Program, method, information processing device and system

Abstract

To provide a program for executing analysis taking account of characteristics of an area and an actual use status of the area.SOLUTION: A program causes a computer including a processor to execute the steps of: acquiring location information of a plurality of users; acquiring information of spots in a prescribed area; calculating a degree of use of the users for each of the spots based on the location information of the users; and calculating a degree of importance of each spot in the area taking account of the degree of use.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present disclosure relates to a program, a method, an information processing device, and a system for acquiring data about an area in which a user is active, based on the user's location information and information about spots visited by the user. [Background technology]

[0002] With the recent spread of smartphones, it is now possible to easily obtain location information of users. If we can obtain location information of multiple users, we can visualize the flow of people and analyze what kind of people gather in what places, and where people flow from. Furthermore, by analyzing the commonalities of the places people visit, it is possible to use the information for regional development, cultural preservation, business, etc.

[0003] For example, Patent Document 1 discloses a system in which, when a route leading to guidance information presented to a user is selected, the guidance information is registered as the user's preference information and assigned a level of importance according to how frequently it is selected by the user. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2012-203501 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the information providing device disclosed in Patent Document 1 is unable to analyze the characteristics of an area while analyzing the preferences of the user.

[0006] The present disclosure aims to provide technology that enables analysis that takes into account the characteristics of an area and the actual usage of that area. [Means for solving the problem]

[0007] In the present disclosure, a program is provided that causes a computer having a processor to execute the steps of acquiring location information of multiple users, acquiring information on spots in a specified area, calculating the user's degree of usage for each of the spots based on the users' location information, and calculating the importance of the spots in the area taking into account the degree of usage. Effect of the Invention

[0008] According to the present disclosure, it is possible to analyze the characteristics of an area by taking into account the actual usage of the area. [Brief description of the drawings]

[0009] [Figure 1] 2 is a diagram illustrating an example of a functional configuration of a server 10 according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram showing an example of a data configuration of a user information DB 1021. [Diagram 3] FIG. 2 is a diagram showing an example of a data configuration of a spot information DB 1022. [Figure 4] 10 is a diagram illustrating an example of the processing of a spot information acquisition unit 1032 and an importance calculation unit 1034. FIG. [Diagram 5] FIG. 2 is a diagram illustrating a process flow of the server 10. [Figure 6] FIG. 13 is a diagram for explaining the processing of a cluster generating unit 1035. [Figure 7] 2 is a diagram illustrating a hardware configuration of a server 10 according to the present disclosure. [Figure 8] 1 is a diagram showing an overall configuration of a system 1 via a network. [Figure 9] FIG. 10 is a diagram for explaining the process of the importance calculation unit 1034 in the modified example. [Figure 10] FIG. 10 is a diagram for explaining the processing of a cluster generating unit 1035 in a modified example. [Figure 11]FIG. 13 is a diagram showing an example in which the usage status of spots in a time series is considered in another embodiment. [Figure 12] FIG. 13 is a diagram showing an example of a calculation pattern of the utilization degree of a spot in another embodiment. [Figure 13] FIG. 13 is a diagram showing an example of area scheduling in another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. Note that the embodiment described below does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the configurations described in the embodiments are necessarily essential components of the present disclosure. In addition, in all drawings describing the embodiments, the same reference numerals are used for common components, and repeated explanations are omitted.

[0011] With the recent development of information processing technology, it is now possible to easily obtain location information of users, and by analyzing the commonalities of places visited by people, it is possible to use this information for regional development, cultural preservation, business, etc. Furthermore, in a society with a declining population, regional development that makes use of the individuality and characteristics of each region is being advocated. For this reason, the development of a method to analyze regional diversity was required. Currently, there is no uniform method of evaluation, and to analyze regional diversity using a uniform method, national spot information and national location information are required. In addition, it is difficult to precisely grasp the characteristics of a region using only existing measures such as "residential area," "entertainment district," and "restaurant district." Specifically, currently, the analysis is based on "population size" and "number of types of facilities," so evaluation can only be done using existing rough classifications such as "residential area," "entertainment district," and "restaurant district." In addition, since there is no standard for the degree of use, it is not possible to evaluate the degree to which it is used as a "residential area," "entertainment district," or "restaurant district." Furthermore, just as an area that can be a tourist destination for a group of tourists is not a tourist destination for residents, the meaning of the area changes for each group. Thus, in the current situation, - Classification of places visited is too rough -Failure to take into account actual usage of visited locations -Relative evaluation across the country is unclear -The standard is uniform regardless of the group to which the user belongs. There was room for improvement as described above. Taking these points into consideration, the applicant arrived at the technical idea described below.

[0012] <1. First embodiment> (1. Functional configuration of server 10) The configuration of the server 10 will be described in detail below. As shown in Fig. 1, the server 10 according to this embodiment includes a communication unit 101, a storage unit 102, and a control unit 103. The communication unit 101 performs processing for the server 10 to communicate with other devices. The communication unit 101 performs transmission processing on a signal generated by the control unit 103 and transmits the signal to the outside. The communication unit 101 performs reception processing on a signal received from the outside and outputs the signal to the control unit 103.

[0013] The storage unit 102 is configured with, for example, a flash memory or the like, and stores data and programs used by the server 10. The storage unit 102 includes, for example, a user information database (Database, hereinafter, abbreviated as DB) 1021 and a spot information DB 1022.

[0014] 2 shows a specific example of user information DB 1021. User information DB 1021 stores the user ID of a user whose location information is acquired by user information acquisition unit 1031 (described later), the acquisition time, and the user's location information (latitude and longitude). The location information may include information about height (as an example, altitude or number of floors). The information stored in user information DB 1021 is not limited to this, and other information such as the user's age (generation), sex, and residential area may also be stored.

[0015] 3 shows a specific example of the spot information DB 1022. The spot information DB 1022 stores information about spots (hereinafter, also referred to as spot information). A spot is a place that a user visits and uses. As an example, spots may include, but are not limited to, stores, shopping malls and other commercial complexes, public facilities such as city halls and parks, and some areas thereof (e.g., a specific place in a park, etc.).

[0016] Specifically, the spot information DB 1022 stores an identification ID for identifying a spot, location information of the spot (latitude, longitude, and information on altitude as necessary), spot name (shop name, etc.), type (classification based on the use of the spot, such as restaurant, theme park, station, etc.), etc. The spot information DB 1022 may also store other information such as the opening days and business hours of the spot, average budget, etc., and may store links to the official homepage, introduction page, etc. of the spot so that various information about the spot can be obtained.

[0017] The control unit 103 is realized by the processor 11 reading a program stored in the storage unit 102 and executing instructions included in the program. The control unit 103 controls the operation of the server 10. Specifically, for example, the control unit 103 exerts functions as a user information acquisition unit 1031, a spot information acquisition unit 1032, a utilization degree calculation unit 1033, an importance calculation unit 1034, and a cluster generation unit 1035. Each function will be described below.

[0018] The user information acquisition unit 1031 acquires user location information and time information (hereinafter collectively referred to as user information) via the communication unit 101. The user location information is, for example, information such as latitude and longitude. The time information is time information at the time when the location information is acquired. As an example, the user information acquisition unit 1031 periodically acquires location information and time information from the user at a certain time interval. Then, the user information acquisition unit 1031 stores the user ID of the user who acquired the location information, the acquisition time, and the user's location information in the user information DB 1021. In this way, it is preferable that the server 10 temporarily stores the acquired user location information in the storage unit 102 so that analysis can be performed using clustering or the like from various viewpoints.

[0019] The user's location information may be obtained using information from a Global Positioning System (GPS) installed in a smartphone, smartwatch, or the like owned by the user. Alternatively, a terminal such as a magnetic reader or IC reader may be installed, and the user may have the terminal read the user's own device, thereby obtaining location information. Furthermore, location information obtained from a base station of a communication device such as a mobile phone, WiFi (Wireless Fidelity, registered trademark), Bluetooth (registered trademark), beacon, or the like may be obtained.

[0020] Furthermore, the user information acquisition unit 1031 may acquire location information based on information posted to a Web service such as a social networking service (SNS).

[0021] As an example, it is preferable that the user information acquisition unit 1031 periodically acquires location information and time information from the user at a certain time interval. The shorter the interval for acquiring the user's location information, the more detailed the analysis can be performed.

[0022] On the other hand, if the time interval for acquiring the location information is long, it is possible to reduce the burden on the system and the network. Therefore, it is preferable that the user information acquiring unit 1031 sets the time interval for acquiring the user's location information while taking into consideration the analysis target and the load on the system. Note that the location information and time information do not need to be acquired at a fixed time interval, and may be shaped to a fixed interval after acquisition.

[0023] The spot information acquisition unit 1032 acquires information on spots within an area to be analyzed (hereinafter, also referred to as an analysis area). Here, the area refers to a predetermined area set by the user. As an example, the area may be an administrative division such as a city, town, or village, may be an area of ​​a predetermined distance (e.g., 10 kilometers) square set by the user, or may be a circular area with a radius of a predetermined distance (e.g., 10 kilometers) from a point set by the user. The spot information acquisition unit 1032 acquires spot information on spots included in the area specified by the user from the spot information DB 1022. Alternatively, the spot information acquisition unit 1032 may acquire spot information on spots included in the analysis area by receiving information linkage from another information providing service, or by scraping multiple homepages.

[0024] The use degree calculation unit 1033 calculates the degree of use by users (hereinafter also referred to as using users) who used spots in the analysis area during a predetermined period. The predetermined period (hereinafter also referred to as analysis period) can be set to any period, and may be, for example, one month. The use degree calculation unit 1033 may divide the map into meshes in a grid at predetermined intervals (for example, 125 m intervals) in advance, and determine whether or not a spot has been visited for each mesh. In this case, when a mesh is visited, it may be determined that one or more spots included in the mesh have all been visited. In addition, when a predetermined spot has a large area such as a large park, there may be cases where multiple meshes exist within one spot. In this case, even if multiple meshes within one spot are visited, it may be determined that the spot has been visited once.

[0025] The usage degree calculation unit 1033 may determine that a user has used a spot when the user visits the spot, or may determine that a user has used the spot when the user visits the spot and stays there for a predetermined time or more. The usage degree calculation unit 1033 refers to the user information DB 1021 and the spot information DB 1022, and calculates the degree of usage by users who have used spots in the analysis area during a predetermined period. Here, the degree of usage may be, for example, the number of visits by a user, the usage time (i.e., the stay time), or the number of uses by a unique user (frequency of use). Other values ​​indicating the degree of usage may also be calculated. When calculating the number of visits, either the number of times as the stated number of users who visited the spot or the number of times as the actual number of users who visited the spot may be used.

[0026] The importance calculation unit 1034 calculates the importance of spots in the analysis area (for example, a TF-IDF value). In this embodiment, the importance calculation unit 1034 calculates the usage importance Ir of the type of spot in the analysis area, taking into account the degree of usage of the spot by the user. Note that any population may be used to calculate the importance. In the example shown below, the population is the whole of Japan, but is not limited to this example.

[0027] As an example, the importance In of the type of spot in the analysis area is calculated using the following formula. In(importance) = Fn(frequency) x Rn(rarity) Fn=(An / Bn) Rn=log(Cn / Dn) An: Number of spots of that type in the analysis area Bn: The number of spots of the same type present throughout Japan (an example of the population) Cn: The total number of areas in Japan Dn: Number of areas where the spot of the same type exists

[0028] For example, in the analysis area R shown in FIG. 4A, the number of spots of the type "cafe" is 15, the number of spots of the type "hot spring" is 5, and the number of spots of the type "gyoza" is 10. Furthermore, the number of spots of the type "cafe" in Japan is 70,000, the number of spots of the type "hot spring" is 20,000, and the number of spots of the type "gyoza" is 50,000. Furthermore, the total number of areas in Japan is 178,397. Furthermore, the number of areas in Japan where spots of the type "cafe" exist is 20,000, the number of areas where spots of the type "hot spring" exist is 15,000, and the number of areas where spots of the type "gyoza" exist is 10,000. In this case, the importance In of the spot type "cafe" is calculated as follows: An: Number of spots of type "cafe" in the analysis area = 15 Bn: Number of spots of type "cafe" existing nationwide = 70,000 Cn: Total number of areas in Japan = 178397 Dn: Number of areas with spots of type "cafe" = 20000 In[cafe] = Fn (frequency) x Rn (rarity) = (An / Bn) x log(Cn / Dn) = (15 / 70000) x log(178397 / 20000) = 0.00020

[0029] In the above manner, when the importance In of spot types in the analysis area R is generally calculated for the types "cafe", "hot spring", and "gyoza", the values ​​shown in Fig. 4B are obtained. However, the importance calculated in this manner has the problem that it only provides information on the number of spots belonging to each type.

[0030] On the other hand, the importance calculation unit 1034 in this embodiment calculates the usage importance Ir by the following formula, in order to take into account the degree of usage of the spot by the user. Ir (importance of use) = Fr (frequency) x Rr (rarity) Fr=(Ar / Br) Rr = log(Cr / Dr) Ar: The degree of use of the spot of the given type in the analysis area Br: The degree of utilization of the relevant type of spot in Japan Cr: Total number of areas in Japan Dr: Number of areas where the spot of that type exists

[0031] For example, in the analysis area R shown in FIG. 4A, the usage level (number of visits, as an example) of the type "cafe" is 70,000, the usage level of the type "hot spring" is 15,000, and the usage level of the type "gyoza" is 10,000. Also, assume that the usage level of the type "cafe" nationwide is 7,000,000, the usage level of the type "hot spring" is 2,500,000, and the usage level of the type "gyoza" is 1,000,000. In this case, the usage importance Ir of the spot type "cafe" is calculated as follows: Ar: Usage rate of spots of type "cafe" in the analysis area = 70,000 Br: Usage rate of spots of type "cafe" existing throughout Japan = 7,000,000 Cr: Total number of areas in Japan = 178397 Dr: Number of areas with spots of type "cafe" = 20,000 Ir[cafe] = Fr(frequency) x Rr(rarity) = (Ar / Br) x log(Cr / Dr) = (70000 / 7000000) x log(178397 / 20000) = 0.0095

[0032] When the usage importance Ir in the analysis area R is calculated for the types "cafe", "hot spring", and "gyoza" in the above manner, the values ​​shown in Fig. 4C are obtained. Comparing Fig. 4B with Fig. 4C, the importance value of the type "cafe" is higher than that of the type "cafe" in the usage importance Ir that takes into account the frequency of use, as compared to the importance In calculated based only on the number of stores. In this way, in this embodiment, the importance calculation unit 1034 calculates the importance taking into account the frequency of use by the user, making it possible to perform analysis based on the user's usage history.

[0033] The cluster generating unit 1035 performs clustering (grouping) of a plurality of analysis areas based on the usage importance Ir of the spots calculated by the importance calculating unit 1034. The cluster generating unit 1035 generates clusters, which are classifications of the analysis areas, for a plurality of analysis areas based on the usage importance Ir of the spots.

[0034] The cluster generating unit 1035 generates clusters based on the commonality of the utilization importance Ir, for example, by using hierarchical clustering, non-hierarchical clustering, or a known algorithm. At this time, the cluster generating unit 1035 may set a target of cluster generation to M1, and generate M1 clusters based on the number of common areas after clustering.

[0035] Furthermore, when performing clustering, the cluster generating unit 1035 may generate clusters taking into consideration at least one of the number of visits to the spot, the time of visit, the duration of stay, and the commonality of the type of spot. In addition, the cluster generating unit 1035 may generate clusters taking into consideration the total duration of stay, the average duration of stay, the number of times the spot has been introduced or cited in media such as television, magazines, the Internet, and SNS, and the number of moving objects.

[0036] Furthermore, when performing clustering, the cluster generation unit 1035 may generate clusters by taking into account weighting factors such as commonality of spots, number of visits to the spots, time of visit, duration of stay, commonality of type of spots, total duration of stay, average duration of stay, number of times featured or cited in media such as television, magazines, the Internet, and SNS, mobile devices, purchasing data, prices of goods or services handled by the spots, and type and variety of goods or services.

[0037] Furthermore, the cluster generating unit 1035 may assign a high value to a meaningful location, i.e., a location with a high rarity, for the spot. A high rarity value is assigned when some users behave in common. For example, a high rarity may be assigned to a location that is visited infrequently. A low rarity is assigned to stations and convenience stores, which are visited by many people. On the other hand, a high rarity is assigned to locations that are visited infrequently, such as bookstores and live music venues that are popular with people with specific hobbies.

[0038] Also, for example, a high rarity may be given to a spot where the stay time or the number of visits per person is long. This means that the stay time at a certain spot is usually within 15 minutes, but if only some users stay there for 60 minutes or more, a high rarity may be given. That is, if users who use a certain station usually use it to get on a train from the station, but some users visit for a long time to take pictures of the train, a cluster may be generated for users who stay there for 60 minutes or more as a pseudo spot A2 separate from the normal spot A. Furthermore, a high rarity may be given to a spot or type of spot at a specific date and time. For example, a cluster may be generated for each event held at a certain facility or event hall as a pseudo spot B2 (or a pseudo spot type C2 separate from the normal spot type C) separate from the normal spot B, and a higher rarity may be given to spot B2 (or spot type C2) than spot B (or spot type C).

[0039] Furthermore, for example, a spot that is associated with few other spots may be given a higher rarity.

[0040] When generating clusters, the cluster generating unit 1035 may select only spots whose rarity exceeds a certain threshold, and then generate clusters based on the commonality of the spots visited by users.

[0041] When generating clusters, the cluster generation unit 1035 may set a high score for clusters that contain many rare spots and generate clusters with higher scores preferentially, or after cluster generation, sort the clusters with the highest scores first to extract clusters.

[0042] When generating clusters, the cluster generating unit 1035 may generate clusters based on zones that group together several spots, rather than generating clusters based on common spots. In this case, the cluster generating unit 1035 may perform clustering using information such as the location information of the zones, the types and attributes of spots that belong to the zones, and the number of visits by users, in the same way as for the spots.

[0043] When generating clusters, the cluster generating unit 1035 may limit the range of spots and zones to be classified and generate clusters based on the spots and zones within the limited range. The cluster generating unit 1035 may also generate clusters within a specified time period within a certain time range. In this case, clusters may be generated based on ranges such as days of the week and time periods.

[0044] Furthermore, when generating clusters, the cluster generating unit 1035 may generate clusters taking into consideration the number of visits to spots and zones, the visit time, the duration of stay, etc. In this way, by performing clustering based on certain elements such as commonality of spots, it becomes possible to grasp the characteristics of each cluster or spot.

[0045] (2. Processing flow) FIG. 5 shows the processing flow of the cluster generation program in the first embodiment of the present disclosure.

[0046] (2.1. Acquisition of User Information) In step S110, the user information acquisition unit 1031 continuously acquires the user's location information and time. Then, the user information acquisition unit 1031 stores the acquired information in the user information DB 1021 in sequence.

[0047] (2.2. Obtaining spot information) In step S120, the spot information acquisition unit 1032 refers to the spot information DB 1022 to acquire spot information about spots included in the analysis area designated by the user.

[0048] (2.3. Calculation of the degree of use) In step S130, the usage degree calculation unit 1033 calculates the degree of usage by users who used the spot in the analysis area during a predetermined period. As an example, the usage degree calculation unit 1033 calculates the number of users who visited the spot in the analysis area during a predetermined period as the number of users who used the spot.

[0049] (2.4. Calculation of Importance) In step S140, the importance calculation unit 1034 calculates the usage importance Ir of the type of spot in the analysis area, taking into account the usage degree of the spot calculated by the usage degree calculation unit 1033. As an example, the importance calculation unit 1034 calculates the usage importance of the type of spot based on the number of visits by the user using the following formula. Ir (importance of use) = Fr (frequency) x Rr (rarity) Fr=(Ar / Br) Rr = log(Cr / Dr) Ar: Number of visits to the spot of the same type in the analysis area Br: Number of visits to spots of the same type across Japan Cr: Total number of areas in Japan Dr: Number of areas where the spot of that type exists

[0050] (2.5. Area Clustering) In step S150, the cluster generation unit 1035 performs clustering of the analysis area based on the usage importance Ir of the spot calculated by the importance calculation unit 1034. The cluster generation unit 1035 performs clustering of the analysis area using hierarchical clustering, for example, as shown below.

[0051] In hierarchical clustering, for example, commonality of the usage importance Ir for each area is regarded as distance or similarity, and areas are clustered. Specifically, for example, if there are three areas A, B, and C, and the types of spots with high importance in the areas are A=(hot spring, souvenir shop, shooting range, cafe, izakaya), B=(hot spring, souvenir shop, shooting range, gyoza, cafe), and C=(movie theater, gyoza, art museum, izakaya, cafe), A and B, which have high commonality of importance (high similarity), may be clustered first, and then A+B and C may be clustered. As candidates for hierarchical clustering, patterns such as A+B+C, A+B, C, A, and B may be generated.

[0052] FIG. 6 is a diagram illustrating the characteristics of the usage importance calculated for each analysis area. Comparing FIG. 6A and FIG. 6B, the usage importance of "hot springs," "souvenir shops," and "shooting ranges" is high in all analysis areas, so it can be inferred that all analysis areas are hot spring towns. In this way, by performing processing by the server 10 in the present disclosure, it is possible to perform an analysis that takes into account the characteristics of the area and the actual usage of the area.

[0053] (3. Hardware Configuration) 7 is a diagram showing a hardware configuration of the server 10. The server 10 is a general-purpose computer. The server 10 is realized, for example, by a stationary PC (Personal Computer), a laptop PC, or the like. The server 10 may also be a portable computer such as a smartphone or a tablet terminal.

[0054] As shown in FIG. 7, the server 10 includes a processor 11, a memory 12, a storage 13, a communication IF 14, and an input / output IF 15.

[0055] The processor 11 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, etc. The memory 12 is for temporarily storing the program and data processed by the program, etc., and is realized by a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage 13 is a storage device for saving data, and is realized by a flash memory or a HDD (Hard Disc Drive), for example. The communication IF 14 is an interface for transmitting and receiving signals so that the server 10 can communicate with an external device. The input / output IF 15 functions as an interface with an input device for receiving input from a user and an output device for presenting information to the user.

[0056] Fig. 8 shows an example of a system 1 in which a server 10 and a user terminal 20 are connected. As shown in Fig. 8, the system 1 according to the present disclosure may be operated by connecting the server 10 and the user terminal 20 via a network. In this case, functions may be distributed between the server 10 and the user terminal 20. Furthermore, functions may be distributed using a plurality of servers.

[0057] Furthermore, the information processing device according to the present disclosure may realize its functions by, for example, a computer executing a program, without relying on the above-mentioned device. The program for realizing the functions of the information processing device may be stored in a computer-readable recording medium such as a Universal Serial Bus (USB) memory, a Compact Disc-Read Only Memory (CD-ROM), a Digital Versatile Disc (DVD), or a Hard Disc Drive (HDD), or may be downloaded to the computer via a network.

[0058] (4.Summary) As described above, in this embodiment, the server 10 executes the steps of acquiring location information of multiple users (S110), acquiring information on spots in a specified area (S120), calculating the user's degree of usage of each spot based on the user's location information (S130), calculating the importance of the spots in the area (as an example, the importance of the type of spot) taking into account the degree of usage (S140), and clustering the areas based on the importance of the spots (S150).

[0059] By adopting such a configuration, it is possible to perform an analysis taking into account the characteristics of the area and the actual usage of the area. A trendy town for young people A social gathering for mothers A fashionable area for trend-conscious people This allows us to grasp these factors and view the region organically (taking into account connections with other elements) and three-dimensionally (taking into account other regions and time series), making it possible to allocate resources effectively for human activities.

[0060] The control unit 103 may compare the importance of spots in the analysis area calculated by the importance calculation unit 1034 with a representative value of the importance of spots in the area cluster generated by the cluster generation unit 1035. The representative value is a value calculated as statistical data, and may include the average, median, mode, minimum, and maximum. For example, the control unit 103 can perform a relative evaluation of the analysis area A within the area cluster X by comparing the representative value of the importance of spots in the area cluster X into which the analysis area A is clustered with the importance of spots in the analysis area A.

[0061] (5. Modifications) A modified example of this embodiment will be described with reference to Figures 9 and 10. This modified example differs from the above embodiment in that the server 10 performs clustering of the analysis area for each cluster of users that has been generated in advance. The following description will focus on the differences.

[0062] In the modified example, a plurality of users are classified into a plurality of clusters in advance, and the usage importance of the spot is calculated for each user belonging to each cluster. The importance calculation unit 1034 calculates the usage importance Ir' by the following formula, in order to take into account the usage degree of the spot by the users belonging to each cluster. Note that in the modified example, the usage importance is calculated based on the staying time at the spot as the usage degree of the user. Ir′ (importance of use per cluster) = Fr′ (frequency per cluster) × Rr′ (rarity per cluster) Fr′=(Ar′ / Br′) Rr′=log(Cr′ / Dr′) Ar′: The time spent by each user in a cluster at a given spot of that type during a given period Br′: The time spent per user at a given spot of the same type throughout Japan during a given period Cr′: Total number of areas in Japan Dr′: Number of areas where the spot of the same type exists

[0063] For example, in the example shown in FIG. 9, the time spent by a user belonging to cluster A in the type "cafe" is 30 minutes, the time spent in the type "hot spring" is 200 minutes, and the time spent in the type "gyoza" is 10 minutes. Furthermore, the time spent nationwide in the type "cafe" is 15 minutes, the time spent in the type "hot spring" is 60 minutes, and the time spent in the type "gyoza" is 45 minutes. Furthermore, the total number of areas in Japan is 178397. Furthermore, the number of areas in Japan where spots of the type "cafe" exist is 20,000, the number of areas where spots of the type "hot spring" exist is 15,000, and the number of areas where spots of the type "gyoza" exist is 10,000.

[0064] In this case, the importance of use Ir of the spot type “cafe” by users belonging to cluster A is calculated as follows: Ar′: Stay time per user in the cluster at the spot of the given type during a given period = 30 minutes Br′: Average time spent per user at a given spot of the same type throughout Japan during a given period = 15 minutes Cr′: Total number of areas in Japan = 178397 Dr′: Number of areas with spots of type “cafe” = 20,000 Ir′[A / cafe]=Fr′(frequency)×Rr′(rarity)=(Ar′ / Br′)×log(Cr′ / Dr′) =(30 / 15)×log(178397 / 20000)=1.90

[0065] In addition, assume that the time spent by a user belonging to cluster B in the type "cafe" is 10 minutes, the time spent in the type "hot spring" is 30 minutes, and the time spent in the type "gyoza" is 120 minutes. In this case, the importance of use Ir of the spot type "cafe" by a user belonging to cluster B is calculated as follows: Ar′: Stay time per user in the cluster at the spot of the given type during a given period = 10 minutes Br′: Average time spent per user at a given spot of the same type throughout Japan during a given period = 15 minutes Cr′: Total number of areas in Japan = 178397Dr′: Number of areas with spots of type “cafe” = 20000 Ir′[A / cafe]=Fr′(frequency)×Rr′(rarity)=(Ar′ / Br′)×log(Cr′ / Dr′) =(10 / 15)×log(178397 / 20000)=0.63

[0066] In this manner, in the modified example, the importance calculation unit 1034 calculates the usage degree of the spot for each cluster to which the user belongs. The cluster generation unit 1035 performs clustering of a plurality of analysis areas based on the usage importance calculated by the importance calculation unit 1034.

[0067] 10 is a diagram illustrating an example of the characteristics of the usage importance calculated for each analysis area for each cluster to which a user belongs. In this manner, in the modified example, the usage degree is calculated for each user belonging to a cluster, so that it is possible to perform an analysis that takes into account the characteristics of an area for users belonging to a specific cluster.

[0068] In addition, in the modified example, the cluster of the user can be set appropriately. For example, the cluster according to the age group of the user may be used, or the cluster according to the gender may be used. In this way, it is possible to grasp the importance of a specific area to a user belonging to a specific age / gender cluster, taking into account the degree of use of the user.

[0069] In addition, the calculation of the degree of use of a user and the calculation of the importance may be performed by dividing the time period. In this way, it is possible to grasp the importance of a specific area in a specific time period, taking into account the degree of use of the user. In addition, in calculating the importance, the frequency may be calculated using the average value (an example of a representative value) of the degree of use (stay time in the above example) in a specific population. By using the average value in this way, it is possible to calculate the importance by finding the standard deviation as the frequency. Note that the average value of the degree of use is only an example, and the importance may be calculated by finding the frequency using other representative values ​​(i.e., at least one of the median, mode, minimum, and maximum).

[0070] Furthermore, the importance calculation unit 1034 may calculate the importance of spots in the analysis area for users belonging to a cluster, taking into account the degree of use by the users, and the cluster generation unit 1035 may execute clustering of areas based on the importance. With this configuration, it becomes possible to analyze areas based on their importance for users belonging to a cluster.

[0071] <2. Other embodiments> Although the embodiments to which the technical scope of the present application is applied have been described above, the present invention is not limited to the above contents.

[0072] For example, in the above embodiment, processing is performed using the usage record of whether or not a user has used a specific spot within the analysis area, but the usage record of the spot over time may also be taken into consideration.

[0073] Specifically, as an example, as shown in FIG. 11A, the utilization degree calculation unit 1033 judges whether or not a user has visited a spot in units of meshes defined at a predetermined interval. Here, each of the sections A to Y corresponds to a spot. The utilization degree calculation unit 1033 detects which spots a user who visited a particular spot visited during a predetermined period based on the timing of the visit (for example, a period before and after every 12 hours).

[0074] In the diagram shown in Fig. 11B, it is shown that of 13 users who visited section A for the first time within a specified period (hereinafter referred to as checking in), after a unit time T (30 minutes as an example in this embodiment) has elapsed from the time of check-in, three users have moved to section B, two to section C, and one to section D. It is also shown that of the 13 users, after 2T has elapsed, three users have moved to section B, two to section C, two to section D, one to section E, and one to section F.

[0075] On the other hand, it is shown that, of the 13 users, 7 were in section B, 3 were in section C, 2 were in section D, and 1 was in section E, unit time T before the check-in timing. Also, it is shown that, of the 13 users, 5 were in section B, 2 were in section C, 3 were in section D, 2 were in section E, and 1 was in section F, 2T before the check-in timing.

[0076] In this way, the usage degree calculation unit 1033 may calculate the usage record of other spots by the user for 12 hours before and after (i.e., a 24-hour period as a relative time based on the check-in) based on the timing when the user checks in to the spot. By acquiring location information for a period before and after each predetermined unit time based on the check-in timing in this way, it is possible to grasp the user's behavior along the time series, and it is also possible to perform clustering taking into account the time series of spots visited by the user. Alternatively, the usage degree calculation unit 1033 may calculate the usage record of other spots by the user for 24 hours as a predetermined absolute time.

[0077] In the above embodiment, the importance calculation unit 1034 uses the whole of Japan as a population when calculating the usage importance of spots in the analysis area, but is not limited to this example. For example, a certain region (e.g., the Kanto region) may be used as the population, or a predetermined period may be used as the population to calculate the importance of spots in the analysis area.

[0078] Specifically, the importance calculation unit 1034 may calculate the usage importance Ir by, for example, the following formula: The technical idea of ​​the present disclosure can be applied to such specifications as well. Ir (importance of use) = Fr (frequency) x Rr (rarity) Fr=(Ar / Br) Rr = (Cr / Dr) Ar: The degree of use of the spot of the given type in the analysis area during a given survey period (e.g., one month) Br: The degree of utilization of the spot type in the analysis area for a given population period (e.g., one year). Cr: Utilization of all spots in a given population period Dr: The degree of use of the spot of the given type in the analysis area during the specified survey period

[0079] For example, the cluster generating unit 1035 may perform clustering of users who visited the clustered areas after performing the above-mentioned clustering of areas. The clustering of users may be performed using a method similar to the above-mentioned clustering of areas. For example, the cluster generating unit 1035 may generate clusters using hierarchical clustering, non-hierarchical clustering, or a known algorithm based on the commonality of the areas visited by users (or the commonality of the clusters to which the areas visited by users belong).

[0080] In addition, the cluster generation unit 1035 may match a pre-generated cluster of users with a cluster of areas generated by the above-mentioned area clustering, and recommend (recommend) an area belonging to the matched cluster to a user belonging to a specific cluster.

[0081] In the above embodiment, the utilization degree calculation unit 1033 divides the map into meshes at predetermined intervals (for example, 125 m intervals) in a grid pattern and determines whether or not a spot has been visited for each mesh. Here, the mesh interval can be set appropriately to 250 m, 500 m, 1 km, etc. In addition, when calculating the utilization degree of a spot within a mesh, the utilization degree may be calculated by applying the number of visits to the mesh to each different spot within the mesh. Alternatively, the utilization degree may be calculated by applying the number of visits to each section into which the mesh is further divided to the spots within the section.

[0082] For example, as shown in Fig. 12A, if the number of visits to a mesh M by a user is 300, the number of visits to all spots within the mesh M may be calculated as 300. Alternatively, as shown in Fig. 12B, the mesh M may be further divided into four sections, and the number of visits to each divided section may be calculated as the number of visits to spots within the section.

[0083] Also, based on the importance of the spot (or the importance of the type of spot) calculated in the above embodiment, the importance of the area to which the spot belongs may be evaluated along the time series (hereinafter, also referred to as area scheduling). FIG. 13 is a diagram comparing the relative values ​​of the importance for the clusters A to D of the users in a specific area along the time series. In this way, by scheduling the area, it is possible to recommend areas such as tourist spots that match the cluster to which the user belongs. Also, by scheduling the area, it is possible to recommend recommended tourist areas according to the travel schedule of the user who belongs to the specific cluster. Also, it is possible to grasp the genre of facilities that are lacking in a specific area according to the actual usage of a specific user. For example, it is possible to use it for a store opening plan such as increasing the number of cafes after grasping the needs such as wanting to go to a cafe after watching a movie. Also, based on the evaluation of the importance of the area along the time series, the area may be clustered.

[0084] The usage degree calculation unit 1033 may calculate the usage degree of the user taking into account the time series of each spot based on the user's location information, and the cluster generation unit 1035 may execute clustering based on the usage degree taking into account the time series of the spots. With this configuration, it becomes possible to analyze the characteristics of an area based on the usage degree of the user taking into account the time series of each spot, without calculating the importance of the spots.

[0085] In addition, sharing of specific information via communication lines is mainly performed via a WAN such as the Internet, but between information processing devices, communication may also be performed only via short-range wireless communication such as Bluetooth (registered trademark) and infrared communication without using a WAN.

[0086] In addition, in the above embodiment, an example of the manner in which each function is provided in the server 10 is described, but this is not limited to this form, and some or all of the functions may be implemented by multiple servers or terminal devices in a manner different from the above embodiment.

[0087] Furthermore, the present invention may be realized as a program that causes an information processing device to execute the functions of the server 10 described above, or as a non-transitory computer-readable recording medium that stores the program.

[0088] Various embodiments of the present invention have been described above, but these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and modifications thereof are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0089] 1: system, 10: server, 11: processor, 12: memory, 13: storage, 20: user terminal, 101: communication unit, 102: memory unit, 103: control unit, 1031: user information acquisition unit, 1032: spot information acquisition unit, 1033: utilization degree calculation unit, 1034: importance calculation unit, 1035: cluster generation unit.

Claims

1. A computer having a processor, acquiring location information of a plurality of users; Obtaining information on spots in a predetermined area; Calculating a degree of use of each of the spots by the user based on the location information of the user; and calculating the importance of the spot in the area, taking the degree of use into consideration.

2. The program according to claim 1 , further comprising: a step of clustering the areas based on the importance of the spots.

3. The program according to claim 2 , further comprising a step of comparing the importance of the spot in the area with a representative value of the importance of spots in a cluster generated by the clustering.

4. In the step of calculating the degree of use of the user, The program according to claim 1 , further comprising: calculating, for each pre-generated user cluster, a usage level of users belonging to that cluster.

5. calculating the importance of the spot in the area to users belonging to the cluster, taking into consideration the degree of use of the spot by users belonging to the cluster; and performing area clustering based on the importance of the areas, based on the importance of the areas.

6. In the step of clustering the areas, The program according to claim 1 , further comprising clustering the area based on a commonality of importance of the spots in the area.

7. Based on the result of the step of clustering the areas, The program according to claim 1 , further comprising clustering of users who have used the area.

8. Based on the result of the step of clustering the areas, The program according to claim 1 , further comprising matching between a pre-generated cluster of users and a cluster of areas generated by the area clustering.

9. In the step of calculating the degree of use of the user, Calculating at least one of the number of visits to the spot and the duration of stay at the spot as the degree of use; The program according to claim 1 , wherein the number of visits is at least one of a number of times as a stated number of users who visited the spot and a number of times as an actual number of users who visited the spot.

10. In the step of calculating the importance of the spot, The program according to claim 1 , further comprising: calculating the importance of the spot based on a predetermined period as a population.

11. The program according to claim 1 , further comprising a step of calculating an importance level taking into consideration a time series of the spots visited by the user, and performing clustering based on the importance level.

12. A step of matching a pre-generated cluster of users with a cluster of areas generated by the area clustering; The program according to claim 2 , further comprising a step of recommending areas belonging to the matched cluster to a user belonging to the cluster.

13. The program according to claim 1 , further comprising a step of evaluating the importance of the areas in chronological order.

14. The program according to claim 13 , further comprising the step of: clustering the areas based on an evaluation of the importance of the areas along a time series.

15. A computer having a processor, acquiring location information of a plurality of users; Obtaining information on spots in a predetermined area; Calculating a degree of use of the user based on location information of the user and taking into account a time series of the spot; A program for executing a step of performing clustering based on the degree of usage taking into account the time series of the spots.

16. A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in any of the inventions according to claims 1 to 15.

17. 16. An information processing apparatus comprising a control unit and a storage unit, the control unit executing all steps executed in the invention according to any one of claims 1 to 15.

18. A system comprising means for executing all the steps performed in any one of claims 1 to 15.

Images