JP7221586B2 - Extraction device, extraction method, and extraction program - Google Patents

Description

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

Conventionally, techniques for extracting information on user behavior have been provided. For example, there is provided a technology for indirectly estimating the facility where the user visited or stayed while using history information intermittently obtained along with the user's actions and movements.

JP 2010-244433 A

However, with the conventional technology described above, it may be difficult to appropriately extract user information that satisfies the regularity. For example, it may be difficult to appropriately extract, for example, information related to a user's continuous behavior only by using history information intermittently obtained according to the user's behavior or movement.

The present application has been made in view of the above, and aims to provide an extraction device, an extraction method, and an extraction program for appropriately extracting user information that satisfies regularity.

An extraction device according to the present application includes an acquisition unit that acquires a plurality of pieces of location information of a user detected during a predetermined period of time, and a predetermined regularity regarding changes in location among the pieces of location information acquired by the acquisition unit. and an extraction unit for extracting a group of position information that satisfies the requirements.

According to one aspect of the embodiment, it is possible to appropriately extract user information that satisfies the regularity.

FIG. 1 is a diagram illustrating an example of extraction processing according to an embodiment. FIG. 2 is a diagram illustrating an example of extraction processing according to the embodiment. FIG. 3 is a diagram showing a configuration example of an extraction system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of an extraction device according to the embodiment. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment; FIG. 6 is a diagram illustrating an example of an action information storage unit according to the embodiment; FIG. 7 is a diagram illustrating an example of a position information storage unit according to the embodiment; FIG. 8 is a diagram illustrating an example of a model information storage unit according to the embodiment; FIG. FIG. 9 is a flowchart illustrating an example of extraction processing according to the embodiment. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the extraction device.

Embodiments for implementing the extraction device, extraction method, extraction program, learning data, and model (hereinafter referred to as "embodiments") according to the present application will be described in detail below with reference to the drawings. Note that the extraction device, extraction method, extraction program, learning data, and model according to the present application are not limited by this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

(embodiment)
[1. Extraction process]
An example of extraction processing according to the embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 and 2 are diagrams illustrating an example of extraction processing according to an embodiment. The examples of FIGS. 1 and 2 show the case of extracting a position information group that satisfies a predetermined regularity regarding changes in position from sensor information (position information) detected by the terminal device 10 used by the user. Also, the extraction processing shown in FIGS. 1 and 2 includes processing for generating a model using a position information group and information indicating the presence or absence of a predetermined action of the user. Note that the extraction process does not have to include the process of generating the model.

[1-1. Configuration of extraction system]
First, before describing FIGS. 1 and 2, an extraction system 1 shown in FIG. 3 will be described. As shown in FIG. 3 , the extraction system 1 includes a terminal device 10 and an extraction device 100 . The terminal device 10 and the extraction device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 3 is a diagram showing a configuration example of an extraction system according to the embodiment. Note that the extraction system 1 shown in FIG. 3 may include a plurality of terminal devices 10 and a plurality of extraction devices 100 .

The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smart phone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. 1 and 2 show a case where the terminal device 10 is a smart phone.

Also, the terminal device 10 has a function such as a GPS (Global Positioning System) sensor, and detects and acquires user position information (sensor information). In addition, the terminal device 10 may estimate and acquire the location information of the user by using the location information of the base station with which it is communicating and the radio waves of WiFi (registered trademark) (Wireless Fidelity). In addition, below, position information may be simply described as a "position."

Moreover, the terminal device 10 may detect various sensor information by various sensors other than a GPS sensor or the like. For example, the terminal device 10 may have a function of an acceleration sensor, and may be capable of detecting and acquiring acceleration information (sensor information) in movement of the user. Further, the terminal device 10 may have various functions such as a temperature sensor and an air pressure sensor, and may be capable of detecting and acquiring environment information such as temperature and air pressure in which the user is placed. In addition, the terminal device 10 may have various functions such as a heartbeat sensor, and may be capable of detecting and acquiring biological information of the user. For example, a user using the terminal device 10 may acquire the user's own context information from the terminal device 10 by wearing a wearable device capable of communicating with the terminal device 10 . For example, a user using the terminal device 10 wears a wristband-type wearable device that can communicate with the terminal device 10, so that the terminal device 10 acquires information about the user's own heartbeat (pulse). It may be possible.

Also, the terminal device 10 receives an operation by the user. Also, the terminal device 10 transmits various information to the extraction device 100 . For example, the terminal device 10 transmits position information, action information, and the like to the extraction device 100 . In addition, below, the terminal device 10 may be described as a user. That is, hereinafter, the user can also be read as the terminal device 10 .

Hereinafter, the user identified by the user ID "U1" may be referred to as "user U1". Thus, hereinafter, when "user U* (* is an arbitrary number)" is described, it indicates that the user is identified by the user ID "U*". For example, when "user U2" is described, the user is identified by the user ID "U2". For example, the extraction system 1 shown in FIG. 3 includes many terminal devices 10 such as the terminal device 10 used by the user U1 and the terminal device 10 used by the user U2.

A terminal device 10 shown in FIG. 1 is an information processing device used by a user U1. The terminal device 10 shown in FIG. 2 is an information processing device used by the user U2. The terminal device 10 accepts various operations by the user. Note that the terminal device 10 may be referred to as a user. That is, the user can also be read as the terminal device 10 .

The extraction device 100 is an information processing device that extracts position information (position information group) that satisfies a predetermined regularity regarding changes in position from among a plurality of pieces of position information of a user detected during a predetermined period. In addition, the extraction device 100 predicts whether or not a predetermined action will occur based on learning data including a position information group and action information corresponding to the position information group (hereinafter also referred to as "target action information"). Generate a model that can be

[1-2. Regarding movement (with position change)]
The example of FIG. 1 shows a case where the extraction device 100 extracts a group of location information that satisfies a predetermined regularity regarding changes in location from among a plurality of pieces of location information of the user detected during dates dt11 to dt18 for user U1. . Note that the user U1 is a user who uses the terminal device 10, and the extraction device 100 acquires the position of the terminal device 10 using a function of the terminal device 10, such as a GPS sensor. Map information MP1 shown in FIG. 1 schematically indicates the position of user U1. Further, in the map information MP1, the positions of the terminal device 10 (the user who owns the terminal device 10) are indicated by positions LC11 to LC18. Incidentally, when the positions LC11 to LC18 are not distinguished, they may be referred to as the position LC. In the following description, the extraction device 100 acquires the position of the user U1 and the behavior information of the user U1 in real time. , extraction processing may be performed. For example, the extraction device 100 may periodically (for example, every other day) acquire the location and action information of each user and perform extraction processing.

First, the extraction device 100 acquires the position LC11 of the user U1 at the date and time dt11. Then, the extraction device 100 acquires a position LC12 indicating that the user U1 is in the XX park (point of interest POI1) at a date and time dt12 later than the date and time dt11. For example, the extraction device 100 extracts points of interest, such as locations where various facilities (points of interest) are located, such as XX park (point of interest POI1) shown in FIG. 1 and YY movie theater (point of interest POI2) shown in FIG. (POI: Point of Interest) has various information (hereinafter also referred to as "POI information").

For example, the extraction device 100 estimates that the user U1 is heading to XX Park by comparing the POI information and the position LC of the user U1. For example, the extraction device 100 acquires a position LC12 indicating that the user U1 is in XX Park at a date and time dt12 later than the date and time dt11, which is different from the position LC11. For example, the extraction device 100 estimates that the user U1 is heading to XX Park by comparing the POI information and the change in the position LC of the user U1. In the example of FIG. 1, the extraction device 100 estimates that the user U1 is moving toward the XX park (from bottom to top in FIG. 1) from the positions LC11 and LC12. Note that the extraction device 100 may estimate the direction of movement of the user based on the acceleration detected by the terminal device 10 . Further, the extraction device 100 may appropriately use various conventional techniques to estimate the movement from the point where the position information was last detected based on the acceleration detected by the terminal device 10 .

Then, the extraction device 100 acquires a position LC13 indicating that the user U1 is at a position different from the position LC12 in the XX park at a date and time dt13 later than the date and time dt12. In the example of FIG. 1, the extraction device 100 estimates that the user U1 is moving in the XX park from the positions LC12 and LC13. The extraction device 100 also estimates the moving speed of the user U1 from the positions LC12 and LC13. Also, the extraction device 100 may estimate the moving speed of the user based on the acceleration detected by the terminal device 10 .

Then, the extraction device 100 acquires a position LC14 indicating that the user U1 is at a position different from the position LC13 in the XX park at a date and time dt14 later than the date and time dt13. In the example of FIG. 1, the extraction device 100 estimates that the user U1 is moving in the XX park from the positions LC13 and LC14. Also, the extraction device 100 estimates the moving speed of the user U1 from the positions LC13 and LC14.

Then, the extraction device 100 acquires a position LC15 indicating that the user U1 is at a position different from the position LC14 in the XX park at a date and time dt15 later than the date and time dt14. In the example of FIG. 1, the extraction device 100 estimates that the user U1 is moving in the XX park from the positions LC14 and LC15. The extraction device 100 also estimates the moving speed of the user U1 from the positions LC14 and LC15.

Then, the extraction device 100 acquires a position LC16 indicating that the user U1 is at a position different from the position LC15 in the XX park at a date and time dt16 later than the date and time dt15. In the example of FIG. 1, the extraction device 100 estimates that the user U1 is moving in the XX park from the positions LC15 and LC16. Also, the extraction device 100 estimates the moving speed of the user U1 from the positions LC15 and LC16.

Then, the extraction device 100 acquires a position LC17 indicating that the user U1 left XX Park at a date and time dt17 later than the date and time dt16. Then, the extraction device 100 acquires a position LC18 indicating that the user U1 is at the A convenience store (shop SP1) at a date and time dt18 later than the date and time dt17. The extraction device 100 also acquires action information AC11 indicating that the user U1 purchased W water at the A convenience store at date and time dt18.

The extraction device 100 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information LC11 to LC18 of the user detected during the dates and times dt11 to dt18 (step S11). For example, the extraction device 100 extracts a position information group that satisfies a predetermined regularity corresponding to the "behavior pattern PT1 (running)" as shown in the model information storage unit 124 (see FIG. 8). For example, the extraction device 100 extracts a position information group in which the position information of the user U1 changes at a speed corresponding to running, such as 10 km/h. In the example of FIG. 1, the extraction device 100 extracts the position information group when the user U1 is running in the XX park (point of interest POI1). For example, the extraction device 100 extracts a position information group in which the change in the position information of the user U1 is moving around XX Park at a speed of 10 km/h, for example.

In the example of FIG. 1, movement from position LC14 to position LC15 in XX park passes through position LC12 in the circling direction of user U1 (clockwise direction in the example of FIG. 1). The extraction device 100 estimates that the user U1 is running in the XX park based on the progress of movement of the user U1 and the speed of the user U1 as described above. Therefore, the extraction device 100 extracts position information LC12 to LC16 in which the user U1 is moving around XX Park during the dates dt12 to dt16. In the example of FIG. 1, the extraction device 100 extracts location information LC12 to LC16 where the user U1 is moving around XX Park on dates and times dt12 to dt16.

Then, the extraction device 100 extracts a behavior that satisfies a predetermined condition (hereinafter, also referred to as a “target behavior”) from among the behaviors of the user outside the target period, which is the period in which the position information group was detected (step S12). . For example, the extraction device 100 extracts target behavior information, which is behavior information that satisfies a predetermined condition, among the behavior information of the user outside the target period (dates and times dt12 to dt16) in which the position information group (position information LC12 to LC16) was detected. to extract In the example of FIG. 1, the extraction device 100 extracts target action information, which is action information that satisfies a predetermined condition among the user's action information within a predetermined period (period PD1) from the end of the target period (date and time dt16). to extract The extraction device 100 may extract target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined range from the position LC16 at the end of the target period (date and time dt16). In the example of FIG. 1, the extraction device 100 extracts action information indicating that the user U1 purchased W water at a convenience store A at a date and time dt18 within a predetermined period (period PD1) from the end of the target period (date and time dt16). AC11 is extracted as the target behavior information. Further, the extraction device 100 extracts action information AC11 indicating that user U1 purchased W water at convenience store A within a predetermined range (for example, within 1 km) from position LC16 at the end of the target period (date and time dt16). Extract as information. Although the example of FIG. 1 shows an example of extracting information only for user U1, it is assumed that similar information is extracted for a large number of users (for example, 10,000).

Then, the extraction device 100 generates a model based on the position information group and the target behavior information (step S13). In the example of FIG. 1, extraction device 100 generates model M1 based on position information LC12 to LC16 and action information AC11. For example, the extraction device 100 generates a model M1 that predicts whether a user whose position information group is extracted will purchase a beverage. For example, the extraction device 100 generates a model M1 that predicts whether the user will purchase a beverage after running. In the example of FIG. 1, the extraction device 100 generates a model M1 using a group of position information extracted for a large number of users (eg, 10,000 users) including the user U1.

For example, the extraction device 100 uses a combination of a position information group extracted as satisfying the regularity of the behavior pattern PT1 and information indicating that a beverage was purchased before and after the behavior as a positive example, and extracts the model M1 to generate For example, the extraction device 100 generates the model M1 by performing learning processing so as to output a score of "1" when a positive example position information group is input. For example, the extraction device 100 generates a model M1 indicating that the closer the score to "1" is output when the position information group is input, the more likely it is that a beverage will be purchased after the behavior of the behavior pattern PT1. Generate. Further, for example, the brewing device 100 may generate the model M1 using a group of position information of the user detected before and after the purchase of the beverage is not performed as negative examples. For example, the extraction device 100 generates the model M1 by performing learning processing so as to output a score of "0" when a negative example position information group is input. For example, the extraction device 100 generates a model M1 indicating that the closer the score to "0" is output when the location information group is input, the lower the possibility that the beverage will be purchased. For example, the extraction device 100 uses, as a negative example, a combination of a group of position information extracted as satisfying the regularity of the behavior pattern PT1 and information indicating that beverages were not purchased before and after the behavior, and a model M1 may be generated.

Note that each model may be generated using various conventional techniques related to machine learning as appropriate. For example, a model may be generated using a technology related to supervised learning machine learning such as SVM (Support Vector Machine). Also, for example, model generation may be performed using techniques related to unsupervised machine learning. For example, model generation may be performed using deep learning techniques. For example, the model may be generated using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). Note that the above description of model generation is an example, and model generation may be performed by a learning method appropriately selected according to obtainable information and the like.

[1-3. Regarding stay (no position change)]
The example of FIG. 2 shows a case where the extraction device 100 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among a plurality of pieces of position information of the user detected during the dates dt21 to dt26 for the user U2. . Note that the user U2 is a user who uses the terminal device 10, and the extraction device 100 acquires the position of the terminal device 10 using a function of the terminal device 10, such as a GPS sensor. The map information MP2 shown in FIG. 2 schematically shows the position of the user U2. Further, in the map information MP2, the positions of the terminal device 10 (the user who owns the terminal device 10) are indicated by positions LC21 to LC23. If the positions LC21 to LC23 are not distinguished, they may be called the position LC. Further, the following describes a case where the extraction device 100 acquires the position of the user U2 and the behavior information of the user U2 in real time. , extraction processing may be performed. For example, the extraction device 100 may periodically (for example, every hour) acquire the location and action information of each user and perform extraction processing.

First, the extraction device 100 acquires the position LC21 of the user U2 at date and time dt21. Then, the extraction device 100 acquires a position LC22 indicating that the user U2 is inside the YY movie theater (point of interest POI2) at date and time dt22 later than date and time dt21.

For example, the extraction device 100 estimates that the user U2 is heading to the YY movie theater by comparing the POI information and the position LC of the user U2. For example, the extraction device 100 acquires a position LC22 indicating that the user U2 is in the YY movie theater at a date and time dt22 later than the date and time dt21, which is different from the position LC21. For example, the extraction device 100 estimates that the user U2 is heading to the YY movie theater by comparing the POI information and the change in the position LC of the user U2. In the example of FIG. 2, the extraction device 100 estimates that the user U2 is moving toward the YY movie theater (from bottom to top in FIG. 2) from the positions LC21 and LC22. Note that the extraction device 100 may estimate the direction of movement of the user based on the acceleration detected by the terminal device 10 . Further, the extraction device 100 may appropriately use various conventional techniques to estimate the movement from the point where the position information was last detected based on the acceleration detected by the terminal device 10 .

Then, the extraction device 100 acquires a position LC22 indicating that the user U2 is in the YY movie theater at a date and time dt23 later than the date and time dt22. In the example of FIG. 2, the extraction device 100 estimates that the user U2 is staying in the YY movie theater based on the position LC22 acquired at the dates and times dt22 and dt23.

Then, the extraction device 100 acquires a position LC22 indicating that the user U2 is in the YY movie theater at a date and time dt24 later than the date and time dt23. In the example of FIG. 2, the extraction device 100 estimates that the user U2 is staying in the YY movie theater from the position LC22 acquired during the dates dt22 to dt24. In addition, the extraction device 100 acquires a position LC22 indicating that the user U2 is in the YY movie theater at a date and time dt25 later than the date and time dt24. In the example of FIG. 2, the extraction device 100 estimates that the user U2 is staying in the YY movie theater based on the position LC22 obtained from date/time dt22 to date/time dt25. Also, for example, the extraction device 100 estimates that the user U2 is watching a movie in the YY movie theater based on the time between the date/time dt22 and the date/time dt25 when the position LC22 of the user U2 is continuously detected. good. For example, the extraction device 100 may estimate that the user U2 is watching a movie in the YY movie theater when the time between date/time dt22 and date/time dt25 is equal to or greater than a predetermined threshold value (for example, 1 hour and 30 minutes). . Note that the position LC22 detected at each of the dates dt22 to dt25 may be a position within a predetermined range (error range) from the position LC22 as long as it can be estimated that the user U2 is located in the YY movie theater.

Then, the extraction device 100 acquires a position LC23 indicating that the user U2 left the YY movie theater at a date and time dt26 later than the date and time dt25. In the example of FIG. 2, the extraction device 100 acquires the position LC23 indicating that the user U2 is at the B restaurant (shop SP2) at the date and time dt26. The extraction device 100 also acquires action information AC21 indicating that the user U2 ate at restaurant B on date and time dt26.

The extraction device 100 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among a plurality of pieces of position information LC21 to LC23 of the user detected during dates dt21 to dt26 (step S21). For example, the extraction device 100 extracts a position information group that satisfies a predetermined regularity corresponding to the "behavior pattern PT2 (stay)" as shown in the model information storage unit 124 (see FIG. 8). For example, the extraction device 100 extracts a group of location information in which the location information of the user U2 has not changed over a predetermined period of time, for example. It should be noted that the position that has not changed here includes the position that has changed within the range of error. In the example of FIG. 2, the extraction device 100 extracts a position information group when the user U2 is staying at the YY movie theater (point of interest POI2). For example, the extraction device 100 extracts a position information group in which the change in position information of the user U2 is within the YY movie theater over a predetermined period of time, for example.

In the example of FIG. 2, since the position LC22 is continuously detected in the YY movie theater during the period from dt22 to dt25, it is estimated that the user U2 is staying in the YY movie theater. Therefore, the extraction device 100 extracts the position information LC22 corresponding to each of the dates dt22 to dt25 indicating that the user U2 is staying in the YY movie theater during the dates dt22 to dt25. In the example of FIG. 2, the extraction device 100 extracts a plurality of pieces of position information LC22 corresponding respectively to dates dt22 to dt25 indicating that the user U2 is staying in the YY movie theater during dates dt22 to dt25.

Then, the extraction device 100 extracts a target action that satisfies a predetermined condition from the user's actions outside the target period, which is the period in which the position information group was detected (step S22). For example, the extraction device 100 extracts target action information, which is action information that satisfies a predetermined condition, among the user's action information outside the target period (dates dt22 to dt25) in which the position information group (four pieces of position information LC22) was detected. to extract In the example of FIG. 2, the extraction device 100 extracts target action information, which is action information that satisfies a predetermined condition, out of the user's action information within a predetermined period (period PD2) from the end of the target period (date and time dt25). to extract For example, the extraction device 100 may extract target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined range from the position LC22 at the end of the target period (date and time dt25). . In the example of FIG. 2, the extraction device 100 extracts action information AC21 indicating that the user U2 ate at restaurant B on date and time dt26 within a predetermined period (period PD2) from the end of the target period (date and time dt25). is extracted as target behavior information. In addition, the extraction device 100 extracts behavior information AC21 indicating that user U2 ate at restaurant B within a predetermined range (for example, within 2 km) from position LC22 at the end of the target period (date and time dt25). Extract as Although the example of FIG. 2 shows an example of extracting information only for user U2, it is assumed that similar information is extracted for a large number of users (eg, 100,000).

Then, the extraction device 100 generates a model based on the position information group and the target behavior information (step S23). In the example of FIG. 2, the extraction device 100 generates the model M2 based on four pieces of position information LC22 and action information AC21. For example, the extraction device 100 generates a model M2 that predicts whether a user whose position information group is extracted will eat and drink. For example, the extraction device 100 generates a model M2 that predicts whether the user will eat or drink after staying. In the example of FIG. 2, the extraction device 100 generates the model M2 using a group of position information extracted for a large number of users (eg, 100,000 users) including the user U2.

For example, the extraction device 100 generates the model M2 by using as a positive example a combination of a position information group extracted as satisfying the regularity of the behavior pattern PT2 and information indicating that eating and drinking was performed before and after the behavior. do. For example, the extraction device 100 generates the model M2 by performing learning processing so as to output a score of "1" when a positive example position information group is input. For example, the extraction device 100 generates a model M2 indicating that the closer the score to "1" is output when the position information group is input, the more likely it is that eating and drinking will be performed after the action of the action pattern PT2. . Further, for example, the extraction device 100 may generate the model M2 by using a group of user position information detected before and after eating and drinking as negative examples. For example, the extraction device 100 generates the model M2 by performing learning processing so as to output a score of "0" when a negative position information group is input. For example, the extraction device 100 generates a model M2 indicating that the closer the score to "0" is output when the location information group is input, the lower the possibility of eating and drinking. For example, the extraction device 100 uses as a negative example a combination of a position information group extracted as satisfying the regularity of the behavior pattern PT2 and information indicating that eating and drinking was not performed before and after the behavior, and generates a model M2. may be generated.

As described above, the extraction device 100 can appropriately extract user information that satisfies the regularity. In the example of FIG. 1, the extraction device 100 extracts a group of position information, assuming that the user's position satisfies a predetermined regularity regarding changes in position when the user is making an action such as going around XX park. . In addition, the extraction device 100 extracts the target behavior outside the target period, which is the period during which the position information group is detected. As a result, the extraction device 100 can associate and extract a group of position information indicating that the user is running and the user's target behavior before and after the position information group. In addition, in the example of FIG. 2, when the user is staying at a predetermined point of interest (YY movie theater, etc.), the extraction apparatus 100 assumes that the user's position satisfies a predetermined regularity regarding changes in position. Extract information group. As a result, the extraction device 100 can extract a position information group indicating that the user is staying at a predetermined position in association with the user's target behavior before and after the position information group. In addition, the extraction device 100 can generate a model that can appropriately estimate whether or not the user's target behavior occurs by generating a model using the position information group extracted in this way. Thus, the extraction device 100 can generate a model that can appropriately estimate the behavior of the user.

[1-4. Target behavior (time) and information provision]
In the above example, the case where the user performs the target action after the target period during which the position information group is detected has been described as an example, but the user's target action may be performed before the target period. . For example, in the example of FIG. 1, when user U1 purchases X beverage at Z convenience store at a point in time (for example, date and time dt10) before the target period (dates dt12 to dt16), extraction device 100 Purchase of X drink may be extracted as a target behavior. For example, the extraction device 100 extracts action information indicating that user U1 purchased X drink at Z convenience store within a predetermined range (for example, within 1 km) from position LC12 at the start of the target period (date and time dt12). Extract as In this way, the extraction device 100 may extract the user's target behavior before the target period, associate the position information group with the user's target behavior before the target period, and store them. Further, the extraction device 100 may provide an external information processing device with information that associates the position information group with the target behavior of the user before the target period. For example, the extraction device 100 may provide information that associates the position information group with the target behavior of the user before the target period to a business operator that is researching the vicinity of the area including XX Park. For example, the extraction device 100 may provide information that associates the position information group with the target behavior of the user before the target period to a business operator planning to open a store near an area including XX Park.

For example, in the example of FIG. 2, if the user U2 is eating and drinking at restaurant C at a time (for example, date and time dt20) before the target period (date and time dt22 to dt25), the extraction device 100 may be extracted as the target behavior. For example, the extraction device 100 uses behavior information indicating that the user U2 ate at restaurant C within a predetermined range (for example, within 2 km) from the position LC22 at the start of the target period (date and time dt22) as the target behavior information. Extract. For example, the extraction device 100 may provide information that associates the position information group with the target behavior of the user before the target period to a business operator that is researching the vicinity of the area including the YY movie theater. For example, the extraction device 100 may provide information that associates a group of position information with target behavior of the user before the target period to a business operator planning to open a store near an area including the YY movie theater.

Note that the extraction device 100 may generate a model based on the position information group and the target behavior before the target period. For example, the extraction device 100 may generate a model for estimating whether the user was eating or drinking before the location information group was extracted. For example, the extraction device 100 generates a model that estimates whether the user ate or ate before the stay.

[1-5. Target behavior (space) and information provision]
In the above example, the case where the user performed the target action in the real space was described as an example, but the user's target action is not limited to the real space, and may be performed in the Internet space (on the web), for example.

For example, in the example of FIG. 1, when the user U1 performs a search using the query "convenience store" using the terminal device 10 at a date and time (for example, date and time dt17) after the target period (dates and times dt12 to dt16), the extraction device 100 may extract the search using the query "convenience store" by the user U1 as the target behavior. In this way, the extraction device 100 may extract the user's target behavior on the web after the target period, and store the position information group and the user's target behavior on the web in association with each other. Further, the extraction device 100 may provide an external information processing device with information that associates the position information group with the user's target behavior on the web. For example, the extraction device 100 may provide information that associates a group of position information with target behavior of the user on the web to a business operator that is researching the vicinity of an area including XX Park. For example, the extraction device 100 may provide information that associates a group of position information with target behavior of the user on the web to a business operator planning to open a store near an area including XX Park.

For example, in the example of FIG. 2, when the user U2 performs a search using the query "restaurant" using the terminal device 10 at a date and time (for example, date and time dt26) after the target period (date and time dt22 to dt25), the extraction device 100 may extract the search using the query "restaurant" by the user U2 as the target behavior. For example, the extraction device 100 may provide information that associates a group of position information with target behavior of the user on the web to a business operator that is researching the vicinity of the area including the YY movie theater. For example, the extraction device 100 may provide information that associates a group of position information with target behavior of the user on the web to a business operator planning to open a store near an area including the YY movie theater. In this way, the extraction device 100 may provide the external information processing device with information for predicting demand based on information that associates the position information group with the user's target behavior on the web.

[1-6. Use of model]
The extraction device 100 may use the models M1, M2, etc. generated in the example described above to estimate whether or not a predetermined action of the user has occurred.

For example, the extraction device 100 may predict whether or not the user U5 will perform a predetermined action by inputting a group of position information extracted for the user U5 into the model M1. For example, the extraction device 100 inputs to the model M1 a group of position information extracted for the user U5 located around ZZ Park, and if the output score is equal to or greater than a predetermined threshold, the user U5 makes a purchase. You can predict.

For example, the extraction device 100 may predict whether or not the user U10 will perform a predetermined action by inputting the position information group extracted for the user U10 to the model M2. For example, the extraction device 100 inputs to the model M2 a group of extracted position information about the user U10 whose position does not change for a predetermined period of time, and predicts that the user U10 eats and drinks when the output score is equal to or greater than a predetermined threshold. You may

[1-7. Extraction on the terminal device side]
In the above example, the extraction device 100 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among a plurality of pieces of position information acquired from the terminal device 10, but each terminal device 10 may extract a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information detected by . In this case, the terminal device 10 may be the extraction device. In this case, the extraction system may include a terminal device 10 as an extraction device and a service providing device that collects information about the regularity extracted by the terminal device 10 and provides a service. This point will be described below.

The terminal device 10 used by each user extracts a position information group that satisfies a predetermined regularity regarding changes in the position of each user from among the plurality of pieces of detected position information. Thereby, the terminal device 10 extracts a position information group that satisfies the regularity of each user. Further, the terminal device 10 may generate (calculate) information related to the regularity extracted for each individual user who uses the terminal device 10, the context for the position, etc., and transmit the result (information) to the service providing device. good.

For example, the terminal device 10 extracts a group of position information that satisfies a predetermined regularity corresponding to the "behavior pattern PT1 (running)", and information about the regularity generated based on the group of position information (for example, circular movement). or context information indicating that the user is running may be transmitted to the service providing apparatus. Further, for example, the terminal device 10 extracts a position information group that satisfies a predetermined regularity corresponding to the “behavior pattern PT2 (stay)”, and information about the regularity generated based on the position information group (for example, position change None) or context information indicating that the user is staying for a certain period of time may be transmitted to the service providing apparatus. The above is just an example, and the terminal device 10 may generate information indicating various regularities and information indicating context. Then, the terminal device 10 may transmit the generated information together with information identifying the terminal device 10 and information identifying the user using the terminal device 10 . The service providing device that has acquired the information from the terminal device 10 may store the information indicating the regularity or the information indicating the context in association with the user, and provide the service to each user based on the information.

In such an extraction system, the terminal device 10 transmits information generated on the client side (terminal device 10) to the service providing device without transmitting position information to the server side (service providing device). can provide the service. In this case, for example, the service providing device provides the service based on list information of points of interest (POI list) and information on regularity and information on context acquired from the terminal device 10 . For example, when information indicating similar regularity is acquired in the vicinity of a predetermined POI, the service providing apparatus may predict that the similar behavior will be performed after the behavior indicating the regularity and provide the service. good. For example, when information indicating regularity PTX is acquired near a predetermined POI, the service providing apparatus has a predetermined number or more of information indicating a behavior pattern of purchasing product X after behavior indicating the regularity PTX. If it has been acquired, information prompting purchase of product X may be provided to the terminal device 10 from which the information indicating the regularity PTX has been acquired in the vicinity of the predetermined POI. Note that the above is just an example, and the service providing apparatus may provide various services based on POI information, information indicating the regularity of user behavior, and information indicating context. In this way, the service providing device can provide services based on information with a higher degree of abstraction than the location information acquired from the terminal device 10 . As a result, the extraction system can provide services to users while taking into consideration the privacy of each user.

[2. Configuration of extraction device]
Next, the configuration of the extraction device 100 according to the embodiment will be described using FIG. FIG. 4 is a diagram illustrating a configuration example of an extraction device according to the embodiment. As shown in FIG. 4, the extraction device 100 has a communication unit 110, a storage unit 120, and a control unit . The extraction device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the extraction device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. may

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network (for example, network N in FIG. 3) by wire or wirelessly, and transmits and receives information to and from the terminal device 10 .

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 according to the embodiment has a user information storage unit 121, a behavior information storage unit 122, a position information storage unit 123, and a model information storage unit 124, as shown in FIG. Although not shown in FIG. 4, the storage unit 120 stores various information related to points of interest, such as the locations of various facilities (points of interest) such as XX park (point of interest POI1) shown in FIG. Information is stored.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various information about users. For example, the user information storage unit 121 stores various types of information regarding user attributes and various types of information regarding user behavior. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment; FIG. The user information storage unit 121 shown in FIG. 5 includes items such as "user ID", "age", and "sex".

"User ID" indicates identification information for identifying a user. For example, a user identified by user ID "U1" corresponds to user U1 shown in the example of FIG. "Age" indicates the age of the user identified by the user ID. Note that the “age” may be a specific age of the user identified by the user ID, such as 35 years old. "Gender" indicates the gender of the user identified by the user ID.

For example, in the example shown in FIG. 5, the age of the user identified by the user ID "U1" is "30's" and the gender is "male". Also, for example, in the example shown in FIG. 5, the age of the user identified by the user ID "U2" is "twenties" and the gender is "female."

Note that the user information storage unit 121 may store various types of information, not limited to the above, depending on the purpose. For example, the user information storage unit 121 may store other demographic attribute information and psychographic attribute information in addition to age and gender. For example, the user information storage unit 121 may store information such as name, home, place of work, interests, family composition, income, lifestyle, and the like.

(Action information storage unit 122)
The behavior information storage unit 122 according to the embodiment stores various types of information regarding user behavior. 6 is a diagram illustrating an example of an action information storage unit according to the embodiment; FIG. For example, the behavior information storage unit 122 stores various behavior information such as behavior of each user. The action information storage unit 122 shown in FIG. 6 includes items such as "user ID", "action ID", "date and time", "type", and "content".

"User ID" indicates identification information for identifying a user. For example, a user identified by user ID "U1" corresponds to user U1 shown in the example of FIG. Also, the "action ID" indicates information for identifying the action of the user. "Date and time" indicates the date and time when the corresponding user action was performed. In the example of FIG. 6, "dt18" or the like is shown, but the "date and time" may store a specific date and time such as "July 6, 2017, 19:31:52". "Type" indicates information about the type of the corresponding user's action. Also, "content" indicates the content targeted in the corresponding user's behavior.

For example, in the example shown in FIG. 6, the user (user U1) identified by the user ID "U1" has performed the action (action AC18) identified by the action ID "AC18". For example, in the example shown in FIG. 6, user U1 purchases W water (action AC18) at A convenience store at date and time dt18.

For example, in the example shown in FIG. 6, the user (user U2) identified by the user ID "U2" has performed the action (action AC26) identified by the action ID "AC26". For example, in the example shown in FIG. 6, user U2 has made a payment for eating and drinking at B restaurant (action AC26) on date and time dt26. In other words, action AC26 suggests that user U2 ate at B restaurant.

Note that the behavior information storage unit 122 may store various types of information, not limited to the above, depending on the purpose. In addition, although FIG. 6 shows the case where the action information is stored in the action information storage unit 122 for each user ID, the action information may be stored not only for each user ID but also in order of time, for example.

(Position information storage unit 123)
The position information storage unit 123 according to the embodiment stores various types of information regarding positions. For example, the position information storage unit 123 stores various information regarding the position detected by the sensor. 7 is a diagram illustrating an example of a position information storage unit according to the embodiment; FIG. The position information storage unit 123 shown in FIG. 7 includes items such as "user ID" and "position information". "Location information" includes items such as "date and time" and "location".

"User ID" indicates identification information for identifying a user. "Position information" indicates the history of the user's position information. "Date and time" indicates the date and time when each piece of position information was acquired. In the example of FIG. 7, "date and time" is illustrated by an abstract code such as "dt11". may be stored. "Position" indicates the position information of the corresponding user at the corresponding date and time. In the example of FIG. 7, the "position" is illustrated by an abstract code "LC11" or the like, but specific latitude/longitude information or the like may be stored in the "position".

For example, in the example shown in FIG. 7, it indicates that the location "LC11" of the user identified by the user ID "U1" was obtained at date and time "dt11". For example, it indicates that the position "LC11" of the terminal device 10 used by the user identified by the user ID "U1" was obtained at the date and time "dt11". For example, in the example shown in FIG. 7, it indicates that the location "LC12" of the user identified by the user ID "U1" was acquired at date and time "dt12". For example, it indicates that the position "LC13" of the terminal device 10 used by the user identified by the user ID "U1" was acquired at the date and time "dt13".

It should be noted that the position information storage unit 123 may store various types of information, not limited to the above, depending on the purpose. Further, the position information storage unit 123 may store information (flag) or the like indicating that the position information group is extracted by the extraction process. Also, the position information storage unit 123 may store information about the user's context.

(Model information storage unit 124)
The model information storage unit 124 according to the embodiment stores information about models. For example, the model information storage unit 124 stores model information (model data) generated by the generation process. 8 is a diagram illustrating an example of a model information storage unit according to the embodiment; FIG. The model information storage unit 124 shown in FIG. 8 includes items such as "model ID", "behavior pattern", and "model data". Although only the model M1 and the model M2 are illustrated in FIG. 8, a plurality of model information (models M3, M4, etc.) corresponding to each behavior pattern may be stored.

"Model ID" indicates identification information for identifying a model. For example, the model identified by model ID "M1" corresponds to model M1 shown in the example of FIG. "Behavioral pattern" indicates the behavioral pattern of the corresponding model. Also, in the "behavior pattern", conditions and the like corresponding to each behavior pattern are stored. For example, the "behavior pattern PT1 (running)" stores conditions for the behavior pattern of the user to correspond to running (for example, moving at a speed of 5 to 30 km/h). Also, "model data" indicates the data of the associated corresponding model. For example, "model data" includes information including nodes in each layer, functions adopted by each node, connection relations of nodes, and connection coefficients set for connections between nodes.

For example, in the example shown in FIG. 8, the model (model M1) identified by the model ID "M1" has a behavior pattern "PT1 (running)", and the target behavior information is before and after the behavior pattern PT1 is performed. Indicates that it is used to predict what will happen. It also indicates that the model data of the model M1 is the model data MDT1.

A model M1 (model data MDT1) is a group of position information of a user, an input layer into which a group of position information satisfying a predetermined regularity regarding changes in position is input, an output layer, and a layer from the input layer to the output layer. A first element belonging to any layer other than the output layer and a second element whose value is calculated based on the first element and the weight of the first element, and is input to the input layer For the sensor information obtained, each element belonging to each layer other than the output layer is set as the first element, and calculation is performed based on the first element and the weight of the first element. It is a model for making the computer function so that the score value is output from the output layer.

Here, it is assumed that the models M1, M2, etc. are realized by a regression model represented by "y= _a1 * _x1 + _a2 * _x2 +...+ _ai * _xi ". In this case, for example, the first element included in model M1 corresponds to input data (xi) such as x1 and x2. Also, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be viewed as a simple perceptron with an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can be regarded as a node of the input layer, and the second element can be regarded as a node of the output layer.

It is also assumed that the models M1, M2, etc. are implemented by a neural network having one or more intermediate layers, such as a DNN (Deep Neural Network). In this case, for example, the first element included in the model M1 corresponds to any node of the input layer or the intermediate layer. Also, the second element corresponds to the next node, which is a node to which the value is transmitted from the node corresponding to the first element. Also, the weight of the first element corresponds to the connection coefficient, which is the weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

It should be noted that the model information storage unit 124 may store various types of model information, not limited to the above, depending on the purpose.

(control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller, and is stored in the storage device inside the extraction device 100 by, for example, a CPU (Central Processing Unit) or MPU (Micro Processing Unit). Various programs (corresponding to an example of an extraction program and a generation program) are implemented by executing them using the RAM as a work area. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 130 performs information processing according to the model M1, the model M2, etc. stored in the model information storage unit 124 to obtain a group of position information of the user that satisfies a predetermined regularity regarding changes in position. is input, the output layer, the first element belonging to any layer from the input layer to the output layer other than the output layer, and the first element and the weight of the first element and a second element whose value is calculated by using the first element and the weight of the first element with respect to the sensor information input to the input layer, with each element belonging to each layer other than the output layer as the first element , the output layer outputs a score value used for predicting whether or not a predetermined action will occur.

For example, the extraction device 100 calculates a usage score and a bid score using a model having an arbitrary structure such as the regression model or neural network described above. Specifically, the models M1, M2, etc. are a group of user position information, and a group of position information that satisfies a predetermined regularity regarding changes in position (that is, each element used to calculate the score described above) is input. The coefficient is set so as to output a score regarding the occurrence or non-occurrence of a predetermined action (that is, a score indicating how likely the user is to perform the predetermined action) when the user is asked to do so. The information providing device 10 uses such models M1, M2, etc. to calculate the score of each user in the corresponding action pattern.

In the above example, the models M1, M2, etc. are a group of user position information, and when a group of position information that satisfies a predetermined regularity regarding changes in position is input, a score regarding the occurrence or non-occurrence of a predetermined action is obtained. An example of a model that outputs is shown. However, the models M1, M2, etc. according to the embodiment may be models generated based on results obtained by repeating data input/output. For example, the model is a learned model (model M1b ). Alternatively, the model may be a learned model that receives a group of user position information that satisfies a predetermined regularity regarding changes in position as an input and outputs the output value of the model M1b. .

Further, when the extraction device 100 performs prediction processing using a GAN (Generative Adversarial Networks), the models M1, M2, etc. may be models forming part of the GAN.

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a generation unit 133, a prediction unit 134, and a provision unit 135, and has functions and actions of information processing described below. realize or perform Note that 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 performs information processing to be described later.

(Acquisition unit 131)
Acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from an external information processing device such as the terminal device 10 . For example, the acquisition unit 131 acquires various types of information from the storage unit 120 such as the user information storage unit 121, the behavior information storage unit 122, the position information storage unit 123, the model information storage unit 124, and the like. For example, the acquisition unit 131 acquires various information detected by the terminal device 10 . For example, the acquisition unit 131 acquires position information and acceleration information detected by the terminal device 10 .

For example, the acquisition unit 131 acquires a plurality of pieces of location information of the user detected during a predetermined period. For example, the acquisition unit 131 acquires the user's behavior information outside the target period, which is the period during which the position information group was detected.

In the example of FIG. 1, the acquisition unit 131 acquires the position LC11 of the user U1 at the date and time dt11. Then, the obtaining unit 131 obtains the position LC12 indicating that the user U1 is in the XX park (point of interest POI1) at the date and time dt12 later than the date and time dt11. For example, the acquisition unit 131 acquires a position LC12 indicating that the user U1 is in the XX park at a date and time dt12 later than the date and time dt11, which is different from the position LC11. For example, the acquisition unit 131 acquires a position LC13 indicating that the user U1 is at a position different from the position LC12 in the XX park at a date and time dt13 later than the date and time dt12. For example, the acquisition unit 131 acquires a position LC14 indicating that the user U1 is at a position different from the position LC13 in the XX park at a date and time dt14 later than the date and time dt13.

For example, the acquisition unit 131 acquires a position LC15 indicating that the user U1 is at a position different from the position LC14 in the XX park at a date and time dt15 later than the date and time dt14. For example, the acquisition unit 131 acquires a position LC16 indicating that the user U1 is at a position different from the position LC15 in the XX park at a date and time dt16 later than the date and time dt15. For example, the acquisition unit 131 acquires a position LC17 indicating that the user U1 left the XX park at a date and time dt17 later than the date and time dt16.

In the example of FIG. 1, the acquisition unit 131 acquires the position LC18 indicating that the user U1 is at the A convenience store (shop SP1) at the date and time dt18 later than the date and time dt17. For example, the acquisition unit 131 acquires action information AC11 indicating that user U1 purchased W water at A convenience store at date and time dt18.

In the example of FIG. 2, the acquisition unit 131 acquires the position LC21 of the user U2 at the date and time dt21. Then, the acquiring unit 131 acquires a position LC22 indicating that the user U2 is inside the YY movie theater (point of interest POI2) at a date and time dt22 later than the date and time dt21. For example, the acquisition unit 131 acquires a position LC22 indicating that the user U2 is in the YY movie theater at a different position from the position LC21 at a date and time dt22 later than the date and time dt21. For example, the acquisition unit 131 acquires the position LC22 indicating that the user U2 is in the YY movie theater at the date and time dt23 later than the date and time dt22. For example, the acquisition unit 131 acquires the position LC22 indicating that the user U2 is in the YY movie theater at the date and time dt24 later than the date and time dt23. For example, the acquisition unit 131 acquires the position LC22 indicating that the user U2 is in the YY movie theater at date dt25 later than date dt24. For example, the acquisition unit 131 acquires a position LC23 indicating that the user U2 left the YY movie theater at date dt26 later than date dt25.

In the example of FIG. 2, the acquisition unit 131 acquires the position LC23 indicating that the user U2 is at the B restaurant (shop SP2) at the date and time dt26. For example, the acquisition unit 131 acquires action information AC21 indicating that the user U2 ate at restaurant B on date and time dt26.

(Extraction unit 132)
The extraction unit 132 extracts various information. For example, the extraction unit 132 extracts various information from the storage unit 120 such as the user information storage unit 121, the behavior information storage unit 122, the position information storage unit 123, the model information storage unit 124, and the like.

For example, the extraction unit 132 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information acquired by the acquisition unit 131 . For example, the extraction unit 132 extracts a plurality of continuously detected position information as a position information group.

For example, the extraction unit 132 extracts target behavior information, which is behavior information that satisfies a predetermined condition, from the behavior information of the user. For example, the extraction unit 132 extracts target behavior information after the target period. For example, the extraction unit 132 extracts the target behavior information within a predetermined range from the position corresponding to the position information at the end of the target period. For example, the extraction unit 132 extracts target behavior information before the target period. For example, the extraction unit 132 extracts the target behavior information within a predetermined range from the position corresponding to the position information at the start of the target period.

In the example of FIG. 1, the extraction unit 132 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information LC11 to LC18 of the user detected at dates dt11 to dt18. For example, the extraction unit 132 extracts a position information group that satisfies a predetermined regularity corresponding to the "behavior pattern PT1 (running)" shown in the model information storage unit 124 (see FIG. 8). For example, the extraction unit 132 extracts a position information group in which the change in the position information of the user U1 changes at a speed corresponding to running, such as 10 km/h. For example, the extraction unit 132 extracts a position information group when the user U1 is running in the XX park (point of interest POI1). For example, the extraction unit 132 extracts a position information group in which the change in the position information of the user U1 is moving around XX Park at a speed of 10 km/h, for example. For example, the extraction unit 132 extracts position information LC12 to LC16 in which the user U1 is moving around XX Park on dates dt12 to dt16.

In the example of FIG. 1, the extraction unit 132 extracts target action information, which is action information that satisfies a predetermined condition, from the user's action information outside the target period, which is the period in which the position information group was detected. For example, the extraction unit 132 extracts the target behavior information, which is behavior information that satisfies a predetermined condition, among the behavior information of the user outside the target period (dates and times dt12 to dt16) in which the position information group (position information LC12 to LC16) was detected. to extract For example, the extracting unit 132 extracts target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined period (period PD1) from the end of the target period (date and time dt16). For example, the extraction unit 132 may extract target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined range from the position LC16 at the end of the target period (date and time dt16). . For example, the extraction unit 132 extracts action information AC11 indicating that user U1 purchased W water at convenience store A at date and time dt18 within a predetermined period (period PD1) from the end of the target period (date and time dt16). Extract as information.

In the example of FIG. 2, the extraction unit 132 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information LC21 to LC23 of the user detected at dates dt21 to dt26. For example, the extraction unit 132 extracts a position information group that satisfies a predetermined regularity corresponding to the "behavior pattern PT2 (stay)" as shown in the model information storage unit 124 (see FIG. 8). For example, the extracting unit 132 extracts a position information group in which the position information of the user U2 has not changed over a predetermined period of time, for example. For example, the extraction unit 132 extracts a position information group when the user U2 is staying at the YY movie theater (point of interest POI2). For example, the extraction unit 132 extracts a position information group in which the change in the position information of the user U2 is within the YY movie theater over a predetermined period of time, for example. For example, the extraction unit 132 extracts a plurality of pieces of position information LC22 indicating that the user U2 is staying in the YY movie theater during the dates dt22 to dt25.

In the example of FIG. 2, the extraction unit 132 extracts target action information, which is action information that satisfies a predetermined condition, from the user's action information outside the target period during which the position information group was detected. For example, the extracting unit 132 extracts target action information, which is action information that satisfies a predetermined condition, among the user's action information outside the target period (dates dt22 to dt25) in which the position information group (four pieces of position information LC22) was detected. to extract For example, the extracting unit 132 extracts target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined period (period PD2) from the end of the target period (date and time dt25). For example, the extraction unit 132 may extract target action information, which is action information that satisfies a predetermined condition, from the user's action information within a predetermined range from the position LC22 at the end of the target period (date and time dt25). . For example, the extraction unit 132 extracts behavior information AC21 indicating that user U2 ate at restaurant B on date and time dt26 within a predetermined period (period PD2) from the end of the target period (date and time dt25) as the target behavior information. Extract as

(Generating unit 133)
The generation unit 133 generates various types of information. For example, the generation unit 133 generates a model from information stored in the user information storage unit 121, the behavior information storage unit 122, the position information storage unit 123, and the like. For example, the generation unit 133 generates a model used for predicting whether or not a predetermined action will occur, based on learning data including a position information group and target action information corresponding to the position information group. For example, the generation unit 133 predicts whether or not a predetermined action will occur based on learning data including the position information group stored in the position information storage unit 123 and the target action information stored in the action information storage unit 122. Generate the model used for

For example, the generation unit 133 generates models M1, M2, etc., and stores the generated models M1, M2, etc. in the model information storage unit 124 . Note that the generation unit 133 may generate the models M1, M2, etc. using any learning algorithm. For example, the generation unit 133 generates the models M1, M2, etc. using learning algorithms such as neural networks, support vector machines, clustering, and reinforcement learning. As an example, when the generating unit 133 generates the models M1, M2, etc. using a neural network, the models M1, M2, etc. are composed of an input layer including one or more neurons, an intermediate layer including one or more neurons, and one and an output layer containing the above neurons.

In the example of FIG. 1, the generation unit 133 generates a model based on the position information group and the target behavior information. For example, the generator 133 generates the model M1 based on the position information LC12 to LC16 and the action information AC11. For example, the generation unit 133 generates a model M1 that predicts whether a user whose position information group is extracted will purchase a beverage. For example, the generation unit 133 generates a model M1 that predicts whether the user will purchase a beverage after running.

In the example of FIG. 2, the generation unit 133 generates a model based on the position information group and the target behavior information. For example, the generator 133 generates the model M2 based on the four pieces of position information LC22 and the action information AC21. For example, the generation unit 133 generates a model M2 that predicts whether the user whose position information group is extracted will eat and drink. For example, the generation unit 133 generates a model M2 that predicts whether the user will eat or drink after staying.

(Prediction unit 134)
The prediction unit 134 predicts various information. For example, the prediction unit 134 predicts whether or not the user will perform a predetermined action based on the position information stored in the position information storage unit 123 . For example, the prediction unit 134 predicts whether or not the user will perform a predetermined action by inputting the position information stored in the position information storage unit 123 to the model stored in the model information storage unit 124 .

For example, the prediction unit 134 predicts the behavior of the user before and after the predetermined period based on the position information group extracted by the extraction unit 132 . For example, the prediction unit 134 predicts whether or not the user will perform a predetermined action based on the output of a model that is used to predict whether or not a predetermined action will occur, and to which the position information group is input.

For example, the prediction unit 134 inputs, to the input layer, a group of position information of the user that satisfies a predetermined regularity regarding changes in position, through information processing according to the models M1, M2, and the like. Then, the prediction unit 134 propagates the input data to the intermediate layer and the output layer, thereby outputting a score regarding whether or not a predetermined action occurs from the output layer.

In the example of FIG. 1, the prediction unit 134 estimates that the user U1 is heading to XX Park by comparing the POI information and the position LC of the user U1. For example, the prediction unit 134 may estimate the moving direction of the user based on the acceleration detected by the terminal device 10 . For example, the prediction unit 134 may appropriately use various conventional techniques to estimate the movement from the point where the position information was last detected based on the acceleration detected by the terminal device 10 .

In the example of FIG. 1, the prediction unit 134 estimates that the user U1 is heading to XX park by comparing the POI information and the change in the position LC of the user U1. For example, the prediction unit 134 estimates that the user U1 is moving toward the XX park (from the bottom to the top in FIG. 1) from the positions LC11 and LC12. For example, the prediction unit 134 estimates that the user U1 is moving in the XX park from the positions LC12 and LC13. For example, the prediction unit 134 estimates the moving speed of the user U1 from the positions LC12 and LC13. For example, the prediction unit 134 may estimate the moving speed of the user based on the acceleration detected by the terminal device 10 . For example, the prediction unit 134 estimates that the user U1 is moving in the XX park from the positions LC13 and LC14. For example, the prediction unit 134 estimates the moving speed of the user U1 from the positions LC13 and LC14. For example, the prediction unit 134 estimates that the user U1 is moving in the XX park from the positions LC14 and LC15. For example, the prediction unit 134 estimates the moving speed of the user U1 from the positions LC14 and LC15. For example, the prediction unit 134 estimates that the user U1 is moving in the XX park from the positions LC15 and LC16. For example, the prediction unit 134 estimates the moving speed of the user U1 from the positions LC15 and LC16. For example, the prediction unit 134 estimates that the user U1 is running in the XX park based on the progress of movement of the user U1 and the speed of the user U1.

In the example of FIG. 2, the prediction unit 134 estimates that the user U2 is heading to the YY movie theater by comparing the POI information and the position LC of the user U2. For example, the prediction unit 134 estimates that the user U2 is heading to the YY movie theater by comparing the POI information and the change in the position LC of the user U2. For example, the prediction unit 134 estimates that the user U2 is moving toward the YY theater (from bottom to top in FIG. 2) based on the positions LC21 and LC22. For example, the prediction unit 134 estimates that the user U2 is staying in the YY movie theater from the position LC22 obtained at the dates and times dt22 and dt23. For example, the prediction unit 134 estimates that the user U2 is staying in the YY movie theater based on the position LC22 obtained from date/time dt22 to date/time dt24. For example, the prediction unit 134 estimates that the user U2 is staying in the YY movie theater based on the position LC22 obtained from date/time dt22 to date/time dt25.

(Providing unit 135)
The providing unit 135 provides various information. For example, the providing unit 135 provides various types of information to an external device such as the terminal device 10 . For example, the providing unit 135 provides each model stored in the model information storage unit 124 to an external information processing device. For example, the providing unit 135 provides information based on the prediction result to an external information processing device. For example, the provision unit 135 may distribute an advertisement regarding a convenience store near XX park to the terminal device 10 of the user U1 who is estimated to be running in XX park. Further, for example, the providing unit 135 may distribute an advertisement regarding restaurants near the YY movie theater to the terminal device 10 of the user U2 who is estimated to be staying in the YY movie theater.

For example, the providing unit 135 may provide a predetermined service provider with information regarding the location information group extracted by the extracting unit 132 . Further, for example, the providing unit 135 may provide information regarding the model generated by the generating unit 133 to an external information processing device. Further, for example, the providing unit 135 may provide information output by the model to an external information processing device. Note that the above is just an example, and the providing unit 135 may provide various types of information based on the position information group extracted by the extracting unit 132 to an external information processing device.

[3. Extraction process flow]
Next, a procedure of extraction processing by the extraction system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of extraction processing according to the embodiment. Also, the extraction processing shown in FIG. 9 includes processing for extracting target behavior information and generating a model.

As shown in FIG. 9, the extraction device 100 acquires a plurality of pieces of location information of a user detected during a predetermined period (step S101). For example, the extraction device 100 acquires a history of position information as shown in the position information storage unit 123 (see FIG. 7). In the example of FIG. 1, the extraction device 100 acquires from the terminal device 10 the location information LC11 to LC18 detected during the dates and times dt11 to dt18.

The extraction device 100 also extracts a position information group that satisfies a predetermined regularity regarding changes in position (step S102). For example, the extraction device 100 extracts a position information group that satisfies a behavior pattern PT1 regarding movement as shown in the model information storage unit 124 (see FIG. 8). In the example of FIG. 1, the extraction device 100 extracts a position information group (position information LC12 to LC16) corresponding to positions traveling around the XX park from among the position information LC11 to LC18.

In addition, the extraction device 100 extracts target behavior information that satisfies a predetermined condition from the behavior information of the user (step S103). For example, the extraction device 100 extracts the target behavior information after the target period (dates dt12 to dt16) from the behavior history shown in the behavior information storage unit 122 (see FIG. 6). In the example of FIG. 1, the extraction device 100 extracts action information AC11 indicating that W water was purchased at A convenience store on date and time dt18.

Then, the extraction device 100 generates a model used for predicting whether or not a predetermined action will occur, based on the position information group and the target action information (step S104). For example, the extraction device 100 generates a model M1 corresponding to the behavior pattern PT1 as shown in the model information storage unit 124 (see FIG. 8). In the example of FIG. 1, the extraction device 100 generates the model M1 using the position information LC12 to LC16 and the action information AC11 corresponding to the position information LC12 to LC16 as correct information.

[4. effect〕
As described above, the extraction device 100 according to the embodiment has the acquisition unit 131 and the extraction unit 132 . Acquisition unit 131 acquires a plurality of pieces of location information of a user detected during a predetermined period. The extraction unit 132 extracts a position information group that satisfies a predetermined regularity regarding changes in position from among the plurality of pieces of position information acquired by the acquisition unit 131 .

As described above, the extraction device 100 according to the embodiment extracts a group of position information that satisfies a predetermined regularity regarding changes in position from among a plurality of pieces of position information of the user, thereby appropriately extracting user information that satisfies the regularity. can be extracted to

In addition, in the extraction device 100 according to the embodiment, the extraction unit 132 extracts a plurality of continuously detected position information as a position information group.

As described above, the extraction device 100 according to the embodiment can appropriately extract user information that satisfies the regularity by extracting a plurality of pieces of continuously detected position information as a position information group.

Also, the extraction device 100 according to the embodiment has a prediction unit 134 . The prediction unit 134 predicts the behavior of the user before and after the predetermined period based on the position information group extracted by the extraction unit 132 .

As described above, the extraction device 100 according to the embodiment can appropriately predict the user's behavior by predicting the user's behavior before and after the predetermined period based on the extracted position information group.

In addition, in the extraction device 100 according to the embodiment, the prediction unit 134 is a model used for predicting whether or not a predetermined action will occur, and based on the output of the model to which the position information group is input, the user's predetermined Predict the presence or absence of action.

As described above, the extraction device 100 according to the embodiment is a model used for predicting whether or not a predetermined action will occur. By predicting the user's behavior can be appropriately predicted.

In addition, in the extraction device 100 according to the embodiment, the acquisition unit 131 acquires the user's behavior information outside the target period, which is the period during which the position information group was detected. The extraction unit 132 extracts target behavior information, which is behavior information that satisfies a predetermined condition, from the behavior information of the user.

As described above, the extraction device 100 according to the embodiment extracts target action information, which is action information that satisfies a predetermined condition, from the user's action information outside the target period, which is the period in which the position information group is detected. Therefore, it is possible to appropriately extract user information that satisfies the regularity.

In addition, in the extraction device 100 according to the embodiment, the extraction unit 132 extracts target behavior information after the target period.

In this way, the extraction device 100 according to the embodiment can appropriately extract user information that satisfies the regularity by extracting the target behavior information after the target period.

In addition, in the extraction device 100 according to the embodiment, the extraction unit 132 extracts the target behavior information within a predetermined range from the position corresponding to the position information at the end of the target period.

As described above, the extraction device 100 according to the embodiment extracts the target behavior information within a predetermined range from the position corresponding to the position information at the end of the target period, thereby appropriately extracting user information that satisfies the regularity. can be extracted.

In addition, in the extraction device 100 according to the embodiment, the extraction unit 132 extracts target behavior information before the target period.

In this way, the extraction device 100 according to the embodiment can appropriately extract user information that satisfies the regularity by extracting the target behavior information before the target period.

In addition, in the extraction device 100 according to the embodiment, the extraction unit 132 extracts the target behavior information within a predetermined range from the position corresponding to the position information at the start of the target period.

As described above, the extraction device 100 according to the embodiment extracts the target behavior information within a predetermined range from the position corresponding to the position information at the start of the target period, thereby appropriately extracting user information that satisfies the regularity. can be extracted.

Further, the extraction device 100 according to the embodiment has a generator 133 . The generation unit 133 generates a model used for predicting whether or not a predetermined action will occur, based on learning data including a position information group and target action information corresponding to the position information group.

As described above, the extraction device 100 according to the embodiment generates a model used for predicting whether or not a predetermined action will occur, based on learning data including a position information group and target action information corresponding to the position information group. By doing so, it is possible to appropriately predict the behavior of the user.

[5. Hardware configuration]
The extraction device 100 according to the above-described embodiments is implemented by a computer 1000 configured as shown in FIG. 10, for example. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the extraction device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a 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 programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending 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. Communication interface 1500 receives data from other devices via network N, sends the data to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N. FIG.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via 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 a PD (Phase change rewritable disc), 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 extraction device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a program or data (for example, models M1, M2, etc.) loaded on the RAM 1200 to control the control unit 130 to realize the function of The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, models M1, M2, etc.) from the recording medium 1800. As another example, these programs are obtained from other devices via the network N. You may

As described above, some of the embodiments of the present application have been described in detail based on the drawings, but these are merely examples, and various modifications, It is possible to carry out the invention in other forms with modifications.

[6. others〕
Further, among the processes described in the above embodiments, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being performed manually can be performed manually. All or part of this can also be done automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Further, each process described in each embodiment described above can be appropriately combined within a range in which the contents of the process are not inconsistent.

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

1 extraction system 100 extraction device 121 user information storage unit 122 action information storage unit 123 position information storage unit 124 model information storage unit 130 control unit 131 acquisition unit 132 extraction unit 133 generation unit 134 prediction unit 135 provision unit 10 terminal device N network

Claims (12)

an acquisition unit that acquires a plurality of location information of a user detected during a predetermined period;
Predetermined regularity regarding positional changes among the plurality of pieces of positional information obtained by the obtaining unit, the predetermined rule indicating to the user that a moving speed corresponds to running based on the positional changes. an extraction unit that extracts a group of position information that satisfies the requirements and indicates that the user is circling a predetermined range ;
a providing unit that provides a service of distributing advertisements to the user running in the predetermined range based on the position information group;
An extraction device comprising: The extractor is
2. The extracting device according to claim 1, wherein a plurality of continuously detected positional information are extracted as said positional information group. a prediction unit that predicts behavior of the user before and after the predetermined period based on the position information group extracted by the extraction unit;
3. A brewing device according to claim 1 or claim 2, further comprising: The prediction unit
A model used for predicting whether or not a predetermined action will occur, wherein the model predicts whether or not the user will perform the predetermined action based on the output of the model to which the position information group is input. 3. The extraction device according to 3. The acquisition unit
Acquiring the behavior information of the user during a period other than the target period, which is the period during which the position information group is detected;
The extractor is
The extracting device according to any one of claims 1 to 4, wherein target action information, which is action information that satisfies a predetermined condition, is extracted from the user's action information. The extractor is
6. The extracting device according to claim 5, wherein the target behavior information after the target period is extracted. The extractor is
7. The extracting device according to claim 6, wherein the target action information is extracted within a predetermined range from a position corresponding to position information at the end of the target period. The extractor is
The extracting device according to any one of claims 5 to 7, wherein the target behavior information before the target period is extracted. The extractor is
9. The extraction device according to claim 8, wherein the target action information is extracted within a predetermined range from a position corresponding to position information at the start of the target period. a generation unit that generates a model to be used for predicting whether or not a predetermined action will occur, based on learning data including the position information group and the target action information corresponding to the position information group;
The extraction device according to any one of claims 5 to 9, further comprising: A computer implemented extraction method comprising:
an obtaining step of obtaining a plurality of location information of the user detected over a predetermined period of time;
Predetermined regularity regarding changes in position among the plurality of pieces of position information obtained by the obtaining step, the predetermined rule indicating to the user that the movement speed corresponds to running based on the change in position. an extracting step of extracting a position information group that satisfies the requirements and indicates that the user is circling a predetermined range ;
a providing step of providing a service of distributing advertisements to the user running in the predetermined range based on the position information group;
An extraction method comprising: an acquisition procedure for acquiring a plurality of location information of a user detected over a predetermined period of time;
Predetermined regularity regarding changes in position among the plurality of pieces of position information obtained by the obtaining procedure, the predetermined rule indicating to the user that the movement speed corresponds to running based on the change in position. an extraction procedure for extracting a position information group that satisfies the requirements and indicates that the user is circling a predetermined range ;
a providing step of providing a service of distributing advertisements to the user running in the predetermined range based on the position information group;
An extraction program characterized by causing a computer to execute

Images