot data by associating the parking lot range with the facility information. For example, the parking lot data generation unit 35 identifies the cluster closest to the facility. Then, the parking lot data generation unit 35 associates the parking lot range indicated by the cluster closest to the facility with that facility. Since the parking lot data generation unit 35 can associate the parking lot range of the nearest parking lot for each facility, it can appropriately generate parking lot data. For example, the parking lot data generation unit 35 can associate the parking lot range and the facility information based on the centroid of the cluster. That is, the parking lot data generation unit 35 extracts the parking lot range closest to the facility with the centroid position of the cluster as the position of the parking lot range.

[0052] Note that there may be a plurality of parking lots provided separately for one facility. Therefore, the parking lot data generation unit 35 may associate a plurality of parking lot ranges with one facility. Alternatively, a plurality of facilities may share a parking lot. One parking lot range may be associated with a plurality of facilities.

[0053] The generation process of the parking lot data will be described with reference to FIG. 2. FIG. 2 is a plan view showing an example where there are three facilities A to C along the road R. The facility A includes a building BA and a parking lot PA. That is, a parking lot PA is attached to the building BA of the facility A. Similarly, the facility B includes a building BB and a parking lot PB, and the facility C includes a building BC and a parking lot PC. A parking lot PB is attached to the building BB of the facility B, and a parking lot PC is attached to the building BC of the facility C.

[0054] When associating the closest facility for each parking position, the parking lots of facilities A, B, and C are set in areas P1 to P3 divided by the dividing line D. That is, area P1 divided by the dividing line D is associated with facility A. Similarly, area P2 divided by the dividing line D is associated with facility B, and area P3 divided by the dividing line D is associated with facility C. Parking lot PA is included in area P3. Therefore, when associating the closest facility for each parking position, there is a possibility that the facilities and the parking lots cannot be appropriately associated. For example, in area P3 corresponding to facility C, both parking lot PA and parking lot PC are included.

[0055] Thus, when the method of this embodiment is not used, it becomes impossible to set an appropriate parking lot range for each facility. In a situation where parking lots of different sizes are adjacent, for example, among the parking positions in a large parking lot, it may occur that the center point of the surrounding parking lot is closer to a certain parking position than the center point of that parking lot. In such a situation, when linking the closest parking position and the facility, an incorrect parking lot range is calculated.

[0056] In this embodiment, the parking lot range setting unit 34 sets the parking lot range based on the cluster. Therefore, the parking lots PA to PC in FIG. 2 are set as different parking lot ranges. The parking lot data generation unit 35 associates each of these parking lot ranges with the facility. The parking lot data generation unit 35 can associate parking lots PA to PC with facilities A to C respectively. Therefore, it becomes possible to generate appropriate parking lot data.

[0057] For example, the clustering unit 33 determines a lump with a parking position density of a certain level or more as a cluster. At the boundary between parking lots and roads R and the like, the density of parking positions is low and it is not determined as a parking available range. Clusters are generated by dividing for each parking lot. Therefore, the correct facility can be associated with each parking lot, and it is possible to prevent the parking lot range from deviating from the actual parking lot.

[0058] In addition, the parking positions extracted from the vehicle position information may include noise points deviated from the accurate positions due to various factors. For example, the parking position data includes noise due to GPS errors at the time of vehicle position recording, specifications of the collection device serving as the probe 7a, etc. Or, when the vehicle 7 stops on the road due to a breakdown or the like, the presence of data not assumed at the time of parking position extraction becomes noise. Such noise is likely to deviate from the area where the parking positions have a certain density or higher. Since the parking positions with noise have a low density, they are not included in the cluster. Therefore, it is possible to regard the parking positions not included in the cluster as noise and remove them. Thereby, appropriate parking lot data can be generated.

[0059] Next, with reference to FIG. 3, a parking lot data generation method according to the present embodiment will be described. FIG. 3 is a flowchart showing the parking lot data generation method.

[0060] First, the vehicle position acquisition unit 30 acquires vehicle position information from the vehicle position DB 1 (S101). For example, the vehicle position acquisition unit 30 reads out the vehicle position information in a certain area from the vehicle position DB 1 for a certain period. The user can specify the area where the user wants to generate the parking lot data. The user can also specify a period such as one month. The vehicle position acquisition unit 30 extracts the vehicle position information in the specified area and the specified period. Further, vehicle information indicating the vehicle type, vehicle speed, on / off state of the engine, etc. may be added to the vehicle position information.

[0061] The facility information acquisition unit 32 acquires the facility position from the facility position DB 2 (S102). The facility information acquisition unit 32 may acquire the facility position in the specified area specified in S101.

[0062] The parking position acquisition unit 31 extracts the parking position from the vehicle position information (S103). For example, when the vehicle position remains within a certain range for a certain time or longer, the parking position acquisition unit 31 can regard that position as the parking position. By doing so, the parking position acquisition unit 31 can acquire parking position information indicating the parking position.

[0063] Furthermore, the parking position acquisition unit 31 may extract the parking position using vehicle information. The parking position acquisition unit 31 can extract the parking position more accurately by using vehicle speed and engine on / off information. That is, the parking position acquisition unit 31 may add extraction conditions according to the vehicle information. For example, the parking position acquisition unit 31 may extract the parking position with the position where the engine on / off is switched as the extraction condition. Alternatively, the parking position acquisition unit 31 may extract the parking position with conditions such as the vehicle speed being below a certain speed as the extraction condition. In other words, the parking position acquisition unit 31 may exclude positions where the engine on / off cannot be switched or positions where the vehicle speed is above a certain level from the parking position.

[0064] The clustering unit 33 clusters the parking positions in order to generate clusters according to the density of the parking positions (S104). By performing density-based clustering, the clustering unit 33 can generate appropriate clusters. Areas with a density equal to or higher than the threshold are grouped as clusters. Areas with a density lower than the threshold are excluded from the clusters. For example, the density at a specific parking position can be obtained based on the number of parking positions within a certain distance from that specific parking position. Using a density-based clustering method, parking positions with a density equal to or higher than a certain density are connected starting from a certain parking position. Then, the clustering unit 33 sets the connected parking positions as clusters.

[0065] The density threshold can be set considering regional characteristics and the number of vehicles included in the probe data. The clustering unit 33 can obtain areas with a density equal to or higher than the threshold using, for example, a density-based clustering method. Specifically, parking positions with a density equal to or higher than a certain density are connected starting from a certain parking position, and the connected parking positions are set as clusters. By doing so, the clustering unit 33 can generate clusters for each parking lot.

[0066] The parking lot range setting unit 34 sets the parking lot range based on the clusters (S105). Since the area where the density is equal to or higher than the threshold value is set as a cluster, the parking lot range setting unit 34 sets one cluster as one parking lot range. The parking lot range is position information indicating the range of the parking lot where the vehicle 7 can park.

[0067] The parking lot data generation unit 35 associates the parking lot range with the existing facilities (S106). That is, the parking lot data generation unit 35 associates the parking lot range for each facility read from the facility location DB 2. The parking lot data generation unit 35 generates parking lot data in which the facility and the parking lot range are associated. The parking lot data generated by the parking lot data generation unit 35 is stored in the parking lot DB 4. The parking lot data generation unit 35 associates the one with the minimum distance between the location of the facility and the centroid of the cluster. According to the regional characteristics, facilities and parking lot ranges that are separated by a certain distance or more may not be associated.

[0068] Furthermore, the parking lot data generation unit 35 registers, in the parking lot DB 4, the parking lot that could not be associated with the facility as a new parking lot (S107). By doing so, it is possible to generate parking lot data regarding the parking lot that is not associated with the existing facility. Even when a new parking lot is established, the parking lot data can be appropriately generated.

[0069] By doing so, even in an area where parking lots of different sizes are adjacent, the parking lot data generation device 3 can associate the parking position with the correct parking lot. The parking lot data generation device 3 regards the area where the parking position has a density equal to or higher than a certain level as the parking lot range. Therefore, errors due to position information noise from GPS or data collection devices and insufficient accuracy of the facility location DB 2 can be appropriately removed as noise. Therefore, parking lot data can be generated with higher accuracy. In addition, during disasters such as earthquakes, the use of parking lots may be restricted. Alternatively, for restoration purposes, spaces other than existing parking lots may be newly used as parking lots. Even in such cases, appropriate parking lot data can be generated promptly, contributing to disaster recovery.

[0070] Embodiment 2 The parking lot data generation system and method according to Embodiment 2 will be described with reference to FIGS. 4 and 5. FIG. 4 is a block diagram showing the system configuration. FIG. 5 is a flowchart showing the parking lot data generation method.

[0071] In this embodiment, a parking lot range DB5 is added to the system 100. Since the configurations other than the parking lot range DB5 are the same as those in Embodiment 1, the description thereof will be omitted.

[0072] The parking lot range DB5 is a database that stores the parking lot ranges of known parking lots. The parking lot range is position data indicating the parking area where vehicles can park in the parking lot. The parking lot range DB5 stores data in which the parking lot range is associated with each parking lot. For example, the known parking lot range may be data automatically created by a computer or data manually created by a user or administrator. Also, the parking lot range may be data partially created automatically and the rest created manually.

[0073] For example, a user or a computer, etc., detects the parking lot position based on satellite images and sets the parking lot range. Alternatively, the parking lot range DB5 may store the parking lot range shown in the parking lot data stored in the parking lot DB4. That is, the parking lot range DB5 may store the parking lot range of the parking lot data generated in the past. The parking lot range of the parking lot range DB5 is updated with the latest information. Since the parking lot range DB5 stores data indicating the parking lot range for some parking lot data in advance, the accuracy can be further improved by using it for parking lot range determination.

[0074] In FIG. 5, step S206 is added to the flowchart of FIG. 3. Since the processing other than step S206 is basically the same as that in the first embodiment, the description will be omitted as appropriate. For example, steps S101 to S107 in FIG. 3 correspond to steps S201 to S205 and steps S207 to S208 respectively.

[0075] In step S205, the parking lot range setting unit 34 sets the parking lot range. Then, the parking lot data generation unit 35 uses the parking lot range newly set in step S205 as a range candidate. And the parking lot data generation unit 35 corrects the range candidate with the known parking lot range (S206). For example, when the known parking lot range and the range candidate overlap, the parking lot data generation unit 35 corrects both ranges as one parking lot range. When the known parking lot range and the range candidate partially overlap, the range obtained by merging the known parking lot range and the range candidate becomes the parking lot range. Also, when one range candidate overlaps with two known parking lot ranges, the parking lot data generation unit 35 may divide the range candidate with the two known parking lot ranges.

[0076] The parking lot data generation unit 35 associates the known facility with the corrected parking lot range (S207). And based on the parking lot range not associated with the known facility, new parking lot data is registered.

[0077] Furthermore, based on the parking lot range corrected in S206, the parking lot data generation unit 35 may update the parking lot DB4 or the parking lot range DB5. By doing so, a highly accurate database can be generated based on the latest parking lot data and parking lot range. Also, in FIG. 4, the parking lot range DB5 and the parking lot DB4 are shown as separate databases, but the parking lot range DB5 and the parking lot DB4 may be constructed as a common database.

[0078] Embodiment 3 The system and method according to Embodiment 3 will be described with reference to FIGS. 6 and 7. FIG. 6 is a block diagram showing the system configuration. FIG. 7 is a flowchart showing a method for generating parking lot data.

[0079] In this embodiment, a facility attribute DB 6 is added to the system 100. Since the configurations other than the facility attribute DB 6 are the same as those in Embodiment 1, the description thereof will be omitted. The facility attribute DB 6 stores attribute information indicating the attributes of facilities. For example, the attribute information may include data indicating the facility genre such as whether the facility is a residential facility, a commercial facility, a public facility, or a private facility, or the attribute information may include data indicating the facility scale such as the floor area and the outer shape area of the facility. Further, the attribute information may include information such as the number of available users, the available period, the available time zone, the parking time, the available parking time zone, the available vehicle types, and the usage frequency per month.

[0080] In FIG. 7, the processes of steps S302 and S306 are different from those in the flowchart of FIG. 3. Since the processes other than steps S302 and S306 are basically the same as those in Embodiment 1, the description thereof will be omitted as appropriate. For example, steps S101, S103 to S105, and S107 in FIG. 3 correspond to steps S301, S303 to S305, and S307, respectively.

[0081] In step S302, the facility information acquisition unit 32 acquires facility information. In this embodiment, the facility information includes the facility location and the attribute information. That is, the facility information acquisition unit 32 reads the attribute information from the facility attribute DB 6 as the facility information. The attribute information preferably includes at least one of the size of the facility, the genre of the facility, and the available time.

[0082] In step S306, the parking lot range is associated with the facility using the attribute information. For example, the number of parking spaces can be estimated according to the scale of the facility. Therefore, a parking lot range suitable for the scale of the facility can be associated. For example, when the nearest parking lot range is too large or too small for the facility scale, the second nearest parking lot range is assigned.

[0083] The parking lot data generation unit 35 can compare the attribute information with the parking lot range and associate the parking lot range with the facility based on the comparison result. The parking lot data generation unit 35 calculates an index indicating the degree of match based on the comparison result between the facility scale and the area of the parking lot range. Then, in addition to the distance between the facility and the parking lot range, the parking lot data generation unit 35 associates the parking lot range with the facility in consideration of the index corresponding to the comparison result. Specifically, the parking lot data generation unit 35 appropriately weights the distance and the index and assigns the parking lot with the highest degree of match to the facility. Of course, the comparison between the attribute information and the parking lot range is not limited to only the facility scale. For example, the parking lot data generation unit 35 may compare using the number of users, vehicle types, usage time bands, parking time, usage frequency, etc. The parking lot data generation unit 35 performs the comparison using various attribute information. The parking lot data generation unit 35 weights and adds a plurality of indexes corresponding to the comparison result and calculates the degree of match for each parking lot. Furthermore, the degree of match may be indexed according to the regional characteristics.

[0084] Note that although the facility attribute DB6 is shown as a database different from the facility location DB2, the facility attribute DB6 may be constructed as the same database as the facility location DB2. It is also possible to use a combination of Embodiment 2 and Embodiment 3. In this case, the system 100 includes both the parking lot range DB5 and the facility attribute DB6. After the parking lot data generation unit 35 corrects the parking lot range using the known parking lot range, the parking lot range may be associated with the facility.

[0085] Note that the system 100 and the parking lot data generation device 3 may be implemented by a single device or may be distributed among multiple devices. For example, the system 100 may be a physically single device including the parking lot data generation device 3 and each database. Alternatively, at least one database and the parking lot data generation device 3 may be mounted on physically different devices. For example, a parking lot data generation system and method may be realized by a plurality of information processing devices connected to a network performing distributed processing. For example, part of the processing of each functional block may be executed by the same device and the rest may be executed by other devices. For example, the processing up to the extraction of the parking position and the processing after clustering may be performed by different devices. Also, the parking lot data generation device 3 may be referred to as a parking lot data generation system.

[0086] In the above description, parking position information indicating the parking position of a vehicle is used as the moving body position information indicating the position of the moving body, but the moving body position information may include information other than the parking position information of the vehicle. For example, the moving body position information indicating the position of the moving body may include the position where a moving body such as a vehicle temporarily stays or the position where it temporarily stops. The moving body position information may be a boarding and alighting position indicating the position where passengers board and alight from a moving body moving at a low speed.

[0087] More specifically, for example, at a boarding and alighting area, passengers can board and alight from a sharing vehicle or the like moving at a low speed. That is, the present embodiment can also be used for a moving body that can be boarded and alighted without completely stopping. The system 100 may specify the range of such a boarding area based on the clustered moving body positions. The system 100 performs clustering based on such moving body positions including the boarding and alighting position, the parking position, the stopping position, etc. The system sets the range of the moving body indicating the boarding and alighting area, the parking lot, the stopping area, etc. based on the cluster. Then, the system associates the range of the moving body with the facility information. By doing so, the system can generate data in which the ranges such as the boarding and alighting area and the parking lot are associated with the facility.

[0088] The system according to this embodiment includes a position acquisition unit that acquires mobile object position information indicating the position of a mobile object, a facility information acquisition unit that acquires facility information including a facility and its position information, a clustering unit that clusters the mobile object positions to generate clusters according to the density of the mobile object positions, a range setting unit that sets a range of the mobile object based on the clusters, and a data generation unit that generates data in which the range is associated with the facility information.

[0089] The method according to this embodiment includes a step of acquiring mobile object position information indicating the position of a mobile object, a step of acquiring facility information including a facility and its position information, a step of clustering the mobile object positions to generate clusters according to the density of the mobile object positions, a step of setting a range of the mobile object based on the clusters, and a step of generating data in which the range is associated with the facility information.

[0090] In addition, part or all of the above-described generation method can be realized by a computer program. The program can be stored using various types of non-transitory computer readable media and supplied to a computer. Non-transitory computer readable media include various types of tangible storage media. Non-transitory computer readable media include, for example, magnetic recording media, magneto-optical recording media, CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memories. Magnetic recording media include, for example, flexible disks, magnetic tapes, and hard disk drives. Magneto-optical recording media include, for example, magneto-optical disks. Semiconductor memories include, for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (Random Access Memory). Also, the program may be supplied to a computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable media can supply the program to a computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

Explanation of Signs

[0091] 100 System 1 Vehicle Position DB 2 Facility Position DB 3 Parking Lot Data Generation Device 4 Parking Lot DB 5 Parking Lot Range DB 6 Facility Attribute DB 7 Vehicle 7a Probe 30 Vehicle Position Acquisition Unit 31 Parking Position Acquisition Unit 32 Facility Information Acquisition Unit 33 Clustering Unit 34 Parking lot range setting unit 35 Parking lot data generation unit

Claims

1. A position acquisition unit that acquires moving body position information indicating the positions of a plurality of moving bodies, a facility information acquisition unit that acquires facility information including a facility equipped with a parking lot and its position information, a clustering unit that clusters the parking positions in order to generate a cluster according to the density of the parking positions of the moving bodies, a parking lot range setting unit that sets a parking lot range for the moving bodies based on the cluster, a parking lot data generation unit that generates parking lot data in which the parking lot range is associated with the facility information, and sets the moving body position when the moving body position of the moving body is the same for a certain period of time or more as the parking position, the clustering unit generates the cluster based on the density distribution of the parking positions, sets a range where the density of the data points indicating the parking positions is continuous and equal to or greater than a threshold value as the parking lot range, the facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time, the parking lot data generation unit calculates the distance between the position of the facility indicated by the facility information and the center of gravity of the cluster, compares the attribute information with the parking lot range, and associates the parking lot range with the facility information according to the comparison result and the distance, a data generation system.

2. Extracts the parking lot range closest to the facility based on the distance, compares the size of the facility indicated by the former attribute information with the size of the closest parking lot range, and if the closest parking lot range is too large or too small for the scale of the facility, assigns the second closest parking lot range to the facility. The data generation system according to claim 1.

3. The position acquisition unit acquires parking position information including the parking position and the parking date and time, performs a comparison using the usage time zone of the parking lot, and associates the parking lot range with the facility. The data generation system according to claim 1 or 2.

4. further includes a parking lot range database in which the parking lot ranges of known parking lots are registered, the parking lot range database is updated based on the parking lot data generated by the parking lot data generation unit. The data generation system according to claim 1 or 2.

5. The clustering unit has a machine learning model that performs density-based clustering. The data generation system according to claim 1 or 2.

6. A computer, A step of obtaining moving body position information indicating the positions of a plurality of moving bodies; A step of obtaining facility information including a facility with a parking lot attached and its position information; A step of clustering the parking positions in order to generate a cluster according to the density of the parking positions of the moving bodies; A step of setting a parking lot range for the moving body based on the cluster; A step of generating parking lot data in which the parking lot range is associated with the facility information, comprising: When the moving body position of the moving body is the same for a certain period of time or more, setting the moving body position as a parking position; Generating the cluster based on the density distribution of the parking positions; Setting a range where the density of data points indicating the parking positions is continuous and equal to or greater than a threshold value as the parking lot range; The facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time; Calculating the distance between the position of the facility indicated by the facility information and the centroid of the cluster; Comparing the attribute information with the parking lot range, and associating the parking lot range with the facility information according to the comparison result and the distance; A data generation method.

7. Extracting the parking lot range closest to the facility based on the distance, Comparing the size of the facility indicated by the former attribute information with the size of the closest parking lot range, and when the closest parking lot range is too large or too small for the scale of the facility, allocating the second closest parking lot range to the facility. The data generation method according to claim 6.

8. Obtaining parking position information including the parking position and the parking date and time, Performing a comparison using the usage time zone of the parking lot, and associating the parking lot range with the facility. The data generation method according to claim 6 or 7.

9. In the parking lot range database, the parking lot ranges of known parking lots are registered, The parking lot range database is updated based on the parking lot data. The data generation method according to claim 6 or 7.

10. The cluster is generated using a machine learning model that performs density-based clustering. The data generation method according to claim 6 or 7.

11. For a computer, A step of obtaining moving body position information indicating the positions of a plurality of moving bodies; A step of obtaining facility information including a facility with a parking lot attached and its position information; To generate a cluster according to the density of the parking positions of the moving body positions, a step of clustering the parking positions; Based on the cluster, a step of setting a parking lot range of the moving body; Executing a step of generating parking lot data in which the parking lot range is associated with the facility information; When the moving body position of the moving body is the same for a certain period of time or more, setting the moving body position as a parking position; Generating the cluster based on the density distribution of the parking positions; Setting, as a parking lot range, a range in which the density of data points indicating the parking positions is continuous and equal to or greater than a threshold value; The facility information has attribute information including at least one of the size of the facility, the genre of the facility, and the available time; Calculating the distance between the position of the facility indicated by the facility information and the center of gravity of the cluster; Comparing the attribute information with the parking lot range, and associating the parking lot range with the facility information according to the comparison result and the distance; Program.

12. Extracting the parking lot range closest to the facility based on the distance; Comparing the size of the facility indicated by the pre-attribute information with the size of the closest parking lot range, and if the closest parking lot range is too large or too small for the scale of the facility, assigning the second closest parking lot range to the facility. The program according to claim 11.

13. Obtaining parking position information including the parking position and the parking date and time; Performing comparison using the usage time zone of the parking lot, and associating the parking lot range with the facility. The program according to claim 11 or 12.

14. In the parking lot range database, the parking lot ranges of known parking lots are registered; The program according to claim 11 or 12, wherein the parking lot range database is updated based on the parking lot data.

15. The program according to claim 11 or 12, wherein the cluster is generated using a machine learning model that performs density-based clustering.

Images