App log analyzer

Abstract

To estimate an area suitable for photographing based on camera application use logs acquired from a plurality of user terminals, and easily grasp the characteristics of the area.SOLUTION: An application log analysis device 1 has: a terminal information acquisition unit that acquires, from a plurality of user terminals 9, information for specifying the user terminals 9, camera application use logs including date information, and positional information for specifying a place where the camera application is used for every use log; a POI estimation unit 17 that estimates a POI suitable for the use of the camera application by classifying the camera application use logs associated with the positional information related to the plurality of user terminals based on the positional information and the date information; and a POI category estimation unit 19 that applies a category related to the type of the POI to the POI estimated by the POI estimation unit 17 based on information related to a POI with a known category.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to an app log analysis device.

Background Art

[0002] In recent years, the number of terminal devices having a camera function has been increasing, and users are increasingly taking pictures casually. Therefore, for example, a method has been studied in which location information of terminals and the number of times of taking pictures of images with the location as a shooting location are acquired from a plurality of terminals, and a recommended shooting location is specified based on this information (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, as a result of the environment in which users can take pictures casually in recent years, it has become difficult to appropriately estimate a place that can be a recommended shooting location only by aggregating information related to the number of times of taking pictures obtained from a plurality of terminals. In addition, since the interests of users are also diversified, even if a recommended shooting location is simply specified, there may be cases where it is not known what features it has.

[0005] The present disclosure has been made in view of the above, and an object thereof is to provide a technology capable of estimating an area suitable for shooting and easily grasping its features based on the usage logs of camera apps acquired from a plurality of user terminals.

Means for Solving the Problems

[0006] To achieve the above object, an app log analysis apparatus according to an aspect of the present disclosure includes a terminal information acquisition unit that acquires, from a plurality of user terminals, information for identifying a user terminal, a usage log of a camera app including date and time information, and position information for specifying a usage location of the camera app for each usage log; a POI estimation unit that estimates a POI suitable for using the camera app by classifying each of the usage logs of the camera app associated with the position information regarding the plurality of user terminals acquired by the terminal information acquisition unit based on the position information and the date and time information; and a POI category estimation unit that assigns a category regarding the type of the POI to the POI estimated by the POI estimation unit based on information regarding a POI whose category is known.

[0007] According to the above app log analysis apparatus, for the usage logs of the camera app associated with the position information acquired from a plurality of user terminals, a POI is estimated by classifying based on the position information and the date and time information. Then, based on information regarding a POI whose category is known, a category regarding the type of the new POI is assigned. With such a configuration, it is possible to estimate an area suitable for shooting based on the usage logs of the app acquired from a plurality of user terminals, and since a category is assigned, the user can easily grasp what kind of POI each POI is. Furthermore, by performing category assignment using information regarding a POI whose category is known, for example, the same category can be assigned to POIs with similar characteristics, so the accuracy of category assignment is improved.

Advantages of the Invention

[0008] According to the present disclosure, there is provided a technique capable of estimating an area suitable for shooting and easily grasping its characteristics based on the usage logs of the camera app acquired from a plurality of user terminals.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments will be described in detail with reference to the drawings. In the description, the same reference numerals are assigned to the same elements or elements having the same function, and redundant descriptions are omitted.

[0011] [Application Log Analysis Device] FIG. 1 is a diagram conceptually explaining the operation of an application log analysis device 1 according to an embodiment.

[0012] The application log analysis device 1 has a function of acquiring the usage logs of applications (applications) in the plurality of user terminals 9 from the user terminals 9 and analyzing them to estimate POIs (Points of Interests) indicating the locations that the users of the user terminals 9 are interested in. In particular, the application log analysis device 1 according to the present embodiment has a function of estimating POIs by focusing on an application that captures images among the applications. The "application that captures images" is not limited to an application that only captures images, and may include, for example, an application that has a function such as posting the image to an SNS (Social Networking Service) after capturing and editing. That is, an application having a photographing function as a part of the application is referred to as an "application that captures images". In the following embodiments, the "application that captures images" may be described as a "camera application".

[0013] In the application log analysis device 1, the usage log of the camera application is collected from the usage logs of the applications on the user terminal 9, and the location of the POI is estimated. This is based on the presumption that the location where the camera application is used means that the user is interested in that location. In recent years, since it has become basic for the user terminal 9 to be equipped with a camera function, the number of applications with a photographing function has been increasing. Also, the camera application itself has been realized to perform operations up to posting on SNS, and the opportunity to take pictures when the user encounters something of interest has been increasing. Therefore, the application log analysis device 1 focuses on where the camera application is used, and estimates that the location where the frequency of operation of the camera application is high is a location where the user is likely to be interested. In the following embodiments, the "usage log of the camera application" may be described as the "camera application log". In the following embodiments, the "usage log of the camera application" may be described as the "camera application log".

[0014] The identification of the POI by the application log analysis device 1 can be performed in units of regions. The region for estimating the presence or absence of the POI is divided into a plurality of fine regions (for example, mesh units), and it is estimated whether a POI exists in each mesh. An image of identifying the POI in units of meshes by the application log analysis device 1 is shown in FIG. 1. FIG. 1 shows a state in which the map M is divided into nine meshes of user terminals. On the map M, based on the usage log of the camera application (camera application log) obtained by the application log analysis device 1 collecting the usage logs of the applications of a plurality of user terminals 9, the location P where the camera application is used in each user terminal 9 is displayed on the map. In the example shown in FIG. 1, it is shown that the camera application was used four times in the mesh m1 and once in the mesh m2. In this case, since the mesh m1 is estimated to be a region where the number of times the camera application is used is large, the application log analysis device 1 can estimate that the mesh m1 is a POI.

[0015] However, simply estimating POIs based only on the number of times the camera app is used in this way may not provide information with sufficient accuracy for use in, for example, recommendations. Also, as characteristics of POIs, while there are those that many users are interested in, there are also POIs that users with specific hobbies are particularly interested in. The former type of POIs can be easily identified from the number of times the camera app is launched, whereas the latter type of POIs may be launched fewer times than the former as the number of times the camera app is launched. Also, although it is estimated to be a POI because the number of times the camera app is used is high, the type of POI at that location may not be identifiable from this information alone. That is, it is assumed that there is room for improvement in the accuracy of information in the estimation of POIs based only on the number of times the camera app is used.

[0016] In the following embodiments, in the app log analysis device 1, a method for identifying POIs while improving the accuracy of information as POIs by combining the usage log of the camera app and other information will be described. Also, a method for identifying what kind of POIs are identified in the app log analysis device 1 will be described.

[0017] Note that the above "mesh unit" is an example, and the basic unit for estimating POIs is not limited to "mesh". For example, when a plurality of POIs (places suitable for shooting) are included in a certain area, it may be preferable to distinguish and handle POIs in a finer unit for that area. When the mesh is divided more finely, it can also be referred to as a "place". Also, regarding the "time series", it may be divided for each time period of a predetermined length, or the estimation of POIs may be performed by focusing on a specific time. In this way, the app log analysis device 1 can classify the camera app log based on the information identifying the location (position) where the camera app was used and the information identifying the date and time, and perform statistical processing related to POIs based on the classified results. Also, the app log analysis device 1 has a function of preparing and aggregating data that can be used for the above-described statistical processing.

[0018] Returning to FIG. 2, each part of the application log analysis device 1 and the user terminal 9 will be described. First, the user terminal 9 will be described. The "user terminal" is a terminal device that the user carries around, and a smartphone, a tablet terminal, etc. can be assumed. The user terminal 9 includes a user application 91, an image information holding unit 92, an application usage log acquisition unit 93, an application usage log transmission unit 94, a position information acquisition unit 95, and a position information transmission unit 96.

[0019] The user application 91 indicates a group of applications (applications) used by the user. In FIG. 2, as an example, a camera application A, a camera application B, a hobby application A, and a hobby application B are shown. The user operates the applications included in the user application 91 and performs operations such as using various user terminals 9.

[0020] The image information holding unit 92 has a function of holding an image taken by any of the camera applications included in the user application 91. Note that the image taken by the camera application may include both a still image and a moving image.

[0021] The app usage log acquisition unit 93 has a function of acquiring the usage log of the app included in the user app 91 on the user terminal 9. The app usage log may include information for identifying the app and information for identifying the usage time of the app. Further, information for identifying the type of the app may be included. The app usage log transmission unit 94 has a function of transmitting the app usage log acquired by the app usage log acquisition unit 93 to the app log analysis device 1. In the present embodiment, the app usage log will be described in the case where it includes information for identifying the time zone when the app is used. That is, the case where the information for identifying the usage time of the app is included in the app usage log will be described. However, the app usage log may be a log for operating the specific function of the app. For example, in the case of a camera app, the log of the shooting operation of the camera may be regarded as the "app usage log". In this case, the information for identifying the usage time of the app is the information for identifying the time when the function is operated. The configuration described in the following embodiments can also read the "app usage log" as the "log of the specific operation in the app" as described above.

[0022] The location information acquisition unit 95 has a function of acquiring the location information of the user terminal 9. The method for acquiring the location information is not particularly limited, and a known method can be used. The information handled here is mainly used for identifying the location of the user terminal 9 when the camera app is used, but basically, the location of the user terminal 9 may be acquired constantly (for example, repeatedly at intervals of several tens of seconds to several minutes). The location information transmission unit 96 has a function of transmitting the location information of the user terminal 9 acquired by the location information acquisition unit 95 to the app log analysis device 1.

[0023] Next, the application log analysis device 1 will be described. The application log analysis device 1 includes an application usage log reception unit 11, an application usage log holding unit 12, a location information reception unit 13, a location information holding unit 14, a filtering unit 15, an auxiliary information holding unit 16, a POI estimation unit 17, a POI information holding unit 18, a POI category estimation unit 19, a categorized POI information holding unit 20, and an output unit 21. Among the above-mentioned units, the application usage log reception unit 11 and the location information reception unit 13 function as terminal-related information acquisition units.

[0024] The application usage log reception unit 11 has a function of receiving and acquiring the application usage log transmitted from the user terminal 9. FIG. 3 shows an example of the application usage log acquired by the application usage log reception unit 11. As shown in FIG. 3, the application usage log may include the usage date and time of the application, the application name, and the type of the application. Note that, as information for identifying the application, character string information or the like for identifying the application may be used instead of the application name. The application usage log may include the usage log of the camera application, but may also include the usage logs of applications other than the usage log of the camera application.

[0025] The application usage log holding unit 12 has a function of holding the application usage log acquired by the application usage log reception unit 11. Note that the application usage log holding unit 12 holds the application usage logs related to a plurality of user terminals 9.

[0026] The location information receiving unit 13 has a function of acquiring the location information of the user terminal 9 transmitted from the user terminal 9. FIG. 4 shows an example of the location information acquired by the location information receiving unit 13. As shown in FIG. 4, the location information includes the date and time and the location information at that date and time. Naturally, this information includes information for identifying the user terminal 9. In FIG. 2, the location information receiving unit 13 is configured to acquire the location information of its own terminal acquired by the user terminal 9 from the user terminal 9. However, the location information does not necessarily have to be acquired directly from the user terminal 9. In the application log analysis device 1, for example, the location information of the base station where the user terminal 9 is located may be used as the location information of the user terminal 9. In such a case, the configuration may be such that information (such as the location information of the base station) to be used as the location information of the user terminal 9 is acquired from a device different from the user terminal 9 (for example, a device that manages the presence of the user terminal 9).

[0027] Note that FIG. 4 also includes columns such as "mesh" and "activity area". The mesh is information for identifying the mesh corresponding to the location information at each date and time. Since this information is based on the mesh used when identifying the POI in the application log analysis device 1, it is given in the application log analysis device 1.

[0028] In addition, the activity range is information that identifies whether the position of the user terminal 9 at each date and time corresponds to the user's daily life range or not (outside the daily range) based on the position information accumulated for the user who holds the user terminal 9. The criterion for determining whether it is the daily life range is not particularly limited. For example, there is a method of setting it within a predetermined range (for example, within a radius of 1.5 km assuming a walking range) based on the user's home address. Also, after specifying the maximum value of the daily movement distance from the user's home based on the past movement history of the user, the distance including 90% of the maximum values of each day may be specified as the daily life range. In addition, existing technologies may be used to distinguish between the user's daily life range and the rest. Here, the case of distinguishing the user's staying location (the position of the user terminal 9) into two types, the daily life range and the rest, has been described. However, it may be divided according to the reason for movement, such as daily life / business trip / travel. The result of distinguishing the user's staying location (information for specifying the activity range) can be used when specifying the POI described later. Therefore, this information is provided in the app log analysis device 1.

[0029] The position information holding unit 14 has a function of holding the position information of the user terminal 9 acquired by the position information receiving unit 13. Note that the position information holding unit 14 holds the position information regarding a plurality of user terminals 9. The above-mentioned association with the mesh and the specification of the activity range may be performed when holding the position information in the position information holding unit 14, or may be performed at a different timing (for example, when estimating the POI).

[0030] The filtering unit 15 has a function of performing filtering using the app usage information held in the app usage log holding unit 12 and the position information held in the position information holding unit 14. In the present embodiment, filtering is an operation of associating the usage log of the camera app (camera app log) included in the app usage log with the position information and then sorting whether to use it for estimating the POI. Examples of the filtering method include a method of selecting the camera app log itself and a method of selecting the user who uses the camera app. Details of the filtering will be described later.

[0031] The auxiliary information holding unit 16 has a function of holding, as auxiliary information, information other than the information acquired from the user terminal 9 that can be used for filtering in the filtering unit 15.

[0032] FIG. 5 shows an example of the auxiliary information held in the auxiliary information holding unit 16. FIG. 5(a) is an example of information related to the change in population per mesh. In FIG. 5(a), information indicating the change in population per unit time is held in association with information (mesh ID) for specifying a mesh. By using such information, it is possible to analyze, for example, how many people are in an area (mesh) where the camera app is used frequently.

[0033] FIG. 5(b) shows an example of information indicating the attributes of the users of the user terminal 9. In FIG. 5(b), information indicating attributes (child-rearing generation, camera hobby, fishing, mountain climbing, etc.) and information serving as the basis for specifying the attributes (app, SNS, questionnaire, etc.) are associated with information (user ID) for specifying a user. For example, for a user specified by the user ID AA01, it is shown that the attribute is specified as "child-rearing generation" based on the usage history of apps for the child-rearing generation and the response history to questionnaires for the child-rearing generation. With such information, for example, when using the camera app log of users with a specific attribute, it may be possible to estimate POIs specialized for people with a specific attribute. Thus, the auxiliary information holding unit 16 holds auxiliary information that can be used for filtering. Note that the present invention is not limited to what is shown in FIG. 5, and auxiliary information can be freely collected and used according to the filtering concept and the like.

[0034] The POI estimation unit 17 has a function of estimating a POI based on the camera app log after filtering by the auxiliary information holding unit 16. A method for estimating a POI basically includes extracting meshes where the number of times the camera app is used per mesh is large (for example, equal to or greater than a predetermined value) and setting them as POIs.

[0035] The POI information holding unit 18 has a function of holding information on the mesh estimated to be a POI by the POI estimation unit 17. FIG. 6 shows an example of the POI information held in the POI information holding unit 18. As shown in FIG. 6, the POI information includes information for specifying the POI (POI ID) and information for specifying the mesh estimated to be a POI (mesh ID). Note that, as will be described later, when the category of the POI is specified, the destination for holding the information may be changed from the POI information holding unit 18 to the categorized POI information holding unit 20.

[0036] The POI category estimation unit 19 has a function of assigning a category to the POI estimated by the POI estimation unit 17. The category assigned in association with the POI indicates a classification according to the characteristics of the POI. For example, when a specific building (such as a castle or a temple) exists in the mesh estimated to be a POI, the type of this building may be used as the category. Also, when it is estimated that a mesh is a POI for a user with a specific hobby (such as fishing or mountain climbing), the hobby may be used as the category. In addition, for example, for a mesh that becomes a POI only during a specific period, such as a famous cherry blossom spot, information specifying the reason for becoming a POI (for example, famous cherry blossom spot) may be used as the category. Thus, the category can be set from various types of information as information indicating the characteristics of the POI. Also, when specifying the category, for example, the information used for filtering in the filtering unit 15 can also be used. This point will be described later.

[0037] The categorized POI information holding unit 20 has a function of holding information on the POI (mesh) to which a category has been assigned in the POI category estimation unit 19. FIG. 7 shows an example of the categorized POI information held in the categorized POI information holding unit 20. As shown in FIG. 7, the categorized POI information has information for specifying the category added compared to the information shown in FIG. 6.

[0038] The output unit 21 has a function of outputting the information held by the POI information holding unit 18 and the categorized POI information holding unit 20. The output unit 21 has a function of preparing and transmitting the information of the POI to be extracted based on a request from an external device or the like, for example. Further, the output unit 21 may output information to a display device such as a monitor or a printer or the like.

[0039] [Application Log Analysis Method] Next, with reference to FIGS. 8 to 16, an application log analysis method by the application log analysis apparatus 1 will be described. As described above, various methods are assumed as the filtering method. Therefore, first, after explaining the overall flow, detailed procedures according to the filtering method will be described.

[0040] (Series of Procedures) As shown in FIG. 8, the application log analysis apparatus 1 first executes step S01. In step S01, the application usage log receiving unit 11 of the application log analysis apparatus 1 acquires the application usage log from the user terminal 9, and the position information receiving unit 13 acquires the position information from the user terminal 9. The acquired data is held in the application usage log holding unit 12 (application usage log) and the position information holding unit 14 (position information). The acquisition of information from the user terminal 9 may be performed periodically (for example, every few hours to several days), or may be performed by transmitting an information providing request from the application log analysis apparatus 1 to the user terminal 9.

[0041] Next, the application log analysis device 1 executes step S02. In step S02, in the filtering unit 15 of the application log analysis device 1, based on the information held in the application usage log holding unit 12 and the position information holding unit 14, the camera application log is extracted, and the usage log and the position information are associated with each other. The camera application log includes the time when the application was used. Therefore, the position information corresponding to the time is extracted from the information held in the position information holding unit 14 and associated. Note that the processing in this step S02 may be performed at the timing when information is acquired from the user terminal 9 in step S01. Also, the application usage log after the above association may be held in the application usage log holding unit 12.

[0042] Next, the application log analysis device 1 executes step S03. In step S03, in the filtering unit 15, based on the above information and the information held in the application usage log holding unit 12, the position information holding unit 14, and the auxiliary information holding unit 16, extraction (filtering) of data to be used for estimating the POI is performed.

[0043] Next, the application log analysis device 1 executes step S04. In step S04, in the POI estimation unit 17, the POI is estimated from the camera application log extracted in step S03. As a method for estimating the POI, for example, a period to be estimated (for example, several hours to several tens of days) is set, and in the period, the mesh unit with a large number of camera application logs (that is, a large number of activations of the camera application) is determined as the POI. As an example, a method of determining in advance a threshold value for estimating the POI and determining the area (mesh) where the number of camera application logs exceeds the threshold value as the POI can be mentioned. However, the criteria for determining the POI are not limited to this. The information related to the area (mesh) estimated as the POI is held in the POI information holding unit 18, for example, in a state where information (ID) for specifying the POI is given. Note that also in the estimation of the POI by the POI estimation unit 17, the information held in the application usage log holding unit 12, the position information holding unit 14, and the auxiliary information holding unit 16 may be used as necessary.

[0044] Next, the application log analysis device 1 executes step S05. In step S05, the POI category estimation unit 19 estimates the category of the POI for the area (mesh) estimated to be a POI in step S04. Information related to the POI for which the category has been estimated is held in the category-identified POI information holding unit 20 in a state where, for example, the estimated category as the estimation result is associated.

[0045] Note that various modes are assumed for the specific procedures of steps S03 to S05. Therefore, the specific procedures will be described later.

[0046] Next, the application log analysis device 1 executes step S06. In step S06, the output unit 21 extracts, from the POI information held in the POI information holding unit 18 and the category-identified POI information holding unit 20, those that satisfy a predetermined condition and outputs them. The predetermined condition includes, for example, the conditions included in a request from an external device or the like. Through the above series of processes, the estimation of the POI and the estimation of the category are completed.

[0047] Next, with reference to FIGS. 9 to 16, a specific example of the procedure related to steps S03 to S05 described above will be described. As described above, various types of information can be assumed for the information used for filtering and POI category estimation. Therefore, below, how to use typical information used for filtering and / or category estimation will be described.

[0048] (Example of filtering based on the user's activity range) FIG. 9 is a diagram for explaining a filtering procedure using information on the user's activity range. In this case, the filtering unit 15 of the application log analysis device 1 calculates the user's daily life range based on the information held in the position information holding unit 14 as step S11. Note that the calculation of the daily life range (step S11) may be performed in advance.

[0049] Next, as step S12, the filtering unit 15 checks whether the location where the camera app is used is outside the daily life area. This is determined based on whether the location information associated with the camera app log is outside the daily life area. In the example shown in this embodiment, when FIGS. 3 and 4 are viewed in association with each other, it can be specified that the user terminal 9 was outside the daily life area when the camera app A was used at "13:00 - 13:05". When the camera app is used outside the daily life area (step S12 - YES), it is determined that the log is used for the estimation of the POI (step S13). On the other hand, when the camera app is used within the daily life area (that is, not used outside the daily life area) (step S12 - NO), it is determined that the log is not used for the estimation of the POI (step S14).

[0050] In this way, by paying attention to the user's activity area and the usage timing of the camera app, the camera app log used for the estimation of the POI may be extracted. In this case, for example, a configuration can be realized in which the log when the camera app is used in the user's daily life is not used for the estimation of the POI. In the above example, a distinction is made between the daily life area and the outside area, but the filtering conditions may be switched according to the purpose of estimating the POI.

[0051] (Example of filtering focusing on user behavior) FIG. 10 is a diagram for explaining the filtering procedure according to the types of apps used before and after the camera app as filtering focusing on the user's behavior. In this case, as step S21, the filtering unit 15 of the app log analysis device 1 identifies the apps used (operated on the user terminal 9) by the user within a predetermined time (for example, 10 minutes before and after) before and after the camera app based on the information held in the app usage log holding unit 12. In the example shown in FIG. 3, for example, the sightseeing app, the SNS app, and the plant encyclopedia app shown in the 10 minutes before and after (12:50 - 13:00 and 13:05 - 13:15) of the usage time period (13:00 - 13:05) of the camera app A can be identified as the apps used before and after the camera app A.

[0052] Next, as step S22, the filtering unit 15 checks whether the SNS app is included in the apps used before and after the camera app. This is determined based on whether the SNS app is included in the apps extracted in step S21 above.

[0053] In the example shown in this embodiment, the "SNS app" is exemplified, but this is just an example, and it is an example considering the high affinity between the camera app and the SNS app. In this embodiment, when using the SNS app before and after the camera app, it is presumed that (or intended to) link the image captured by the camera app with the SNS app, and filtering is performed based on the idea of using this camera app log for the estimation of the POI. When the SNS app is used before and after the camera app A (step S22 - YES), it is determined that the log is used for the estimation of the POI (step S23). On the other hand, when the SNS app is not used before and after the camera app A (step S22 - NO), it is determined that the log is not used for the estimation of the POI (step S24).

[0054] In this way, by focusing on the relationship between the camera app and the apps used before and after the camera app, the camera app log used for the estimation of the POI may be extracted. In this case, for example, a configuration capable of extracting the camera app log used for the estimation of the POI by focusing on a specific action of the user before and after using the camera app can be realized. Instead of the above example, for example, a configuration that focuses only after using the camera app may be used. Also, instead of the SNS app, extraction may be performed based on the presence or absence of the use of an app for a specific hobby.

[0055] (Example of category identification using user behavior) When extracting the camera app log used for estimating POI using the types of apps used before and after the camera app shown in FIG. 10, the type of app used as the criterion for extracting the camera app log may be used as the type of category assigned to the POI. FIG. 11 is a diagram for explaining the procedure of estimating the category using the same information when performing filtering according to the types of apps used before and after the camera app as filtering focusing on the user's actions.

[0056] In this case, the filtering unit 15 of the app log analysis device 1 identifies, as step S31, the apps used by the user (operated on the user terminal 9) within a predetermined time (for example, 10 minutes before and after) before and after the camera app based on the information held in the app usage log holding unit 12. This procedure is the same as step S21 shown in FIG. 10. Further, the filtering unit 15 extracts the camera app log used for estimating the POI by the procedure shown in FIG. 10. The procedure at this time is, for example, the same as steps S22 to S24 in FIG. 10.

[0057] Next, after identifying the camera app log used for estimating the POI by the procedure shown in FIG. 10, the POI estimation unit 17 performs the process of estimating the POI as step S32. The procedure for estimating the POI is not particularly limited. Next, for the POI estimated in step S32, the POI category estimation unit 19 identifies the category of the POI as step S33. At this time, the POI category estimation unit 19 focuses on the app used as the criterion for extracting the camera app log in the filtering unit 15, and assigns a category corresponding to the type of the app to the POI. In the example shown in FIG. 10, the camera app log used for estimating the POI is extracted based on the SNS app. In this case, for the area (mesh) estimated to be the POI, the category of the POI may be "SNS related (POI with high affinity to the SNS app)".

[0058] When the app used as a criterion for extracting the camera app log used for POI estimation has a strong relationship with more specific hobbies (e.g., fishing, mountain climbing, etc.), the reason for using the camera app may be related to that hobby. Therefore, when estimating POIs from the camera app log extracted using information related to such hobbies, these POIs may be related to the hobbies. Thus, as described above, by assigning information identifying the type of app used as the extraction criterion as the category related to the POI that is the estimation result, it is possible to estimate and assign a category that seems highly relevant to the POI.

[0059] In this way, in addition to extracting the camera app log used for POI estimation by focusing on the relationship between the camera app and the apps used before and after the camera app, it may also be configured to use information (here, the type) about the apps used before and after the camera app as the estimation result of the category for the POI. In this case, for example, by focusing on the specific actions of the user before and after using the camera app, a configuration that can identify the category of the POI can be realized.

[0060] Note that depending on the type of app for extracting the camera app log used for POI estimation, the use or non-use of the logic used in FIG. 11 may be changed. For example, when extracting the camera app log for POI estimation based on an app related to a hobby, the category is assigned using the method shown in FIG. 11, but when extracting the camera app log based on other apps (e.g., apps that seem to have low relevance to hobbies), the category may not be assigned using the method shown in FIG. 11.

[0061] (Example of filtering and category identification using user segments) Instead of filtering and category identification using information on the types of applications used before and after the camera application described with reference to FIGS. 10 and 11, the same procedure may be performed using other information. The other information is not limited to information obtained from the user terminal 9, such as, for example, the usage log of the application and the location information of the user terminal 9, and may be information held in the auxiliary information holding unit 16 or the like. Hereinafter, an example focusing on attributes will be described as a segment for classifying users.

[0062] FIG. 12 is a diagram for explaining a procedure for performing filtering and category identification based on information on the attributes of the user held in the auxiliary information holding unit 16 as filtering focusing on the attributes of the user. In this case, first, the filtering unit 15 of the application log analysis device 1 identifies a segment for each user who owns the user terminal 9 based on the information held in the auxiliary information holding unit 16 as step S41. For example, when the auxiliary information holding unit 16 holds the information shown in FIG. 5(b), the attributes assigned to each user can be used as segments. As other segments, for example, segments based on the gender, place of residence, occupation, etc. of the user can also be considered.

[0063] Next, as step S42, the filtering unit 15 classifies (extracts) the camera application logs used for the estimation of the POI for each segment of the user. This procedure corresponds to the extraction of the camera application logs used for the estimation of the POI (for example, steps S12 to S14 in FIG. 9). In order to classify the camera application logs for each segment, there will be as many groups divided for the estimation of the POI as the number of segments. Note that the group actually performing the estimation of the POI may be a part of these groups.

[0064] Next, as step S43, the POI estimation unit 17 performs a process of estimating a POI. The method for estimating the POI is not particularly limited, but for each classification based on segments, a process related to POI estimation is performed. Next, as step S44, the POI category estimation unit 19 identifies the category of the POI. At this time, the POI category estimation unit 19 uses the segment used for the classification of the camera app log in the filtering unit 15 as the category related to the POI.

[0065] As described above, since the camera app logs used for POI estimation are classified based on segments, it is considered that the POIs estimated from the classified camera app log group are related to those segments. Therefore, when estimating a POI from a camera app log classified using a segment such as an attribute related to the user, this POI may be related to that segment. Thus, as described above, by assigning information related to the segment used for the classification of the camera app log as the category related to the POI that is the estimation result, a category that seems to be more relevant can be assigned to the POI.

[0066] In this way, it may be configured to focus on the segment of the user who owns the user terminal 9, extract (classify) the camera app logs used for POI estimation, and further assign information related to the segment as a category to the estimated POI. In this case, since a category of a POI corresponding to the segment of the user can be assigned, a configuration can be realized that can assign a category estimated to be highly accurate to some extent. Note that how to acquire the information used for the segment (information as shown in FIG. 5(b)) and based on which information to classify the camera app log can be changed as appropriate.

[0067] (Example of Filtering and Category Identification Focusing on the Type of Camera App) Next, filtering and category identification focusing on the types of camera apps will be described with reference to FIG. 13. This method can be effective, for example, when a camera app specialized for a specific use (e.g., a camera app having functions suitable for recording related to a specific hobby) is being used on the user terminal 9. As shown in FIG. 13, first, the POI estimation unit 17 of the app log analysis device 1 classifies the camera app log acquired from the user terminal 9 as step S51 for each type of camera app. Since the user terminal 9 often has multiple types of camera apps installed, the camera app log transmitted from one user terminal 9 may include those derived from multiple types of camera apps. Therefore, it is classified for each type.

[0068] Next, as step S52, the POI estimation unit 17 performs a process of estimating the POI for each type of the classified camera app. The method for estimating the POI is not particularly limited, but the process related to POI estimation is performed for each group of camera app logs classified based on the type of camera app.

[0069] Next, the POI category estimation unit 19 determines, as steps S53 to S55, whether to estimate the category of the POI based on the type of camera app. When the camera app is of a general type (e.g., one that is standardly installed on the user terminal 9), the classification result is unlikely to be biased towards a specific one based on the type of camera app. On the other hand, since the startup log of a camera app assumed to be used for a specific purpose has a high relevance to that specific purpose, it is considered effective to use that purpose as the app's category. As described above, since the camera app logs used for POI estimation are classified based on the segment, the POI estimated from the classified group of camera app logs may be related to that segment.

[0070] Therefore, as step S53, the POI category estimation unit 19 determines whether the camera application used as the classification criterion is for a specific category. Here, if the camera application is for a specific category (step S53 - YES), the category of the camera application (usage, features, etc.) is assigned to the category of the POI (step S54). On the other hand, if the camera application is not for a specific category (step S53 - NO), the category of the camera application is not assigned to the category of the POI (step S55), and no category is given to the POI. In this way, by focusing on the type of camera application, the camera application log used for POI estimation is extracted (classified), and further, for the estimated POI, the information may be assigned as a category according to the type of camera application. In this case, it becomes possible to specify the category of the POI by using the relationship between the camera application and the category. In particular, when a characteristic camera application is used, a configuration that can accurately assign a category can be realized. Note that whether to use the type of camera application for the category of the POI can be determined in advance and held in the auxiliary information holding unit 16 or the like in advance as information serving as a criterion for performing the category assignment.

[0071] (POI estimation considering the population in mesh units) Next, as a method for estimating the POI, an example considering other requirements will be described instead of simply taking the mesh with a large number of camera application logs as the POI. In the above embodiment, the application log analysis device 1 has been basically described assuming that, as shown in FIG. 1, the mesh with a large number of camera application logs within a predetermined period is estimated as the POI. However, for example, if the number of user terminals 9 existing in the mesh is large, it is assumed that the number of camera application logs increases regardless of the presence or absence of the POI in the mesh. Therefore, a method of estimating the POI may be adopted after performing a calculation considering the population in the mesh. FIG. 14 shows an example thereof.

[0072] First, as shown in step S61, when estimating the POI, the POI estimation unit 17 calculates the total number of times of the camera application log for each mesh unit. Next, as shown in step S62, the POI estimation unit 17 calculates the ratio of the number of times of the camera application log to the population for each mesh unit. In order to perform this calculation, for example, population information as shown in FIG. 5(a) is acquired in advance. When the auxiliary information holding unit 16 holds the information shown in FIG. 5(a) in advance, for example, the number of times of the camera application log in each time zone (for example, the time zone corresponding to the population statistics shown in FIG. 5(a)) in each mesh is first calculated, and this is divided by the population in the corresponding time zone of the corresponding mesh shown in FIG. 5(a). As a result, the number of times of the camera application log with respect to the population is calculated. After performing the above calculation for each mesh, the POI estimation unit 17 estimates, as step S63, a mesh in which "camera application log number / population" is equal to or greater than a predetermined value as a POI. With such a configuration, it is possible to prevent the situation where a place where the number of camera application logs has increased simply due to an increase in the population is estimated as a POI.

[0073] Note that when estimating the POI using a camera application log with a time width wider than the unit time zone (which is 1 hour in FIG. 5(a)) that is the unit of population calculation shown in FIG. 5(a), various additional calculations and changes may be made. For example, after calculating "camera application log number / population" for each unit time zone, it may be possible to obtain the average of the calculation results in each unit time zone. Also, it may be possible to obtain the average of population fluctuations in advance for each unit time zone, and for each mesh, obtain the ratio of the sum of the number of times of the camera application log in all of the time zones that are the POI estimation targets with respect to this. Thus, in the concept of using the ratio of the number of camera application logs to the population, the calculation method can be appropriately changed.

[0074] (Specification of the POI category using data of POIs whose categories were specified in the past) Next, with reference to FIGS. 15 and 16, another method for specifying the category of a POI will be described. The previous examples basically explained the case of estimating a POI from the number of camera application logs per mesh unit and assigning a category to the POI from the camera application log or other peripheral information. In contrast, a method of assigning a category to a POI whose category has not been specified will be described using data of POIs whose categories have been specified in the past (the categories are known).

[0075] First, as step S71, the POI category estimation unit 19 acquires information on the change over time of the number of times the camera application is used for the information of the POIs whose categories have been specified and are held in the category-specified POI information holding unit 20. As described above, the category-specified POI information holding unit 20 holds information for specifying POIs to which categories are assigned. Also, using the mesh ID, information related to the position information of the mesh can be extracted from the position information holding unit 14. Using these pieces of information, the POI category estimation unit 19 creates information related to the change over time of the number of times the camera application is used for each POI. FIG. 16 is a diagram showing an example of the change over time. FIG. 16 shows, for example, the change over time of the number of times the camera application is used at a POI that is a cherry blossom spot. At a cherry blossom spot, it is assumed that during the cherry blossom blooming period (period T1 shown in FIG. 16), the number of times the camera application is used increases extremely, and the distribution peaks especially on the day of full bloom (date Td shown in FIG. 16). Thus, there may be spots at a POI where the number of times the camera application is used increases only in a specific season. Also, for example, at a spot where the evening scenery is characteristic, the number of times the camera application is used may increase only in the evening. Thus, for a POI where the number of times the camera application is used can vary during a specific period or time zone, it may be possible to specify the category of the POI using that variation. Specifically, it is a method of specifying the category of a POI whose category is unknown with reference to the variation (seasonal variation or time variation) of the camera application log at an existing POI whose category is known.

[0076] To implement the above method, first, as step S71, for POIs with known categories, the POI category estimation unit 19 acquires the temporal change of the camera app log. Then, as step S72, for POIs with unspecified categories, the POI category estimation unit 19 acquires the temporal change of the camera app log. Furthermore, the temporal change may be quantified using, for example, time-series clustering or the like. Also, a value evaluating the peak magnitude may be obtained using, for example, the ratio between the number of camera app logs at the peak time (e.g., the full bloom date of cherry blossoms) and the average number of camera app logs on other days.

[0077] As described above, for category identification using the temporal change of the camera app log, for example, for POIs with a small temporal change in the camera app log, subsequent processing may be omitted. Also, whether to calculate daily variation (which changes on a daily to monthly basis like a cherry blossom spot) or temporal variation (which is characterized by temporal change like a sunset spot) may be configured to be selected, for example, from the data variation or trend in POIs with unspecified categories.

[0078] Next, as step S73, the POI category estimation unit 19 determines whether there is a tendency similar to the temporal change of the camera app log count (temporal change of the number of times the camera app is used) calculated in step S72 among the temporal changes of the camera app log counts (temporal change of the number of times the camera app is used) for each POI calculated in step S71. At this time, for example, when the temporal change is quantified in the previous processing, similar ones may be searched by comparing the numerical values. Also, when quantification is not performed, POIs showing similar variations may be identified using a classification method using known statistical processing, or for example, classification may be performed focusing on the peak date and time and the distribution of the number of times the camera app is used centered around the peak.

[0079] If something having a tendency similar to the change over time of the number of times the camera app was used (change over time of the number of camera app logs) calculated in step S72 is included in the data of the category-specified POIs calculated in step S71 (step S73 - YES), it is determined that the category-specified POIs and the POIs with unspecified categories are included in the same category, and the same category as the POIs with a similar tendency is assigned to the POIs with unspecified categories. On the other hand, if something having a tendency similar to the change over time of the number of times the camera app was used (change over time of the number of camera app logs) calculated in step S72 is not included in the data of the category-specified POIs calculated in step S71 (step S73 - NO), in this procedure, it is determined not to assign a category to the POIs with unspecified categories (step S75).

[0080] In this way, by using the method of assigning the same category to POIs with similar changes over time using the data of the change over time of the number of camera app logs (number of times the camera app was used) in POIs where the category has been specified, it becomes possible to accurately assign categories to POIs that particularly have characteristics where the number of times the camera app is used can change over time.

[0081] Note that as POIs where seasonal variations (daily variations) are assumed, for example, areas where there are things like plants whose blooming times change can be considered. Also, places affected by climate change (e.g., ski resorts, mountainous areas, etc.) are also assumed to have seasonal variations in the number of times the camera app is used.

[0082] On the other hand, as POIs where time variations are assumed, for example, places affected by the position of the sun can be considered. Also, places where some event is held at a specific time (e.g., feeding animals is done at a fixed time every day, etc.) are also assumed to have time variations in the number of times the camera app is used. Also, areas where the number of times the camera app is used becomes large only in a specific time zone of a specific season can also be assumed.

[0083] As described above, when identifying POIs from the number of times the camera app is used, by focusing on this time variation or daily variation and adopting a configuration in which POIs showing similar variations are determined to belong to the same category, it is possible to identify the category of POIs with an unspecified category by using the information of known POIs.

[0084] Note that instead of the configuration of "determining that POIs showing similar variations belong to the same category", for example, it may be determined that POIs showing similar variations belong to the same type of category (not the same category but a category having similar characteristics). For example, a famous cherry blossom spot and a famous autumn foliage spot are expected to have the camera app log concentrated in a specific period in the same way. However, the periods when the usage log of the camera app is concentrated are different between spring and autumn. Thus, it may be configured to complement the information for estimating the category of POIs with an unspecified category by using the information of POIs having similar variations although the periods are different.

[0085] Note that the filtering procedure and the categorization procedure shown in FIGS. 9 to 15 can be combined as appropriate. For example, as filtering, a method of combining a plurality of the above-described methods (for example, combining filtering using the activity range and filtering by the apps used before and after) can also be adopted.

[0086] [Function] According to the above-described application log analysis device 1, for the usage log of the camera application associated with the location information acquired from a plurality of user terminals 9, the POI is estimated by classifying based on the location information and the date and time information. Then, based on the information related to the POI whose category is known, a category regarding the type of the new POI is assigned. With such a configuration, based on the usage log of the application acquired from a plurality of user terminals, it is possible to estimate an area suitable for shooting. Also, since the category is assigned, the user can easily grasp what kind of POI each POI is. Furthermore, by performing category assignment using the information related to the POI whose category is known, for example, the same category can be assigned to POIs with similar characteristics, so the accuracy of category assignment is improved.

[0087] An area with a large number of usage logs of the camera application can be assumed to be a POI suitable for the use of the camera application for more users. Therefore, by estimating the above area as a POI, it is possible to estimate an area suitable for shooting.

[0088] Also, among the POIs, there are POIs with characteristics in the change over time of the usage log of the camera application. Therefore, by comparing the change over time of the usage log of the camera application in the POI whose category is known with the change over time of the usage log of the camera application at the location estimated as the POI, and by adopting a configuration for estimating the category of the POI, it is possible to accurately estimate the category, especially for the POIs of the category with characteristics in the change over time.

[0089] Also, when the change over time of the usage log of the camera application in the POI whose category is known is similar to the change over time of the usage log of the camera application at the location estimated as the POI, the same category as the POI whose category is known may be assigned. With such a configuration, based on the tendency to be similar to the POI whose category is known, the same category is assigned to the POI, so the category can be estimated accurately.

[0090] Also, like the above-described application log analysis device 1, after filtering each of the usage logs of the camera application associated with the location information acquired from a plurality of user terminals 9 based on the terminal-related information which is information regarding each of the plurality of user terminals, a POI is estimated by classifying based on the location information and the date and time information. In such a configuration, since the POI is estimated after removing the usage logs of the camera application that may be noise in the estimation of the POI by performing filtering, a location more suitable as the POI can be estimated.

[0091] As described above in detail, it is obvious to those skilled in the art that this embodiment is not limited to the embodiments described in this specification. This embodiment can be implemented as a modified and changed aspect without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is for the purpose of illustrative explanation and has no restrictive meaning for this embodiment.

[0092] For example, as described above, the application log analysis device 1 described in the above embodiment can be variously modified. Therefore, the functions of each part may be changed in response to the changes in each part.

[0093] For example, in the above embodiment, it has been described that various changes can be made to the application log analysis device 1. However, the application log analysis device 1 only needs to include a configuration for specifying the category using the information of the POI whose category is known at least when estimating the category of the POI newly estimated in the POI estimation unit 17. Within this range, various changes can be made to the above-described application log analysis device 1. For example, in the application log analysis device 1, the filtering by the filtering unit 15 may be omitted.

[0094] [Others] The block diagrams used in the description of the above embodiments show functional unit blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one physically or logically combined device, or may be realized using two or more physically or logically separated devices directly or indirectly (for example, using wired, wireless, etc.) connected, and these multiple devices. The functional block may be realized by combining software with the above one device or the above multiple devices. Also, the term "device" described in this embodiment can be read as a circuit, device, unit, etc.

[0095] Functions include, but are not limited to, judgment, decision, determination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, regarded as, notification (broadcasting), notification (notifying), communication (communicating), transfer (forwarding), configuration (configuring), reconfiguration (reconfiguring), allocation (allocating, mapping), assignment (assigning), etc. For example, a functional block (component) that functions as transmission is called a transmission unit or a transmitter. In any case, as described above, the realization method is not particularly limited.

[0096] FIG. 17 is a diagram showing an example of the hardware configuration of the application log analysis apparatus 1 according to this embodiment. Physically, the application log analysis apparatus 1 may be configured as a computer device including a processor C1, a memory C2, a storage C3, a communication device C4, an input device C5, an output device C6, a bus C7, and the like.

[0097] In the following description, the term "device" can be read as a circuit, device, unit, etc. The hardware configuration of the application log analysis device 1 may be configured to include one or more of each device shown in FIG. 17. Alternatively, it may be configured without including some of the devices.

[0098] Each function in the application log analysis device 1 is realized by causing a processor C1 to load a predetermined software onto hardware such as a memory C2, so that the processor C1 performs operations and controls communication by a communication device C4 and reading and / or writing of data in the memory C2 and a storage C3.

[0099] The processor C1, for example, operates an operating system to control the entire computer. The processor C1 may be composed of a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, etc. Further, the processor C1 may be configured to include a GPU (Graphics Processing Unit). For example, each functional unit of the application log analysis device 1 may be realized by the processor C1.

[0100] Also, the processor C1 reads a program (program code), software module, and data from the storage C3 and / or the communication device C4 into the memory C2, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, each functional unit of the application log analysis device 1 may be stored in the memory C2 and realized by a control program operating on the processor C1. Although it has been described that the above various processes are executed by one processor C1, they may be executed simultaneously or sequentially by two or more processors C1. The processor C1 may be implemented on one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

[0101] Memory C2 is a computer-readable recording medium and may be composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory C2 may also be referred to as a register, cache, main memory (main storage device), etc. Memory C2 can store a program (program code), software module, etc. executable for implementing the settlement information management method according to an embodiment of the present invention.

[0102] Storage C3 is a computer-readable recording medium and may be composed of at least one of, for example, optical discs such as CD-ROM (Compact Disc ROM), hard disk drives, flexible disks, magneto-optical disks (e.g., compact discs, digital versatile discs, Blu-ray (registered trademark) discs), smart cards, flash memories (e.g., cards, sticks, key drives), floppy (registered trademark) disks, magnetic strips, etc. Storage C3 may also be referred to as an auxiliary storage device. The above-mentioned recording medium may be, for example, a database, server, or other appropriate medium including Memory C2 and / or Storage C3.

[0103] Communication device C4 is hardware (transceiving device) for performing communication between computers via a wired and / or wireless network and is also referred to as, for example, a network device, network controller, network card, communication module, etc.

[0104] The input device C5 is an input device (such as a keyboard, mouse, microphone, switch, button, sensor, etc.) that receives external input. The output device C6 is an output device (such as a display, speaker, LED lamp, etc.) that performs output to the outside. Note that the input device C5 and the output device C6 may have an integrated configuration (such as a touch panel).

[0105] Also, each device such as the processor C1 and the memory C2 is connected by a bus C7 for communicating information. The bus C7 may be composed of a single bus or may be composed of different buses between devices.

[0106] The processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in the present disclosure may be rearranged as long as there is no contradiction. For example, regarding the methods described in the present disclosure, the elements of various steps are presented using an exemplary order and are not limited to the specific order presented.

[0107] The input / output information, etc. may be stored in a specific location (such as a memory) or may be managed using a management table. The input / output information, etc. may be overwritten, updated, or appended. The output information, etc. may be deleted. The input information, etc. may be transmitted to other devices.

[0108] The determination may be made based on a value represented by 1 bit (0 or 1), may be made based on a truth value (Boolean: true or false), or may be made based on a numerical comparison (such as comparison with a predetermined value).

[0109] Each aspect / embodiment described in the present disclosure may be used alone, in combination, or may be switched and used during execution. Also, the notification of predetermined information (such as the notification of "being X") is not limited to being explicitly performed and may be performed implicitly (for example, by not performing the notification of the predetermined information).

[0110] Software should be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether called software, firmware, middleware, microcode, hardware description language, or by any other name.

[0111] Also, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and wireless technologies (such as infrared, microwave, etc.), at least one of these wired and wireless technologies is included within the definition of the transmission medium.

[0112] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0113] The terms "system" and "network" as used in this disclosure are used interchangeably.

[0114] As used in this disclosure, the terms "determining" and "deciding" may encompass a variety of operations. "Determining" and "deciding" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up (e.g., searching in a table, database, or other data structure), ascertaining, and considering something as having been "determined" or "decided". Also, "determining" and "deciding" may include considering something as having been "determined" or "decided" after receiving (e.g., receiving information), transmitting (e.g., transmitting information), inputting, outputting, accessing (e.g., accessing data in a memory), etc. Further, "determining" and "deciding" may include considering something as having been "determined" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. That is, "determining" and "deciding" may include considering something as having been "determined" or "decided" after performing some operation. Also, "determining (deciding)" may be read as "assuming", "expecting", "considering", etc.

[0115] The terms "connected" and "coupled," or any variations thereof, mean any direct or indirect connection or coupling between two or more elements and can include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements can be physical, logical, or a combination thereof. For example, "connected" may be read as "accessed." As used in this disclosure, two elements can be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as, by way of some non-limiting and non-exhaustive examples, electromagnetic energy having wavelengths in the radio frequency region, microwave region, and optical (both visible and invisible) region.

[0116] As used in this disclosure, the recitation "based on" does not mean "based solely on" unless otherwise specified. In other words, the recitation "based on" means both "based solely on" and "based at least in part on."

[0117] In this disclosure, when the terms "include," "including," and variations thereof are used, these terms are intended to be inclusive in the same manner as the term "comprising." Further, the term "or" as used in this disclosure is not intended to be exclusive.

[0118] In this disclosure, for example, when articles are added by translation, as in the case of a, an, and the in English, this disclosure may include that the noun following these articles is in the plural form.

[0119] In the present disclosure, the term "A and B are different" may mean that "A and B are different from each other". Note that the term may also mean that "A and B are each different from C". Terms such as "separate" and "coupled" may also be interpreted in the same way as "different".

[0120] [Appendix] An app log analysis device according to an embodiment acquires, from a plurality of user terminals, information for identifying the user terminals, a usage log of a camera app including date and time information, and location information for specifying the location where the camera app is used for each usage log. A terminal information acquisition unit, and each of the usage logs of the camera app associated with the location information regarding the plurality of user terminals acquired by the terminal information acquisition unit is classified based on the location information and the date and time information, thereby estimating a POI suitable for using the camera app. A POI estimation unit, and a POI category estimation unit that assigns a category regarding the type of the POI based on information related to a POI whose category is known for the POI estimated by the POI estimation unit.

[0121] According to the above app log analysis device, for the usage logs of the camera app associated with the location information acquired from a plurality of user terminals, a POI is estimated by classifying based on the location information and the date and time information. Then, based on information related to a POI whose category is known, a category regarding the type of the new POI is assigned. With such a configuration, it is possible to estimate an area suitable for shooting based on the usage logs of the app acquired from a plurality of user terminals, and since a category is assigned, the user can easily grasp what kind of POI each POI is. Furthermore, by performing category assignment using information related to a POI whose category is known, for example, the same category can be assigned to POIs with similar characteristics, so the accuracy of category assignment is improved.

[0122] Here, the POI estimation unit may estimate, as a POI, an area where the usage log of the camera application is high during a specific period.

[0123] An area where the usage log of the camera application is high can be assumed to be a POI suitable for using the camera application for more users. Therefore, by estimating the above area as a POI, an area suitable for shooting can be estimated.

[0124] The apparatus further includes a storage unit that holds information for specifying a POI whose category is known and information indicating the change over time of the usage log of the camera application at this POI. The POI category estimation unit calculates the change over time of the usage log of the camera application at the location estimated as the POI, and estimates the category of the location estimated as the POI by comparing it with the change over time of the usage log of the camera application at the POI whose category is known. This may also be an aspect.

[0125] Among POIs, there are POIs characterized by the change over time of the usage log of the camera application. Therefore, by comparing the change over time of the usage log of the camera application at a POI whose category is known with the change over time of the usage log of the camera application at the location estimated as a POI, and configuring to estimate the category of the POI, it is possible to accurately estimate the category especially for POIs of categories characterized by the change over time.

[0126] The POI category estimation unit calculates the change over time of the usage log of the camera application at the location estimated as the POI, and when the change over time of the usage log of the camera application at the location estimated as the POI is similar to the change over time of the usage log of the camera application at the POI whose category is known, assigns the category of the POI whose category is known to the POI estimated by the POI estimation unit. This may also be an aspect.

[0127] As described above, when the change over time of the usage log of the camera application at a POI whose category is known is similar to the change over time of the usage log of the camera application at the location estimated as the POI, by adopting a configuration in which the same category as that of the POI with a known category is assigned, the category can be accurately estimated.

[0128] The apparatus may further include a filtering unit that filters each of the usage logs of the camera application associated with the location information regarding the plurality of user terminals acquired by the terminal information acquisition unit, based on the terminal-related information regarding each of the plurality of user terminals. The POI estimation unit estimates a POI suitable for the use of the camera application by classifying each of the usage logs of the camera application associated with the location information regarding the plurality of user terminals, after being filtered by the filtering unit, based on the location information and the date and time information.

[0129] After filtering each of the usage logs of the camera application associated with the location information acquired from the plurality of user terminals, based on the terminal-related information which is information regarding each of the plurality of user terminals, a POI is estimated by classifying based on the location information and the date and time information. With such a configuration, since the usage logs of the camera application that may be noise in the estimation of the POI are removed by performing filtering and then the POI is estimated, a location more suitable as the POI can be estimated.

[0130] An application log analysis apparatus according to an embodiment acquires, from a plurality of user terminals, information for identifying a user terminal, a usage log of a camera application including date and time information, and position information for specifying a usage location of the camera application for each usage log. The apparatus includes a terminal information acquisition unit, a filtering unit, and a POI estimation unit. The filtering unit filters a usage log of the camera application in which the position information acquired by the terminal information acquisition unit for each of the plurality of user terminals is associated, based on terminal-related information which is information regarding each of the plurality of user terminals, to filter out usage logs of the camera application that satisfy specific conditions. The POI estimation unit estimates a POI suitable for the use of the camera application by classifying the usage logs of the camera application associated with the position information, which are extracted by the filtering by the filtering unit, based on the position information and the date and time information.

[0131] According to the above application log analysis apparatus, after filtering each of the usage logs of the camera application associated with the position information acquired from the plurality of user terminals based on the terminal-related information which is information regarding each of the plurality of user terminals, a POI is estimated by classifying based on the position information and the date and time information. As described above, since the POI is estimated using the usage logs of the camera application after filtering based on the terminal-related information regarding each of the plurality of user terminals, it is possible to estimate an area suitable for shooting based on the usage logs of the applications acquired from the plurality of user terminals. In particular, since the POI is estimated after removing the usage logs of the camera application that may be noise in the estimation of the POI by performing filtering, a place more suitable as the POI can be estimated.

[0132] The POI estimation unit may estimate, as a POI, an area where the usage logs of the camera application are frequent during a specific period.

[0133] Areas with a large number of usage logs of the camera app can be assumed to be POIs suitable for using the camera app for more users. Therefore, by estimating the above areas as POIs, areas suitable for shooting can be estimated.

[0134] The POI estimation unit may estimate, as a POI, an area where the ratio of the number of usage logs of the camera app to the population within the area is large during a specific period.

[0135] The number of usage logs of the camera app can vary not only in terms of the attractiveness of the POI but also according to the influence of the population of the area. Therefore, by adopting a configuration in which an area where the ratio of the number of usage logs of the camera app to the population within the area is large during a specific period is estimated as a POI, it becomes possible to estimate the POI in a state where the influence due to differences in population is excluded.

[0136] The terminal-related information is the location information of the user terminal during the time period when the camera app is not being used. The terminal information acquisition unit acquires the location information of the user terminal outside the usage location of the camera app from the plurality of user terminals. The filtering unit identifies the action range of the user of the user terminal from the location information of the user terminal during the time period when the camera app is not being used. When the location information associated with the usage log of the camera app matches the daily life range as the action range of the user, it may be determined not to use the usage log of the camera app for the estimation of the POI in the POI estimation unit.

[0137] Since the usage log of the camera app in the user's daily life area may be related to personal photography, it may not be suitable for estimating POIs that can be presented to other users. Therefore, as described above, based on the location information of the user terminal during the time period when the camera app is not being used, the activity area of the user of the user terminal is identified, and it is determined that the usage log of the camera app at locations that match the daily life area as the user's activity area will not be used for POI estimation. This prevents the estimation of POIs based on the usage log of the camera app in the daily life area. Note that when identifying the activity area, the location information of the user terminal during the time period when the camera app is being used may also be combined and used.

[0138] The terminal-related information is the usage log of applications other than the camera app on the user terminal. The terminal information acquisition unit acquires the usage logs of applications other than the camera app from the plurality of user terminals, and the filtering unit extracts the usage log of the camera app to be used for POI estimation in the POI estimation unit based on the types of applications used within a predetermined time before and after the use of the camera app, which are specified based on the usage log of applications other than the camera app.

[0139] When the camera app is used on the user terminal, cooperation with other applications is assumed. Also, when the use of the camera app is based on a specific hobby or the like, it is assumed that related applications will be used before and after it. Therefore, as described above, by extracting the usage log of the camera app to be used for POI estimation in the POI estimation unit based on the types of applications used within a predetermined time before and after the use of the camera app on the user terminal, it is possible to estimate POIs from the usage log of the camera app in which related applications are used before and after, and thus it is possible to estimate POIs with a strong relationship with related applications.

[0140] The terminal-related information is information for identifying a segment related to the user of the user terminal, and the filtering unit may extract, as the usage log of the camera app used in the user terminal held by a user who matches a specific segment, the usage log of the camera app used for estimating a POI in the POI estimation unit.

[0141] As described above, by adopting a configuration in which the usage log of the camera app used for estimating a POI in the POI estimation unit is extracted using information for identifying a segment related to the user, it becomes possible to estimate a POI related to the segment of the user.

[0142] The terminal-related information is information for identifying the type of the camera app in the user terminal, and the terminal information acquisition unit acquires, from the plurality of user terminals, information for identifying the type of the used camera app for each usage log of the camera app, and the filtering unit may extract, as the usage log of the camera app used for estimating a POI in the POI estimation unit, the usage log of a specific type of camera app among the usage logs of the camera app in the user terminal.

[0143] Depending on the type, there may be a camera app specialized for a specific use. Therefore, as described above, by adopting a configuration in which the usage log of the camera app used for estimating a POI in the POI estimation unit is extracted based on the type of the camera app, it becomes possible to estimate a POI related to a specific camera app.

[0144] The apparatus further includes a POI category estimation unit that assigns a category related to the type of the POI to the POI estimated by the POI estimation unit, and the POI category estimation unit may assign a category to the POI based on the terminal-related information used for filtering in the filtering unit.

[0145] As described above, when assigning a category related to the type of POI to the estimated POI, by adopting a configuration in which a category based on the terminal-related information used for filtering in the filtering unit is assigned, it becomes possible to assign a category based on the terminal-related information.

Explanation of Signs

[0146] 1… Application log analysis device, 11… Application usage log reception unit, 12… Application usage log holding unit, 13… Location information reception unit, 14… Location information holding unit, 15… Filtering unit, 16… Auxiliary information holding unit, 17… POI estimation unit, 18… POI information holding unit, 19… POI category estimation unit, 20… Category specified POI information holding unit, 21… Output unit, 9… User terminal, 91… User application, 92… Image information holding unit, 93… Application usage log acquisition unit, 94… Application usage log transmission unit, 95… Location information acquisition unit, 96… Location information transmission unit.

Claims

1. a terminal information acquisition unit that acquires, from a plurality of user terminals, information for identifying the user terminal, a usage log of a camera app including date and time information, and location information for identifying a location where the camera app was used for each of the usage logs; a POI estimation unit that estimates a POI suitable for using the camera app by classifying each of the camera app usage logs associated with the position information related to the plurality of user devices acquired by the terminal information acquisition unit based on the position information and the date and time information; a POI category estimation unit that assigns a category related to a type of POI to the POI estimated by the POI estimation unit based on information related to a POI whose category is known; a storage unit that stores information that identifies a POI whose category is known and information that indicates a change over time in a usage log of a camera app in the POI; The POI category estimation unit calculates a change over time of a usage log of the camera app in the place estimated as the POI, and compares the change over time of the usage log of the camera app with a POI whose category is known, thereby estimating a category of the place estimated as the POI. App log analyzer.

2. The application log analysis device according to claim 1 , wherein the POI estimation unit estimates, as a POI, an area in which there are many usage logs of the camera application in a specific period.

3. 3. The application log analysis device of claim 1, wherein the POI category estimation unit calculates a change over time in the usage log of the camera app at a location estimated as the POI, and if the change over time in the usage log of the camera app at a POI whose category is known is similar, the POI whose category is known is assigned to the POI estimated by the POI estimation unit.

4. The device further includes a filtering unit that filters each of the camera application usage logs associated with the position information related to the plurality of user terminals acquired by the device information acquisition unit based on device-related information related to each of the plurality of user terminals; The application log analysis device according to any one of claims 1 to 3, wherein the POI estimation unit estimates a POI suitable for use of the camera application by classifying each of the camera application usage logs associated with the location information regarding the multiple user terminals after filtering by the filtering unit, based on the location information and the date and time information.

Images