Activity area estimation device, activity area estimation method and program

Abstract

To improve the accuracy of estimating an activity area of a target user.SOLUTION: An activity area estimation device comprises a first generation unit, a usefulness determination unit, and an activity area estimation unit. The first generation unit generates first location information based on first post information of a target user. The usefulness determination unit determines whether or not the first location information is useful for estimating an activity area of the target user in a real space, using related user information about a related user who is a user related to the target user. The activity area estimation unit estimates the activity area of the target user using the first location information which is determined to be useful.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an activity area estimation device, an activity area estimation method, and a program.

Background Art

[0002] Various SNSs (Social Networking Services) are generally widely used, and the use of information provided in SNSs (SNS information) is being attempted. Examples of such usage purposes include marketing, human resources surveys for job seekers and applicants for further education, and the like.

[0003] For example, Patent Document 1 discloses a technique for estimating the activity location of a target user using the account information of the target user. The estimation device described in Patent Document 1 includes a first position distribution generation unit, a second position distribution generation unit, and an estimation unit.

[0004] The first position distribution generation unit generates a first position distribution of the target user based on the account information of the target user in social media. The second position distribution generation unit generates a second position distribution of a friend based on the account information of a friend related to the target user in social media. The estimation unit estimates the activity location of the target user based on the generated first position distribution and the generated second position distribution. According to Patent Document 1, the first position distribution is generated based on, for example, post information included in the account information.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, the location information included in the posted information generally varies. For example, the posted information may include places the poster wants to visit, or locations related to general news that the poster is interested in, etc. Thus, when the posted information includes location information that is not related to the activity area of the target user, if the activity area of the target user is estimated using such location information, the estimation result may be an area that is not appropriate as the activity area of the target user.

[0007] An example of the object of the present invention is, in view of the above-described problems, to provide an activity area estimation device, an activity area estimation method, a program, etc. capable of improving the accuracy of estimating the activity area of a target user.

Means for Solving the Problems

[0008] According to one aspect of the present invention, first generation means for generating first location information based on first posted information of a target user; usefulness determination means for determining whether the first location information is useful for estimating the activity area of the target user in the real space using related user information regarding a related user who is a user related to the target user; and activity area estimation means for estimating the activity area of the target user using the first location information determined to be useful. An activity area estimation device is provided.

[0009] According to one aspect of the present invention, one or more computers generate first location information based on first posted information of a target user, determine whether the first location information is useful for estimating the activity area of the target user in the real space using related user information regarding a related user who is a user related to the target user, and estimate the activity area of the target user using the first location information determined to be useful. An activity area estimation method is provided.

[0010] According to one aspect of the present invention, one or more computers are caused to generate first location information based on first posting information of a target user, determine whether the first location information is useful for estimating an activity area of the target user in the real space, using related user information about a related user who is a user related to the target user, and a program is provided for causing the activity area of the target user to be estimated using the first location information determined to be useful.

Advantages of the Invention

[0011] According to one aspect of the present invention, it becomes possible to improve the accuracy of estimating the activity area of a target user.

Brief Description of the Drawings

[0012]

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

Mode for Carrying Out the Invention

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and the description will be omitted as appropriate.

[0014] [Overview] FIG. 1 is a diagram showing an overview of the activity area estimation device 102. The activity area estimation device 102 includes a first generation unit 122, a usefulness determination unit 124, and an activity area estimation unit 125.

[0015] The first generation unit 122 generates first location information based on the first posting information of the target user.

[0016] The usefulness determination unit 124 determines whether the first location information is useful for estimating the activity area of the target user in the real space by using the related user information regarding the related users who are the users related to the target user.

[0017] The activity area estimation unit 125 estimates the activity area of the target user by using the first location information determined to be useful.

[0018] According to this activity area estimation device 102, it is possible to improve the accuracy of estimating the activity area of the target user.

[0019] FIG. 2 is a flowchart showing an overview of the activity area estimation process.

[0020] The first generation unit 122 generates first location information based on the first posting information of the target user (step S101).

[0021] The usefulness determination unit 124 determines whether the first location information is useful for estimating the activity area of the target user in the real space, using the related user information about the related user who is a user related to the target user (step S103).

[0022] The activity area estimation unit 125 estimates the activity area of the target user, using the first location information determined to be useful (step S104).

[0023] According to this activity area estimation device 102, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0024] Hereinafter, the details of the embodiment will be described.

[0025] [Embodiment 1] (Configuration example of the information processing system 100) FIG. 3 is a diagram showing a configuration example of the information processing system 100. The information processing system 100 is a system for estimating the activity area of a target user in the real space using SNS (Social Networking Service) information. The information processing system 100 includes an SNS system 101 and an activity area estimation device 102.

[0026] Hereinafter, the "activity area estimation device" is also simply referred to as the "estimation device".

[0027] The SNS system 101 and the estimation device 102 are connected via the network NT so that they can transmit and receive information to and from each other. The network NT is, for example, a communication line configured by wire, wireless, or a combination thereof.

[0028] (Configuration example of the SNS system 101) The SNS system 101 is a system that provides an SNS, and includes, for example, one or more management devices (not shown) and one or more terminal devices (not shown). Note that the information processing system 100 may include a plurality of SNS systems 101. In this case, each SNS system 101 may be configured in the same manner.

[0029] Each of the one or more management devices is a device that manages SNS information. Each of the plurality of terminal devices is a device used by a user of the SNS (hereinafter also referred to as an "SNS user"), and is, for example, a smartphone, a tablet terminal, a personal computer, or the like. Each of the plurality of terminal devices is connected to one or more management devices via a network NT or the like.

[0030] The SNS is a service provided using a management device. The SNS is provided, for example, to pre-registered SNS users. The SNS includes, for example, one or more of a service in which an SNS user publishes posted information using their account, a service for communicating with other SNS users (hereinafter also referred to as "other SNS users"), and the like. Note that the SNS is not limited to these.

[0031] (SNS information) SNS information is information used to provide the SNS. SNS information includes, for example, at least one of (1) profile information, (2) posted information, (3) conversation information with other SNS users, and (4) association information with other SNS users for each SNS user. Note that the SNS information is not limited to these.

[0032] (1) The profile information may include, for example, at least one of residence information, work place information, hobbies, attribute information, and the like. Note that the profile information is not limited to these.

[0033] The place of residence information is information indicating the place of residence of the SNS user. The place of work information is information indicating the place of work of the SNS user. Each of the place of residence information and the place of work information may be indicated by, for example, latitude and longitude, may be indicated by an administrative division corresponding to any of prefectures, municipalities, cho, and address, or may be indicated by information identifying each of a plurality of predetermined regions. The plurality of predetermined regions are, for example, regions divided by meshes of a predetermined size, but are not limited thereto.

[0034] Note that the method of indicating the position in each of the place of residence information and the place of work information is not limited to those exemplified here. Also, the method of indicating the position in the place of residence information and the place of work information may be the same or different.

[0035] The attribute information may include, for example, one or more of gender, date of birth, and the like.

[0036] (2) The post information may include at least one of text information, image information, and position information. The post information may further include one or more of a reaction to the post information, a posting time, and the like. Note that the post information is not limited thereto.

[0037] The image information may be one or both of a still image and a moving image.

[0038] The position information is information indicating the position where the post information is uploaded to the management device. The position information may be a GEO tag such as GPS (Global Positioning System) information obtained using the function of the terminal device that uploaded the post information. The position information may include a position specified by, for example, the management device from an image of a landmark included in the image information.

[0039] The position information may be indicated by, for example, latitude and longitude, may be indicated by a division corresponding to any of prefectures, municipalities, cho, and address, or may be indicated by information identifying each of a plurality of predetermined regions. Note that the method of indicating the position in the position information is not limited to those exemplified here.

[0040] Reactions to the posted information include, for example, comments on the posted information from other SNS users, "likes", etc. Note that the reactions to the posted information are not limited to these.

[0041] The posting time is information indicating the time when the posted information is uploaded to the management device. The posting time may be represented by, for example, year, month, day, and time. Note that the method of representing the posting time is not limited to this.

[0042] (3) The conversation information includes, for example, conversations with one or more other SNS users like a chat.

[0043] (4) The association information includes, for example, the accounts of other SNS users in a predetermined relationship such as a friendship relationship or a family relationship. The friendship relationship is, for example, a relationship formed by an agreement between the parties. Note that the accounts of other SNS users in a family relationship may be included in the profile information.

[0044] (Functional configuration example of the activity area estimation device 102) FIG. 4 is a diagram showing a functional configuration example of the activity area estimation device 102. The estimation device 102 is a device that estimates the activity area of a target user in the real space using the SNS information managed in the SNS system 101.

[0045] Functionally, the estimation device 102 includes, for example, a target user reception unit 121, a first generation unit 122, a second generation unit 123, a usefulness determination unit 124, an activity area estimation unit 125, and an output unit 126.

[0046] The target user reception unit 121 receives the account of the target user based on, for example, the input of the user of the estimation device 102 (hereinafter also referred to as the "device user").

[0047] The target user is, for example, an SNS user selected by the device user or the like as the target for estimating the activity area.

[0048] The target account is an account used by the target user in the SNS provided by the SNS system 101. Therefore, the target account is associated with the target user, and the target user can be identified using the target account.

[0049] The first generation unit 122 generates first location information based on the first posting information of the target user.

[0050] The first posting information is posting information included in the SNS information of the target user.

[0051] The first location information is information indicating a location obtained based on the first posting information.

[0052] FIG. 5 is a diagram showing a functional configuration example of the first generation unit 122. Functionally, the first generation unit 122 includes, for example, a first acquisition unit 122a and a first location generation unit 122b.

[0053] The first acquisition unit 122a acquires at least the first posting information from the SNS system 101 among the SNS information of the target user.

[0054] The first location generation unit 122b generates first location information based on the first posting information acquired by the first acquisition unit 122a. The first location information is generated using, for example, at least one of text information, location information, and an image included in the first posting information.

[0055] Refer to FIG. 4 again. The second generation unit 123 identifies related users of the target user and generates related user information including second location information using the profile information of the related users.

[0056] FIG. 6 is a diagram showing a functional configuration example of the second generation unit 123. Functionally, the second generation unit 123 includes, for example, a related user identification unit 123a, a second acquisition unit 123b, and a second location generation unit 123c.

[0057] The related user identification unit 123a identifies related users of the target user.

[0058] Related users are SNS users related to the target user, and may include, for example, at least one of direct related users and indirect related users. A direct related user is an SNS user directly associated with the target user. An indirect related user is an SNS user indirectly associated with the target user. Indirect related users may include, for example, SNS users associated with direct related users. Indirect related users may include, for example, SNS users associated with indirect related users.

[0059] The method by which the related user identification unit 123a identifies related users is various. The method for identifying related users will be described later.

[0060] The second acquisition unit 123b acquires at least profile information among the SNS information of the related users identified by the related user identification unit 123a.

[0061] The second location generation unit 123c acquires residence information from the profile information of the related users acquired by the second acquisition unit 123b, and generates related user information including second location information. This second location information may include, for example, the acquired residence information. Note that the second location information may be any information indicating the activity location of the related user, and may be the residence information of the related user as described above, or may include other information. Examples of other information include the work location information of the related user.

[0062] Refer to FIG. 4 again. The usefulness determination unit 124 determines whether the first location information is useful for estimating the activity area of the target user in the real space by using the related user information regarding the related users.

[0063] The usefulness determination unit 124 may determine, for example, whether the first location information is useful by using the relevant user information and a predetermined determination criterion. Then, for example, when the determination criterion is satisfied, the usefulness determination unit 124 may determine that the first location information is useful. Also, for example, when the determination criterion is not satisfied, the usefulness determination unit 124 may determine that the first location information is not useful.

[0064] Details of the determination criterion will be described later.

[0065] The activity area estimation unit 125 estimates the activity area of the target user by using the first location information determined to be useful by the usefulness determination unit 124. A general method may be used for this estimation. Examples thereof will be described later.

[0066] The output unit 126 outputs activity area information including the activity area estimated by the usefulness determination unit 124.

[0067] So far, the functional configuration example of the estimation device 102 has been described. Note that the estimation device 102 may have the function of one or both of the management device and the terminal device included in the SNS system 101, for example. From here, a physical configuration example of the estimation device 102 will be described.

[0068] (Physical Configuration Example of the Activity Area Estimation Device 102) FIG. 7 is a diagram showing a physical configuration example of the estimation device 102. Physically, the estimation device 102 has, for example, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070.

[0069] The bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the network interface 1050, the input interface 1060, and the output interface 1070 to transmit and receive data to and from each other. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0070] The processor 1020 is a processor implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0071] The memory 1030 is a main storage device implemented by a RAM (Random Access Memory) or the like.

[0072] The storage device 1040 is an auxiliary storage device implemented by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, a ROM (Read Only Memory), or the like. The storage device 1040 stores program modules for realizing the functions of the device having this. By the processor 1020 loading these program modules into the memory 1030 and executing them, the functions corresponding to the program modules are realized.

[0073] The network interface 1050 is an interface for connecting the device having this to the network NT.

[0074] The input interface 1060 is an interface for a user to input information. The input interface 1060 is composed of, for example, a touch panel, a keyboard, a mouse, or the like.

[0075] The output interface 1070 is an interface for presenting information to the user. The output interface 1070 is composed of, for example, a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0076] Note that the estimation device 102 may be physically composed of a plurality of devices. In this case, each device may have, for example, the configuration shown in FIG. 7. Also, each device such as the management device and the terminal device constituting the SNS system 101 may have, for example, the configuration shown in FIG. 7.

[0077] (Operation example of activity area estimation device 102) The activity area estimation device 102 executes an activity area estimation process.

[0078] The activity area estimation process is a process for estimating the activity area of a target user in the real space using SNS information. The activity area estimation process is started, for example, when the target user reception unit 121 receives the account of the target user. Note that the trigger for starting the activity area estimation process is not limited to this.

[0079] Figs. 8 to 9 are flowcharts showing an example of the activity area estimation process.

[0080] Refer to Fig. 8. The first generation unit 122 generates first location information based on the first post information of the target user (step S101).

[0081] Specifically, for example, the first acquisition unit 122a acquires at least the first post information from the SNS system 101 among the SNS information of the account received by the target user reception unit 121 (that is, the SNS information of the target user) (step S101a).

[0082] The target user reception unit 121 may receive a specified period together with the account of the target user. In this case, the first acquisition unit 122a may acquire at least the first post information from the SNS system 101 among the SNS information of the target user whose posting time is included in the specified period.

[0083] The first location generation unit 122b generates first location information based on the first post information acquired in step S101a (step S101b). The first location information may be one or plural.

[0084] As described above, the first location information is generated using, for example, at least one of text information, location information, and an image included in the first post information.

[0085] When using the text information included in the first submission information, for example, the first location generation unit 122b may extract the location included in the text information and generate first location information including the extracted location.

[0086] The locations included in the text information are, for example, place names, addresses, facility names, etc., but are not limited thereto. Specifically, for example, from the text information "There seems to be a festival at the nearby ○○ Station.", first location information including "○○ Station" is generated. For example, from the text information "Tokyo seems to be cold, but it seems warm in the local area.", first location information including "Tokyo" is generated. For example, from the text information "I want to go to New York someday.", first location information including "New York" is generated.

[0087] When using the position information included in the first submission information, for example, the first location generation unit 122b may generate first location information including the position information.

[0088] When using the image included in the first submission information, for example, when a predetermined image such as a landmark is extracted from the image, the first location generation unit 122b may generate first location information including the location corresponding to the predetermined image. The predetermined image may be, for example, pre-held by the first location generation unit 122b. Also, general techniques such as pattern matching and machine learning models may be used for the technique of extracting the predetermined image.

[0089] The second generation unit 123 identifies related users of the target user and generates related user information including second location information using the profile information of the related users (step S102).

[0090] Specifically, for example, the related user identification unit 123a identifies related users of the target user (step S102a).

[0091] (Method for identifying related users) The related user identification unit 123a may identify related users, for example, using at least one of information such as the association information, conversation information, and posting information (first posting information) of the target user. The related user identification unit 123a may appropriately obtain the at least one piece of information used to identify related users from either one or both of the SNS system 101 and the first acquisition unit 122a.

[0092] When using association information, for example, the related user identification unit 123a may identify an SNS user who uses the account included in the association information as a related user.

[0093] When using conversation information, for example, the related user identification unit 123a may identify an SNS user who uses the account that is the conversation partner in the conversation information as a related user.

[0094] When using the first posting information, for example, the related user identification unit 123a may identify an SNS user corresponding to the name, account, etc. included in the first posting information as a related user. Also, for example, the related user identification unit 123a may identify an SNS user who appears together with the target user in the photo included in the first posting information as a related user.

[0095] The related users identified in step S102a may be one or more.

[0096] The second acquisition unit 123b acquires at least profile information from the SNS information of the related users identified in step S102a (step S102b).

[0097] When a plurality of related users are identified in step S102a, the second acquisition unit 123b may acquire at least profile information for each of the plurality of related users.

[0098] The second location generation unit 123c generates related user information including second location information using the profile information acquired in step S102b (step S102c).

[0099] For example, as described above, the second location generation unit 123c acquires the residence location information from the profile information acquired in step S102b. Then, the second location generation unit 123c generates second location information including the acquired residence location information. Further, the second location generation unit 123c may generate related user information including other information in addition to the second location information as needed.

[0100] When a plurality of related users are specified in step S102a, the second location generation unit 123c may generate related user information including second location information for each of the plurality of related users. Specifically, for example, the second location generation unit 123c may generate a plurality of second location information including the residence location information of each of the plurality of related users. Then, the second location generation unit 123c may generate a plurality of related user information including each of the generated plurality of second location information.

[0101] Refer to FIG. 9. The usefulness determination unit 124 determines whether the first location information is useful for estimating the activity area of the target user in the real space using the related user information generated in step S102c (step S103).

[0102] (Determination criteria) The determination criteria include the following criterion 1. Further, the determination criteria may further include at least one of the following criteria 2 to criterion 4. Note that the determination criteria are not limited to this.

[0103] (Criterion 1) Criteria regarding the positional relationship in the real space of the locations indicated by the first location information and the second location information

[0104] Specifically, for example, criterion 1 is that the location indicated by the first location information is included in the location indicated by the second location information in the real space.

[0105] More specifically, for example, assume that there are a plurality of pieces of first location information, which are the above-mentioned "XX Station", "Tokyo", and "New York". Also assume that there are a plurality of related users, and the residence information included in the second location information of each of the plurality of related users is "Kyoto City", "Osaka City", and "Kobe City". When, for example, "XX Station" is included in "Osaka City", the usefulness determination unit 124 determines that "XX Station" is useful.

[0106] Note that the criterion 1 is not limited to this. For example, the place indicated by the first location information may overlap with the place indicated by the second location information in the real space. The criterion 1 may be that the distance in the real space between the places indicated by the first location information and the second location information is equal to or less than a predetermined threshold. Also, the determination criterion may include one criterion corresponding to the criterion 1, or may include a plurality of criteria corresponding to the criterion 1.

[0107] (Criterion 2) Criterion related to a predetermined specific place

[0108] Specifically, for example, the criterion 2 is that the first location information does not correspond to a predetermined specific place. The specific place is, for example, a place generally visited for sightseeing or the like, such as the Sky Tree or the Tokyo Tower, or a place frequently mentioned in general conversations.

[0109] Note that the criterion 2 is not limited to this. For example, the criterion 2 may be that the first location information corresponds to a predetermined specific place.

[0110] (Criterion 3) Criterion regarding the positional relationship in the real space of the places included in the plurality of first location information when there are a plurality of first location information

[0111] Specifically, for example, the criterion 3 is that the distance in the real space of the places included in the plurality of first location information is equal to or less than a predetermined threshold. This threshold may be the same as the threshold used in other criteria, or may be different.

[0112] More specifically, for example, assume that a plurality of first location information includes "Tokyo", "Shinjuku", "Shibuya", and "Osaka City". Also assume that the threshold value is 100 km. "Osaka City" is more than 100 km away from each of "Tokyo", "Shinjuku", and "Shibuya". Also, each location of "Tokyo", "Shinjuku", and "Shibuya" is 100 km or less from at least one other location.

[0113] In this case, the usefulness determination unit 124 determines that "Osaka City" is not useful. Also, the usefulness determination unit 124 determines that "Tokyo", "Shinjuku", and "Shibuya" are useful.

[0114] Note that the criterion 3 is not limited to this.

[0115] (Criterion 4) Criteria related to the hobbies or attributes of related users

[0116] Specifically, for example, the criterion 3 is that the location indicated by the first location information is a location related to the hobbies or attributes of the related user.

[0117] More specifically, for example, assume that the hobby of the related user is "watching movies", and the location indicated by the first location information is a filming location for movies. In this case, the usefulness determination unit 124 determines that the first location information is useful.

[0118] When the determination criteria include a plurality of criteria, the application relationship (such as the priority of application) of the plurality of criteria may be determined as appropriate.

[0119] When a plurality of related user information each including a plurality of second location information is generated in step S102c, the usefulness determination unit 124 may determine whether the first location information is useful using the plurality of second location information. That is, in this case, whether the first location information is useful may be determined using the plurality of second location information included in each of the plurality of related user information.

[0120] The activity area estimation unit 125 estimates the activity area of the target user using the first location information determined to be useful in step S103 (step S104).

[0121] For example, the activity area estimation unit 125 generates, as the activity area of the target user, the distribution (posting distribution) in the real space of the location indicated by the first location information determined to be useful in step S103.

[0122] The posting distribution can be said to be the distribution in the real space of the locations that are useful for estimating the activity area of the target user among the locations obtained based on the first posting information (i.e., the first location information). There are various ways to represent the posting distribution. For example, the posting distribution may be a two-dimensional geographical distribution represented using coordinates of latitude and longitude. The posting distribution may also be a two-dimensional geographical distribution represented using unit areas of a predetermined size. This unit area may be an area corresponding to administrative divisions such as countries, prefectures, cities, wards, towns, and villages, or may be an area divided by meshes of a predetermined size such as 1 Km × 1 Km or 100 m × 100 m. Note that the method of representing the posting distribution is not limited to these.

[0123] For example, the activity area estimation unit 125 may estimate the posting distribution using a general method as described above. Then, the activity area estimation unit 125 may use the estimated posting distribution as the activity area estimated for the target user (i.e., the activity area of the target user). Specifically, for example, as disclosed in Japanese Patent Laid-Open No. 2022-114389, the posting distribution may be generated using a predetermined distribution function. As an example of this distribution function, a density estimation function for estimating the distribution by a nonparametric method can be given. Also, as an example of the density estimation function of the nonparametric method, a kernel density estimation function (see Equation (1)) can be given.

[0124] In generating the contribution distribution, weighting may be performed on the first location information determined to be useful based on the first contribution information. For example, weighting may be performed on the first location information determined to be useful according to the contribution date and time. [Number]

[0125] The contribution distribution p(L p ) represented by Equation (1) is a set of kernel density estimation values of the contribution information in each distribution area. In Equation (1), l p represents the set of locations indicated by the first location information. h p represents the contribution bandwidth. The contribution bandwidth h p is a parameter indicating the influence range of each sample in kernel density estimation. The contribution bandwidth h p may be a preset value, a value obtained by learning from a plurality of contribution locations in advance, or the like. w p represents the contribution weight. K p represents the contribution kernel function.

[0126] FIG. 10 is a diagram showing an example of the contribution distribution obtained by kernel density estimation. Each of the contribution distributions shows the influence range (for example, a circular shape of a normal distribution) of the contribution bandwidth centered on the location indicated by the first location information. In the influence range of the location indicated by the first location information, the central score is the largest, and the score decreases as the distance from the center increases.

[0127] Note that the method for generating the contribution distribution is not limited to this. The contribution distribution may be generated using, for example, appropriate statistical processing. Also, for example, the activity area estimation unit 125 may generate a contribution distribution (histogram) by counting the number of contribution locations included in each distribution area.

[0128] Refer to FIG. 9. The activity area estimation unit 125 outputs the activity area estimated in step S104 (step S105) and ends the activity area estimation process.

[0129] The output method is, for example, one or more of causing it to be displayed on a display unit (not shown), transmitting it to another device (not shown) via a network NT or the like, and the like. Note that the output method is not limited to these.

[0130] (Function and effect) As described above, according to the present embodiment, the estimation device 102 includes a first generation unit 122, a usefulness determination unit 124, and an activity area estimation unit 125.

[0131] The first generation unit 122 generates first location information based on the first posting information of the target user. The usefulness determination unit 124 determines whether the first location information is useful for estimating the activity area of the target user in the real space using the related user information regarding the related user who is a user related to the target user. The activity area estimation unit 125 estimates the activity area of the target user using the first location information determined to be useful.

[0132] Thereby, by using the related user information, it is possible to determine the first location information that satisfies a predetermined criterion (that is, has a predetermined relationship) with the related user from among the first location information generated based on the first posting information. Since the related user is a user related to the target user, generally, the first location information having a predetermined relationship with the related user is highly likely to be the activity area of the target user. Therefore, it is possible to improve the accuracy of estimating the activity area of the target user.

[0133] According to the present embodiment, the first location information is generated using at least one of text information, location information, and an image included in the first posting information.

[0134] In general SNSs, posting information often includes at least one of text information, location information, and an image. Therefore, the first location information can be generated using the posting information of general SNSs. Therefore, it is possible to improve the accuracy of estimating the activity area of a target user who uses a general SNS.

[0135] According to the present embodiment, the estimation device 102 includes a second generation unit 123 that identifies related users of the target user and generates related user information including second location information using the profile information of the related users.

[0136] In a general SNS, profile information often includes places where the SNS user is daily present, such as the place of residence and the place of work. Therefore, it is possible to determine whether the first location information is useful using the places where the related users are daily present, and there is a high possibility that the usefulness of the first location information can be appropriately determined. Accordingly, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0137] According to the present embodiment, the profile information includes the place of residence information of the related users. The second location information includes the place of residence information obtained from the profile information.

[0138] Thereby, it is possible to determine whether the first location information is useful using the place of residence, which is the place where the related users are daily present, and there is a high possibility that the usefulness of the first location information can be appropriately determined. Accordingly, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0139] According to the present embodiment, the related users include at least one of a direct related user directly associated with the target user and an indirect related user associated with the direct related user.

[0140] Thereby, it is possible to determine whether the first location information is useful for estimating the activity area of the target user in the real space using the related user information of the related users who are likely to be relatively close to the target user. And the activity area can be estimated using the first location information determined to be useful. Accordingly, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0141] According to this embodiment, whether the first location information is useful is determined using the relevant user information and a predetermined determination criterion. The determination criterion includes a criterion regarding the positional relationship in the real space of the locations indicated by the first location information and the second location information, respectively.

[0142] By determining the usefulness of the first location information using such a determination criterion, it is possible to determine that the first location information that is highly likely to be related to the activity area of the target user is useful. Therefore, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0143] According to this embodiment, the relevant users are included in a plurality of relevant users. The relevant user information is included in the plurality of relevant user information of each of the plurality of relevant users. The second location information is included in the plurality of second location information of each of the plurality of relevant users. Whether the first location information is useful is determined using the plurality of second location information included in each of the plurality of relevant user information.

[0144] Thereby, it is possible to determine the usefulness of the first location information using the second location information regarding each of the plurality of relevant users. By using the plurality of second location information, it is possible to estimate the activity area of the target user using a plurality of useful first location information. Therefore, it becomes possible to improve the accuracy of estimating the activity area of the target user.

[0145] [Embodiment 2] In Embodiment 1, an example of estimating the activity area of the target user using only the first location information determined to be useful was described. In order to estimate the activity area of the target user, the second location information may be further used.

[0146] In this embodiment, for the sake of simplicity, differences from Embodiment 1 will be mainly described, and descriptions overlapping with Embodiment 1 will be omitted as appropriate.

[0147] Functionally, the estimation device may include an activity area estimation unit 225 that replaces, for example, the activity area estimation unit 125 according to Embodiment 1.

[0148] In this case, the information processing system may be configured in substantially the same manner as the information processing system 100 according to the first embodiment, except that the estimation device includes an activity area estimation unit 225 that replaces the activity area estimation unit 125.

[0149] (Functional configuration example of the activity area estimation unit 225) The activity area estimation unit 225 estimates the activity area of the target user using the first location information determined to be useful by the usefulness determination unit 124 and the second location information generated by the second location generation unit 123c. That is, in the present embodiment, the activity area of the target user is estimated using the second location information in addition.

[0150] FIG. 11 is a diagram showing a functional configuration example of the activity area estimation unit 225. Functionally, the activity area estimation unit 225 includes, for example, a first distribution generation unit 225a, a second distribution generation unit 225b, and an activity area generation unit 225c.

[0151] The first distribution generation unit 225a generates a posting distribution using the first location information determined to be useful by the usefulness determination unit 124.

[0152] The second distribution generation unit 225b generates a related user distribution using the second location information generated by the second location generation unit 123c.

[0153] The related user distribution is the distribution in the real space of the location indicated by the second location information generated by the second location generation unit 123c. The second location information may be, for example, the place of residence, workplace, etc. of the related user, which is information indicating the activity location of the related user as described above. Therefore, the related user distribution can also be said to be the distribution of the activity locations of the related users.

[0154] The activity area generation unit 225c estimates, as the activity area of the target user, an area where the post distribution and the second related user distribution generated by each of the first distribution generation unit 225a and the second distribution generation unit 225b overlap each other. That is, the activity area of the target user is estimated using the overlap between the post distribution generated based on the first location information and the related user distribution generated based on the second location information.

[0155] (Another example of the operation of the activity area estimation device) The activity area estimation process includes an estimation process (step S204) that replaces the estimation process (step S104) according to Embodiment 1. In this case, the activity area estimation process may be configured in substantially the same manner as the activity area estimation process according to Embodiment 1, except for this point.

[0156] FIG. 12 is a flowchart showing an example of the estimation process (step S204).

[0157] The first distribution generation unit 225a generates a post distribution (step S204a) using the first location information determined to be useful in step S103.

[0158] The post distribution may be the same as the post distribution according to Embodiment 1. Therefore, the first distribution generation unit 225a may generate the post distribution using the same method as the method by which the activity area estimation unit 125 according to Embodiment 1 generates the post distribution.

[0159] The second distribution generation unit 225b generates a related user distribution (step S204b) using the second location information generated in step S102c.

[0160] For example, the second distribution generation unit 225b may generate the related user distribution using a method substantially the same as the method by which the activity area estimation unit 125 according to Embodiment 1 generates the post distribution. That is, the second distribution generation unit 225b may generate a related user distribution that replaces the post distribution by using the second location information instead of the first location information in the method by which the activity area estimation unit 125 according to Embodiment 1 generates the post distribution.

[0161] The activity area generation unit 225c estimates, as the activity area of the target user, an area where the post distribution and the related user distribution generated by each of the first distribution generation unit 225a and the second distribution generation unit 225b overlap each other (step S204c).

[0162] FIG. 13 is a diagram showing an example of the activity area of the target user estimated based on the post distribution and the related user distribution. In the figure, each of the post distribution and the related user distribution is shown by a solid line and a dotted line. In the figure, the activity area of the target user is an area where the post distribution represented by the solid line and the related user distribution represented by the dotted line overlap each other.

[0163] Note that in this figure, an example is shown in which both the first location information and the second location information are plural, and both the post distribution and the related user distribution based on these are plural, but each of the first location information and the second location information may be one or more. Therefore, each of the post distribution and the related user distribution may also be one or more.

[0164] (Function and Effect) As described above, according to the present embodiment, the activity area of the target user is estimated by further using the second location information.

[0165] Thereby, it is possible to narrow down to a more appropriate area than estimating the activity area only from the first location information. Therefore, it is possible to improve the accuracy of estimating the activity area of the target user.

[0166] According to the present embodiment, the activity area of the target user is estimated using the overlap between the post distribution generated based on the first location information and the related user distribution generated based on the second location information.

[0167] Thereby, it is possible to narrow down to a more appropriate area than estimating the activity area only from the first location information. Therefore, it is possible to improve the accuracy of estimating the activity area of the target user.

[0168] The embodiments and modifications of the present invention have been described above with reference to the drawings. These are merely examples of the present invention, and various configurations other than those described above can also be adopted.

[0169] Also, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order. However, the execution order of the steps executed in each of the embodiments is not limited to the order described. In each of the embodiments, the order of the illustrated steps can be changed within a range that does not interfere with the content. Further, the above-described embodiments and modifications can be combined within a range where the contents do not conflict.

[0170] Some or all of the above embodiments can also be described as follows in the appended claims, but are not limited thereto.

[0171] 1. A first generation means for generating first location information based on first posting information of a target user; A usefulness determination means for determining whether the first location information is useful for estimating an activity area of the target user in the real space by using related user information regarding a related user who is a user related to the target user; An activity area estimation means for estimating the activity area of the target user by using the first location information determined to be useful. An activity area estimation device. 2. The first location information is generated by using at least one of text information, location information, and an image included in the first posting information. The activity area estimation device according to 1. 3. The activity area estimation device further includes a second generation means for identifying the related user of the target user and generating the related user information including second location information by using profile information of the related user. The activity area estimation device according to 1. or 2. 4. The profile information includes residence information of the related user. The second location information includes the residence information obtained from the profile information. The activity area estimation device according to 3. 5. The related user includes at least one of a direct related user directly associated with the target user and an indirect related user associated with the direct related user. The activity area estimation device according to 3. or 4. 6. Whether the first location information is useful is determined using the related user information and a predetermined determination criterion. The determination criterion includes a criterion regarding the positional relationship in the real space of the locations indicated by the first location information and the second location information, respectively. The activity area estimation device according to any one of 3. to 5. 7. The related user is included in a plurality of related users. The related user information is included in the plurality of related user information of each of the plurality of related users. The second location information is included in the plurality of second location information of each of the plurality of related users. Whether the first location information is useful is determined using the plurality of second location information included in each of the plurality of related user information. The activity area estimation device according to any one of 3. to 6. 8. The activity area of the target user is further estimated using the second location information. The activity area estimation device according to any one of 3. to 6. 9. The activity area of the target user is estimated using the overlap between the posting distribution generated based on the first location information and the related user distribution generated based on the second location information. The activity area estimation device according to 8. 10. One or more computers Based on the first submission information of the target user, generate first location information, Using the related user information about the related user who is a user related to the target user, determine whether the first location information is useful for estimating the activity area of the target user in the real space, Using the first location information determined to be useful, estimate the activity area of the target user Activity area estimation method. 11. The first location information is generated using at least one of text information, location information, and images included in the first submission information The activity area estimation method according to 10. 12. Further including identifying the related user of the target user and generating the related user information including second location information using the profile information of the related user The activity area estimation method according to 10. or 11. 13. The profile information includes the residence information of the related user, The second location information includes the residence information obtained from the profile information The activity area estimation method according to 12. 14. The related user includes at least one of a direct related user directly associated with the target user and an indirect related user associated with the direct related user The activity area estimation method according to 12. or 13. 15. Whether the first location information is useful is determined using the related user information and a predetermined determination criterion, The determination criterion includes a criterion regarding the positional relationship in the real space of the locations indicated by the first location information and the second location information respectively The activity area estimation method according to any one of 12. to 14. 16. The related user is included in a plurality of related users, The related user information is included in the multiple pieces of related user information of each of the multiple related users. The second location information is included in the multiple pieces of second location information of each of the multiple related users. Whether the first location information is useful is determined using the multiple pieces of second location information included in each of the multiple pieces of related user information. The activity area estimation method according to any one of 12. to 15. 17. The activity area of the target user is further estimated using the second location information. The activity area estimation method according to any one of 12. to 15. 18. The activity area of the target user is estimated using the overlap between the post distribution generated based on the first location information and the related user distribution generated based on the second location information. The activity area estimation method according to 17. 19. On one or more computers, Generate first location information based on the first post information of the target user, Using the related user information regarding a related user who is a user related to the target user, determine whether the first location information is useful for estimating the activity area of the target user in the real space, A program for causing execution of estimating the activity area of the target user using the first location information determined to be useful. 20. The first location information is generated using at least one of text information, location information, and an image included in the first post information. The program according to 19. 21. For further causing execution of identifying the related user of the target user and generating the related user information including the second location information using the profile information of the related user. The program according to 19. or 20. 22. The profile information includes the residential address information of the associated user, The second location information includes the residential address information obtained from the profile information The program according to 21. 23. The associated user includes at least one of a direct associated user directly associated with the target user and an indirect associated user associated with the direct associated user The program according to 21. or 22. 24. Whether the first location information is useful is determined using the associated user information and a predetermined determination criterion, The determination criterion includes a criterion regarding the positional relationship in the actual space of the locations indicated by the first location information and the second location information respectively The program according to any one of 21. to 23. 25. The associated user is included in a plurality of associated users, The associated user information is included in the plurality of associated user information of each of the plurality of associated users, The second location information is included in the plurality of second location information of each of the plurality of associated users, Whether the first location information is useful is determined using the plurality of second location information included in each of the plurality of associated user information The program according to any one of 21. to 24. 26. The activity area of the target user is further estimated using the second location information The program according to any one of 21. to 24. 27. The activity area of the target user is estimated using the overlap between the post distribution generated based on the first location information and the associated user distribution generated based on the second location information The program according to 26. 28. A recording medium on which the program according to any one of 19 to 27 is recorded.

Explanation of Signs

[0172] 100 Information processing system 101 SNS system 102 Activity area estimation device 121 Target user reception unit 122 First generation unit 122a First acquisition unit 122b First location generation unit 123 Second generation unit 123a Related user identification unit 123b Second acquisition unit 123c Second location generation unit 124 Usefulness determination unit 125, 225 Activity area estimation unit 126 Output unit 225a First distribution generation unit 225b Second distribution generation unit 225c Activity area generation unit

Claims

1. a first generation means for generating first location information based on first posting information of a target user; a usefulness determination means for determining whether the first location information is useful for estimating an activity area of the target user in the real space by using related user information regarding a related user who is a user related to the target user; and an activity area estimation means for estimating the activity area of the target user by using the first location information determined to be useful. An activity area estimation device.

2. The first location information is generated by using at least one of text information, location information, and an image included in the first posting information. The activity area estimation device according to Claim 1.

3. The activity area estimation device according to Claim 1 or 2, further comprising a second generation means for identifying the related user of the target user and generating the related user information including second location information by using profile information of the related user. The activity area estimation device according to Claim 1 or 2.

4. The profile information includes residence information of the related user, and the second location information includes the residence information obtained from the profile information. The activity area estimation device according to Claim 3.

5. The related user includes at least one of a direct related user directly associated with the target user and an indirect related user associated with the direct related user. The activity area estimation device according to Claim 3.

6. Whether the first location information is useful is determined by using the related user information and a predetermined determination criterion, and the determination criterion includes a criterion regarding a positional relationship in the real space of the locations indicated by the first location information and the second location information, respectively. The activity area estimation device according to Claim 3.

7. The related user is included in a plurality of related users, the related user information is included in the plurality of related user information of each of the plurality of related users, the second location information is included in the plurality of second location information of each of the plurality of related users, and whether the first location information is useful is determined by using the plurality of second location information included in each of the plurality of related user information. The activity area estimation device according to Claim 3.

8. The activity area of the target user is further estimated by using the second location information. The activity area estimation device according to Claim 3.

9. One or more computers Generate first location information based on the first posting information of the target user. Using related user information about a related user who is a user related to the target user, determine whether the first location information is useful for estimating the activity area of the target user in the real space. Estimate the activity area of the target user using the first location information determined to be useful. Activity area estimation method.

10. On one or more computers, Generate first location information based on the first posting information of the target user. Using related user information about a related user who is a user related to the target user, determine whether the first location information is useful for estimating the activity area of the target user in the real space. A program for causing the activity area of the target user to be estimated using the first location information determined to be useful.

Images