JP2013008289A - Behavior pattern generation apparatus, behavior pattern generation method and behavior pattern generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately extract the behavior of a user.SOLUTION: A basic behavior pattern identification section 230 individually deploys positional information items, acquired from a life log storage section 210, within the same day on the space-time having temporal periodicity of 24 hours and calculates an approximation curve approximating each of the deployed positional information items for each date. The basic behavior pattern identification section 230 then deploys positional information items which become sources of approximation curves similar to each other, from among the approximation curves of each date, on the space-time again, calculates an approximation curve approximating each of the deployed positional information items and identifies a trajectory indicated by the calculated approximation curve as a basic behavior pattern indicating the trajectory of basic behaviors of a user.

Description

  The present invention relates to a behavior pattern generation device, a behavior pattern generation method, and a behavior pattern generation program.

  Conventionally, time series data mining is known as a technique for extracting frequent patterns from a large amount of time series data. By using this time series data mining, for example, purchase data including customer ID, purchased product and purchase date and time can be recorded, and typical product purchase patterns by customers can be extracted from a large amount of purchase data. it can. For example, a product purchase pattern extracted using time-series data mining is useful for product sales strategies, corporate product development, and the like.

  In addition, recently, a method has been proposed in which time-series data mining is used not only for extracting a product purchase pattern as described above but also for extracting an action pattern representing a transition of a user's place of stay. For example, a method has been proposed in which time series data mining is used to extract time series information of a user's place of stay from user's place of stay information, stay start time or stay end time of the stay place (for example, Patent Literature 1). In addition, for example, a method of extracting a place where a user stays from GPS (Global Positioning System) received data mounted on a mobile terminal possessed by the user using time series data mining has been proposed (for example, Non-Patent Document 1).

JP 2010-191589 A

Daniel Ashbrook, Thad Starner, College Of Computing Georgia Institute of Technology, “Using GPS to Learn Significant Locations and Predict Movement Across Multiple Users”, Personal and Ubiquitous Computing, 2003

  For example, in the above-described method for extracting the behavior pattern representing the transition of the user's place of stay, when the behavior pattern moving in the order of “A point → B point → C point” is extracted, “A point, B point, C point” In other words, the user's behavior pattern during the movement from “B point” to “C point” cannot be extracted. Thus, in the method for extracting the behavior pattern described above, it is only possible to obtain discrete information representing the user's staying point in time series, and the behavior pattern of the moving user is accurately identified. Is not necessarily true. Therefore, it is also impossible to provide a service according to the behavior of the user who moves between the points extracted as the behavior pattern.

  Human behavior includes discrete behavior such as purchasing behavior and continuous behavior such as mobile behavior. Should be understood as having continuous continuity. Therefore, in the case of extracting human behavior patterns, it is expected to develop a technique for extracting continuous action data along a time axis including a moving action pattern instead of extracting as discrete data.

  The present invention has been made in view of the above, and an object of the present invention is to provide a behavior pattern generation device, a behavior pattern generation method, and a behavior pattern generation program that can accurately specify a user's behavior.

  In order to solve the above-described problems and achieve the object, the present invention relates to a receiving unit that receives user position information, the user who stores the position information and time information at the time of receiving the position information in association with each other. Acquires position information stored in the information storage unit and the user information storage unit, and expands the acquired position information on the same day individually on a time space having a time periodicity of 24 hours and expands A calculation unit for calculating each approximated position information for each date, and the approximate curve for each date calculated by the calculation unit, which is the source of the approximate curves similar to each other. The position information is newly developed on the space-time, an approximate curve that approximates each of the developed position information is calculated, and the trajectory indicated by the calculated approximate curve is the basic action that indicates the trajectory of the basic action of the user. As a pattern And having a specifying unit configured to specify.

  Further, the present invention is the behavior pattern generation method performed by the computer according to the above-described invention, comprising: a position information receiving step for receiving user position information; the position information; and time information at the time of receiving the position information. The position information acquired from the user information storage unit stored in association with each other on the same day is individually expanded on a time space having a time periodicity of 24 hours, and each of the expanded position information is approximated. A calculation step of calculating an approximate curve for each date, and the position information that is the basis of the approximate curves similar to each other from the approximate curves of the dates calculated by the calculation step are re-applied on the space-time. An approximate curve that expands and approximates each of the expanded position information is calculated, and the trajectory indicated by the calculated approximate curve is specified as a basic action pattern indicating the trajectory of the user's basic behavior. Characterized in that it comprises a specifying step of.

  Further, the present invention is an action pattern generation program to be executed by a computer, the computer comprising: a position information receiving procedure for receiving position information of a user; the position information; and time information at the time of receiving the position information. The position information acquired from the user information storage unit stored in association with each other on the same day is individually expanded on a time space having a time periodicity of 24 hours, and each of the expanded position information is approximated. From the calculation procedure for calculating the approximate curve for each date and the approximate curve of each date calculated by the calculation procedure, the position information that is the basis of the approximate curves that are similar to each other is re-applied on the space-time. An approximate curve that expands and approximates each of the expanded position information is calculated, and a trajectory indicated by the calculated approximate curve is represented as a basic action pattern indicating a trajectory of a basic action of the user. Characterized in that to execute a specific procedure for identifying a down.

  According to the present invention, there is an effect that a user's action can be specified with high accuracy.

FIG. 1 is a functional block diagram illustrating the configuration of the behavior pattern generation device according to the first embodiment. FIG. 2 is a diagram illustrating an example of a basic action pattern. FIG. 3 is a diagram illustrating an example of behavior pattern data. FIG. 4 is a diagram illustrating an example of user position determination. FIG. 5 is a diagram illustrating a flow of behavior pattern generation processing according to the first embodiment. FIG. 6 is a diagram illustrating a flow of user position determination processing according to the first embodiment. FIG. 7 is a diagram illustrating an example of a computer that executes an action pattern generation program.

  Hereinafter, an embodiment of an action pattern generation device, an action pattern generation method, and an action pattern generation program disclosed in the present application will be described in detail with reference to the drawings. Each example described later is merely an embodiment, and does not limit the behavior pattern generation device, the behavior pattern generation method, and the behavior pattern generation program disclosed in the present application. In addition, the embodiments described later can be appropriately combined within a range that does not cause a contradiction in the processing contents.

[Configuration of Action Pattern Generation Device (Example 1)]
FIG. 1 is a functional block diagram illustrating the configuration of the behavior pattern generation device according to the first embodiment. As illustrated in FIG. 1, the behavior pattern generation device 200 according to the first embodiment is in a state where it can communicate with a plurality of user devices 100 via the network 1.

  The user device 100 is a device carried by the user, and is, for example, a mobile phone, a smartphone, or a PHS (Personal Handy-phone System). The user apparatus 100 is equipped with, for example, a GPS (Global Positioning System). And the user apparatus 100 transmits the positional information (latitude and longitude) acquired by GPS to the action pattern generation apparatus 200 sequentially.

  As shown in FIG. 1, the behavior pattern generation device 200 includes a life log storage unit 210, a reception unit 220, a basic behavior pattern specification unit 230, a behavior pattern generation unit 240, a display unit 250, and a determination unit 260. And a notification unit 270. The behavior pattern generation apparatus 200 can be implemented by an information processing apparatus such as a personal computer or a server.

  The life log storage unit 210 stores, for each user of the user device 100, log information related to the user's staying point. Specifically, for each user, the life log storage unit 210 stores the position information (latitude and longitude) received from the user terminal 100, the time information when the position information is received, and the user action content corresponding to the time information. Log information associated with the action information shown is stored. Note that the user's behavior information is information written by the user himself / herself to a scheduler or ToDo list published by the behavior pattern generation device 200, and corresponds to information such as going to work, going to work, lunch, leaving work, returning home, etc. To do. When storing the log information in the life log storage unit 210, the behavior pattern generation apparatus 200 acquires the behavior information of each user from a scheduler, a ToDo list, and the like, and associates the information with each user.

  In the life log storage unit 210, log information sufficient for specifying a basic action pattern by a basic action pattern specifying unit 230 (to be described later) and generating an action pattern by the action pattern generating unit 240 is stored.

  The receiving unit 220 receives position information transmitted from the user device 100 as needed. Then, the receiving unit 220 stores the received position information in the life log storage unit 210 in association with the position information reception time.

  The basic action pattern specifying unit 230 specifies the basic action pattern indicating the basic action of each user carrying the user terminal 100, in other words, the most likely one as the movement trajectory of the user. Specifically, the basic behavior pattern specifying unit 230 develops the position information acquired from the life log storage unit 210 on the same day individually on a time space having a time periodicity of 24 hours. An approximate curve that approximates each piece of position information is calculated for each date. Then, the basic behavior pattern specifying unit 230 develops the position information that is the basis of the approximate curves that are similar to each other from the approximate curves of each date, and expands them in time space, and approximates each of the developed position information. A curve is calculated, and the trajectory indicated by the calculated approximate curve is specified as a basic behavior pattern indicating a trajectory of the user's basic behavior. Hereinafter, the processing of the basic action pattern specifying unit 230 will be described with reference to FIGS. 2 and 3. FIG. 2 is a diagram illustrating an example of a basic action pattern. FIG. 3 is a diagram illustrating an example of behavior pattern data.

  First, the basic action pattern specifying unit 230 obtains, from the life log storage unit 210, log information within a certain setting period for a certain user and within a set range with a departure point, departure time, return point, and return time. Get all. For example, the basic action pattern specifying unit 230 acquires all the log information in April to July that has an error between points within a few meters and an error between times within a few minutes. For example, the basic action pattern specifying unit 230 sets the log information satisfying the conditions as April 1, April 4, April 9, May 5, May 7, May 9, June. Log information for 9th and 7th July is acquired.

  Subsequently, the basic action pattern specifying unit 230 develops it on a time space having a time periodicity of 24 hours with the position information included in the acquired log information of one day (for example, April 1) as a coordinate point. (Plot). Subsequently, the basic action pattern specifying unit 230 calculates an approximate curve that approximates a set of points plotted on the space-time, and sets it as an action pattern for a certain day (for example, April 1). For example, the basic behavior pattern specifying unit 230 calculates an approximate curve that best approximates a continuous curve in which only one point is determined for each point on the time axis, and the trajectory indicated by the calculated approximate curve. A behavior pattern of a certain day (for example, April 1) is assumed. Note that the basic behavior pattern specifying unit 230 can calculate an approximate curve using approximation by a least square method, linear approximation, logarithmic approximation, polynomial approximation, exponential approximation, moving average, or the like.

  Similarly, the basic action pattern specifying unit 230 also calculates approximate curves for the acquired log information of other days, and sets the calculated approximate curve trajectory as the action pattern for each day.

  Subsequently, the basic behavior pattern specifying unit 230 compares the approximate curves indicating the daily behavior patterns described above with each other, and those whose errors between the approximate curves are within a predetermined range belong to the same category. Log information acquired from the log storage unit 210 is classified. For example, the basic action pattern specifying unit 230 compares the approximate curve indicating the April 1 action pattern with the approximate curve indicating the April 4 action pattern, and if the error is within a predetermined range. The log information on April 1 and the log information on April 4 are classified into the same category. Also, the behavior pattern of April 1 and the remaining days (behavior patterns of April 9, May 5, May 7, May 9, June 9, and July 7) And categorize log information. Similarly, the basic behavior pattern specifying unit 230 performs the behavior pattern of April 4 and the remaining other days (April 9, May 5, May 7, May 9, June 9). , The behavior pattern of July 7) and the behavior pattern of April 9 and the remaining days (May 5, May 7, May 9, June 9) The behavioral pattern on July 7 is compared with the brute force, and the log information is classified. In addition, when calculating the error between the approximate curves described above, the basic behavior pattern specifying unit 230 compares the values of the curves at the same time every certain time and takes the average error. For example, when calculating an error by comparing curve values every 30 minutes, the basic behavior pattern specifying unit 230 compares the curve values at time “00:00” to obtain an error, and then calculates the time “00 The calculation of the error every 30 minutes is repeated such that the error is obtained by comparing the values of the curve of “: 30”. Subsequently, the basic action pattern specifying unit 230 divides the calculated total sum of errors by the total number of comparisons (48 for one day in the case of every 30 minutes), and this is used as an error between approximate curves. . For example, if the error between the calculated approximate curves is within 20 m, for example, the basic behavior pattern specifying unit 230 determines that they belong to the same category.

  Subsequently, the basic behavior pattern specifying unit 230 specifies the category having the largest number of classified log information. Subsequently, the basic action pattern specifying unit 230 regards log information belonging to the specified category as a set of log information of the basic action pattern, and plots the position information included in the log information as a coordinate point on the time space. Then, the basic action pattern specifying unit 230 calculates an approximate curve that approximates the plotted position information, and specifies the trajectory indicated by the calculated approximate curve as the basic action pattern.

  For example, as illustrated in FIG. 2, the basic action pattern specifying unit 230 uses the position information included in the log information of the basic action pattern as “T: periodic time axis”, “E: spatial axis 1 (for example, latitude). ”And“ N: space axis 2 (for example, longitude) ”. Then, the basic action pattern specifying unit 230 calculates an approximate curve that approximates the plotted position information, and specifies the trajectory indicated by the calculated approximate curve as the basic action pattern. In FIG. 2, the approximate curve indicating the basic action pattern seems to move the user only in the direction of “E: space axis 1”, but this is for convenience of explanation.

  Based on the time information, the behavior pattern generation unit 240 generates behavior pattern data in which the behavior information of the user is associated on the approximate curve of the basic behavior pattern identified by the basic behavior pattern identification unit 230. Specifically, the behavior pattern generation unit 240 applies each point on the approximate curve of the basic behavior pattern that is the same time as the time indicated by the time information associated with the behavior information in the life log storage unit 210. Action pattern data associated with action information is generated.

  For example, as illustrated in FIG. 3, the behavior pattern generation unit 240 generates behavior pattern data in which behavior information such as going to work, going to work, lunch, leaving work, and returning home is associated with the approximate curve indicating the basic behavior pattern.

  As described above, the basic behavior pattern specifying unit 230 and the behavior pattern generation unit 240 generate a basic behavior pattern and behavior pattern data for each user. And the basic action pattern specific | specification part 230 sets the basic action pattern specified for every user as data used for the determination of the determination part 260 mentioned later.

  The display unit 250 transmits the behavior pattern generated by the behavior pattern generation unit 240 to a computer used by the user and provides it to the user. By doing in this way, a user can be made to grasp | ascertain own action at a glance. Note that the display unit 250 can also accept corrections and additional notes from the user with respect to the behavior information of the behavior pattern data.

  The determination unit 260 compares the position information indicating the current position of the user with the action pattern, and determines whether or not the user's current position is out of the action pattern. Hereinafter, the determination of the user position will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of user position determination. The determination unit 260 calculates the distance between the user's current position (observation user position) indicated by the position information and the corresponding position in the basic action pattern. For example, as illustrated in FIG. 4, the calculated distance is a fixed distance. It is determined whether or not (predetermined threshold) or more.

  For example, as illustrated in FIG. 4 described above, the notification unit 270 determines that the determination unit 260 determines that the distance between the current position of the user and the corresponding position based on the action pattern is equal to or greater than a predetermined threshold. The user is notified that it is out of the basic action pattern. For example, if the user on the train has fallen asleep without getting off the train at the next stop station, the user's current position deviates from the behavior pattern, so the notification unit 270 notifies the user. Will do. In this way, for example, it is possible to discover a situation where the user's behavior is different from the daily life, such as getting over the train, and inform the user.

[Processing by Action Pattern Generation Device (Example 1)]
The flow of processing performed by the behavior pattern generation device according to the first embodiment will be described with reference to FIGS. 5 and 6. FIG. 5 is a diagram illustrating a flow of behavior pattern generation processing according to the first embodiment. FIG. 6 is a diagram illustrating a flow of user position determination processing according to the first embodiment.

[Behavior pattern generation processing]
First, the flow of action pattern generation processing will be described with reference to FIG. The behavior pattern generation process illustrated in FIG. 5 is executed for each user by receiving a processing instruction from the administrator of the behavior pattern generation apparatus 200 together with a behavior pattern generation condition (such as a setting period and a setting range), for example. In addition, you may make it receive from a management to selection of the user made into a process target.

  As illustrated in FIG. 5, the basic behavior pattern specifying unit 230 acquires all log information satisfying a predetermined setting condition from a life log storage unit 210 for a certain user (S101). Subsequently, the basic behavior pattern specifying unit 230 plots the position information included in the log information for one day from the log information acquired in S101 on the space-time (S102).

  Subsequently, the basic behavior pattern specifying unit 230 calculates an approximate curve that approximates a set of points plotted on the space-time, and sets the behavior pattern as a certain day (S103). Subsequently, the basic action pattern specifying unit 230 determines whether or not an action pattern has been created from all log information acquired in S101 (S104). As a result of the determination, when the action pattern is not generated from all the log information (No in S104), the process returns to S101 described above and the generation of the action pattern is continued.

  On the other hand, when the action pattern is generated from all the log information as a result of the determination (S104, Yes), the basic action pattern specifying unit 230 compares the approximate curves of the action patterns with each other, and the error is within a predetermined range. The log information acquired in S101 is classified into the same category (S105).

  Subsequently, the basic action pattern specifying unit 230 specifies the category having the largest number of log information classified in S105 (S106). Subsequently, the basic action pattern specifying unit 230 plots the log information belonging to the category specified in S105 anew on the space-time (S107).

  Subsequently, the basic action pattern specifying unit 230 calculates an approximate curve that approximates the position information plotted in S107, and specifies a trajectory indicated by the calculated approximate curve as a basic action pattern (S108). And the action pattern data which linked | related action information with each point on the approximate curve of the basic action pattern which is the same time as the time which the time information matched with action information shows is produced | generated (S109), and a process is complete | finished To do.

[User position determination processing]
Subsequently, the flow of the user position determination process will be described with reference to FIG. The user position determination process illustrated in FIG. 6 is started by detecting the activated user terminal 100 and receiving position information indicating the current position from the activated user terminal 100.

  As illustrated in FIG. 6, when the determination unit 260 receives position information indicating the current position of the user (S201), the determination unit 260 displays the basic action pattern of the user carrying the user terminal 100 that is the transmission source of the position information received in S101. Obtain (S202).

  Subsequently, the determination unit 260 calculates the distance between the current position of the user and the corresponding position of the basic action pattern (S203). Subsequently, the determination unit 260 calculates the distance between the current position of the user indicated by the position information and the corresponding position in the basic action pattern, and determines whether the calculated distance is equal to or greater than a certain distance (predetermined threshold). Determine (S204).

  If the determination unit 260 determines that the distance between the current position of the user and the corresponding position in the basic action pattern is equal to or greater than a certain distance (S204, Yes), the notification unit 280 deviates from the basic action pattern. To the user (S205). On the other hand, when the determination unit 260 determines that the distance between the current position of the user and the corresponding position in the basic action pattern is less than a certain distance (No in S204), the user position determination process is performed in S201 described above. Return to.

[Effects of Example 1]
As described above, the behavior pattern generation device 200 individually develops the position information of the user on the same day on a time space having a time periodicity of 24 hours, and extracts each of the developed position information. An approximate curve to be approximated is calculated for each date. Then, the behavior pattern generation device 200 develops the position information that is the basis of the approximate curves that are similar to each other from the approximate curves for each date, and develops the approximate information for each of the developed position information. And the trajectory indicated by the calculated approximate curve is specified as the basic behavior pattern indicating the trajectory of the basic behavior of the user. As described above, according to the first embodiment, it is possible to identify the moving user's action pattern with high accuracy by specifying the most probable movement locus of the user. In other words, according to the first embodiment, the user's behavior pattern is not captured as discrete time-series information including the place of stay and the stay time information as in the past, but the user's presence position information and its position are By capturing it as trajectory information in space-time composed of time information when the user is present, the action pattern of the moving user can be accurately identified.

  Also, in the first embodiment, log information that satisfies a predetermined condition, for example, log information within a certain setting period and that is within a set range with a departure point, departure time, return point, and return time is a life log. All are acquired from the storage unit 210. For example, in the first embodiment, all log information in April to July is acquired with an error between points within a few meters and an error between times within a few minutes. In other words, in the first embodiment, only the log information satisfying the predetermined condition is acquired and the approximate curve is calculated, so that data that lowers the specific accuracy of the basic action pattern can be selected in advance. It is not necessarily limited to acquiring log information that satisfies both the setting period and the setting range. For example, only log information that satisfies the setting range is acquired from all log information of the user. You can also.

  In the first embodiment, when the distance between the current position of the user and the corresponding position in the basic action pattern is equal to or larger than a predetermined threshold, that is, when the position of the user is out of the basic action pattern, Notify the user to that effect. For this reason, for example, it is possible to discover a situation in which the user's behavior is different from the day-to-day, such as getting over the train, and to inform the user.

  Moreover, in Example 1, the action pattern data which linked | related basic action pattern and action information are produced | generated, and it provides to a user. From such a thing, a user can be made to grasp | ascertain own action at a glance.

  In the first embodiment, a case has been described in which log information satisfying predetermined conditions (setting period and setting range) is acquired and a basic action pattern is specified. In other words, the case where the basic action pattern under a predetermined condition is specified has been described. For example, if the log information is sufficiently accumulated, the basic action pattern is specified in more detailed units, such as every day or every week. It can also be used to specify basic behavior patterns in special cases such as holidays.

  Hereinafter, Example 2 will be described as another embodiment of the behavior pattern generation device, the behavior pattern generation method, and the behavior pattern generation program according to the present invention.

(1) Device Configuration, etc. Each component of the behavior pattern generation device 200 shown in FIG. 1 is functionally conceptual and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution or integration of the behavior pattern generation device 200 is not limited to the illustrated one, and for example, the basic behavior pattern specifying unit 230 and the determination unit 260 may be integrated functionally or physically. As described above, all or some of the constituent elements of the behavior pattern generation device 200 may be configured to be functionally or physically distributed / integrated in arbitrary units according to various loads or usage conditions. it can.

(2) Action pattern generation program Various processes (see, for example, FIGS. 5 and 6) of the action pattern generation apparatus 200 described in the first embodiment are performed by using a program such as a personal computer or a workstation. It can be realized by executing with. Therefore, an example of a computer that executes an action pattern generation program having the same function as that of the action pattern generation apparatus 200 described in the first embodiment will be described below with reference to FIG. FIG. 7 is a diagram illustrating an example of a computer that executes an action pattern generation program.

  As illustrated in FIG. 7, a computer 300 having functions similar to the functions of the behavior pattern generation device 200 includes, for example, a memory 301 and a CPU (Central Processing Unit) 302. Further, the computer 300 includes a hard disk drive interface 303 and an optical disk drive interface 304 as shown in FIG. As shown in FIG. 7, the computer 300 includes a serial port interface 305, a video adapter 306, and a network interface 307. The computer 300 connects these units 301 to 307 via a bus 308.

  As shown in FIG. 7, the memory 301 includes a ROM (Read Only Memory) and a RAM (Random Access Memory). The ROM stores a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 303 is connected to the hard disk drive 309 as shown in FIG. The optical disc drive interface 304 is connected to the optical disc drive 310 as shown in FIG. For example, a removable storage medium such as an optical disk is inserted into the optical disk drive 310. As shown in FIG. 7, the serial port interface 305 is connected to, for example, a mouse 400 and a keyboard 500. As shown in FIG. 7, the video adapter 306 is connected to a display 600, for example.

  Here, as shown in FIG. 7, the hard disk drive 309 stores, for example, an OS (Operating System), an application program, a program module, and program data.

  That is, an action pattern generation program having the same function as that of the action pattern generation apparatus 200 described above is stored in, for example, the hard disk drive 309 as a program module in which a command executed by the computer 300 is described. That is, a program module describing a procedure for executing the same processing (FIG. 5, FIG. 6, etc.) as the behavior pattern generation device 200 described in the first embodiment is stored in the hard disk drive 309. For example, in this program module, a procedure for executing the same processing as the basic behavior pattern specifying unit 230, the behavior pattern generation unit 240, the determination unit 260 and the like described above is described.

  Data used for processing by the behavior pattern generation program is stored as program data, for example, in the hard disk drive 309. For example, the program data corresponds to various information stored in the life log storage unit 210 described in the first embodiment.

  Then, the CPU 302 reads the program module and program data stored in the hard disk drive 309 to the RAM as necessary, and executes the same processing (FIGS. 5, 6, etc.) as described in the first embodiment. Follow the steps for:

  The program modules and program data related to the behavior pattern generation program are not limited to being stored in the hard disk drive 309, and may be stored in, for example, the optical disk drive 310 that is a removable storage medium. . In this case, the CPU 302 reads program modules and program data related to the behavior pattern generation program via the optical disc drive 310. Or the program module and program data which concern on an action pattern generation program may be memorize | stored in the other computer connected via networks (LAN (Local Area Network), WAN (Wide Area Network), etc.). In this case, the CPU 302 reads program modules and program data related to the behavior pattern generation program from another computer via the network interface 307.

  Instead of the CPU 302 operating by a program to perform various processes, for example, the process can be performed using an electronic circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). Further, a flash memory or the like can be used as the memory 301.

(3) Behavior pattern generation method The behavior pattern generation method as described below is realized by the behavior pattern generation device 200 described in the first embodiment.

  That is, a behavior pattern generation method performed by a computer, which is acquired from a storage unit that stores a location information reception step for receiving location information of a user, the location information, and time information at the time of reception of the location information in association with each other. Among the above-mentioned position information, those on the same day are individually developed on a time space having a time periodicity of 24 hours, and an approximate curve that approximates each of the developed position information is calculated for each date. Steps (for example, S102 to S104 in FIG. 5), and the position information that is the basis of the approximate curves similar to each other among the approximate curves of the dates calculated by the calculation step is developed again on the space-time. Then, an approximate curve that approximates each of the developed position information is calculated, and the trajectory indicated by the calculated approximate curve is specified as a basic action pattern indicating the trajectory of the basic action of the user That particular step and (see, e.g., S108 of FIG. 5) behavior pattern generation method comprising realized.

DESCRIPTION OF SYMBOLS 1 Network 100 User apparatus 200 Behavior pattern production | generation apparatus 210 Life log memory | storage part 220 Reception part 230 Basic behavior pattern specific | specification part 240 Behavior pattern generation part 250 Display part 260 Judgment part 270 Notification part 300 Computer 301 Memory 302 CPU
303 Hard Disk Drive Interface 304 Optical Disk Drive Interface 305 Serial Port Interface 306 Video Adapter 307 Network Interface 308 Bus 309 Hard Disk Drive 310 Optical Disk Drive 400 Mouse 500 Keyboard 600 Display

Claims (6)

A receiving unit for receiving user location information;
A user information storage unit that stores the position information and time information at the time of receiving the position information in association with each other;
The position information stored in the user information storage unit is acquired, and among the acquired position information, those on the same day are individually developed on a time space having a time periodicity of 24 hours, A calculating unit that calculates an approximate curve that approximates each of the dates, and
Approximation for approximating each of the developed position information by re-developing the position information on the basis of mutually similar approximate curves from the approximate curves for each date calculated by the calculation unit. An action pattern generation apparatus comprising: a specifying unit that calculates a curve and specifies a trajectory indicated by the calculated approximate curve as a basic action pattern indicating a user's basic action trajectory.   The calculation unit acquires only the position information satisfying a predetermined condition from the position information stored in the user information storage unit, and individually develops the approximate curve on each date. The behavior pattern generation device according to claim 1, wherein the behavior pattern generation device calculates each of the behavior patterns. A determination unit that calculates a distance between a current position of the user indicated by the position information and a corresponding position in the basic action pattern, and determines whether the calculated distance is equal to or greater than a predetermined threshold;
The behavior pattern generation device according to claim 2, further comprising: a notification unit configured to notify the user when the determination unit determines that the distance is greater than or equal to a predetermined threshold. . The user information storage unit further stores action information indicating a user action content corresponding to the time information,
A generating unit that generates behavior pattern data associated with the behavior information stored in the user information storage unit on the approximate curve identified as the basic behavior pattern by the identifying unit;
The behavior pattern generation device according to claim 1, further comprising: a display unit that transmits the behavior pattern data generated by the generation unit to a device used by a user. A behavior pattern generation method performed by a computer,
A location information receiving step for receiving location information of the user;
Among the position information acquired from the user information storage unit that stores the position information and time information at the time of receiving the position information in association with each other, the information on the same day is individually stored on a time space having a time periodicity of 24 hours. A calculation step of calculating an approximate curve that approximates each of the expanded position information for each date,
From the approximate curves of each date calculated by the calculation step, the position information that is the basis of the approximate curves similar to each other is re-expanded on the space-time, and approximation that approximates each of the expanded position information A behavior pattern generation method characterized by including a specific step of calculating a curve and specifying a trajectory indicated by the calculated approximate curve as a basic behavior pattern indicating a trajectory of a behavior that is a basis of the user. An action pattern generation program to be executed by a computer,
In the computer,
A location information receiving procedure for receiving user location information;
Among the position information acquired from the user information storage unit that stores the position information and time information at the time of receiving the position information in association with each other, the information on the same day is individually stored on a time space having a time periodicity of 24 hours. A calculation procedure for calculating an approximate curve that approximates each of the expanded position information for each date,
From the approximate curves of each date calculated by the calculation procedure, the position information that is the basis of the approximate curves that are similar to each other is expanded again on the space-time, and the approximation that approximates each of the expanded position information A behavior pattern generation program characterized by calculating a curve and executing a specific procedure that specifies a trajectory indicated by the calculated approximate curve as a basic behavior pattern indicating a trajectory of a behavior that is a basic of the user.

Images