Inter-area movement flow generation device, inter-area movement flow generation method, and inter-area movement flow generation program

Abstract

To provide a technique capable of offering information for avoiding congestion by classifying buildings including facilities and grasping how people move with respect to the classified buildings.SOLUTION: An inter-area movement flow generation device according to an embodiment comprises: an information acquisition unit that acquires map information corresponding to an area for which congestion forecasts are generated and position information of users staying in the area; a statistical data generation unit that determines to which building included in the map information the user belongs and generates statistical data for each building; a clustering control unit that performs clustering to classify the buildings into a predetermined number of clusters on the basis of the statistical data; an analysis control unit that generates sequence patterns indicating how users moved between the clusters on the basis of the position information; and an output control unit that outputs the sequence patterns.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to an inter-area movement flow generation device, an inter-area movement flow generation method, and an inter-area movement flow generation program. [Background technology]

[0002] In urban development, the control of travel demand by people visiting stations or cities is being considered in order to revitalize the areas around stations or the city itself. The background to this is that securing resources to meet peak demand places a heavy burden on facilities and transportation that tend to be congested. On the other hand, facilities and transportation with few users face the problem of low sales efficiency. For example, one-day passes have a flat rate that assumes an average amount of travel. Furthermore, planning how to use one-day passes to travel efficiently between multiple facilities using transportation is left to individual research.

[0003] Stamp rallies and other events provide incentives for visiting multiple facilities, but the goal is to collect stamps, and they have little impact on surrounding facilities. Also, if coupons are issued for each commercial facility, they are considered an individual service for the facility, and the impact on the area surrounding the facility is limited. Furthermore, if it is assumed that people will visit commercial facilities by car, parking spaces must be secured according to the size of the facility, which increases costs.

[0004] For example, Patent Document 1 proposes a technology that identifies the congestion level using a mesh area for each time period from the departure station to the arrival station, and displays the congestion level at the departure station or arrival station for each time period using the mesh. Also, Patent Document 2 proposes a technology that stores the congestion adjustment policy of an operator and the behavioral patterns of users, identifies corresponding services from the behavioral patterns of users, and generates guidance information that promotes or avoids the use of the services that are subject to adjustment based on the congestion adjustment policy. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2022-045243 [Patent Document 2] Japanese Patent Publication No. 2022-187210 Summary of the Invention [Problem to be solved by the invention]

[0006] For example, Patent Document 1 can measure the congestion level for each mesh, but has the problem of not taking into account how people actually move. Also, Patent Document 2 does not collect behavioral patterns using people's travel purposes, so there is a problem that the information is insufficient to promote or avoid use of the target for adjustment.

[0007] This invention was made in light of the above circumstances, and its purpose is to provide a technology that can provide information to avoid congestion by classifying buildings, including facilities, and understanding how people move around the classified buildings. [Means for solving the problem]

[0008] An inter-area movement flow generation device according to an embodiment includes an information acquisition unit that acquires map information corresponding to an area for which a congestion forecast is to be generated and location information of users staying in the area; a statistical data generation unit that determines to which building included in the map information the user belongs and generates statistical data for each building; a clustering control unit that performs clustering to classify the buildings into a predetermined number of clusters based on the statistical data; an analysis control unit that generates sequential patterns that indicate how the users moved between the clusters based on the location information; and an output control unit that outputs the sequential patterns. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing an example of the hardware configuration and software configuration of an inter-area movement flow generation device according to this embodiment. [Figure 2] FIG. 2 is a sequence diagram showing an example of a congestion forecast generation procedure performed by the inter-area movement flow generation device according to this embodiment. [Figure 3] FIG. 3 is a diagram showing an example of map information acquired by the information acquisition unit according to the present embodiment. [Figure 4] FIG. 4 is a diagram showing an example of buildings included in the map information according to this embodiment. [Figure 5] FIG. 5 is a diagram showing an example of statistical data generated for each building according to this embodiment. [Figure 6] FIG. 6 is a diagram showing an example in which the buildings included in the map information of FIG. 2 are classified into seven clusters. [Figure 7] FIG. 7 is a diagram showing an example in which buildings included in map information are classified into a predetermined number of clusters. [Figure 8] FIG. 8 shows an example of an integrated sequential pattern generated by integrating a cluster with an extracted sequential pattern by the analysis control unit. [Figure 9] FIG. 9 is a diagram showing an example of an integrated sequential pattern generated using some of the clusters. [Figure 10] FIG. 10 is a diagram showing an example of a sequence pattern integrated by age group. [Figure 11] FIG. 11 is a diagram showing an example of an integrated sequential pattern generated using user attribute information. [Figure 12] FIG. 12 is a diagram showing an example of a combination of congestion forecasts and integrated sequence patterns. DETAILED DESCRIPTION OF THE INVENTION

[0010] The inter-area movement flow generation device, inter-area movement flow generation method, and inter-area movement flow generation program will be described in detail below with reference to the drawings. Note that in the following embodiments, parts with the same numbers perform similar operations, and redundant description will be omitted. For example, when there are multiple identical or similar elements, a common symbol may be used to describe each element without distinguishing between them, or a sub-number may be used in addition to the common symbol to describe each element with distinction between them.

[0011] [Embodiment] (composition) FIG. 1 is a block diagram showing an example of the hardware configuration and software configuration of an inter-area movement flow generation device according to this embodiment. 1, the inter-area movement flow generation device 1 includes a control unit 11, a program storage unit 12, a data storage unit 13, a communication interface 14, and an input / output interface 15. The input / output interface 15 is connected to an input unit 151 and an output unit 152.

[0012] The inter-area travel flow generation device 1 is configured with one or more computers. The inter-area travel flow generation device 1 is installed at a predetermined location of a business operator that manages a facility.

[0013] The control unit 11 controls the inter-area movement flow generation device 1. The control unit 11 includes a hardware processor such as a central processing unit (CPU).

[0014] The program storage unit 12 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 control processes according to this embodiment. Hereinafter, the OS and each application program will be collectively referred to as the program.

[0015] The data storage unit 13 may be, for example, a combination of a nonvolatile memory such as an SSD that can be written to and read from at any time, and a volatile memory such as a RAM (Random Access Memory), as a storage medium.

[0016] The communication interface 14 includes one or more wired or wireless communication modules. For example, the communication interface 14 includes a communication module that connects, via wire or wireless, to an external device installed outside the inter-area movement flow generation device 1, either directly or via a network. For example, the communication interface 14 includes a communication module that connects, via a network, to a terminal carried by a user who visits a specific area, via wire or wireless. Here, the terminal may be a mobile terminal (e.g., a smartphone, a wearable terminal, etc.). In other words, the communication interface 14 may be any general communication interface as long as it can communicate with external devices, including terminals carried by users, and send and receive various information under the control of the control unit 11.

[0017] The input / output interface 15 is connected to the input unit 151, the output unit 152, etc. The input / output interface 15 is an interface that enables transmission and reception of information between the control unit 11 and the input unit 151 and the output unit 152. The input / output interface 15 may be integrated with the communication interface 14. For example, the input / output interface 15 may be wirelessly connected to the control unit 11 and the input unit 151 or the output unit 152 using short-range wireless technology or the like, and may transmit and receive information using the short-range wireless technology.

[0018] The input unit 151 includes, for example, a keyboard, a pointing device, etc., which are used by an administrator who manages the inter-area movement flow generation device 1 to input various information to the inter-area movement flow generation device 1. The input unit 151 may also include a reader for reading data to be stored in the program storage unit 12 or the data storage unit 13 from a memory medium such as a USB memory, or a disk device for reading such data from a disk medium.

[0019] The output unit 152 includes a display that displays output data to be presented to the manager from the inter-area movement flow generation device 1, a printer that prints the data, and the like.

[0020] Next, the software configuration of the inter-area movement flow generation device 1 will be described in detail. The control unit 11 includes an information acquisition unit 111, a statistical data generation unit 112, a clustering control unit 113, an analysis control unit 114, a congestion forecast control unit 115, and an output control unit .

[0021] The information acquisition unit 111 accesses the network via the communication interface 14 and acquires map information corresponding to the area for which a congestion forecast is to be generated, and location information of users who are or have been present in the map information. Details of the acquired map information and location information will be described later. Furthermore, the information acquisition unit 111 accesses the network via the communication interface 14 and acquires a congestion forecast for the area corresponding to the map information. For example, the congestion forecast may be mesh-like congestion information that divides a map into meshes and indicates the degree of congestion. In other words, the congestion forecast may be general information that can be acquired via the network.

[0022] The statistical data generation unit 112 generates statistical data based on map information and location information. Here, the statistical data is data indicating the number of visitors to each building at each predetermined time. The method for generating the statistical data will be described in detail later.

[0023] The clustering control unit 113 performs clustering on the statistical data. For example, the clustering control unit 113 performs clustering to classify buildings included in the map information into a predetermined number of clusters based on the statistical data. Note that the algorithm for clustering performed by the clustering control unit 113 may be a commonly used method, and detailed description thereof will be omitted here.

[0024] The analysis control unit 114 analyzes the movement history of users between clusters (groups of classified buildings) and generates a sequential pattern. Here, the sequential pattern is information representing the movement history indicating how multiple users whose location information has been acquired moved between clusters. Details of the method for generating the sequential pattern will be described later. The analysis control unit 114 may also use the generated sequential pattern to generate an integrated sequential pattern indicating the frequency of movement between clusters. Details of the method for generating the integrated sequential pattern will be described later.

[0025] The congestion forecast control unit 115 updates the congestion forecast. The congestion forecast control unit 115 uses the integrated sequence pattern to update the congestion forecast acquired by the information acquisition unit 111. For example, the congestion forecast control unit 115 may predict how the congestion forecast will change in the future, taking into account the amount of movement in the integrated sequence pattern.

[0026] The output control unit 116 outputs the updated congestion forecast. For example, the output control unit 116 controls the output unit 152 to display the updated congestion forecast on its display. Alternatively, the output control unit 116 controls the output unit 152 to transmit the updated congestion forecast to the terminal that received the generation instruction via the communication interface 14.

[0027] The data storage unit 13 also includes an acquired information storage unit 131. The acquired information storage unit 131 is used to store various information acquired by the information acquisition unit 111 (map information, location information, congestion forecast, etc.).

[0028] Furthermore, although not shown in the figure, a terminal carried by a user who visits a certain area may have the hardware configuration and software configuration of the inter-area movement flow generation device 1 shown in Fig. 1. For example, the terminal may have a control unit, a data storage unit, a program storage unit, a communication interface, and an input / output interface, similar to the configuration of the inter-area movement flow generation device 1 shown in Fig. 1, and the control unit of the terminal may have each of the software configurations described with reference to Fig. 1.

[0029] (operation) FIG. 2 is a sequence diagram showing an example of a congestion forecast generation procedure performed by the inter-area movement flow generation device 1 according to this embodiment. The control unit 11 of the inter-area movement flow generation device 1 reads out and executes the program stored in the program storage unit 12, thereby realizing the operation of this flowchart.

[0030] First, this flowchart starts when the administrator of the inter-area movement flow generation device 1 inputs an instruction to create a congestion forecast for a certain area through the input unit 151. Alternatively, this flowchart starts when the control unit 11 receives an instruction to create a congestion forecast through the communication interface 14 from a terminal owned by any user, which is an external device.

[0031] In step ST101, the information acquisition unit 111 acquires map information. For example, the information acquisition unit 111 accesses a network via the communication interface 14 and acquires map information corresponding to the area for which a congestion forecast is to be generated. That is, the map information is map information corresponding to the area for which a congestion forecast is to be generated, and may be information expressed as a two-dimensional map such as OpenStreetMap. Furthermore, the destination accessed by the information acquisition unit 111 may be any server that provides map information. The information acquisition unit 111 stores the acquired map information in the acquired information storage unit 131.

[0032] FIG. 3 is a diagram showing an example of map information acquired by the information acquisition unit 111 according to this embodiment.

[0033] As shown in FIG. 3, the information acquisition unit 111 acquires map information corresponding to the area for which a congestion forecast is to be generated. In this embodiment, the map information shown in FIG. 3 represents several buildings together for simplicity's sake, but it is not necessary to group the buildings together in this manner, and it goes without saying that each building may be represented individually. Here, the position in the map information can be represented by X and Y coordinates. Therefore, the position of a building included in the map information can be represented by the vertices of a polygon. For example, the information acquisition unit 111 converts the position of a building included in the map information into information represented by the vertices of a polygon. Alternatively, the information acquisition unit 111 acquires map information in which the position of a building is represented by the vertices of a polygon. Note that the vertices of a building are represented by the coordinates of the map information as well as by latitude and longitude.

[0034] FIG. 4 is a diagram showing an example of buildings included in the map information according to this embodiment. As shown in Fig. 4, buildings on a map are usually depicted as polygons. For example, the building shown in Fig. 4 is represented by five vertices. Therefore, in this embodiment, the position of the building is represented by the coordinates of the vertices of the polygon, and this represented information is included in the map information.

[0035] In step ST102, the information acquisition unit 111 acquires location information. For example, the information acquisition unit 111 accesses the network via the communication interface 14 and acquires location information of terminals owned by users who are or have been present in the map information. The location information includes information on the latitude and longitude of the current location of the terminal and information on the latitude and longitude of the terminal's past locations. The location information may also include attribute information indicating the attributes of the user who owns the terminal, such as the age, gender, residential area, and occupation of the user who owns the terminal. The attribute information may also include user identification information capable of identifying the user who owns the terminal, such as name, address, date of birth, facial photo, email address, and credit card number. Here, the information acquisition unit 111 may access any server or the like that collects location information. For example, the information acquisition unit 111 stores the acquired location information in the acquired information storage unit 131.

[0036] In step ST103, the statistical data generation unit 112 generates statistical data based on the map information and location information. The statistical data generation unit 112 generates statistical data indicating the flow of people for each building based on the map information and location information stored in the acquired information storage unit 131. For example, the statistical data generation unit 112 may generate statistical data by determining to which building a user belongs (or belonged) based on the building's location (vertex information of a polygon) and location information (latitude and longitude of the terminal). For example, the statistical data generation unit 112 calculates the distance between the terminal and the building based on the building's location and location information, and determines that the user has stopped at the closest building. By repeating this determination, the statistical data generation unit 112 generates statistical data indicating to which building the user belonged over time. Then, the statistical data generation unit 112 outputs the generated statistical data, map information, and location information to the clustering control unit 113.

[0037] FIG. 5 is a diagram showing an example of statistical data generated for each building according to this embodiment. FIG. 5 shows an example of statistical data in which the vertical axis represents the number of people and the horizontal axis represents time. That is, FIG. 5 shows statistical data showing the change in the number of people in a certain building over a day. Furthermore, the statistical data shown in FIG. 5 shows how the number of users who stopped by a certain building increases or decreases over time by age group. The statistical data generation unit 112 generates statistical data such as that shown in FIG. 5 for each building included in the map information shown in FIG. 3. Furthermore, by using the statistical data, it is possible to know how long a user stayed (remained) in each building.

[0038] In this embodiment, the statistical data is data that represents the number of people on the vertical axis and the time on the horizontal axis, but the statistical data is not limited to this data, and it goes without saying that any statistical data that can be used for clustering, which will be described in detail below, may be used.

[0039] In step ST104, the clustering control unit 113 performs clustering on the statistical data. For example, the clustering control unit 113 generates vector data for each hour of the statistical data shown in FIG. 5 and performs clustering based on the vector data. Furthermore, when clustering, the clustering control unit 113 may use the distance between the buildings to be clustered and surrounding buildings as a parameter. The clustering control unit 113 outputs the clustered map information, statistical data, location information, etc. to the analysis control unit 114.

[0040] FIG. 6 is a diagram showing an example in which the buildings included in the map information of FIG. 2 are classified into seven clusters. 6, the clustering control unit 113 classifies buildings included in the map information into seven clusters corresponding to statistical data, i.e., people flows. For example, buildings are classified into clusters according to the purpose of use, such as stations, commercial areas, residential areas, and offices. In this embodiment, the number of clusters to be classified can be specified.

[0041] FIG. 7 is a diagram showing an example in which buildings included in map information are classified into a predetermined number of clusters. Here, k in Fig. 7 indicates the number of clusters. For example, Fig. 7(a) shows the case where k=4, i.e., classification into four clusters, Fig. 7(b) shows the case where k=5, i.e., classification into five clusters, Fig. 7(c) shows the case where k=6, i.e., classification into six clusters, and Fig. 7(d) shows the case where k=7, i.e., classification into seven clusters.

[0042] In step ST105, the analysis control unit 114 analyzes the user's movement history between clusters (groups of classified buildings) and generates a sequential pattern. For example, the analysis control unit 114 links the movement history included in the location information to clusters and generates a sequential pattern between the linked clusters. For example, if cluster 1 is abbreviated as J, outside the map information as O, and cluster 3 as C3, the sequential pattern, which is the movement history between clusters (between buildings) corresponding to the user's location information (movement history), can be expressed as follows:

[0043] User00001 J→J→C3→C3→C3→J User00002 J→C3→C3→O User00003 O→J→J→O ...

[0044] In step ST106, the analysis control unit 114 ranks the sequential patterns. As described above, the analysis control unit 114 extracts frequently occurring sequential patterns from the sequential patterns, which are the movement history of users between buildings, using a predetermined algorithm, and ranks the extracted sequential patterns. For example, the analysis control unit 114 sorts the sequential patterns and extracts sequential patterns up to a predetermined rank, starting with the most frequently occurring one. Note that the algorithm is not limited to the one described above, and any algorithm may be used. Furthermore, since the sequential patterns up to a predetermined rank are extracted in order to reduce calculation time, it goes without saying that all sequential patterns may be extracted if there is no need to reduce calculation time.

[0045] In step ST107, the analysis control unit 114 integrates the sequential patterns. The analysis control unit 114 integrates all clusters (all groups of buildings) and the extracted sequential patterns. For example, the analysis control unit 114 uses the extracted sequential patterns to generate a diagram (integrated sequential pattern) that expresses how a user moves between clusters.

[0046] FIG. 8 is a diagram showing an example of an integrated sequential pattern generated by the analysis control unit 114 by integrating a cluster with an extracted sequential pattern. In the integrated sequential pattern shown in Fig. 8, the arrows become thicker as the number of user movements between clusters increases, i.e., the frequency with which they appear in the sequential pattern increases. For example, in the example of Fig. 7, it can be seen that there are more instances of staying in cluster 3, movement from cluster 3 to outside the map information (indicated as "outside" in Fig. 7), movement from cluster 3 to cluster 6, movement from cluster 6 to outside the map information, and movement from outside the map information to cluster 6 than the other movements.

[0047] Furthermore, while FIG. 8 shows an example in which sequential patterns are integrated between all clusters (i.e., between building groups), it is also possible to generate an integrated sequential pattern by integrating sequential patterns between some clusters.

[0048] FIG. 9 is a diagram showing an example of an integrated sequential pattern generated using some of the clusters. The example in Fig. 9 shows the integration of sequential patterns from cluster 3, cluster 6, and outside of map information. As shown in Fig. 9, the integration of sequential patterns does not necessarily involve integrating all clusters, but may involve integrating sequential patterns related to some clusters. Of course, it is also possible to generate multiple integrations of sequential patterns related to some clusters.

[0049] The analysis control unit 114 may also generate an integrated sequential pattern by dividing the data by age group. In this case, in steps ST102 to ST107, movement information for each age group is acquired, clustering is performed based on the movement information, and an integrated sequential pattern is generated.

[0050] FIG. 10 is a diagram showing an example of a sequence pattern integrated by age group. The example in FIG. 10 shows integrated sequential patterns for 2019 and 2021. As shown in FIG. 10, in 2019, many users remained in cluster 4, whereas in 2021, such movement ceased and movement from cluster 6 to cluster 5 increased. The analysis control unit 114 may compare the integrated sequential patterns for each age group and indicate changed parts (different parts are indicated by dotted lines in FIG. 10). This allows the administrator and users of the inter-area movement flow generation device 1 to know how people's movements are changing by using the integrated sequential patterns for each age group.

[0051] That is, the analysis control unit 114 may generate an integrated sequential pattern based on user attribute information. In this case, in steps ST102 to ST107, movement information is acquired, and clustering is performed for each attribute information included in the movement information, and an integrated sequential pattern is generated.

[0052] FIG. 11 is a diagram showing an example of an integrated sequential pattern generated using user attribute information. The example in FIG. 11 shows the integrated sequential patterns of users who visit buildings included in the map information only for one day (e.g., a user who happens to visit a building included in the map information only one day on the weekend) and users who visit buildings included in the map information several times a week (e.g., a user whose workplace is in a building included in the map information). As shown in FIG. 11, it can be seen that users who visit buildings included in the map information only for one day make fewer trips from other clusters to cluster 1, from cluster 6 to cluster 5, and between cluster 7 and cluster 3 compared to other trips. Furthermore, it can be seen that users who visit buildings included in the map information several times a week make more trips between cluster 3 and cluster 1 and between cluster 3 and cluster 7 compared to other trips, unlike the users who visit buildings only for one day. Furthermore, it can be seen that users who visit buildings included in the map information several times a week stay in cluster 4 and cluster 5 and move from cluster 6 to cluster 5 compared to other trips. The analysis control unit 114 may compare integrated sequential patterns using user attributes and detect differences (for example, in the example of FIG. 11, the different parts are indicated by dotted lines). In this way, by generating integrated sequential patterns based on user attribute information, the administrator and users of the inter-area movement flow generation device 1 can understand differences in behavior patterns according to differences in user attribute information.

[0053] As described above, by generating an integrated sequence pattern based on user attribute information, it is possible to grasp people's behavioral patterns and forecast people's movements even if their behavioral patterns have changed significantly due to an infectious disease or other reasons.

[0054] Although Fig. 11 is generated using user identification information, it is also possible to generate a corresponding diagram using attribute information that does not include user identification information. For example, a diagram corresponding to Fig. 11 can be generated by generating an integrated sequential pattern for weekends and an integrated sequential pattern for weekdays and comparing these sequential patterns.

[0055] In step ST108, the information acquisition unit 111 acquires a congestion forecast. The information acquisition unit 111 accesses the network via the communication interface 14 and acquires the congestion forecast for the area corresponding to the map information. The information acquisition unit 111 outputs the acquired congestion forecast to the congestion forecast control unit 115.

[0056] In step ST109, the congestion forecast control unit 115 updates the congestion forecast. The congestion forecast control unit 115 updates the congestion forecast acquired in step ST108 using the integrated sequence pattern. For example, the congestion forecast control unit 115 may predict how the congestion forecast will change in the future, taking into account the amount of movement in the integrated sequence pattern.

[0057] Conventional congestion forecasts predict how people will move within a mesh-shaped frame. However, in this embodiment, conventional congestion forecasts predict how people will move within a mesh using an integrated sequence pattern that indicates how people (users) within the frame are moving. This makes it possible to better reflect the trends in how people move, thereby improving prediction accuracy compared to conventional congestion forecasts. The congestion forecast control unit 115 outputs the updated congestion forecast to the output control unit 116.

[0058] FIG. 12 is a diagram showing an example of a combination of congestion forecasts and integrated sequence patterns. FIG. 12(a) shows a mesh-type congestion forecast, and FIG. 12(b) shows a diagram in which the mesh-type congestion forecast and an integrated sequence pattern are superimposed. In the mesh-type congestion forecast in FIG. 12(a), the degree of congestion is indicated using different shades of color and different colors. However, in the example in FIG. 12(a), for simplicity, no colors are used. For example, the congestion forecast control unit 115 may update the congestion forecast using the diagram shown in FIG. 12(b). For example, the congestion degree of a certain mesh and the integrated sequence pattern of the clusters belonging to the corresponding mesh may be referenced to predict how the mesh will transition in the future.

[0059] Furthermore, the congestion forecast control unit 115 may predict how crowded a store (building) belonging to a mesh (area block) to be monitored will be. That is, the congestion forecast control unit 115 may compare location information with the building location and predict the congestion level of the building based on the congestion level within the building and the integrated sequential pattern. For example, the original cluster to which the building belongs may be designated as cluster 3. Furthermore, a cluster excluding the building may be designated as cluster 3*, and the building may be designated as a new cluster 8. As described above, statistical data is generated for each building. Therefore, when linking the movement history included in the location information to a cluster, cluster 8 may be abbreviated as C8, and the analysis control unit 114 may extract it as a frequently occurring sequential pattern by performing the same process as described above. Furthermore, the congestion forecast control unit 115 may determine the congestion level by measuring the frequency of appearance of C8. Furthermore, when the statistical data generation unit 112 generates statistical data, the current congestion level of people staying in C8 may be determined by measuring the number of users currently belonging to the building. The congestion forecast control unit 115 may then compare the past average congestion level with the current congestion level and refer to the sequence pattern to predict the congestion level of the building.

[0060] In step ST110, the output control unit 116 outputs the updated congestion forecast. For example, the output control unit 116 controls the output unit 152 to display the updated congestion forecast on its display. Alternatively, the output control unit 116 controls the output unit 152 to transmit the generation instruction to the terminal that received it via the communication interface 14. The administrator of the inter-area movement flow generation device 1 or the user who owns the terminal can know what the future congestion level will be based on the congestion forecast with improved prediction accuracy.

[0061] (Effects of the embodiment) According to the embodiment described above, the inter-area movement flow generation device 1 clusters and expresses user movements between buildings included in map information. This makes it possible to grasp how users move between classified buildings. Furthermore, the inter-area movement flow generation device 1 generates integrated sequential patterns based on the grasped information and updates the congestion forecast using the integrated sequential patterns. This improves the accuracy of the congestion forecast.

[0062] [Other embodiments] It should be noted that the present invention is not limited to the above embodiment. For example, it is possible to provide a congestion forecast for a specific date and time designated by a user using the updated congestion forecast.

[0063] Furthermore, operations such as updating the congestion forecast may be performed by a mobile device owned by a user. For example, the mobile device may acquire the congestion forecast and the integrated sequence pattern, and further generate an updated congestion forecast based on the acquired information.

[0064] In short, this invention is not limited to the above-described embodiments, and various modifications can be made in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in combination as appropriate as possible, and in such cases, the combined effects can be obtained. Furthermore, the above-described embodiments include inventions at various stages, and various inventions can be extracted by appropriately combining the disclosed multiple constituent elements. [Explanation of symbols]

[0065] 1...Inter-area movement flow generation device 11...Control unit 111…Information acquisition department 112...Statistical data generation unit 113...Clustering control unit 114...Analysis control unit 115...Congestion forecast control unit 116...Output control unit 12...Program memory section 13...Data storage unit 131...Acquired information storage unit 14...Communication interface 15...Input / output interface 151...input section 152...Output section

Claims

1. an information acquisition unit that acquires map information corresponding to an area for which a congestion forecast is to be generated and location information of users staying in the area; a statistical data generating unit that determines which building included in the map information the user belongs to and generates statistical data for each of the buildings; a clustering control unit that performs clustering to classify the buildings into a predetermined number of clusters based on the statistical data; an analysis control unit that generates a sequential pattern that indicates how the user moved between the clusters based on the location information; an output control unit that outputs the sequence pattern; An inter-area movement flow generation device comprising:

2. The information acquisition unit further acquires a mesh-shaped congestion forecast corresponding to the area, a congestion forecast control unit that updates the congestion forecast using the sequence pattern; The output control unit outputs the updated congestion forecast. The inter-area movement flow generation device according to claim 1 .

3. the congestion forecast control unit predicts a degree of congestion in the building based on a degree of congestion in the building belonging to a mesh to be monitored and the sequence pattern; The inter-area movement flow generation device according to claim 2 .

4. the analysis control unit generates the sequential pattern by linking the movement history included in the location information to the cluster. The inter-area movement flow generation device according to claim 1 .

5. the analysis control unit ranks the sequential patterns and generates an integrated sequential pattern using the frequency of movement between clusters in the sequential patterns up to a predetermined rank. The inter-area movement flow generation device according to any one of claims 1 to 4.

6. the analysis control unit generates the sequential pattern based on a time period of a movement history included in the location information. The inter-area movement flow generation device according to claim 1 .

7. the analysis control unit generates the sequential pattern based on attribute information of the user included in the location information. The inter-area movement flow generation device according to claim 1 .

8. the analysis control unit generates the sequential pattern using some of the clusters. The inter-area movement flow generation device according to claim 1 .

9. An inter-area movement flow generation method executed by a processor of an inter-area movement flow generation device, comprising: acquiring map information corresponding to an area for which a congestion forecast is to be generated and location information of users staying in the area; determining to which building included in the map information the user belongs; generating statistical data for each of the buildings; performing clustering to classify the buildings into a predetermined number of clusters based on the statistical data; generating a sequential pattern indicating how the user moved between the clusters based on the location information; outputting the sequential pattern; An inter-area movement flow generation method comprising:

10. An inter-area movement flow generation program comprising instructions to be executed by a processor of an inter-area movement flow generation device, acquiring map information corresponding to an area for which a congestion forecast is to be generated and location information of users staying in the area; determining to which building included in the map information the user belongs; generating statistical data for each of the buildings; performing clustering to classify the buildings into a predetermined number of clusters based on the statistical data; generating a sequential pattern indicating how the user moved between the clusters based on the location information; outputting the sequential pattern; An inter-area movement flow generation program comprising:

Images