JP6687648B2 - Estimating device, estimating method, and estimating program - Google Patents

Description

  The present invention relates to an estimation device, an estimation method, and an estimation program.

  Conventionally, a technique has been proposed in which position information is acquired from a terminal device owned by a user and various information processing is performed based on the acquired position information.

  As a technology using position information, for example, a technology is known in which an application that integrates a plurality of navigation applications is used to perform navigation by selecting an appropriate navigation application according to the transportation means specified by the user. According to such a technique, it is specified whether the user's movement status is car movement, train movement, or foot movement based on the current position, movement speed, acceleration, vibration, sound, and the like.

Japanese Patent No. 6123573

  However, in the above-mentioned conventional technique, it is not always possible to accurately estimate the moving state of the user. For example, when a user travels in a car, various situations such as stopping at traffic lights and traffic congestion occur, so even if variables such as the user's current position and travel speed are acquired, the travel situation can be accurately estimated. Not always possible.

  The present application has been made in view of the above, and an object thereof is to provide an estimation device, an estimation method, and an estimation program that can accurately estimate the movement situation of a user.

  The estimation device according to the present application is a first acquisition unit that acquires first position information that is position information that is acquired in association with an application that is associated with a transportation unit, and position information that indicates the position of a predetermined user. A second acquisition unit that acquires second position information, a feature amount based on the first position information acquired by the first acquisition unit, and a feature amount based on the second position information acquired by the second acquisition unit. And an estimation unit that estimates the movement status of the predetermined user based on the above.

  According to the aspect of the embodiment, it is possible to accurately estimate the movement situation of the user.

FIG. 1 is a diagram illustrating an example of an estimation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the estimation system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the user terminal according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the estimation device according to the embodiment. FIG. 5 is a diagram illustrating an example of the first position information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the model storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the second position information storage unit according to the embodiment. FIG. 8 is a flowchart (1) showing a processing procedure according to the embodiment. FIG. 9 is a flowchart (2) showing the processing procedure according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the estimation device.

  Hereinafter, modes (hereinafter, referred to as “embodiments”) for implementing an estimation device, an estimation method, and an estimation program according to the present application will be described in detail with reference to the drawings. It should be noted that the estimation device, the estimation method, and the estimation program according to the present application are not limited by this embodiment. Further, the respective embodiments can be appropriately combined within the range in which the processing content is not inconsistent. Also, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicated description will be omitted.

[1. Example of estimation processing according to the embodiment]
First, an example of the estimation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an estimation process according to the embodiment. Specifically, in FIG. 1, the estimation device 100 includes first position information, which is position information acquired in association with an application (hereinafter, simply referred to as “app”) associated with a moving unit, The second position information, which is the position information indicating the position of the predetermined user, is acquired, and the estimation process for estimating the movement situation of the predetermined user is performed based on the characteristics of each of the first position information and the second position information. Here is an example:

  The estimation device 100 illustrated in FIG. 1 is an information processing device that executes the estimation process according to the embodiment, and is, for example, a server device that communicates with a terminal device or the like used by a user. The estimation device 100 according to the embodiment acquires identification information for identifying each user and information indicating the position of each user in association with each other, and stores the acquired information as position information. For example, the estimation device 100 is a management server for a plurality of applications installed in a terminal device used by a user, and periodically acquires position information from the user as each application is used. Note that the estimation device 100 may perform a service of providing the accumulated position information, the estimated user's movement status, and the like to other businesses. In the embodiment, the estimation device 100 uses, for example, a navigation service or a map providing service that provides traffic guidance using user position information, a transfer guidance service that provides train change guidance, a taxi dispatch service that provides taxi dispatch, and a location. Provide applications related to game services that provide games that use information.

The user terminal 10 ₁ and 10 ₂ shown in FIG. 1 is an information processing terminal such as a smartphone. In an embodiment, the user terminal 10 ₁ is utilized by the user U01, the user terminal 10 ₂ is used by the user U02. Hereinafter, when it is not necessary to distinguish the user terminals 10 ₁ and 10 _2, etc., they are collectively referred to as “user terminal 10”. Further, when it is not necessary to distinguish the users U01 and U02 and the like, they are collectively referred to as “user”. In the following, the user terminal 10 may be read as a user. For example, “the user transmits the position information” may actually mean that “the user terminal 10 used by the user transmits the position information”.

  The user terminal 10 detects the position where the device is located (for example, numerical values of longitude and latitude) by using, for example, GPS (Global Positioning System) and acquires position information that is information indicating the detected position. . The position information may include not only the information indicating the position but also the time when the position is detected. Then, the user terminal 10 transmits the detected position information to the estimation device 100, for example, according to the control of the application to be used or the request of the estimation device 100. Specifically, the user terminal 10 periodically and continuously transmits the position information to the estimation device 100 according to the control (function) of the navigation application and the map service provided by the estimation device 100 to the user. The position information transmitted from the user terminal 10 is accumulated in the storage unit included in the estimation device 100 and used for various information processing.

  Here, a provider who provides a service such as an administrator of the estimation device 100 may desire to develop a service that suits the user's movement situation. For example, a service provider may provide a service suitable for moving a vehicle to a user moving in a vehicle (for example, delivery of an advertisement related to an automobile, delivery of an advertisement of a store that the user is supposed to visit according to the moving speed, etc.). ) Is desired. Further, the service provider desires to activate an appropriate application on the user terminal 10 or perform a push notification according to the user's movement situation. As described above, there is a need for the service provider to accurately grasp the movement status of the user.

  In addition, by preparing definition information (model) corresponding to a movement situation (for example, movement of a car or train) and comparing the definition information with the situation (context) of the user, the movement situation of the user can be estimated. Is also possible. However, it is difficult to prepare the definition information for every means of transportation, and the definition information (for example, estimating that a movement exceeding a predetermined speed is an automobile movement) accurately indicates the means of transportation. However, it cannot be said that the accuracy with which the user's movement situation is estimated is high.

  Therefore, the estimating apparatus 100 estimates the moving means of a predetermined user by using the first position information, which is the position information acquired in advance by the moving means in association with the application. For example, when the car navigation application is activated in the user terminal 10 and the car navigation application is used by the user, the estimation device 100 regards the moving means of the user as an “automobile”. Then, the estimation device 100 extracts the feature of the behavior of the user when the moving means is the “automobile” based on the acquired first position information. Specifically, the estimation device 100 determines whether or not the user's moving means is an “automobile” based on the characteristic amount of the transition of the position information of the user when the moving means is an “automobile”. Generate a model. After that, the estimation device 100 inputs the second position information to the generated model when the position information of a predetermined user whose moving means is unknown (for the sake of distinction, referred to as “second position information”) is acquired. Then, the moving means of the user is estimated based on the output index value (score) and the like. In other words, the estimation device 100 regards an app (such as the car navigation app described above) whose moving means is estimated with extremely high accuracy as an app associated with the moving means, and determines the first position information acquired from the app. The model is learned (generated) as correct data. As a result, the estimation device 100 can accurately estimate the moving state of the user. Hereinafter, the estimation process according to the embodiment will be described along the flow with reference to FIG.

In the example shown in FIG. 1, the user U01 is riding on the vehicle 20, in use the installed car navigation application to the user terminal 10 _1. At this time, the user terminal 10 ₁ detects the periodically and continuously (for example, several tens of seconds and timing of every few minutes) the position of the user U01, acquires information indicating the position of the user U01. Then, the user terminal 10 ₁ transmits the acquired position information to the estimation device 100.

Estimating apparatus 100 acquires position information transmitted from the user terminal 10 ₁ as the first position information (step S01). Specifically, the estimation device 100 acquires, as the first position information, information in which the “automobile”, which is the moving unit associated in the car navigation application, and the position information of the user U01 are associated with each other. In addition, the estimation apparatus 100 may have definition information defined in advance regarding the association between the application and the transportation means. For example, the estimation device 100 may receive information defining that the car navigation application and the moving means “automobile” are associated with each other from the administrator of the estimation device 100 or the like.

  The estimation device 100 stores the position information (first position information) associated with the moving means in the first position information storage unit 121 (step S02). Although not shown in FIG. 1, the estimation device 100 also acquires and stores the first position information from users other than the user U01. Through such processing, the estimation device 100 acquires sufficient first position information required for model generation described later.

  After that, the estimation device 100 generates a model for estimating the movement situation (step S03). For example, the estimation device 100 refers to the transition of the position information acquired from the user U01, and learns the moving characteristic of the moving means “automobile” based on the characteristic amount of the position information. Specifically, the estimation apparatus 100 calculates the moving amount (moving distance) of the user U01 for each predetermined time, the moving speed of the user U01 in the predetermined time, the length of time that the user U01 stays at substantially the same point, and the movement of the user U01. The moving means "automobile" using map information (for example, whether or not the user U01 is moving on a road when the position information of the user U01 is compared with known map information) as a feature amount. Learn the characteristics of movement in.

  When a plurality of position information of a predetermined user is input through the learning process, the estimation device 100 determines whether or not the plurality of position information of the predetermined user is movement by the moving means “automobile”. Generate a model for estimation. In other words, the estimation device 100 uses a model that outputs an index value (score) indicating the accuracy of "moving in a car" by a predetermined user when a plurality of pieces of position information of the predetermined user are input. To generate. The estimation device 100 stores the generated model in the model storage unit 122. Various known learning processes and the like may be used for the model generation.

After that, the estimation device 100 acquires the position information (second position information) of the user U02 who is a user whose transportation is unknown (step S04). For example, the user U02 is a user position information by the user terminal 10 ₂ is acquired in a state that does not utilize moving means associated application. It is assumed that the user U02 uses, for example, an application for portal service, which is an application to which the moving means is not associated, among the applications provided by the estimation device 100. In this case, the user terminal 10 ₂ in accordance with features of the portal service app, continuously obtains the position information of the user U02 during login portal service, and transmits the acquired position information to the estimation device 100.

  The estimation apparatus 100 acquires the position information (second position information) whose moving means is unknown as described above, and stores the position information in the second position information storage unit 123 (step S05). Then, when a sufficient amount of information is accumulated as the information to be input to the model, the estimation device 100 estimates the moving state of the user U02 using the model (step S06).

  Specifically, the estimation device 100 inputs the second position information of the user U02 acquired over a predetermined time into the model and refers to the output score. Then, when the output score exceeds the predetermined threshold, the estimation device 100 determines that the moving state of the user U02 is “automobile” and the user U02 is moving in the automobile when the output score exceeds the predetermined threshold. presume.

  On the other hand, when the output score is less than or equal to the predetermined threshold value, the estimation device 100 estimates that the moving state of the user U02 is not the “vehicle” as the moving state of the user U02. In this case, the estimation device 100 may estimate the movement situation of the user U02 by inputting the second position information of the user U02 to another model corresponding to another movement means.

  In this way, the estimation device 100 according to the embodiment acquires the first position information, which is the position information acquired in association with the app associated with the moving means. In addition, the estimation device 100 acquires second position information that is position information indicating the position of a predetermined user (user U02 in the example of FIG. 1). Then, the estimation device 100 estimates the moving state of the predetermined user based on the acquired characteristic amount based on the first position information and the characteristic amount based on the second position information acquired by the second acquisition unit.

  That is, the estimating device 100 according to the embodiment estimates the moving means of a predetermined user by using the first position information acquired in association with an application in which the moving means can be specified in advance, such as a car navigation application, as correct answer data. . As a result, the estimation device 100 can estimate with high accuracy the moving means of the user, which is difficult to estimate only with position information. As a result, the estimation device 100 can accurately estimate the moving state of the user.

In the example of Figure 1 above, the estimating apparatus 100 showed that acquires position information which the user terminal 10 ₁ and 10 ₂ is detected from the user terminal 10 ₁ and 10 _2. However, estimating apparatus 100, regardless of the transmission from the user terminal 10 ₁ and 10 _2, by the user terminal 10 ₁ and 10 ₂ to crawl (crawl) at predetermined time intervals, it is configured to obtain position information Good. Also, estimating apparatus 100, necessarily rather than obtaining the location information that the user terminal 10 ₁ and 10 ₂ itself detects the user terminal 10 _first estimation apparatus 100 based on the detected information from the user terminal 10 ₁ and 10 ₂ And 10 ₂ are estimated, and the estimated information may be used as the position information of the user terminals 10 ₁ and 10 ₂ .

  Further, in the example of FIG. 1 described above, it is shown that the estimation device 100 extracts the feature amount of the moving means based on the first position information. However, the estimation device 100 may extract the characteristic amount of the moving means based on information including various sensor information (acceleration, sound, temperature, humidity, etc.) acquired together with the first position information. Hereinafter, the estimation device 100 that performs the estimation process according to the above-described embodiment and the estimation system 1 including the estimation device 100 will be described in detail.

[2. Configuration of estimation system]
Next, the configuration of the estimation system 1 including the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the estimation system 1 according to the embodiment. As illustrated in FIG. 2, the estimation system 1 according to the embodiment includes a user terminal 10 and an estimation device 100. These various devices are communicably connected to each other via a network N in a wired or wireless manner. Further, the number of each device included in the estimation system 1 shown in FIG. 2 is not limited to that shown. For example, the estimation system 1 may include a plurality of user terminals 10.

  As described above, the user terminal 10 is an information processing terminal such as a mobile phone including a smartphone, a tablet terminal, a desktop PC (Personal Computer), a notebook PC, or a PDA (Personal Digital Assistant). The user terminal 10 also includes a wearable device that is an eyeglass-type or clock-type information processing terminal. Furthermore, the user terminal 10 may include various smart devices having an information processing function for acquiring position information. For example, the user terminal 10 may include a smart home appliance such as a TV (Television), a refrigerator, and a vacuum cleaner, a smart vehicle such as an automobile, a drone, a household robot, and the like. The application according to the embodiment is not limited to an application executed on a mobile terminal such as a smartphone, but may be an application executed on a smart home appliance described above.

  The user terminal 10 acquires and stores the position information of its own device according to the operation by the user and the function of the user terminal 10. For example, the user terminal 10 acquires position information by communicating with an external system such as the GPS system described above. Then, the user terminal 10 transmits the acquired position information to the estimation device 100.

  As described above, the estimation device 100 acquires the first position information, which is the position information acquired in association with the application with which the moving means is associated, and the second position information of the predetermined user, and the respective positions are acquired. It is a server device that estimates the movement status of a predetermined user based on the characteristic amount of information.

  The estimating apparatus 100 may have a function as a service server that provides various services. For example, the estimation device 100 provides the user with a disaster information transmission service that provides disaster information and various alarm information, a navigation service that transmits traffic guidance, and a game that uses position information. The estimation apparatus 100 may provide various services other than the above services. In addition, the estimation device 100 may have a function as a web server that provides a website related to the service. For example, the estimation device 100 is related to a portal site, a news site, an auction site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a web blog, and the like. You may deliver the web page containing various information to the user terminal 10.

[3. Configuration of user terminal]
Next, the configuration of the user terminal 10 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the user terminal 10 according to the embodiment. As shown in FIG. 3, the user terminal 10 includes a communication unit 11, an input unit 12, a display unit 13, a detection unit 14, a storage unit 15, and a control unit 16.

(About communication unit 11)
The communication unit 11 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the estimation device 100 and the like. The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like.

(About input unit 12 and display unit 13)
The input unit 12 is an input device that receives various operations from a user. For example, the input unit 12 is realized by an operation key or the like included in the user terminal 10. The display unit 13 is a display device for displaying various information. For example, the display unit 13 is realized by a liquid crystal display or the like. When a touch panel is used for the user terminal 10, a part of the input unit 12 and the display unit 13 are integrated.

(About the detection unit 14)
The detection unit 14 detects various kinds of information regarding the user terminal 10. Specifically, the detection unit 14 detects a user's operation on the user terminal 10, position information of the user terminal 10, information about a device connected to the user terminal 10, an environment of the user terminal 10, and the like. To do. In the example illustrated in FIG. 3, the detection unit 14 includes an operation detection unit 141, a position detection unit 142, an external device detection unit 143, and an environment detection unit 144.

(About the operation detection unit 141)
The operation detection unit 141 detects a user operation on the user terminal 10. For example, the operation detection unit 141 detects a user operation based on the information input to the input unit 12. That is, the operation detection unit 141 detects that there is an input of an operation of touching the screen on the input unit 12, input of a voice, and the like. Further, the operation detection unit 141 may detect that the user has started a predetermined application. When such an application is an application that operates the imaging device in the user terminal 10, the operation detection unit 141 detects that the imaging function is used by the user. Further, the operation detection unit 141 may detect an operation such as the user terminal 10 itself being moved, based on data detected by an acceleration sensor, a gyro sensor, or the like provided in the user terminal 10.

(About the position detection unit 142)
The position detection unit 142 detects the current position of the user terminal 10. Specifically, the position detection unit 142 receives a radio wave transmitted from a GPS satellite and detects a position (for example, latitude and longitude) indicating the current position of the user terminal 10 based on the received radio wave.

  The position detection unit 142 can detect the position by various methods. For example, the position detection unit 142 may detect the position by using various communication functions of the user terminal 10, not limited to the GPS satellite.

  For example, the position detection unit 142 detects the position of the user terminal 10 using the Wi-Fi (registered trademark) communication function of the user terminal 10 or a communication network provided by each communication company. Specifically, the position detection unit 142 detects the position of its own device by performing Wi-Fi communication or the like and measuring the distance to a nearby base station or access point.

  In addition, the position detection unit 142 may detect the position by using the Bluetooth (registered trademark) function of the user terminal 10. For example, the position detection unit 142 detects the position of its own device by connecting to a beacon transmitter connected by the Bluetooth function.

  Further, the position detection unit 142 may detect the position of its own device by using PDR (Pedestrian Dead Reckoning) technology using an acceleration sensor, a gyro sensor, or the like. Further, the position detection unit 142 may detect the position of the own device based on the geomagnetic pattern of the structure measured in advance and the geomagnetic sensor included in the own device.

  Further, for example, when the user terminal 10 has a function equivalent to a non-contact type IC card used in a station ticket gate or a store (or, the user terminal 10 has a function of reading a history of the non-contact type IC card). If the user terminal 10 has settled the boarding fee at the station, the used position is recorded. The position detection unit 142 may detect the position of the user terminal 10 by acquiring such information. Further, the position may be detected by an optical sensor, an infrared sensor, or the like included in the user terminal 10.

  The position detection unit 142 detects the position of its own device using one or a combination of the above-described methods. And the acquisition part 161 mentioned later acquires the positional information on the user terminal 10 based on the information of the position which the position detection part 142 detected, and the detected time.

(About the external device detection unit 143)
The external device detection unit 143 detects an external device connected to the user terminal 10. For example, the external device detection unit 143 detects the external device based on the exchange of communication packets with the external device. Then, the external device detection unit 143 recognizes the detected external device as a terminal connected to the user terminal 10. Further, the external device detection unit 143 may detect the type of connection with the external device. For example, the external device detection unit 143 detects whether the external device is connected by wire or by wireless communication. In addition, the external device detection unit 143 may detect a communication method used in wireless communication. In addition, the external device detection unit 143 may detect the external device based on information acquired by a radio wave sensor that detects a radio wave emitted by the external device, an electromagnetic wave sensor that detects an electromagnetic wave, or the like.

(About environment detection unit 144)
The environment detection unit 144 detects the environment in the user terminal 10. The environment detection unit 144 uses various sensors and functions provided in the user terminal 10 to detect information about the environment. For example, the environment detection unit 144 may be a microphone that collects sounds around the user terminal 10, an illuminance sensor that detects illuminance around the user terminal 10, or an acceleration sensor (or an acceleration sensor that detects physical movement of the user terminal 10). , A gyro sensor, etc.), a humidity sensor that detects the humidity around the user terminal 10, a geomagnetic sensor that detects the magnetic field at the location of the user terminal 10, and the like. Then, the environment detection unit 144 detects various information using various sensors. For example, the environment detection unit 144 detects a noise level around the user terminal 10 and whether the surroundings of the user terminal 10 have an illuminance suitable for imaging. Furthermore, the environment detection unit 144 may detect surrounding environment information based on a photograph or video taken by the camera.

(About storage unit 15)
The storage unit 15 stores various information. The storage unit 15 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. For example, the storage unit 15 stores various information detected by the detection unit 14 in association with the detected date and time. Specifically, the storage unit 15 stores position information based on the position detected by the position detection unit 142. The storage unit 15 also stores information regarding the applications installed in the user terminal 10.

(About control unit 16)
The control unit 16 is, for example, a controller, and various programs stored in a storage device inside the user terminal 10 use a RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. It is realized by being executed. The control unit 16 is a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  The control unit 16 controls a process of providing the estimation device 100 with the position information of the user terminal 10. For example, the control unit 16 controls execution of a program (application) for realizing the position information providing process of the user terminal 10. The program may be downloaded to and executed by the user terminal 10 by accessing the estimation device 100, or a server device (estimation device 100 or an external server that provides various programs) according to an operation by a user U01 having the user terminal 10. ), And may be installed in the user terminal 10.

  As illustrated in FIG. 3, the control unit 16 includes an acquisition unit 161, a reception unit 162, and a transmission unit 163, and realizes or executes the functions and actions of information processing described below. For example, the control unit 16 realizes the functions and actions of information processing described below by executing the above-described program using the RAM as a work area. The internal configuration of the control unit 16 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship between the processing units included in the control unit 16 is not limited to the connection relationship illustrated in FIG. 3 and may be another connection relationship.

(About the acquisition unit 161)
The acquisition unit 161 acquires various kinds of information. For example, the acquisition unit 161 acquires various information detected by the detection unit 14 by controlling the detection unit 14. For example, the acquisition unit 161 acquires the position information of the user terminal 10 based on the information detected by the position detection unit 142. The acquisition unit 161 may acquire information about the context of the user terminal 10 including not only the position information but also various sensor information such as information about the environment around the user terminal 10.

  The acquisition unit 161 may acquire the position information every predetermined time. For example, the acquisition unit 161 acquires the position information by controlling the above-described detection unit 14 periodically (every 1 minute, every 3 minutes, every 5 minutes, etc.). The timing at which the acquisition unit 161 acquires the position information may be set by the estimation device 100.

  In addition, the acquisition unit 161 acquires information regarding the application related to the position information. The application related to the position information is, for example, an application that controls a function of detecting the position of the user. That is, the acquisition unit 161 acquires information in which the position information of the user and the application that controls the process for acquiring the position information are associated with each other. In other words, the acquisition unit 161 acquires, together with the position information, information indicating which function of the application acquired the position information. Note that the acquisition unit 161 may acquire information that the position information is not acquired by the function of any installed application but is acquired by the function of the OS (Operating System), for example. Good.

(About receiving unit 162)
The receiving unit 162 receives various kinds of information. For example, the reception unit 162 receives a request for position information transmitted from the estimation device 100. The receiving unit 162 sends the received information to each processing unit of the control unit 16.

(About the transmitter 163)
The transmission unit 163 transmits various information. For example, the transmission unit 163 transmits the position information to the estimation device 100 according to the request received by the reception unit 162.

  For example, the transmission unit 163 associates the identification information for identifying the user, the position information acquired by the acquisition unit 161, and the application that has performed the control for acquiring the position information, and the estimation device 100. Send to. At this time, the transmission unit 163 may transmit the position information every time the position information is acquired by the acquisition unit 161, or may transmit the position information every predetermined period. For example, even if the transmission unit 163 periodically (every 1 minute, every 3 minutes, every 5 minutes, every 1 hour, etc.), the positional information is acquired by the acquisition unit 161, the predetermined time is set. Alternatively, the position information may be transmitted to the estimation device 100. Further, the timing at which the transmission unit 163 transmits the position information may be set by the estimation device 100.

[4. Configuration of estimation device]
Next, the configuration of the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the estimation device 100 according to the embodiment. As shown in FIG. 4, the estimation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The estimation apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the estimation apparatus 100, and a display unit (for example, a liquid crystal display) for displaying various information. You may have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10 or the like via the network N.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a first position information storage unit 121, a model storage unit 122, and a second position information storage unit 123.

(Regarding the first position information storage unit 121)
The first position information storage unit 121 stores, among the position information of the user, the position information acquired in association with the application associated with the moving means. Here, FIG. 5 illustrates an example of the first position information storage unit 121 according to the embodiment. FIG. 5 is a diagram illustrating an example of the first position information storage unit 121 according to the embodiment. In the example shown in FIG. 5, the first position information storage unit 121 has items such as “terminal ID”, “user ID”, and “first position information”. In addition, the item of “first position information” has small items such as “use application”, “transportation means”, “acquisition date and time”, “position”, “accuracy”, and “various sensor information”.

  The “terminal ID” indicates identification information for identifying the user terminal 10 used by the user. “User ID” indicates identification information for identifying a user. In addition, in this specification, the identification information as shown in FIG. 5 may be used as a reference code. For example, the user identified by the user ID “U01” may be referred to as “user U01”.

  Each user may own a plurality of user terminals 10. In this case, the estimation device 100 uses the identification information for uniquely identifying the user to associate the position information acquired from the plurality of user terminals 10 with the user. Note that the user identification information is, for example, a service ID (user account) given to each user in the service provided by the estimation device 100. The ID may be issued not only by the estimation device 100 but also by a business partner who cooperates with the estimation device 100. Thereby, even if one user uses a plurality of user terminals 10 or logs in to a service in different environments, the estimation device 100 uniquely identifies the user and acquires the position information. You can In addition, the estimation device 100 may use, as the user identification information, cookie information when the service is used, a terminal ID unique to the terminal, or the like.

  The “first position information” indicates the position information acquired in association with the application associated with the moving means. The “used application” indicates the name or identification information of the application that has performed the control of acquiring the position information. “Transportation means” indicates a transportation means associated with the application.

  The “acquisition date and time” indicates the date and time when the position was detected (acquired) by the user terminal 10. “Position” indicates a specific position of the user (in other words, the user terminal 10). In FIG. 5, the position is expressed by a concept such as “G01”, but in reality, the position item stores specific information indicating the position of the user (for example, numerical values of longitude and latitude). .

  "Accuracy" indicates the accuracy of the information indicating the position of the user. In the embodiment, the accuracy is indicated by three levels of “low”, “medium”, and “high”, for example. The accuracy is stored according to the accuracy with which the position of the user can be specified, for example, based on the detection unit when the position is detected by the user terminal 10. Specifically, in the case of a detection unit (for example, when the detection unit is only GPS) where an error of several tens to several hundreds of meters occurs when specifying the position of the user, the acquired position information The accuracy is "low". Further, in the case of a detecting means having a higher accuracy than the position information of which the accuracy is “low” (for example, when the detecting means is a combination of Wi-Fi, GPS, etc.), it is acquired by the acquiring means. The accuracy of the obtained position information is "medium". Further, in the case of a detection unit having a higher accuracy than the first position information having the “medium” accuracy (for example, when the detection unit uses Bluetooth (beacon)), the acquisition unit acquires the information. The accuracy of the obtained first position information is “high”. Note that the above-described accuracy determination is an example, and the estimation device 100 may flexibly change the accuracy determination criterion in accordance with the position information detection technology.

  “Various sensor information” indicates information detected by various sensors when the position is detected. In FIG. 5, various sensor information is represented by a concept such as “X01”, but in reality, various sensor information items include various sensors such as acceleration of the user terminal 10, temperature and humidity, and surrounding voice information. The specific information acquired by is stored.

  That is, in FIG. 5, as an example of the data stored in the first position information storage unit 121, as the first position information of the user U01 who uses the user terminal 10 identified by the terminal ID “C01”, the application “car navigation system” is used. It is indicated that the information acquired by ", and the means of transportation associated with the" car "is stored. In addition, an example of the first position information indicates that the user U01 is located at the position “G01” at the acquisition date and time “T01”, the accuracy of the position is “medium”, and the various sensor information is “X01”. ing.

  Although not shown in FIG. 5, user attribute information and the like may be stored in the first position information storage unit 121 together with the position information. Specifically, the first position information storage unit 121 stores various specific information such as the user's age, sex, occupation, annual income, place of residence, etc. as attribute information.

  In addition, the first position information storage unit 121 may store user interest and interest information, a user action history, and the like based on a service usage history and the like. For example, the interest / interest information is information set for the user by the estimation device 100 through the use of various services (a category that the user is likely to have an interest in based on the purchase history or the search history of the user, Information content). Further, the action history information is a user's action history in various services (browsing history of web pages, purchase history of products, search history, etc.).

(About the model storage unit 122)
The model storage unit 122 stores a model that is generated based on the first position information and that is used to estimate the movement situation of the user. Here, FIG. 6 illustrates an example of the model storage unit 122 according to the embodiment. FIG. 6 is a diagram illustrating an example of the model storage unit 122 according to the embodiment. In the example shown in FIG. 6, the model storage unit 122 has items such as “model ID”, “moving means”, and “learning data”.

  The “model ID” indicates identification information that identifies the model. “Transportation means” indicates the type of transportation means estimated by the model. The “learning data” indicates a group of information used for learning the model. In FIG. 6, the learning data is represented by a concept such as “P01”, but in reality, the items of the learning data store information regarding a plurality of first position information used for learning.

  That is, in FIG. 6, as an example of the data stored in the model storage unit 122, the model M01 identified by the model ID “M01” is for estimating whether or not the user is moving by the moving means “automobile”. Of the learning data “P01” and is a model learned (generated) using the learning data “P01”.

(About the second position information storage unit 123)
The second position information storage unit 123 stores the second position information that is the position information indicating the position of the predetermined user and that is the position information that is the target of the estimation process according to the embodiment. In other words, the second position information storage unit 123 stores the position information corresponding to the user whose transportation means is unknown. Here, FIG. 7 illustrates an example of the second position information storage unit 123 according to the embodiment. FIG. 7 is a diagram illustrating an example of the second position information storage unit 123 according to the embodiment. In the example shown in FIG. 7, the second position information storage unit 123 has items such as “terminal ID”, “user ID”, and “second position information”. The item “second position information” has small items such as “acquisition date and time”, “position”, “accuracy”, and “various sensor information”.

  Each item such as "terminal ID", "user ID", "acquisition date and time", "position", "accuracy", and "various sensor information" corresponds to the same item shown in FIG. The “second position information” indicates position information acquired from a user whose transportation is unknown.

  That is, in FIG. 7, the second position information of the user U02 who uses the user terminal 10 identified by the terminal ID “C02” is stored as an example of the data stored in the second position information storage unit 123. Is shown. Further, as an example of the second position information of the user U02, the user U02 is located at the position “G21” at the acquisition date and time “T21”, the accuracy of the position is “medium”, and the various sensor information is “X21”. It is shown that.

  Note that, like the first position information storage unit 121, the second position information storage unit 123 may store user attribute information, user interest / interest information, user action history, and the like.

(Regarding the control unit 130)
The control unit 130 is, for example, a controller, and various programs (corresponding to an example of the estimation program) stored in the storage device inside the estimation device 100 are executed by the CPU, the MPU, or the like by using the RAM as a work area. Will be realized. The control unit 130 is a controller, and is realized by an integrated circuit such as an ASIC or FPGA.

  As illustrated in FIG. 4, the control unit 130 includes a first acquisition unit 131, a generation unit 132, a second acquisition unit 133, and an estimation unit 134, and has the functions and actions of information processing described below. Realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4 and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relation of each processing unit included in the control unit 130 is not limited to the connection relation shown in FIG. 4, and may be another connection relation.

(About the first acquisition unit 131)
The 1st acquisition part 131 acquires the 1st position information which is the position information acquired in relation to the application with which the transportation was matched.

  For example, the 1st acquisition part 131 acquires the 1st position information acquired by the navigation application with which the transportation means by walking or a bicycle was matched. Specifically, the first acquisition unit 131 acquires, as the first position information, position information acquired by an application for user navigation on the premise of moving means such as walking or bicycle.

  In addition, the first acquisition unit 131 acquires the first position information acquired by the car navigation application associated with the vehicle-based transportation means. For example, the 1st acquisition part 131 acquires the 1st position information from the user terminal 10 which starts the car navigation application and is performing car navigation.

  In addition, the first acquisition unit 131 is the position information of the user who has used the vehicle allocation application that is an application that requests the vehicle allocation, and is acquired in the section where the user has moved in the vehicle allocated via the vehicle allocation application. The obtained position information may be acquired as the first position information. The vehicle allocation application is, for example, a taxi vehicle allocation application for calling a taxi to a predetermined position. According to the taxi dispatch application, time information on boarding and time when getting off the taxi (for example, time when the boarding fee is paid through the application) are stored. The 1st acquisition part 131 specifies the section which the user moved based on the information acquired by the taxi dispatch application, for example, and acquires the position information acquired in the section concerned as the 1st position information. In this case, in the position information indicating the movement of the section, "vehicle (taxi)" is associated as the means of movement.

  In addition, the first acquisition unit 131 uses the position information of the user who has used the route search application and the position information acquired at the boarding time indicated by the route search application, to move the position indicated by the route search application. It may be acquired as the first position information together with the means.

  For example, the user uses an app that searches for train routes, and searches for boarding times and alighting times of trains heading for a desired destination. At this time, it is assumed that the user is on the train between the boarding time and the getting-off time. Therefore, the first acquisition unit 131 acquires the position information acquired during the boarding time indicated by the route search application, as the first position information associated with the transportation means “train”. In addition, the route search application may perform a route search for other transportation means such as a bus as well as a train. In this case, the 1st acquisition part 131 acquires the 1st position information with which the transportation searched by the user was matched.

  Further, the first acquisition unit 131 may acquire the map information corresponding to the position information together with the position information. The map information is information that allows the position corresponding to the position information to be plotted, and includes, for example, topographical information such as rivers and mountains, and information about artifacts such as roads and railroad tracks. According to such map information, it is possible to extract what route the user is moving. Specifically, the estimation device 100 plots the transition of the position information of the user on the map information to determine whether the user is traveling on the track, traveling on the road, or traveling on the sea. It is possible to extract route information such as whether or not. The estimation unit 134, which will be described later, can highly accurately estimate the type of transportation the user is moving on the basis of these topographical information and route information.

  Further, the first acquisition unit 131 may acquire the sensor information corresponding to the first position information together with the first position information. The sensor information is various information detected by the detection unit 14 of the user terminal 10. For example, the user terminal 10 detects the position of the user, and also detects surrounding audio information (for example, environmental sound emitted by a car on which the user is riding or a train), acceleration, temperature, humidity, and the like. The first acquisition unit 131 acquires, from the user terminal 10, the sensor information thus detected along with the position.

  Moreover, the 1st acquisition part 131 acquires the precision which the position was detected in the acquired 1st position information. As described above, the user terminal 10 detects the position by using various functions (acquisition means). In general, the accuracy of the information indicating the position of the user varies depending on the function used for detection. For example, the case of detecting the position of the user by GPS, the case of detecting the position of the user by using the communication function by Wi-Fi, and the case of detecting the position of the user by using the communication function by beacon, The accuracy of identifying the position is different. For example, when the position of the user is detected using the communication function using the beacon, the position of the user can be specified with an accuracy of several meters, such as where in the building the user is located. On the other hand, when detecting the position of the user by GPS, it is difficult to specify the position of the user with accuracy within a range of several meters, such as where in the building the user is located. In general, since it is possible to more accurately specify the topography, the route, and the like that the user has moved by using the highly accurate position information, the estimation device 100 may preferentially acquire the highly accurate position information. Good.

  For example, the first acquisition unit 131 acquires the detection means when the user terminal 10 detects the position as described above, when acquiring the information regarding the position from the user terminal 10. Then, the first acquisition unit 131 acquires, as the first position information, information in which the position and the detection unit (in other words, accuracy) are associated with each other. In this case, the 1st acquisition part 131 may acquire beforehand the definition information etc. which defined the relation between a detection means and accuracy. Specifically, the 1st acquisition part 131 acquires the definition information that the accuracy of the position information detected using the beacon function is "high" from the administrator etc. of the estimation device 100. Then, when the first acquisition unit 131 acquires the information about the position and the detection unit from the user terminal 10, the accuracy information corresponding to the detection unit is associated with the position, and the associated information is the first position information. To get as.

  Further, the first acquisition unit 131 may acquire various pieces of information regarding the user together with the first position information. For example, the first acquisition unit 131 acquires the attribute information of the user based on the information registered by the user in the service to be used. In addition, the first acquisition unit 131 may acquire the interest information of the user in the service and the action history information of the user. The 1st acquisition part 131 may acquire various information using various existing technologies (for example, advertising distribution technology etc. which distribute an advertisement based on a user's interest and behavior). Further, the first acquisition unit 131 may acquire the first position information together with the date and time information including the day of the week information.

  Further, the first acquisition unit 131 may acquire, as the first position information, the communication status between the user terminal 10 and another device. Specifically, the first acquisition unit 131 acquires the communication status in which the user terminal 10 is accessing the Internet or the like via the access point. In this case, the 1st acquisition part 131 acquires the information detected from the communication condition with an access point as the 1st position information. Specifically, the first acquisition unit 131 calculates the installation position of the access point in communication with the user terminal 10, and acquires it as the first position information of the user terminal 10 based on the calculated installation position of the access point. You may do it. In addition, the first acquisition unit 131 acquires the position of the user terminal 10 by detecting communication between the station ticket gate device and the user terminal 10, or acquires the position based on the IP address of the user terminal 10. May be.

  The first acquisition unit 131 does not necessarily have to acquire the first position information at the same time as the time when the user terminal 10 detects the position. That is, the first acquisition unit 131 does not acquire the first position information in real time, but collects the position information stored in the storage unit 15 of the user terminal 10 when using the first position information for various processes described below. It may be acquired as one position information. The first acquisition unit 131 stores the acquired first position information in the first position information storage unit 121. Then, the generating unit 132, which will be described later, generates a model corresponding to the moving means when the first position information acquired by the first acquiring unit 131 reaches a sufficient amount for model generation.

(Regarding the generation unit 132)
The generation unit 132 generates a model for estimating the movement status of the user corresponding to the first position information, based on the first position information acquired by the first acquisition unit 131.

  For example, the generation unit 132 performs learning for extracting the feature amount of the first position information for each associated moving means. Specifically, the generation unit 132 learns the feature amount extracted based on the transition of the position information. For example, the generation unit 132 extracts, as the characteristic amount, a moving speed or a moving distance in a predetermined time (for example, time until two consecutive position information pieces are acquired by a specific user).

  Further, the generation unit 132 may extract the terrain or route selected in the movement of the user as the feature amount based on the map information. If the user's means of transportation is a train, it is assumed that the route selected for the user's movement is always on the track. That is, the generation unit 132 extracts a feature amount that a user whose transportation means is a train tends to select a track as a route of movement.

  Then, the generation unit 132 generates a model for estimating the moving means of the user based on the extracted feature amount. Note that existing processes may be used for the model learning process and the generation process. For example, the generating unit 132 learns the acquired first position information by using deep learning or the like to extract the feature amount in the first position information for each moving means, and to obtain the model for each moving means. May be generated.

  Specifically, when the second position information whose movement means is unknown is input, the generation unit 132 determines whether the movement means of the user corresponding to the second position information is the movement means corresponding to the model. A model that outputs an index value (score) indicating whether or not is generated. Specifically, the generation unit 132 uses the first position information associated with the moving means called an automobile to estimate whether the moving means of the user corresponding to the second position information is an automobile. Generate a model.

  In addition, the generation unit 132 may generate a model that estimates the moving means of the user, including the acquired sensor information and the like. In this case, the generation unit 132 generates a model to which various sensor information is added as an element (feature amount) for determining the moving means of the user. For example, the generation unit 132 generates a model using the voice information detected together with the position information. In this case, the generation unit 132 extracts, based on the information acquired by the first acquisition unit 131, voice information (for example, a vehicle running sound or an engine sound) having characteristics that serve as a determination criterion, and A model including the feature quantity is generated. In this case, for example, when the estimation unit 134 described below acquires the voice information together with the second position information, the estimation unit 134 inputs the acquired voice together with the second position information into the model. Then, when the voice information has a feature similar to, for example, a running sound of a car or an engine sound, the estimation unit 134 may estimate that the user is highly likely to use the car as a transportation means. it can. This is because it is assumed that when the voice information is input to the model, a relatively high score is output from the model as compared with the case where the voice information is not input.

  The generation unit 132 stores the model generated for each transportation means in the model storage unit 122. It should be noted that the generation unit 132 does not generate a model for each moving means, but indicates, when the second position information is input, what kind of moving means the user of the second position information uses. A single model that outputs multiple index values may be generated.

  The generation unit 132 may generate the model using any known learning algorithm. For example, the generation unit 132 may generate a model using a learning algorithm such as a neural network, a support vector machine, clustering, or reinforcement learning. For example, the model includes an input layer to which predetermined data (for example, second position information of the user to be processed) is input, and positive example data (for example, moving means associated with the first position information). An output layer that outputs a score indicating the correlation, and a determination element (for example, a feature amount extracted from the first position information) that belongs to any layer from the input layer to the output layer and other than the output layer , And the weight value of each determination element may be included.

(About the second acquisition unit 133)
The 2nd acquisition part 133 acquires the 2nd position information which is the position information which shows the position of a predetermined user. For example, the second acquisition unit 133 acquires the second position information as the position information of the user whose transportation means is unknown.

  The second acquisition unit 133 may acquire the second position information together with the map information and various sensor information, as with the first acquisition unit 131. The second acquisition unit 133 acquires the position information associated with the identification information of the user as the second position information, and stores it in the second position information storage unit 123. Then, the second acquisition unit 133 sends the second position information of the predetermined user to the estimation unit 134 when a sufficient amount of the second position information of the user is accumulated for the estimation process.

(About the estimation unit 134)
The estimation unit 134 determines a predetermined user based on the feature amount based on the first position information acquired by the first acquisition unit 131 and the feature amount based on the second position information acquired by the second acquisition unit 133. Estimate the movement situation.

  For example, the estimation unit 134 uses the model generated by the generation unit 132 to estimate the movement status of a predetermined user based on the second position information acquired by the second acquisition unit 133. Specifically, the estimation unit 134 inputs the second position information into the model and estimates the movement status of a predetermined user based on the output score.

  For example, the estimation unit 134, based on the first position information acquired by the navigation application associated with the walking or bicycle moving means, determines the movement status of the predetermined user such that the predetermined user walks or moves by bicycle. Estimate what you are doing. For example, the estimation unit 134 uses a model generated based on the first position information acquired by the navigation application associated with a walking or bicycle moving means, and thereby a predetermined user walks or bicycles. Estimate whether or not

  In addition, the estimation unit 134, based on the first position information acquired by the car navigation application that is associated with the vehicle-based transportation means, that the predetermined user is moving by the vehicle as the movement status of the predetermined user. To estimate. For example, the estimating unit 134 estimates whether or not a predetermined user is moving by a car by using a model generated based on the first position information acquired by the car navigation application.

  In addition, the estimation unit 134, based on the first position information acquired in the section traveled by the user in the vehicle allocated via the vehicle allocation application, the predetermined user's movement status indicates the movement of the vehicle by the predetermined user. You may infer what you are doing. For example, the estimation unit 134 uses the model generated based on the first position information acquired in the section traveled by the user in the vehicle allocated via the vehicle allocation application to allow the predetermined user to move by the vehicle. Estimate whether or not In addition, the estimation unit 134 may use a model generated based on only the first position information acquired in the section traveled by the user in the taxi that is allocated via the taxi allocation application, for example. In this case, the estimation unit 134 can estimate not only that the user is moving by car, but also that the user is moving by “taxi”.

  In addition, the estimation unit 134 determines, based on the first position information acquired during the boarding time indicated by the route search application, as the movement status of the predetermined user, by the movement means indicated by the route search application by the predetermined user. You may presume that you are moving. For example, the estimation unit 134 estimates, for example, that the user has traveled by train, by bus, by airplane, etc., according to the transportation means in the route search application.

  In addition, the estimation unit 134 determines a predetermined value based on the route or terrain information indicated by the first position information extracted based on the map information and the route or terrain information indicated by the second position information extracted based on the map information. The movement status of the user may be estimated. That is, the estimation unit 134 extracts not only the position indicated by the position information (for example, the numerical values of longitude and latitude) but also the map information corresponding to the position information to extract the terrain or route on which the user is moving.

  For example, the generation unit 132 generates a model including the topography and route of the user moving in the first position information. Then, the estimation unit 134 inputs the second position information into the model, including the map information corresponding to the second position information (for example, the terrain where the user is moving). With this, the estimation unit 134 can input information such as the terrain or route on which the user corresponding to the second position information is moving, and thus the estimation unit 134 is associated with the moving means corresponding to the first position information. Can be output with higher accuracy. Specifically, when the user corresponding to the second position information is moving on the road, the estimation unit 134 highly accurately estimates that the moving means is an “automobile” and corresponds to the second position information. When the user is moving on the track, it can be highly accurately estimated that the moving means is a "train". Alternatively, the estimation unit 134 can highly accurately estimate that the moving means is a “ship” or an “airplane” when the user corresponding to the second position information is moving on the sea.

  In addition, the estimation unit 134 may estimate the movement status of the predetermined user based on the sensor information corresponding to the first position information and the sensor information corresponding to the second position information. For example, the estimation unit 134 estimates the movement status of a predetermined user based on the voice information or acceleration information corresponding to the first position information and the voice information or acceleration information corresponding to the second position information.

  For example, the estimation unit 134 determines the degree of similarity between the voice information (e.g., vehicle running sound and engine sound) acquired together with the first position information and the sound information acquired together with the second position information as the second position. It may be one of the determination factors as to whether or not the transportation means of the user corresponding to the information is “automobile”. In addition, the estimation unit 134 determines the similarity between the acceleration information acquired together with the first position information (for example, the time from the stationary point until reaching a predetermined speed) and the acceleration information acquired together with the second position information. It may be one of the determination factors as to whether or not the user's means of transportation corresponding to the second position information is an “automobile”. In addition, the estimation unit 134 may perform the estimation process using information such as temperature, humidity, and altitude in addition to the voice information and the acceleration information. For example, for a moving means (such as a ship or an airplane) having characteristics such as temperature, humidity, altitude, etc. due to a special moving environment, the accuracy of estimation processing is improved by determining the degree of similarity of sensor information. be able to.

[5. Processing procedure]
Next, a processing procedure performed by the estimation device 100 according to the embodiment will be described with reference to FIGS. 8 and 9. First, the procedure of model generation processing by the estimation apparatus 100 will be described with reference to FIG. FIG. 8 is a flowchart (1) showing a processing procedure according to the embodiment.

  As illustrated in FIG. 8, the estimation device 100 determines whether the first position information has been acquired from the user (step S101). When the first position information is not acquired (step S101; No), the estimation device 100 waits until it is acquired.

  On the other hand, when the first position information is acquired (step S101; Yes), the estimation device 100 stores the acquired first position information in the storage unit 120 (step S102). Then, the estimation device 100 determines whether or not the sufficient amount of first position information has been accumulated for the model generation process (step S103). If sufficient first position information is not accumulated (step S103; No), the estimation device 100 repeats the acquisition process of the first position information (step S101).

  On the other hand, when sufficient first position information is accumulated (step S103; Yes), the estimation device 100 uses the accumulated first position information to estimate the user's moving means for each moving means. The model is generated (step S104). The estimation device 100 stores the generated model in the storage unit 120 (step S105). Note that the estimation device 100 may appropriately update the generated model when the first position information is newly acquired.

  Next, the procedure of the estimation process performed by the estimation device 100 will be described with reference to FIG. FIG. 9 is a flowchart (2) showing the processing procedure according to the embodiment.

  The estimation device 100 determines whether or not the second position information has been acquired from a predetermined user (step S201). When the second position information is not acquired (step S201; No), the estimation device 100 waits until it is acquired.

  On the other hand, when the second position information is acquired (step S201; Yes), the estimation device 100 stores the acquired second position information in the storage unit 120 (step S202). Then, the estimation device 100 determines whether or not a sufficient amount of second position information has been accumulated for the movement situation estimation process (step S203). When sufficient second position information is not accumulated (step S203; No), the estimation device 100 repeats the acquisition process of the second position information (step S201).

  On the other hand, when sufficient second position information is accumulated (step S203; Yes), the estimation device 100 estimates the moving means (moving condition) of the user corresponding to the second position information by using the model ( Step S204).

[6. Modification example)
The estimation device 100 described above may be implemented in various different forms other than the above-described embodiment. Therefore, a modified example of the embodiment will be described below.

[6-1. Estimating user situation]
In the above embodiment, the estimation device 100 has mainly shown the movement means of the user as the movement state of the user. Here, the estimation device 100 may perform processing of estimating not only the moving means but also the situation and emotions of the moving user.

  For example, the estimation device 100 acquires information indicating the emotion of the user when acquiring the first position information. For example, the estimation device 100 acquires position information by a communication application in which the user has a conversation or chat with another user, and acquires the content of the conversation or the like. Then, when the content of the conversation or the like is positive, the estimation device 100 stores that the emotion of the user is positive together with the position information. Alternatively, the estimation device 100 acquires position information by a voice reproduction application for listening to music and also acquires a situation in which the user is listening to music.

  After that, the estimation device 100 acquires the second position information that does not include information such as emotions. Then, the estimation device 100 determines, based on the transition of the position corresponding to the first position information and the transition of the position corresponding to the second position information, the emotional state of the user as the movement status of the user corresponding to the second position information. To estimate. For example, if the second position information indicates that the second position information is moving on a route or area in which a plurality of users frequently have a positive conversation in the first position information, the estimation device 100 determines that the second position information is the second position information. It is estimated that the corresponding user also has a positive emotion. Alternatively, the estimation device 100 corresponds to the second position information when the second position information indicates that the plurality of users are moving on a route or area in which the frequency of listening to music is relatively high in the first position information. It is presumed that users who also listen to music tend to listen to music.

  In this way, the estimation device 100 is not limited to the moving means, and the situation (emotion etc.) of the user corresponding to the second position information is based on the action taken by the user in the first position information, the estimated feeling, etc. ) Is estimated. Thereby, the estimation device 100 can specify, for example, an area where the user has a positive emotion, an area where the user has a negative emotion, or an area where the emotion is elevated in a shopping mall or a theme park.

  The estimating apparatus 100 may estimate the moving means of the user based on the content of the communication application or the like. For example, the estimation device 100 extracts, from the user's message in the communication app, a message that the transportation means can estimate, such as “I am driving now” or “I am late because of congestion”. For example, the estimation device 100 holds in advance definition information such as words associated with the transportation means (for example, “automobile” and “traffic jam”), and estimates the transportation means of the user based on the definition information. May be. In addition, the estimation device 100 may generate a model that learns the characteristics of a message issued when the user is in an automobile or the like, and may estimate that the user is in the automobile based on the model. Good.

[6-2. App type)
In the above embodiment, the estimation device 100 shows an example in which the first position information is acquired from a user who has used a car navigation application or the like, but examples of the application are not limited thereto.

  For example, the estimation device 100 may acquire the first position information acquired by a running application that records running. By performing the estimation process based on the first position information, the estimation device 100 causes the user corresponding to the second position information to run or simply walk when the second position information is acquired. It is possible to estimate with high accuracy what is being done.

  In addition, the estimation device 100 may acquire the first position information acquired by a cycling app that records cycling information. By performing the estimation process based on the first position information, the estimation device 100 determines whether the user corresponding to the second position information moves on a bicycle when the second position information is acquired. Alternatively, it is possible to highly accurately estimate whether or not the user is walking.

  In addition, the estimation device 100 may acquire the first position information acquired by a reservation application or the like regarding a transportation system such as an aircraft or a bullet train. For example, when the position information is acquired during the time period when the user makes a reservation for the transportation, the estimation device 100 estimates the transportation as the transportation means and acquires the first position information.

[6-3. location information〕
In the above embodiment, the position information is acquired from the GPS information acquired by the user terminal 10 or the access point. However, the estimation device 100 may acquire the position information of the user terminal 10 from different information.

  For example, the estimation device 100 may acquire the position information of the user terminal 10 based on the history of the user using various services. Specifically, the estimation device 100 estimates the station frequently input from the user terminal 10 in the route search service as the nearest station to the user. Then, the estimation device 100 may acquire a predetermined range including the nearest station as the area where the user terminal 10 is located. According to such processing, the estimation apparatus 100 can acquire the position information of the user terminal 10 even when the user terminal 10 does not have the function of acquiring the position information.

  Further, the user terminal 10 may exchange position information with each other among a plurality of operating applications. For example, it is assumed that the estimation device 100 acquires position information from the portal application related to the user terminal 10. On the other hand, it is assumed that the user has started the car navigation application at the same time as the portal application, and that the car navigation application is not communicating with the estimation device 100. At this time, the portal application according to the user terminal 10 estimates the position information acquired by the portal application together with the information that the car navigation application is activated in the user terminal 10 (for example, a flag added to the location information). Send to. As a result, the estimation device 100 corresponds to the position information based on the information that the car navigation application is running on the user terminal 10, even when the position information is acquired from the portal application whose transportation means is unknown. It can be estimated that the means of transportation is a car.

[6-4. Configuration of user terminal]
In the above embodiment, the configuration example of the user terminal 10 has been described with reference to FIG. However, the user terminal 10 does not necessarily need to include all the processing units illustrated in FIG. For example, the user terminal 10 does not necessarily have to include the display unit 13 and the detection unit 14. Further, the user terminal 10 may be separated into two or more devices to realize the configuration shown in FIG. For example, the user terminal 10 may be realized by two or more devices having a configuration in which a detection device including at least the detection unit 14 and the acquisition unit 161 and a communication device including at least the communication unit 11 are separated. .

[7. Hardware configuration]
The estimation device 100 and the user terminal 10 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration illustrated in FIG. 10. Hereinafter, the estimation device 100 will be described as an example. FIG. 10 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the estimation device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program dependent on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from another device via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100. The data generated by the CPU 1100 is transmitted via the communication network 500 to another device. Send to device.

  The CPU 1100 controls output devices such as a display and a printer and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. The CPU 1100 also outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the estimation device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the HDD 1400 stores the data in the storage unit 120. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the communication network 500.

[8. Other]
Further, of the processes described in the above embodiment, all or part of the processes described as being automatically performed may be manually performed, or the processes described as manually performed may be performed. All or part of the process can be automatically performed by a known method. In addition, the processing procedures, specific names, information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various kinds of information shown in each drawing are not limited to the illustrated information.

  Further, each component of each device shown in the drawings is functionally conceptual, and does not necessarily have to be physically configured as shown. That is, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part of the device may be functionally or physically distributed / arranged in arbitrary units according to various loads and usage conditions. It can be integrated and configured. For example, the first acquisition unit 131 and the second acquisition unit 133 illustrated in FIG. 4 may be integrated. Further, for example, the information stored in the storage unit 120 may be stored in an external storage device via the network N.

  Further, for example, in the above-described embodiment, the example in which the estimation device 100 performs the acquisition process of acquiring the position information of the user terminal 10 and the estimation process of estimating the moving state of the user corresponding to the second position information has been shown. . However, the estimation device 100 described above may be separated into an acquisition device that performs the acquisition process and an estimation device that performs the estimation process. In this case, the acquisition device includes at least the first acquisition unit 131 and the second acquisition unit 133. The estimation device includes at least the estimation unit 134. Further, the processing by the estimation device 100 according to the embodiment is realized by the estimation system 1 including each device such as the acquisition device and the estimation device.

  Further, the above-described embodiments and modified examples can be appropriately combined within a range in which the processing content is not inconsistent.

[9. effect〕
As described above, the estimation device 100 according to the embodiment includes the first acquisition unit 131, the second acquisition unit 133, and the estimation unit 134. The 1st acquisition part 131 acquires the 1st position information which is the position information acquired in relation to the application with which the transportation was matched. The 2nd acquisition part 133 acquires the 2nd position information which is the position information which shows the position of a predetermined user. The estimation unit 134 determines a predetermined user based on the feature amount based on the first position information acquired by the first acquisition unit 131 and the feature amount based on the second position information acquired by the second acquisition unit 133. Estimate the movement situation.

  As described above, the estimation device 100 according to the embodiment estimates the moving means of a predetermined user by using the first position information acquired in advance in association with the app with which the moving means can be specified, as the correct data. As a result, the estimation device 100 can accurately estimate the moving state of the user even with respect to the moving means of the user, which is difficult to estimate only with the position information.

  In addition, the estimation device 100 according to the embodiment generates a model for estimating the movement status of the user corresponding to the first position information, based on the first position information acquired by the first acquisition unit 131. The unit 132 is further included. The estimation unit 134 uses the model generated by the generation unit 132 to estimate the movement status of a predetermined user based on the second position information acquired by the second acquisition unit 133.

  As described above, the estimation device 100 according to the embodiment can estimate the moving state of the user with higher accuracy by using the model generated based on the first position information.

  In addition, the first acquisition unit 131 acquires the first position information acquired by the navigation application associated with the walking or bicycle moving means. The estimation unit 134 estimates, based on the first position information acquired by the first acquisition unit 131, that the predetermined user is walking or moving by bicycle as the movement status of the predetermined user.

  As described above, the estimation device 100 according to the embodiment performs the estimation process based on appropriate correct data by using the position information acquired by the application associated with the moving means such as walking or bicycle. You can

  In addition, the first acquisition unit 131 acquires the first position information acquired by the car navigation application associated with the vehicle-based transportation means. The estimation unit 134 estimates, based on the first position information acquired by the first acquisition unit 131, that the predetermined user is moving by an automobile as the movement status of the predetermined user.

  As described above, the estimation device 100 according to the embodiment can perform the estimation process based on appropriate correct answer data by using the position information acquired by the application associated with the transportation means of the automobile.

  In addition, the first acquisition unit 131 is the position information of the user who has used the vehicle allocation application that is an application that requests the vehicle allocation, and is acquired in the section where the user has moved in the vehicle allocated via the vehicle allocation application. The obtained position information is acquired as the first position information. The estimation unit 134 estimates, based on the first position information acquired by the first acquisition unit 131, that the predetermined user is moving by an automobile as the movement status of the predetermined user.

  As described above, the estimation device 100 according to the embodiment can obtain detailed transportation means and position information including the section in which the user boarded by using the information obtained by the vehicle allocation application, and thus the estimation accuracy can be improved. Can be improved.

  In addition, the first acquisition unit 131 uses the position information of the user who has used the route search application and the position information acquired at the boarding time indicated by the route search application, to move the position indicated by the route search application. The first position information is acquired together with the means. Based on the first position information acquired by the first acquisition unit 131, the estimation unit 134 indicates that the predetermined user is moving by the moving means indicated by the route search application, as the movement status of the predetermined user. Presume that.

  As described above, the estimation device 100 according to the embodiment acquires the correct answer data of the section used by the user and the transportation means (transportation means) by using the information acquired by the route search application. As a result, the estimation device 100 can improve the estimation accuracy.

  The first acquisition unit 131 also acquires map information corresponding to the position information. The estimating unit 134 includes a route or terrain information indicated by the first position information extracted based on the map information acquired by the first obtaining unit 131 and a route or terrain indicated by the second position information extracted based on the map information. The movement status of a predetermined user is estimated based on the information.

  As described above, the estimation device 100 according to the embodiment can perform estimation processing including topographical information such as roads and railroads, rivers and seas, and information such as routes on a map, thus improving estimation accuracy. Can be made.

  In addition, the first acquisition unit 131 acquires the sensor information corresponding to the first position information together with the first position information. The second acquisition unit 133 acquires the second position information and the sensor information corresponding to the second position information. The estimation unit 134 estimates the movement status of a predetermined user based on the sensor information corresponding to the first position information and the sensor information corresponding to the second position information.

  As described above, the estimation device 100 according to the embodiment can more accurately understand the movement status of a predetermined user by acquiring the position information including the sensor information, and thus the estimation accuracy can be improved. it can.

  In addition, the first acquisition unit 131 acquires, together with the first position information, voice information or acceleration information corresponding to the first position information. The second acquisition unit 133 acquires voice information or acceleration information corresponding to the second position information together with the second position information. The estimation unit 134 estimates the movement status of a predetermined user based on the voice information or acceleration information corresponding to the first position information and the voice information or acceleration information corresponding to the second position information.

  In this way, the estimation device 100 according to the embodiment can more accurately grasp the movement situation of a predetermined user by acquiring information specific to the moving means, such as voice information and acceleration information, and thus the estimation can be performed. The accuracy of can be improved.

  As described above, some of the embodiments of the present application have been described in detail based on the drawings, but these are examples, and various modifications based on the knowledge of those skilled in the art, including the modes described in the section of the disclosure of the invention, It is possible to implement the present invention in other forms with improvements.

  Also, the above-mentioned "section (module, unit)" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition unit or an acquisition circuit.

1 estimation system 10 user terminal 100 estimation device 110 communication unit 120 storage unit 121 first position information storage unit 122 model storage unit 123 second position information storage unit 130 control unit 131 first acquisition unit 132 generation unit 133 second acquisition unit 134 Estimator

Claims (12)

A first acquisition unit for acquiring first position information, which is position information acquired in association with the application associated with the transportation means;
A second acquisition unit for acquiring second position information, which is position information indicating the position of the predetermined user;
When the feature amount based on the first position information acquired by the first acquisition unit and the feature amount based on the second position information acquired by the second acquisition unit are similar, the movement status of the predetermined user is determined. An estimating unit that estimates that the vehicle is moving by a moving means associated with the application ,
An estimation device comprising: The first acquisition unit,
Acquiring the first position information, which is the position information acquired for each application associated with the transportation means,
The estimation unit is
When the feature amount based on the first position information acquired by the first acquisition unit and the feature amount based on the second position information acquired by the second acquisition unit are similar, the movement status of the predetermined user is determined. , Estimating that the movement is performed by the movement means associated with the application from which the first position information is acquired,
The estimation device according to claim 1, wherein A generation unit that generates a model for estimating the movement situation of the user corresponding to the first position information, based on the first position information acquired by the first acquisition unit,
Further equipped with,
The estimation unit is
Estimating the movement status of the predetermined user based on the second position information acquired by the second acquisition unit using the model generated by the generation unit,
The estimation device according to claim 1 or 2 , characterized in that. The first acquisition unit,
Acquires the first position information acquired by the navigation application associated with the means of walking or biking,
The estimation unit is
Based on the first position information acquired by the first acquisition unit, it is estimated that the predetermined user is walking or moving by bicycle as the movement status of the predetermined user.
The estimation device according to any one of claims 1 to 3 , characterized in that. The first acquisition unit,
Acquires the first position information acquired by the car navigation application that is associated with the means of transportation by car,
The estimation unit is
Based on the first position information acquired by the first acquisition unit, it is estimated that the predetermined user is moving by an automobile as the movement status of the predetermined user.
Estimating apparatus according to any one of claims 1-4, characterized in that. The first acquisition unit,
The positional information of a user who uses a vehicle allocation application that is an application for requesting vehicle allocation, the positional information acquired in a section traveled by the user in the vehicle allocated via the vehicle allocation application is the first information. Obtained as location information,
The estimation unit is
Based on the first position information acquired by the first acquisition unit, it is estimated that the predetermined user is moving by an automobile as the movement status of the predetermined user.
Estimating apparatus according to any one of claims 1-5, characterized in that. The first acquisition unit,
The position information of the user using the route search application, which is acquired at the boarding time indicated by the route search app, is acquired as the first position information together with the transportation means indicated by the route search app. Then
The estimation unit is
Based on the first position information acquired by the first acquisition unit, it is estimated that the predetermined user is moving by the moving means indicated by the route search application, as the movement status of the predetermined user. To do
Estimating apparatus according to any one of claims 1-6, characterized in that. The first acquisition unit,
Obtaining map information corresponding to the location information,
The estimation unit is
The route or terrain information indicated by the first position information extracted based on the map information acquired by the first obtaining unit, and the route or terrain information indicated by the second position information extracted based on the map information. Based on the estimation of the movement status of the predetermined user,
Estimating apparatus according to any one of claims 1-7, characterized in that. The first acquisition unit,
Acquire sensor information corresponding to the first position information together with the first position information,
The second acquisition unit,
Acquire sensor information corresponding to the second position information together with the second position information,
The estimation unit is
Estimating the movement status of the predetermined user based on the sensor information corresponding to the first position information and the sensor information corresponding to the second position information,
Estimating apparatus according to any one of claims 1-8, characterized in that. The first acquisition unit,
Acquiring voice information or acceleration information corresponding to the first position information together with the first position information,
The second acquisition unit,
Acquiring voice information or acceleration information corresponding to the second position information together with the second position information,
The estimation unit is
Estimating the movement status of the predetermined user based on voice information or acceleration information corresponding to the first position information and voice information or acceleration information corresponding to the second position information;
The estimation device according to claim 9 , wherein An estimation method performed by a computer,
A first acquisition step of acquiring first position information, which is position information acquired in association with the app associated with the transportation means;
A second acquisition step of acquiring second position information, which is position information indicating the position of the predetermined user;
When the feature amount based on the first position information acquired by the first acquisition step and the feature amount based on the second position information acquired by the second acquisition step are similar, the movement status of the predetermined user is determined. An estimating step of estimating that the vehicle is moving by a moving means associated with the application ,
An estimation method characterized by including. A first acquisition procedure for acquiring first position information, which is position information acquired in association with the app associated with the transportation means;
A second acquisition procedure for acquiring second position information, which is position information indicating the position of a predetermined user,
When the feature amount based on the first position information acquired by the first acquisition procedure and the feature amount based on the second position information acquired by the second acquisition procedure are similar, the movement status of the predetermined user is determined. An estimating procedure for estimating that the vehicle is moving by a moving means associated with the application ,
An estimation program characterized by causing a computer to execute.

Images