Attribute estimation device and attribute estimation method

Abstract

To provide a technique for efficiently estimating attributes of a user.SOLUTION: An attribute estimation apparatus for estimating attributes of a user includes: an area setting unit which determines a stay-related area related to a location where a first user stays, on the basis of a position at a past point of time of a first device associated with the first user; and an estimation unit which estimates an attribute of the user. The estimation unit estimates an attribute of the first user on the basis of behavior of the first user, and estimates, when a position of a second device associated with a second user is included in the stay-related area, that the second user has the same attribute as the first user.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to an attribute estimation device and an attribute estimation method. [Background technology]

[0002] Various technologies have been proposed for providing appropriate advertisements to users. Patent Document 1 describes a technology that estimates a gathering area that includes all of a user's places of stay as the user's living area, and provides the user with information about facilities and the like related to this living area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-53593 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology of Patent Document 1 can provide information only to users whose living areas can be estimated. Therefore, it is not possible to estimate the attributes of users whose living areas cannot be estimated, and information can only be provided to a limited number of users. An object of some aspects of the present invention is to provide a technology for efficiently estimating user attributes. [Means for solving the problem]

[0005] According to some embodiments, An attribute estimation device for estimating a user's attribute, comprising: an area setting means for determining a stay-related area related to a place where a first user stayed, based on a position of a first device associated with the first user at a past time; and an estimation means for estimating a user's attribute, wherein the estimation means estimates the attribute of the first user based on at least one of information including the first user's behavior regarding visits or stays at specific places and the first user's purchase history of specific products, and when the position of a second device associated with a second user is included in the stay-related area, estimates that the second user has the same attribute as the first user; The area setting means sets a time period including a time point at which the moving speed of the first device is equal to or less than the first threshold speed for a first threshold time or more. The corresponding additional distance and determining the size of the stay-related area based on the , attribute estimation device is provided. [Effects of the Invention]

[0006] According to the above embodiment, the attributes of a user can be estimated efficiently. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a diagram illustrating an example of the hardware configuration of an information processing apparatus and a communication device according to some embodiments. [Figure 2] FIG. 2 is a diagram illustrating an example of the functional configuration of an information processing apparatus and a communication device according to some embodiments. [Figure 3] FIG. 2 is a diagram illustrating information used by an information processing apparatus according to some embodiments. [Figure 4] FIG. 2 is a diagram illustrating information used by an information processing apparatus according to some embodiments. [Figure 5] FIG. 10 is a diagram illustrating an example of stay-related areas and estimation conditions according to some embodiments. [Figure 6] FIG. 10 is a diagram illustrating an example of an operation of an information processing apparatus according to some embodiments. [Figure 7] FIG. 10 is a diagram illustrating an example of an operation of an information processing apparatus according to some embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be combined in any desired manner. Furthermore, the same reference numerals are used to designate identical or similar components, and redundant descriptions will be omitted.

[0009] With reference to FIG. 1, an example hardware configuration of a system according to some embodiments will be described. The system shown in FIG. 1 includes an information processing device 100 and a plurality of communication devices 110. The information processing device 100 and each of the plurality of communication devices 110 can communicate with each other via a wide area network 120 such as the Internet. The information processing device 100 may be, for example, a computer. As will be described in detail below, the information processing device 100 is used to estimate a user's attribute. Therefore, the information processing device 100 may be referred to as an attribute estimation device. When the information processing device 100 performs processing in response to a request from another device, the information processing device 100 may be referred to as a server.

[0010] Communication device 110 is typically a device that can be moved with a user. For example, communication device 110 may be a portable device that can be carried by a user (e.g., a smartphone, a mobile phone, a tablet computer, or a smart watch). Alternatively, communication device 110 may be a communication device installed in a vehicle (e.g., an in-vehicle telematics control unit (TCU) or a navigation device).

[0011] The information processing device 100 may have the hardware components shown in Fig. 1. The processor 101 controls the overall operation of the information processing device 100. The processor 101 may be configured by, for example, a central processing unit (CPU). The processor 101 may be a single processor or a set of multiple processors connected to each other so that they can communicate with each other.

[0012] The memory 102 stores programs and data used in the processing of the information processing device 100. The memory 102 may be configured, for example, by combining a random access memory (RAM) and a read-only memory (ROM).

[0013] The input device 103 is a device for obtaining instructions from a user of the information processing device 100. The input device 103 may be configured, for example, by a combination of one or more of a keyboard, a button, a touchpad, and a microphone. The display device 104 is a device for visually presenting information to the user of the information processing device 100. The display device 104 may be, for example, a dot matrix display such as a liquid crystal display. The information processing device 100 may have a device (for example, a touch screen) in which the input device 103 and the display device 104 are integrated.

[0014] The communication circuit 105 is a circuit for communicating with devices external to the information processing device 100. When the information processing device 100 performs wired communication, the communication circuit 105 may be a network interface card (NIC) having a connector for connecting a cable. When the information processing device 100 performs wireless communication, the communication circuit 105 may be a wireless communication module including an antenna and a baseband processing circuit.

[0015] The secondary storage device 106 is a device for non-volatilely storing data used in the processing of the information processing device 100. The secondary storage device 106 is configured by, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0016] Communication device 110 may have the hardware components shown in Fig. 1. Processor 111, memory 112, and communication circuit 113 may be similar to processor 101, memory 122, and communication circuit 105, and therefore redundant description will be omitted.

[0017] The positioning sensor 114 is a sensor for measuring the geographical position of the communication device 110. The positioning sensor 114 may be, for example, a Global Navigation Satellite System (GNSS) sensor. The speed sensor 115 is a sensor for measuring the moving speed of the communication device 110.

[0018] An example of functional blocks of the information processing device 100 and the communication device 110 according to some embodiments will be described with reference to Fig. 2. Fig. 2 illustrates functions for the information processing device 100 to estimate a user's attribute. The information processing device 100 and the communication device 110 may also have other functions.

[0019] The communication device 110 may have the functional blocks shown in Fig. 2. Each functional block may be implemented by the processor 111 operating in accordance with instructions from a program stored in the memory 112. Alternatively, some or all of the functional blocks in Fig. 2 may be implemented by a dedicated circuit such as an application specific integrated circuit (ASIC).

[0020] The position measurement unit 211 measures the geographical position (hereinafter simply referred to as "position") of the communication device 110, for example, using the positioning sensor 114. The position of the communication device 110 may be expressed by two-dimensional coordinates on the Earth's surface (e.g., latitude and longitude) or by other geocodes. The position measurement unit 211 may measure the position of the communication device 110 at multiple points in time. For example, the position measurement unit 211 may measure the position of the communication device 110 periodically (e.g., every 10 seconds, every minute, every 5 minutes, or every 10 minutes). The position measurement unit 211 may measure the position of the communication device 110 without using the positioning sensor 114. For example, the position measurement unit 211 may measure the position of the communication device 110 based on the distances to multiple base stations. In this case, the communication device 110 may not include the positioning sensor 114.

[0021] The speed measurement unit 212 measures the moving speed of the communication device 110 using, for example, the speed sensor 115. The speed measurement unit 212 may measure the moving speed of the communication device 110 at multiple points in time. For example, the speed measurement unit 212 may measure the moving speed of the communication device 110 each time the position measurement unit 211 measures the position of the communication device 110. The speed measurement unit 212 may measure the moving speed of the communication device 110 without using the speed sensor 115. For example, the speed measurement unit 212 may measure the speed by dividing the distance between the positions at two points in time measured by the position measurement unit 211 by the interval between these two points in time. In this case, the communication device 110 does not need to include the speed sensor 115.

[0022] The vehicle power state acquisition unit 213 acquires the power state (i.e., whether it is on or off) of the vehicle in which the communication device 110 is mounted. The vehicle power state acquisition unit 213 may be included in the communication device 110 when the communication device 110 is a device mounted on the vehicle. The power state of the vehicle may refer to the state of the ignition power. The vehicle may be a vehicle powered by gasoline (a so-called gasoline vehicle), a vehicle powered by electricity (a so-called electric vehicle), or a vehicle powered by both sources (a so-called hybrid vehicle). Regardless of the type, when the power state of the vehicle is on, the vehicle is running, and when the power state of the vehicle is off, the vehicle is not running.

[0023] The movement information providing unit 214 provides movement information of the communication device 110 to the information processing device 100, for example, using the communication circuit 113. The movement information may be information including the position of the communication device 110 and the movement speed of the communication device 110 at that position. The movement information providing unit 214 may transmit the movement information to the information processing device 100 every time the movement information is generated (for example, every time the position measurement unit 211 measures the position of the communication device 110). Alternatively, the movement information providing unit 214 may transmit the movement information to the information processing device 100 periodically (for example, once a day or once a week) with a period longer than the period in which the movement information is generated. Alternatively, the movement information providing unit 214 may transmit the movement information to the information processing device 100 in response to a request from a user or a request from the information processing device 100. Alternatively, the movement information providing unit 214 may transmit the movement information to the information processing device 100 in response to the occurrence of a specific event (for example, the start of a specific application). The generated movement information may be stored in the memory 112 until it is transmitted to the information processing device 100, and after transmission, may be deleted from the memory 112. The movement information providing unit 214 may provide the information processing device 100 with the state of the vehicle's power supply acquired by the vehicle power supply state acquiring unit 213.

[0024] The information processing device 100 may have the functional blocks shown in Fig. 2. Each functional block may be realized by the processor 101 operating in accordance with instructions of a program read from the secondary storage device 106 to the memory 102. Alternatively, some or all of the functional blocks in Fig. 2 may be realized by a dedicated circuit such as an ASIC.

[0025] The information management unit 201 manages information used for the operation of the information processing device 100. For example, the information management unit 201 manages user information 300 and device information 310 shown in FIG. 3. The user information 300 is information about a user. In the example shown in FIG. 3, the user information 300 is managed using a table, and this table has columns 301 to 303. The user information 300 has a record for each user. Column 301 indicates a user ID for uniquely identifying a user. Column 302 indicates the user's contact information. The contact information may be a phone number or an email address. Column 303 indicates the user's attributes. The user's attributes may be, for example, income level (e.g., high income bracket) or whether the user has a pet (e.g., pets). The user's attributes may include the user's interests. For example, the user's attributes may include interests such as outdoors, childcare, parenting, and motorsports. The user's attributes may be managed by the presence or absence of flags for multiple items (e.g., wealthy bracket, pets).

[0026] The information management unit 201 may manage the user information 300 (for example, create a new entry, update and delete an existing entry) based on an input from the user of the information processing device 100. Alternatively, the information management unit 201 may manage the user information 300 based on an input from the user of the communication device 110. The attributes shown in column 303 of the user information 300 may be estimated by the information processing device 100, as will be described later.

[0027] Device information 310 is information about devices. In the example shown in FIG. 3, device information 310 is managed by a table, and this table has columns 311 to 313. Device information 310 has a record for each device. Column 311 indicates a device ID for uniquely identifying a device. Column 312 indicates a device ID for uniquely identifying a user who owns the device. In this way, each device managed by device information 310 is associated with a user. Column 312 of device information 310 corresponds to column 301 of user information 300. Column 313 indicates the type of device. The type of device may be a portable device such as a smartphone, or an in-vehicle device installed in a vehicle.

[0028] The information management unit 201 may manage the device information 310 (for example, create a new entry, update and delete an existing entry) based on an input from a user of the information processing device 100. Alternatively, the information management unit 201 may manage the device information 310 based on an input from a user of the communication device 110.

[0029] Movement history management unit 202 manages the movement history of multiple communication devices 110. The movement history of communication device 110 may refer to movement information (e.g., location and movement speed) of communication device 110 at multiple past points in time. In the example shown in Fig. 3, movement history 320 is managed by a table, and this table has columns 321 to 324. Movement history 320 has a record for each individual date and time for each of multiple communication devices 110.

[0030] Column 311 indicates a device ID for uniquely identifying a device. Column 321 of movement history 320 corresponds to column 312 of device information 310. Column 322 indicates the date and time at which movement information was generated by communication device 110. In the example of FIG. 3, movement information is generated every five minutes, but this is not limited to this. Also, in the example of FIG. 3, movement information is generated at the same date and time for multiple communication devices 110, but movement information may be generated at different dates and times for each communication device 110. Column 323 indicates the position of each communication device 110 at each individual point in time. Column 324 indicates the movement speed of each communication device 110 at each individual point in time.

[0031] In response to receiving location information from communication device 110, movement history management unit 202 may generate a record of movement history 320 based on the location information. Furthermore, movement history management unit 202 may delete unnecessary records from movement history 320. For example, movement history management unit 202 may delete from movement history 320 records for which a threshold time has elapsed since the date and time indicated in column 322.

[0032] The region setting unit 203 determines a stay-related region of an individual user based on movement information (e.g., location and movement speed) of an individual device associated with the individual user at multiple past points in time. The movement information of an individual device at multiple past points in time is stored in the movement history 320. The stay-related region may be a region related to a place where the user stayed. A stay may be a state in which the user stays in a specific place for a threshold time T1 (e.g., 6 hours) or more. When the user stays in a specific place for the threshold time T1 or more, the movement speed of the user's communication device 110 may be equal to or less than a threshold speed V1 for the threshold time T1 or more. Therefore, the region setting unit 203 may determine the stay-related region based on the position of the communication device 110 where the movement speed of the communication device 110 is equal to or less than the threshold speed T1 for the threshold time T1 or more. The threshold speed V1 is set to a value indicating that the user with the communication device 110 is staying in a specific place. For example, the threshold speed V1 may be set to 4 km / h. The set value of the threshold speed V1 is stored in, for example, the secondary storage device 106.

[0033] A stay-related region of a certain user may be a region in which there is a possibility that a user who is estimated to have the same attributes as this user exists. For example, if a certain user is staying at home, other users in the vicinity (e.g., within a radius of about 200 meters) may have the same attributes as this user (e.g., if the user lives in an upscale residential area and is in the high-income bracket, it is highly likely that the users around him / her are also in the high-income bracket). In another example, if a certain user is staying at work, other users in the same workplace (e.g., within a radius of about 50 meters) may have the same attributes as this user (e.g., if the user works at a fitness club and is interested in exercise, it is highly likely that other users who visit the workplace are also interested in exercise). Therefore, in some embodiments, the region setting unit 203 sets the stay-related region to a range wider than the location where the user actually stayed (the location of the communication device 110).

[0034] The region setting unit 203 may include, in the stay-related region, positions that are within the additional distance from the position of the communication device 110 at each of the multiple time points. The stay-related region may be a union of circular regions that are centered on the position of the communication device 110 at each of the multiple time points and have the additional distance as their radius. The additional distance may be a fixed value (e.g., 100 m) that is set in advance. Alternatively, the region setting unit 203 may determine the additional distance based on various factors.

[0035] For example, the region setting unit 203 may determine the additional distance based on a time period (hereinafter referred to as a stay time period) including a time when the moving speed of the communication device 110 is equal to or less than the threshold speed V1 continuously for at least the threshold time T1, and may determine the size of the stay-related region accordingly. A time period may refer to multiple divisions that make up a day. For example, a day is made up of three time periods: morning (7:01 to 12:00), daytime (12:01 to 19:00), and nighttime (19:01 to 7:00). For example, suppose a user is staying at a certain place during the nighttime. In this case, this place is likely to be the user's residence. Therefore, the region setting unit 203 increases the additional distance (for example, to 100 m) when the stay time period is during the nighttime. This allows locations near the user's residence to be included in the stay-related region. Furthermore, suppose a user is staying at a certain place during the morning or daytime. In this case, this place is likely to be the user's workplace. Therefore, the area setting unit 203 sets a small additional distance (for example, 50 m) when the stay time zone is morning or afternoon, thereby preventing locations outside the user's workplace from being included in the stay-related area.

[0036] The region setting unit 203 may determine the additional distance based on the user's behavior and determine the size of the stay-related region accordingly. The region setting unit 203 may perform this process by referring to the behavior information 400 shown in FIG. 4, for example. The behavior information 400 may be created in advance by the user of the information processing device 100, for example, and stored in the secondary storage device 106. The behavior information 400 is information related to the user's behavior. In the example shown in FIG. 4, the behavior information 400 is managed by a table, and this table has columns 401 to 405. The behavior information 400 has a record for each user's behavior.

[0037] Column 401 indicates the user's behavior. As described above, a stay may be staying at a particular location for a threshold time (e.g., 6 hours) or more. The threshold time may differ for each location. A visit may be staying at a particular location for a threshold time (e.g., 10 minutes) or more, which is shorter than a stay. By comparing with the threshold time in this way, cases where the user simply passes through can be excluded.

[0038] Column 402 indicates the additional distance used for each activity. The additional distance may vary depending on the activity. In the example of FIG. 4, the additional distance is set to three levels: 200 m, 100 m, and 50 m, but this is not limited to these. Generally, the fewer people who regularly perform a particular activity (e.g., the number of athletes), the fewer people with the same attributes for that activity are likely to be around the user's stay location, so the additional distance may be smaller. From a similar perspective, the higher the cost required for the activity, the shorter the additional distance may be. The additional distance may also be set based on characteristics specific to the activity. For example, a user who visits a pet shop is likely to own a pet, and it is assumed that the apartment complex in which this user lives allows pets. However, it is not necessarily the case that pets are allowed in the residences nearby this apartment complex. Therefore, by setting the additional distance to 50 m for a visit to a pet shop, only other users who live in the same apartment complex as the user are included in the stay-related area. Columns 403 to 405 of the activity information 400 will be described later.

[0039] When the communications device 110 is a device mounted on a vehicle, the region setting unit 203 may determine the stay-related region based on a location where the vehicle has been in an inactive state for a threshold time T2 or more (e.g., six hours). When the user parks the vehicle, the user may be staying in the vicinity of the vehicle. Therefore, the region setting unit 203 may also determine such a location as the stay-related region. The duration of the vehicle's inactive state may be measured by the communications device 110 and transmitted to the information processing device 100, or may be calculated by the information processing device 100 based on a change in the power state (from on to off, from off to on) transmitted from the communications device 110.

[0040] 3, the description of the functional blocks of the information processing device 100 will continue. The attribute estimation unit 204 estimates the attributes of a user. The attribute estimation unit 204 may estimate the attributes based on the user's behavior and the attributes based on the user's location in a stay-related area of ​​another user.

[0041] First, estimation of attributes based on user behavior will be described. The attribute estimation unit 204 may estimate a user's attributes based on the user's behavior. Column 403 of the behavior information 400 in FIG. 4 indicates attributes estimated for specific behavior. For example, a user who stayed at a campsite is estimated to have an outdoor attribute. The user's behavior related to visiting and staying at a specific location may be determined based on the movement history 320. For example, the attribute estimation unit 204 may estimate that the user performed a specific behavior based on the user's communication device 110 staying at the specific location for a time period corresponding to the specific location. For example, in the example shown in the behavior information 400 in FIG. 4, if the user visited a pet shop, it may be estimated that the user visited the pet shop based on the user's communication device 110 staying there for 30 minutes or more. If the user visited a campsite, it may be estimated that the user stayed at the campsite based on the user's communication device 110 staying there for 3 hours or more.

[0042] The attribute estimation unit 204 may determine the user's attribute based on something other than the user's visit or stay at a specific place. For example, the attribute estimation unit 204 may estimate the user's attribute based on the user's purchase history of a specific product. If the user has purchased a pet-related product, it may be estimated that the user has a pet attribute. The attribute estimation unit 204 may update the attribute (column 303) of the user information 300 based on the estimation result of the user's attribute.

[0043] Next, the estimation of attributes based on being located within another user's stay-related area will be described. The attribute estimation unit 204 may estimate attributes of a user whose attributes are not registered in the user information 300 based on attributes of a user whose attributes are already registered in the user information 300. In the following description, a user whose attributes are already registered in the user information 300 is referred to as a reference user, and a user whose attributes are not registered in the user information 300 is referred to as a target user. The attributes of the reference user may be estimated based on behavior. The attribute estimation unit 204 estimates that the target user has the same attributes as the reference user when certain estimation conditions are met. Based on this estimation result, the attribute estimation unit 204 may update the attributes of the target user (column 303) in the user information 300. In some embodiments, the estimation conditions are based on the reference user's stay-related area and movement information of the communication device 110 associated with the target user. For example, the estimation conditions may include that the location of the communication device 110 associated with the target user is included in the reference user's stay-related area. The stay-related area of ​​the reference user is generated based on past movement information of the reference user's communication device 110, and whether the estimation condition is satisfied is determined based on past movement information of the target user's communication device 110. Therefore, even if the reference user and the target user were not in close locations at a specific time in the past, it can be determined whether the reference user and the target user can be estimated to have the same attribute.

[0044] The estimation condition may be based on a time period. For example, the estimation condition may include that the location of the communication device 110 of the target user is included in the reference user's stay-related area during a time period in which the movement speed of the communication device 110 of the reference user is equal to or less than a threshold speed V1 for a period of at least a threshold time T1. If this condition is satisfied, the target user is estimated to have the same attribute as the reference user. By taking the time period into consideration in this way, the same attribute is assigned to users with similar lifestyles. Furthermore, by taking the time period into consideration, even if the time when the reference user stayed and the time when the target user stayed are different, the attribute of the target user can be estimated as long as they are included in the same time period.

[0045] After the attribute estimation unit 204 estimates that the target user has a specific attribute, it may estimate that the target user does not have the attribute based on the target user's behavior. If the attribute estimation unit 204 estimates that the target user does not have the specific attribute, it may update the attribute (column 303) in the user information 300 (specifically, delete the attribute). The attribute estimation unit 204 may not assign an attribute that has been deleted to the same user for a predetermined period (e.g., three years). Column 405 of the behavior information 400 indicates behaviors used to determine that the target user does not have the specific attribute. The behaviors used to determine that the target user does not have the specific attribute may be based on the behavior of a reference user referenced to estimate the target user's attribute. For example, suppose that the reference user visits a childcare facility (e.g., a nursery school), which assigns the childcare attribute to the reference user. Then, suppose that the target user's communication device 110 is located in the reference user's related area, which assigns the childcare attribute to the target user. If the target user subsequently visits an elementary or junior high school, it is considered that the target user has already finished childcare. Therefore, the attribute estimation unit 204 may estimate that the target user does not have the attribute of childcare, and may delete childcare from the attributes of the target user.

[0046] A specific method for determining a stay-related area and estimating attributes will be described with reference to FIG. 5. First, with reference to FIG. 5(a), a description will be given of a daily activity of a user of a communication device 110 in an example scenario. The user stays at home 501 from the previous night until the current morning, and then walks along route 506 to station 502. The user boards a train at station 502, travels along route 507, and gets off at station 503. The user walks from station 503 to workplace 504 along route 508. After working for eight hours at workplace 504, the user travels by car (e.g., taxi or bus) along route 509 to pet shop 505 and spends about an hour shopping. During these activities, the user wears or keeps nearby his or her communication device 500 (e.g., a smartphone). The communication device 500 may have a configuration similar to that of the communication device 110 described above.

[0047] The movement speed of communication device 110 at multiple points in time while the user is at home 501 (for example, points in time when movement information is periodically generated by communication device 110) remains equal to or less than threshold speed V1 for at least threshold time T1. Therefore, region setting unit 203 includes positions within the additional distance from these multiple points in the stay-related region. In this way, stay-related region 510 is determined. Stay-related region 510 may be a union of circular regions whose centers are the positions of communication device 110 at each of the multiple points in time, and whose radii are the additional distances.

[0048] The movement speed of communication device 110 at multiple points in time while the user is at workplace 504 (for example, points in time when movement information is periodically generated by communication device 110) remains equal to or less than threshold speed V1 for at least threshold time T1. Therefore, region setting unit 203 includes positions within the additional distance from these multiple points in the stay-related region. In this way, stay-related region 511 is determined. Stay-related region 510 may be a union of circular regions whose centers are the positions of communication device 110 at each of the multiple points in time, and whose radii are the additional distances.

[0049] The stay-related area 510 is determined for the user's stay in the nighttime, and the stay-related area 511 is determined for the user's stay in the daytime. Therefore, the stay-related area 510 may be larger than the stay-related area 511. For example, an additional distance of 200 m may be used to determine the stay-related area 510, and an additional distance of 50 m may be used to determine the stay-related area 511.

[0050] When the user travels on foot along route 506, the travel speed of communication device 110 at each point in time during this period is greater than threshold speed V1. Therefore, no stay-related area is set for route 506. Similarly, no stay-related area is set for routes 507 to 509 along which the user travels.

[0051] While the user is in pet shop 505, the movement speed of communication device 110 is equal to or less than threshold speed V1. However, because the time spent there (e.g., 1 hour) is shorter than threshold time T1 (e.g., 6 hours), no stay-related area is set for pet shop 505.

[0052] The area setting unit 203 does not need to use movement information of the communication device 110 from a time point earlier than a specific threshold time in determining the stay-related area. The location where the user stays may change over time. For example, if the user is transferred or moves, the location where the user stays will change. Therefore, the area setting unit 203 can generate a highly accurate stay-related area by not using old movement information (i.e., movement information from a time point earlier than a specific threshold time).

[0053] Next, a description will be given of the estimation of a user's attribute by attribute estimation unit 204. The user of communication device 500 visited pet shop 505. Therefore, attribute estimation unit 204 estimates that this user has a pet attribute and registers this in user information 300. Attribute estimation unit 204 may use other visit information or information other than the visit to estimate that the user of communication device 500 has a different attribute.

[0054] Assume that the location of the communication device 520 of the target user at a certain point in the past was included in the stay-related area 510. In this case, the target user may have the same attributes as the reference user because the target user is active in the living area of ​​the reference user. Therefore, the attribute estimation unit 204 determines that the communication device 520 of the target user satisfies the estimation condition and estimates that the target user associated with the communication device 520 has the same attributes as the reference user who has the stay-related area 510. On the other hand, the attribute estimation unit 204 may determine that the estimation condition is not satisfied if the location of the communication device 520 of the target user was not included in the stay-related area 510 at any point in the past. In this case, the attribute estimation unit 204 does not estimate that the target user associated with the communication device 520 has the same attributes as the reference user who has the stay-related area 510.

[0055] The estimation condition may include that the location of the communication device 520 of the target user is included in the stay-related area of ​​the reference user during a time period including multiple time points at which the movement speed of the communication device 500 of the reference user is equal to or less than the threshold speed V1 for a continuous period of at least a threshold time T1. Assume that the movement speed of the communication device 500 of the reference user is equal to or less than the threshold speed V1 for nine consecutive hours from 10:00 PM to 7:00 AM, which is included in the evening time period. In this case, the attribute estimation unit 204 may determine that the estimation condition is satisfied when the location of the communication device 520 of the target user is included in the stay-related area 510 (stay-related area) for a continuous period of at least a threshold time T2 (e.g., five hours or more) during the evening time period. Otherwise (e.g., when the location of the communication device 520 of the target user is included in the stay-related area 510 for only three hours during the evening time period), the attribute estimation unit 204 may determine that the estimation condition is not satisfied. If such an estimation condition is satisfied, it is highly likely that the target user is also staying in a location included in the stay-related area 510. For example, if the reference user and the target user live in the same apartment building, this estimation condition is highly likely to be satisfied. Therefore, by determining such an estimation condition, it is possible to identify a reference user who has the same attribute (for example, the same income level) as the target user.

[0056] The size of the stay-related area may vary depending on the attribute that the target user is estimated to have. In the above example, the reference user is assigned a pet attribute by visiting pet shop 505. In this case, the size of the stay-related area for assigning the pet attribute to the target user may be different from the size of the stay-related area for assigning other attributes to the target user. As described above, the size of the stay-related area for assigning other attributes to the target user may be based on the fact that the target user stayed during the nighttime, and the size of the stay-related area for assigning the pet attribute to the target user may be based on the assignment distance specified in column 402 of the behavior information 400.

[0057] Another example of the estimation condition will be described with reference to FIG. 5(b). When the communication device of the reference user is a communication device mounted on a vehicle, the region setting unit 203 may determine the stay-related region based on the length of time the vehicle was not activated. For example, the region setting unit 203 may include, in the stay-related region, a position within a specific distance from the position of the communication device during the time the vehicle was not activated. The activation state of the vehicle may be acquired from the communication device 110 by the movement history management unit 202, and the date and time when the activation state of the vehicle changed may be recorded in the movement history 320. The specific distance may be a value intended to include parking lots, for example, 100 m.

[0058] The estimation condition may include that the target user's communication device is a vehicle-mounted communication device and the target user's vehicle has not been started at a location included in the reference user's stay-related area. If this condition is met, it is highly likely that the target user is using the same parking lot as the reference user.

[0059] In the example of FIG. 5(b), it is assumed that the electronic device of the reference user is a device mounted on a vehicle 571, and that the vehicle 571 has not been activated in a parking lot 570 for a threshold time. In this case, the area setting unit 203 determines a stay-related area 572. The attribute estimation unit 204 determines that the electronic device of the target user is a device mounted on a vehicle 580, and that the vehicle 580 has not been activated in the stay-related area 572 at some point in the past. In this case, the attribute estimation unit 204 determines that the estimation condition is satisfied.

[0060] The estimation condition may be further based on a time period during which the target user's vehicle was not started. For example, the attribute estimation unit 204 may determine that the estimation condition is satisfied when the target user's vehicle was not started within the stay-related area during a time period that includes a time period during which the reference user's vehicle was not started to determine the stay-related area.

[0061] When a threshold number of estimation conditions among the various estimation conditions described above are satisfied, the attribute estimation unit 204 estimates that the target user associated with the communication device 520 has the same attribute as the reference user who has the stay related area 510, and in other cases, the attribute estimation unit 204 does not need to estimate that the target user associated with the communication device 520 has the same attribute as the reference user who has the stay related area 510. The threshold number may be 1 (i.e., it is sufficient that any one estimation condition is satisfied), may be the same number as the estimation conditions to be determined (i.e., all estimation conditions need to be satisfied), or may be a number between these.

[0062] Referring again to FIG. 3, the description of the functional blocks of information processing device 100 will continue. Information providing unit 205 provides information to a user of communication device 110 according to the attributes of the user. Information providing unit 205 may determine the information to be provided based on advertisement information 330 shown in FIG. 3. In the example shown in FIG. 3, advertisement information 330 is managed by a table, and this table has columns 331 to 332. Advertisement information 330 has a record for each attribute value. Column 331 indicates the attributes possessed by the user. Column 332 indicates the content of the advertisement to be provided to the user.

[0063] When a user's attributes are estimated based on the user's behavior, the information providing unit 205 may provide the user with information based on the behavior. Column 404 of the behavior information 400 indicates the type of vehicle to be recommended as an example of information to be provided to the user. For example, the information providing unit 205 may provide information about new cars to a reference user who has been assigned a childcare attribute based on having visited a hospital with an obstetrics and gynecology department, and a target user who has been assigned a childcare attribute based on the reference user. The information providing unit 205 may provide information about used cars to a reference user who has been assigned a childcare attribute based on having visited a childcare facility, and a target user who has been assigned a childcare attribute based on the reference user.

[0064] As described above, when the estimation condition is satisfied, the target user is estimated to have the same attribute as the reference user. Therefore, when it is estimated that the target user has the same attribute as the reference user, the information providing unit 205 provides the target user with information according to this attribute.

[0065] A method for managing movement history 320 executed by the information processing device 100 according to some embodiments will be described with reference to Fig. 6. Each step of the method in Fig. 6 may be executed by the processor 101 operating in accordance with instructions of a program read from the secondary storage device 106 to the memory 102. Alternatively, some or all of the steps in Fig. 6 may be executed by a dedicated circuit such as an ASIC. The information processing device 100 may repeatedly execute the method in Fig. 6.

[0066] In S601, the movement history management unit 202 receives movement information from the communication device 110. The movement history management unit 202 may wait for the movement information to be transmitted from the communication device 110, or may request the communication device 110 to transmit the movement information. In S602, the movement history management unit 202 updates the movement history 320 using the acquired movement information. As described above, the movement history management unit 202 generates a new record of the movement history 320 for each communication device 110 and for each date and time when the movement information was generated.

[0067] An information providing method executed by the information processing device 100 according to some embodiments will be described with reference to Fig. 7. Each step of the method in Fig. 7 may be executed by the processor 101 operating in accordance with instructions of a program read from the secondary storage device 106 to the memory 102. Alternatively, some or all of the steps in Fig. 7 may be executed by a dedicated circuit such as an ASIC. The information processing device 100 may start the method in Fig. 7 in response to a request from a user of the information processing device 100. The method in Fig. 7 includes an attribute estimation method (S701 to S703) for estimating an attribute of the user.

[0068] In S701, as described above, the attribute estimation unit 204 estimates the attributes of a user based on the user's behavior and updates the attributes of the user information 300. If there are multiple referring users, the attribute estimation unit 204 executes S701 for each user.

[0069] In S702, the region setting unit 203 determines a stay-related region for the reference user based on the movement history of the reference user's communication device, as described above. As described above, a reference user is a user whose attributes have already been registered in the user information 300. If there are multiple reference users, the region setting unit 203 executes S702 for each reference user.

[0070] In S703, the attribute estimation unit 204 estimates attributes of the target user based on the movement history of the target user's communication device, as described above. As described above, the target user is a user whose attributes are not registered in the user information 300. If there are multiple target users, the attribute estimation unit 204 executes S703 for each target user. When it is determined that one target user satisfies the estimation conditions for the stay-related areas of two or more reference users, the attribute estimation unit 204 may set all of the attributes of these two or more reference users as the attributes of the target user.

[0071] In S704, the information providing unit 205 provides an advertisement to the user based on the attributes, as described above. For example, the information providing unit 205 sends an advertisement related to the user's attributes to the user's email address. By accurately estimating the attributes of the target user in S703, an appropriate advertisement can be provided to the target user in S704.

[0072] In the above-described embodiment, the attributes of the target user are attributes estimated from the attributes of the reference user. Therefore, if an attempt is made to estimate the attributes of other users based on the attributes of the target user, accuracy may decrease. Therefore, in S702 of FIG. 7, it is not necessary to estimate a stay-related area for a user who was previously the target user. Instead, for a user who was previously the target user, a stay-related area may be estimated using an additional distance that is shorter than that for the reference user, and the stay-related area may be used to estimate the attributes in S703.

[0073] 3, information such as the user information 300 is stored in the secondary storage device 106. Alternatively, information such as the user information 300 may be stored in a device (e.g., a database server) external to the information processing device 100, and the information processing device 100 may acquire necessary information from this external device.

[0074] In the above-described embodiment, the movement history management unit 202 included in the information processing device 100 manages the movement history of the communication device 110. Alternatively, a device external to the information processing device 100 may manage the movement history, and the information processing device 100 may obtain necessary information from this external device.

[0075] In the above-described embodiment, the information providing unit 205 included in the information processing device 100 provides information to the user. Alternatively, an external device to the information processing device 100 may provide information to the user, and the information processing device 100 may provide necessary information (e.g., user attributes) to this external device.

[0076] <Summary of the embodiment> <Item 1> An attribute estimation device (100) for estimating a user's attribute, an area setting means (203) for determining stay-related areas (510, 511) related to places where the first user stayed based on a past location of a first device (500) associated with the first user; An estimation means (204) for estimating a user attribute (303), The estimation means Estimating attributes of a first user based on a behavior (401) of the first user; an attribute estimation device that estimates that a second user has the same attribute as the first user when the location of a second device (520) associated with the second user is included in the stay-related area; According to this item, the user's attributes can be estimated based on the device being located in a stay-related area of ​​another user, so that the user's attributes can be estimated efficiently. <Item 2> Item 1. The attribute estimation device according to Item 1, wherein, when the first device is a device mounted on a first vehicle (571), the area setting means determines the stay-related area based on a location where the first vehicle has been in an inactive state for a threshold time or more. According to this item, the stay-related area is determined based on the type of device, thereby improving the accuracy of estimating the user's attributes. <Item 3> 3. The attribute estimation device according to item 1 or 2, wherein the region setting means determines the stay-related region based on a position of the first device where the movement speed of the first device is equal to or less than a first threshold speed continuously for a first threshold time or more. According to this item, it is possible to estimate the location where the user stayed for a certain period of time, thereby improving the accuracy of estimating the user's attributes. <Item 4> 4. The attribute estimation device according to any one of items 1 to 3, wherein the region setting means determines the size of the stay-related region based on a time period including a time point at which the movement speed of the first device is equal to or less than a first threshold speed continuously for at least a first threshold time. According to this item, a stay-related area of ​​a size according to a time period can be determined, thereby improving the accuracy of estimating the attributes of a user. <Item 5> 5. The attribute estimation device according to any one of items 1 to 4, wherein the estimation means estimates that the first user has performed a specific behavior based on the first device remaining in a specific location for a time period corresponding to the specific location. According to this item, the accuracy of estimating the user's attributes is improved because the user's behavior is estimated based on the user's stay time. <Item 6> 6. The attribute estimation device according to any one of items 1 to 5, wherein the region setting means determines a size of the stay-related region based on a behavior of the first user. According to this item, the stay-related area is determined according to the user's behavior, thereby improving the accuracy of estimating the user's attributes. <Item 7> 7. The attribute estimation device according to any one of items 1 to 6, wherein the estimation means estimates that the second user has the same attribute as the first user when the position of the second device is included in the stay-related area during a time period in which the movement speed of the first device is equal to or less than a first threshold speed continuously for a first threshold time or more. According to this item, the accuracy of estimating user attributes is improved because the stays of users are compared for each time period. <Item 8> 8. The attribute estimation device according to any one of items 1 to 7, wherein the estimation means estimates that the second user does not have the attribute based on the second user performing a specific action after the second user has been estimated to have the specific attribute. This item allows for ignoring user attributes that have changed over time, thereby improving the accuracy of estimating user attributes. <Item 9> A program for causing a computer to function as each means of the attribute estimation device according to any one of items 1 to 8. According to this item, the above item is provided in the form of a program. <Item 10> An attribute estimation method for estimating an attribute of a user, comprising: an area setting step (S702) in which an area setting means (203) determines stay-related areas (510, 511) related to places where the first user stayed, based on a past location of a first device (500) associated with the first user; A step (S701) in which an estimation means (204) estimates an attribute (303) of the first user based on the behavior of the first user; An attribute estimation method comprising: a step (S703) in which the estimation means estimates that the second user has the same attribute as the first user if the location of a second device associated with the second user is included in the stay-related area. According to this item, the user's attributes can be estimated based on the device being located in a stay-related area of ​​another user, so that the user's attributes can be estimated efficiently.

[0077] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0078] 100 Information processing devices, 110 Communication devices, 510-511 Stay-related areas

Claims

1. An attribute estimation device for estimating a user's attribute, comprising: an area setting means for determining a stay-related area related to a place where a first user has stayed, based on a past location of a first device associated with the first user; An estimation means for estimating an attribute of a user, The estimation means Inferring attributes of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; If a location of a second device associated with a second user is included in the stay-related region, it is assumed that the second user has the same attribute as the first user; The area setting means determines the size of the stay-related area based on an additional distance corresponding to a time period including a time point at which the movement speed of the first device is equal to or less than the first threshold speed for a first threshold time or more.

2. An attribute estimation device for estimating a user's attribute, comprising: an area setting means for determining a stay-related area related to a place where a first user has stayed, based on a past location of a first device associated with the first user; An estimation means for estimating an attribute of a user, The estimation means Inferring attributes of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; If a location of a second device associated with a second user is included in the stay-related region, it is assumed that the second user has the same attribute as the first user; The area setting means determines the size of the stay-related area based on an additional distance determined with reference to information associating the behavior of the first user with the additional distance.

3. An attribute estimation device for estimating a user's attribute, comprising: an area setting means for determining a stay-related area related to a place where a first user has stayed, based on a past location of a first device associated with the first user; An estimation means for estimating an attribute of a user, The estimation means Inferring attributes of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; If a location of a second device associated with a second user is included in the stay-related region, it is assumed that the second user has the same attribute as the first user; The attribute estimation device, wherein after the second user is estimated to have a specific attribute, the estimation means, based on the second user performing a specific action, estimates that the second user does not have the specific attribute by referring to information associating the specific action with conditions for deleting the specific attribute.

4. 4. The attribute estimation device according to claim 1, wherein, when the first device is a device mounted on a first vehicle, the area setting means determines the stay-related area based on a location where the first vehicle has been in an inactive state for a threshold time or more.

5. 5. The attribute estimation device according to claim 1, wherein the region setting means determines the stay-related region based on a position of the first device where a moving speed of the first device is equal to or less than a first threshold speed continuously for a first threshold time or more.

6. 6. The attribute estimation device according to claim 1, wherein the estimation means estimates that the first user has performed a specific behavior based on the first device remaining in a specific location for a time period corresponding to the specific location or longer.

7. 7. The attribute estimation device according to claim 1, wherein the estimation means estimates that the second user has the same attribute as the first user when the position of the second device is included in the stay-related area during a time period in which the movement speed of the first device is equal to or less than a first threshold speed continuously for a first threshold time or more.

8. A program for causing a computer to function as each means of the attribute estimation device according to any one of claims 1 to 7.

9. An attribute estimation method for estimating an attribute of a user, comprising: an area setting step in which area setting means determines a stay-related area related to a place where the first user stayed, based on a position at a past time of a first device associated with the first user; a step in which an estimation means estimates an attribute of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; the estimation means estimates that the second user has the same attribute as the first user when a location of a second device associated with the second user is included in the stay-related area; The attribute estimation method, wherein the area setting means determines the size of the stay-related area based on an additional distance corresponding to a time period including a time point at which the movement speed of the first device is equal to or less than the first threshold speed for a first threshold time period or more.

10. An attribute estimation method for estimating a user's attribute, comprising: an area setting step in which area setting means determines a stay-related area related to a place where the first user stayed, based on a position at a past time of a first device associated with the first user; a step in which an estimation means estimates an attribute of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; the estimation means estimates that the second user has the same attribute as the first user when a location of a second device associated with the second user is included in the stay-related area; The area setting means determines the size of the stay-related area based on an additional distance determined with reference to information associating the behavior of the first user with the additional distance.

11. An attribute estimation method for estimating a user's attribute, comprising: an area setting step in which area setting means determines a stay-related area related to a place where the first user stayed, based on a position at a past time of a first device associated with the first user; a step in which an estimation means estimates an attribute of the first user based on at least one of information including behavior of the first user regarding visits or stays at specific places and a purchase history of specific products of the first user; the estimation means estimates that the second user has the same attribute as the first user when a location of a second device associated with the second user is included in the stay-related area; An attribute estimation method in which, after the second user is estimated to have a specific attribute, the estimation means, based on the second user performing a specific action, estimates that the second user does not have the specific attribute by referring to information associating the specific action with conditions for deleting the specific attribute.

Images