JP2017173999A - Life pattern prediction device for predicting life pattern of user in future period, portable terminal, program, and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a life pattern prediction device, a portable terminal, a program, and a method with which it is possible to predict the life pattern of a user in a future period.SOLUTION: The life pattern prediction device comprises position information accumulation means in which the time-series data of portable terminal position information and day/time is accumulated, and behavioral type extraction means for extracting a behavioral type based on staying from the time-series data. In addition, the life pattern prediction device includes life pattern type assignment means for assigning, for each unit period, prescribed one of life pattern types on the basis of one or more behavioral types, and life pattern type prediction means for predicting the life pattern type of a user in a future period on the basis of life pattern types in time series in a past period (> unit period).SELECTED DRAWING: Figure 2

Description

  The present invention relates to a technique for predicting user behavior by analyzing a past log in position information of a mobile terminal.

  In the communication facility, since the history of the location information of the base station under the control of the mobile terminal is recorded, the stay location and the stay time as the user behavior possessing the mobile terminal can be estimated using this information. In this case, the mobile terminal does not need to activate a GPS (Global Positioning System) function and does not need to transmit positioning information via the network. On the other hand, the base station position information has a problem that the spatial granularity is coarse and the time interval is not constant. However, for example, information for determining a rough action of the user such as “stay” can be used.

  Conventionally, there is a technique of recording an action log indicating that a user has participated in a specific event when the user moves on a specific geographical route (see, for example, Patent Document 1). According to this technique, when the user moves along the geographical route and can participate in the event, the content related to the event is provided to the user.

JP 2014-139837 A

  According to the above-described conventional technology, the position information of the mobile terminal possessed by the user is clearly specified, and information corresponding to the purpose of the stay is provided to the mobile terminal.

  On the other hand, the inventors of the present application may divide the daily behavior of an unspecified number of people into several life patterns. I thought. That is, for a specific user, by analyzing the past daily life pattern, for example, the daily life pattern can be predicted. I thought. In this case, information necessary at an appropriate time according to the predicted life pattern can be provided to the user's portable terminal.

  Then, according to this invention, it aims at providing the life pattern prediction apparatus, portable terminal, program, and method which can predict the life pattern of a user's future period.

According to the present invention,
Position information storage means for storing position information of the mobile terminal and time-series data of date and time;
In the life pattern prediction device for predicting the life pattern of the user's future period, the behavior pattern extraction means for extracting the behavior type based on the stay from the time series data,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
And life pattern type predicting means for predicting a life pattern type of a user's future period based on a time-series life pattern type in a past period (> unit period).

According to another embodiment of the life pattern prediction apparatus of the present invention,
It is also preferable that the life pattern type assigning means assigns a life pattern type based on a combination of a plurality of behavior types in a unit period.

According to another embodiment of the life pattern prediction apparatus of the present invention,
The life pattern type assigning means preferably assigns the life pattern type based on the transition of a plurality of behavior types in the unit period.

According to another embodiment of the life pattern prediction apparatus of the present invention,
The life pattern type predicting means preferably also predicts the life pattern type of the user in the future period based on the appearance probability of each life pattern type in the past period.

According to another embodiment of the life pattern prediction apparatus of the present invention,
The life pattern type predicting means preferably calculates the appearance probability for each life pattern type based on the periodicity of a plurality of life pattern types in the past period.

According to another embodiment of the life pattern prediction apparatus of the present invention,
Life pattern type verification means for verifying whether the behavior type extracted by the behavior type extraction means after the start of the future period is consistent with the behavior type constituting the life pattern type predicted by the life pattern type prediction means It is also preferable to have it.

According to another embodiment of the life pattern prediction apparatus of the present invention,
The behavior type extraction means further extracts the start / end time of each behavior type,
Based on the life pattern type predicted by the life pattern type prediction unit, the behavior type extracted by the behavior type extraction unit and the start / end time thereof, the behavior time prediction for predicting the start / end time of the behavior type in the future period of the user It is also preferable to further have means.

According to another embodiment of the life pattern prediction apparatus of the present invention,
It is also preferable that the action time predicting unit applies the distribution of the start and end times of the action type in the life pattern type calculated by the life pattern type predicting unit as having the highest appearance probability.

According to another embodiment of the life pattern prediction apparatus of the present invention,
Action time prediction means
For each life pattern type, calculate the distribution of the start and end times of the behavior type,
It is also preferable to make a prediction based on the probability based on the distribution of the appearance probability for each life pattern type and the start / end time of the behavior type.

According to another embodiment of the life pattern prediction apparatus of the present invention,
Action time verification means for verifying whether the start / end time of the action type extracted by the action type extraction means after the start of the future period is consistent with the start / end time of the action type predicted by the action time prediction means It is also preferable to have it.

According to another embodiment of the life pattern prediction apparatus of the present invention,
It further has a machine learning engine that is constructed from teachers using time series life pattern types collected from an unspecified number of people for each unit period.
It is also preferable that the life pattern type predicting means inputs a time series life pattern type in the past period to the machine learning engine and predicts a life pattern type in the future period as an output thereof.

According to another embodiment of the life pattern prediction apparatus of the present invention,
The unit period is a day,
The past period is consecutive days,
The future period is the next day,
In the machine learning engine teacher data, the day of the week is associated with the daily life pattern type of the time series,
It is also preferable that the life pattern type predicting means inputs a time-series life pattern type in the past consecutive days to the machine learning engine and predicts a life pattern type of the next day as an output thereof.

According to the present invention,
Position information storage means for storing position information and time-series data of date and time;
In a mobile terminal having a behavior type extraction means for extracting a behavior type based on stay from time series data, and predicting a life pattern of a user's future period,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
A life pattern type predicting means for predicting a life pattern type of the user's future period based on a time-series life pattern type in the past period (> unit period);
It is characterized by having.

According to the present invention,
A computer installed in a device that predicts the life pattern of the user's future period,
Position information storage means for storing position information of the mobile terminal and time-series data of date and time;
In a program that functions as a behavior type extraction means for extracting a behavior type based on stay from time series data,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
The computer is caused to function as a life pattern type predicting means for predicting a life pattern type of a user's future period based on a time series life pattern type in a past period (> unit period).

According to the present invention, in the life pattern prediction method of the device for predicting the life pattern of the user's future period,
The apparatus has a location information storage unit that stores location information of the mobile terminal and time-series data of date and time,
The apparatus extracts a behavior type based on stay from time series data,
A second step of assigning one of the predetermined life pattern types based on one or more behavior types for each unit period;
And a third step of predicting the life pattern type of the user's future period based on the time-series life pattern type in the past period (> unit period).

  According to the life pattern prediction apparatus, portable terminal, program, and method of the present invention, it is possible to predict the life pattern of the user's future period.

It is a spatial external view showing the stay of a portable terminal. It is a functional block diagram of the life pattern prediction apparatus in this invention. It is explanatory drawing showing the process of a positional information storage part and an action type extraction part. It is explanatory drawing showing the process of a lifestyle pattern type | mold allocation part. It is explanatory drawing showing the process of a life pattern type estimation part. It is explanatory drawing showing the process of a life pattern type verification part. It is explanatory drawing showing the process of an action time estimation part. It is explanatory drawing showing the process of an action time verification part. It is a system block diagram of the life pattern prediction apparatus arrange | positioned as a communication equipment apparatus.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a spatial external view showing a stay of a mobile terminal.

  A mobile terminal (for example, a mobile phone or a smartphone) possessed by a user is always under the control of a base station regardless of the position. It is connected to a wide area communication network (cellular phone network). According to FIG. 1, the user's home address and work place, and the area around D station, which is a visit destination, are “stay places”. Further, the user is moving at a place other than the home, the workplace, and the vicinity of the D station.

  In a communication facility that integrates a large number of base stations, base station position information with a coarse spatial granularity and a constant time interval is recorded for each mobile terminal. “Coarse spatial granularity” means that the geographical distance between location information is relatively long. Further, “the time interval is not constant” means that the recording time interval of the position information varies relatively.

  The base station connected to the wide area wireless communication network records the date and time as a communication history by communicating with the mobile terminal 2 located under the base station. The communication history is not limited to a call that requires a user operation on the mobile terminal, transmission / reception of mail, and browsing of a web page. Even when data transmitted / received automatically by an application installed in the mobile terminal is recorded as a communication history from the mobile terminal 2 by the base station.

  FIG. 2 is a functional configuration diagram of the life pattern prediction apparatus according to the present invention.

  The life pattern prediction apparatus 1 according to the present invention predicts a life pattern of a user's future period. According to FIG. 2, the position information storage unit 101, the teacher data group 102, the behavior type extraction unit 11, the life pattern type assignment unit 12, the life pattern type prediction unit 13, the machine learning engine 14, the life pattern A type verification unit 15, a behavior time prediction unit 16, and a behavior time verification unit 17 are included. The predicted life pattern is input to the application processing unit, and various services corresponding to the life pattern are provided to the user. These functional components are realized by executing a program that causes a computer installed in the apparatus to function. In addition, according to FIG. 2, the flow of processing using each functional component can be understood as a life pattern estimation method of the apparatus.

  FIG. 3 is an explanatory diagram illustrating processing of the position information accumulation unit and the behavior type extraction unit.

[Position information storage unit 101]
The location information storage unit 101 stores location information of the mobile terminal and time-series data of date and time.
According to FIG. 3, latitude and longitude are represented as position information. The latitude and longitude may be position information of a base station that communicates with the mobile terminal.
The time series data in the position information storage unit 101 is referred to by the behavior type extraction unit 11.

[Behavior type extraction unit 11]
The behavior type extraction unit 11 refers to the time series data of the location information storage unit 101 and extracts a behavior type based on stay.
“Staying” means being located within a predetermined distance range for a predetermined time or more. Or it is good also as being located in one map range which divided on the map equally for predetermined time or more.
“Behavior type” means “stay at home” that is stay at home, “stay at work” that is stay at work, and “other stay” that is stay at other places. This classifies and classifies “stays” and is a component for classifying “life pattern types” to be described later. In addition, based on “stay”, a period that is not “stay” can be extracted and “moving”, meaning can be classified and classified within the range where behavior can be estimated, and this is classified into “life pattern type” It is good also as a component for.
The daily behavior types extracted by the behavior type extraction unit 11 are output to the life pattern type assignment unit 12.

  The behavior type extraction unit 11 extracts a home position and a workplace position that characterize the user's behavior from the position information history. First, a plurality of stay points of the user, a stay start date and time and a stay end date and time at each stay point are specified. Then, the number of stay days is calculated for each of the plurality of stay points, the stay point having the most stay days is extracted as a home stay point, and the stay point having the second most stay days is extracted as a work stay point.

  As another embodiment, the behavior type extraction unit 11 may be a machine learning engine that learns a time zone with a behavior type (such as stay at home / work stay with respect to a time zone) as teacher data. Good. In this case, the closest action type can be extracted by inputting the time series data of the position information storage unit 101 to the machine learning engine.

  According to FIG. 3, the user's daily behavior type is specified from the staying point at home and the staying point at work. According to this user, the stay at home is roughly from 21:00 to 7:00, and the stay at work is from 9:00 to 19:00.

  FIG. 4 is an explanatory diagram illustrating processing of the lifestyle pattern type assigning unit.

[Life pattern type assignment unit 12]
The life pattern type assigning unit 12 assigns any predetermined life pattern type based on one or more behavior types for each unit period.
The unit period may be, for example, 24 hours a day, or may be one day that is not necessarily fixed at 24 hours, such as from the sunrise time at a predetermined place to the next day's sunrise time, or a predetermined period of 24 hours. Only the time zone may be extracted every day. Further, it may be a short period such as 12 hours a half day, or may be a long period such as one week, one month, or one year.

“Life pattern types” are categorized based on the type, combination, number of appearances, appearance order (transition), etc. of “behavior types” (stay at home / work stay, etc.) in a unit period (for example, 24 hours a day) It is a template. According to FIG. 4, a person's life pattern type can be roughly divided into five as follows.
<Life pattern type A (working type)>
Continuous home stay and continuous work stay each exist for more than 2 hours, and continuous other stay is 2 hours or less Assumed users: Adults (normal work, multiple work), students (normal school, part-time work) ,
Housewife (part-time regular work)
<Life pattern type B (outing type)>
Continuous home stay and continuous other stay each exist for more than 2 hours, and continuous work stay is 2 hours or less Assumed users: adults (holidays), students (weekdays + dating), housewives (weekdays)
<Life pattern type C (home type)>
When staying at home for more than 2 hours, and staying at work and staying at other places for 2 hours or less Assumed users: Working adults (holidays), students (holidays), housewives (holidays)
<Life pattern type D (work & go-out type)>
When continuous stays at home, continuous work stays and continuous other stays exist for more than 2 hours Assumed users: Working adults (normal work + dating), students (normal attending school + dating),
Housewife (part-time work)
<Life pattern type Z (others)>
When staying at home is 2 hours or less Assumed users: Adults (business trips, travel), students (travel), housewives (travel)

The life pattern type assigning unit 12 may assign a life pattern type based on “a combination of a plurality of behavior types” in a unit period (for example, one day).
The life pattern type assigning unit 12 may assign a life pattern type based on “a plurality of behavior type transitions” in a unit period.
The life pattern types can be classified into various patterns according to the usage of the service.

  The life pattern type assigning unit 12 outputs the assigned life pattern to the life pattern type predicting unit 13.

  FIG. 5 is an explanatory diagram illustrating processing of the life pattern type prediction unit.

[Life pattern type prediction unit 13]
The life pattern type prediction unit 13 predicts the life pattern type of the user in the future period based on the time series life pattern type in the past period (> unit period). Here, the “period” is defined as follows, for example.
Unit period: day (for example, one day (24 hours))
Past period: consecutive days (for example, 2 weeks (for 14 days))
Future period: Next day (for example, the same day (next day) (24 hours))
Specifically, the life pattern type of the user “the day” can be predicted from the life pattern type of “the past two weeks”.

  Further, the life pattern type prediction unit 13 may predict the life pattern type of the user in the future period based on the “appearance probability” of each life pattern type in the past period. Here, the appearance probability for each life pattern type may be calculated based on “periodicity” of a plurality of life pattern types in the past period.

  The life pattern type prediction unit 13 of the present invention inputs a time series life pattern type in the past period to the machine learning engine 14 and predicts a life pattern type in the future period as an output thereof.

[Machine learning engine 14]
The machine learning engine 14 is constructed by constructing, as teacher data, time-series life pattern types for each unit period collected from an unspecified number of people.
Approximately 98% of the unspecified number of people are included in the aforementioned life patterns A to D. According to FIG. 5, it is considered that the machine learning engine 14 will learn life patterns at the following ratios.
Life pattern A: 34%
Life pattern B: 28%
Life pattern C: 24%
Life pattern D: 12%
Life pattern Z: 2%

  The teacher data of the machine learning engine 14 is obtained by associating a day of the week with a daily time-series life pattern type. In this case, the life pattern type prediction unit 13 inputs a time series life pattern type on consecutive days with past days of the week to the machine learning engine 14, and predicts a life pattern type according to the day of the next day as the output. can do.

  Specifically, the machine learning engine 14 may be based on a Bayesian network that predicts the lifestyle pattern of the next day based on the lifestyle pattern of consecutive days.

  A “Bayesian network” is a graphical network that describes a causal relationship between nodes by probability. The network in the present invention refers to a graph structure in which the daily life pattern type is “node” and the similarity given to arcs between nodes is given as “weight”. A Bayesian network is a model of probabilistic reasoning that expresses inference of causal relations between a plurality of nodes by a directed acyclic graph structure and expresses a relation between individual variables by a conditional probability. A directed acyclic graph structure is one in which an arrow is attached to an arc (directed), and the path of the arrow does not circulate through a node. By using the Bayesian network, it is possible to quantitatively estimate the life pattern type of the future day as the probability of an uncertain event from the life pattern types of the past several days that have already passed.

  The life pattern type predicted by the life pattern type prediction unit 13 is output to the application processing unit.

  FIG. 6 is an explanatory diagram illustrating processing of the lifestyle pattern type verification unit.

[Life pattern type verification unit 15]
The life pattern type verification unit 15 is optional, and after the start of the future period, the behavior type extracted by the behavior type extraction unit 11 from the time series data of the user's mobile terminal on the current day is the life pattern. It is verified whether or not it matches with the behavior type constituting the life pattern type predicted by the type prediction unit 13. The correctness based on the verification is output to the application processing unit.

  According to the life pattern type verification unit, for example, a user who is predicted to be a life pattern type A (working type) on the day and is scheduled to receive a return mail for the return home according to the return time by the application processing unit is actually Suppose that it is detected that the day is a life pattern type C (home type). In that case, the verification result can be output to the application processing unit, and the mail delivery can be canceled immediately.

FIG. 7 is an explanatory diagram illustrating processing of the behavior time prediction unit.
[Behavior time prediction unit 16]
The behavior type extraction unit 11 further extracts the start / end time of each behavior type. At this time, the behavior time prediction unit 16 determines the user's future period based on the life pattern type predicted by the life pattern type prediction unit 13, the behavior type extracted by the behavior type extraction unit 11, and its start / end time. Predict the start and end times of behavior types. The predicted start / end time is output to the application processing unit.

Here, the behavior time prediction unit 16 can also apply the distribution of the start and end times of the behavior type in the life pattern type calculated by the life pattern type prediction unit 13 as having the highest appearance probability.
In addition, the behavior time prediction unit 16 calculates the distribution of the start and end times of the behavior type for each life pattern type, and predicts based on the probability of the appearance probability and the distribution of the start and end times of the behavior type for each life pattern type. It may be a thing.

  FIG. 8 is an explanatory diagram illustrating processing of the action time verification unit.

[Action time verification unit 17]
The behavior time verification unit 17 predicts, by the behavior time prediction unit 16, the behavior type start / end time extracted by the behavior type extraction unit 11 from the time-series data of the mobile terminal of the current day after the start of the future period. It is verified whether or not it matches the start / end time of the action type. The correctness based on the verification is output to the application processing unit.

  According to the action time verification unit 17, for example, it is predicted that the return will be at 21:00 on the day of the life pattern type A (working type), and the application processing unit will deliver a direct mail for the returnee according to the return time. Suppose that it is detected that the user has actually returned home at 18:00 although it is actually a lifestyle pattern type A (working type). In this case, the verification result can be output to the application processing unit, and the mail delivery scheduled at 21:00 can be canceled suddenly.

  FIG. 9 is a system configuration diagram of a life pattern prediction device arranged as a communication equipment device.

  The life pattern prediction device 1 is preferably configured as a communication equipment device installed in a wide area wireless communication network (mobile phone network). In this case, the life pattern predicting apparatus 1 stores, as an optional function, a communication interface unit connected to a wide area communication network, a base station location information management unit, and a communication history collection in order to accumulate communication history in the location information accumulation unit 101 And a position information history generation unit.

The base station location information management unit stores the base station identifier and the base station location information in association with each other.
The communication history collection unit collects the communication history of the date and time and the base station identifier for each portable terminal 2 from the base station to which the portable terminal 2 is connected.
Communication history (terminal identifier, date / time, base station identifier)
The location information history generation unit further associates base station location information corresponding to the base station identifier for each communication history using the base station location information management unit. The communication history is output to the position information storage unit 101.

  As described above in detail, according to the life pattern prediction apparatus, portable terminal, program, and method of the present invention, it is possible to predict the life pattern of the user in the future period.

  By predicting a lifestyle pattern in the future period, the application processing unit can provide effective information in an appropriate time zone for each user. For example, event information for the evening can be distributed to a user who seems to have free time in the evening of the day. In particular, by analyzing the characteristics of the location where the user appears, by not obtaining specific location information (latitude and longitude), the user's privacy pattern in the future period can be obtained without requiring the user's privacy information. Can be predicted.

In the above-described embodiment of the present invention, the life pattern in the future period is predicted, but the present invention is not necessarily limited to the prediction in the future period. You may estimate the life pattern of the past or the present specific period for which position information was not able to be acquired. In addition, the user may be notified of the predicted life pattern type itself, or may advise health guidance based on the predicted life pattern type.
In addition, although the position information is acquired by the base station, the position information may be acquired by another system such as a GPS system.

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Life pattern prediction apparatus 101 Position information storage part 102 Teacher data group 11 Behavior type extraction part 12 Life pattern type allocation part 13 Life pattern type prediction part 14 Machine learning engine 15 Life pattern type verification part 16 Action time prediction part 17 Action time verification Part 2 Mobile terminal

Claims (15)

Position information storage means for storing position information of the mobile terminal and time-series data of date and time;
In the life pattern predicting device for predicting the life pattern of the future period of the user, the behavior type extracting means for extracting the behavior type based on stay from the time series data,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
A life pattern predicting apparatus comprising: a life pattern type predicting means for predicting a life pattern type of the user in the future period based on a life series type of time series in a past period (> unit period). 2. The life pattern predicting apparatus according to claim 1, wherein the life pattern type assigning unit assigns the life pattern type based on a combination of a plurality of behavior types in the unit period. The life pattern predicting device according to claim 1 or 2, wherein the life pattern type assigning unit assigns the life pattern type based on a plurality of behavior type transitions in the unit period. The life pattern type predicting means predicts a life pattern type of the user in the future period based on the appearance probability of each life pattern type in the past period. The life pattern prediction apparatus described in 1. The life pattern predicting device according to claim 4, wherein the life pattern type predicting means calculates an appearance probability for each of the life pattern types based on periodicity of a plurality of life pattern types in the past period. . Life that verifies whether or not the behavior type extracted by the behavior type extraction means is consistent with the behavior type constituting the lifestyle pattern predicted by the lifestyle pattern prediction means after the start of the future period The life pattern prediction apparatus according to claim 1, further comprising a pattern type verification unit. The behavior type extracting means further extracts the start / end time of each behavior type,
Based on the life pattern type predicted by the life pattern type prediction unit, the behavior type extracted by the behavior type extraction unit and the start / end time thereof, the start / end of the behavior type in the future period of the user The life pattern prediction apparatus according to claim 1, further comprising behavior time prediction means for predicting time. 8. The behavior time predicting unit applies a distribution of start and end times of the behavior type in the life pattern type calculated by the life pattern type predicting unit as having the highest appearance probability. Life pattern prediction device. The action time prediction means includes
For each life pattern type, calculate the distribution of the start and end times of the behavior type,
The life pattern prediction apparatus according to claim 7 or 8, wherein prediction is performed based on a probability based on a distribution of an appearance probability for each life pattern type and a start / end time of the behavior type. An action for verifying whether the start / end time of the action type extracted by the action type extracting means after the start of the future period is consistent with the start / end time of the action type predicted by the action time predicting means The life pattern prediction apparatus according to claim 7, further comprising a time verification unit. It further has a machine learning engine that is constructed from teachers using time series life pattern types collected from an unspecified number of people for each unit period.
The life pattern type predicting means inputs a time-series life pattern type in the past period to the machine learning engine, and predicts a life pattern type in the future period as an output thereof. The life pattern prediction apparatus according to any one of 10. The unit period is a day,
The past period is consecutive days;
The future period is the next day,
In the teacher data of the machine learning engine, day of the week is associated with a daily life pattern type of time series,
The life pattern type predicting means inputs a time-series life pattern type in the past consecutive days to the machine learning engine, and predicts a life pattern type of the next day as an output thereof. 11. The life pattern prediction apparatus according to 11. Position information storage means for storing position information and time-series data of date and time;
In the portable terminal that has a behavior type extraction means for extracting a behavior type based on stay from the time series data, and predicts a life pattern of the user's future period,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
A life pattern type predicting means for predicting a life pattern type of the user's future period based on a time-series life pattern type in a past period (> unit period);
A portable terminal characterized by comprising: A computer installed in a device that predicts the life pattern of the user's future period,
Position information storage means for storing position information of the mobile terminal and time-series data of date and time;
In the program that functions as an action type extracting means for extracting an action type based on stay from the time series data,
Life pattern type assigning means for assigning any predetermined life pattern type based on one or more behavior types for each unit period;
A program for causing a computer to function as a life pattern type predicting means for predicting a life pattern type of a future period of the user based on a time series life pattern type in a past period (> unit period). In the life pattern prediction method of the device for predicting the life pattern of the user's future period,
The apparatus has a location information storage unit that stores location information of a mobile terminal and time-series data of date and time,
The apparatus extracts a behavior type based on stay from the time series data, and
A second step of assigning one of the predetermined life pattern types based on one or more behavior types for each unit period;
And a third step of predicting a life pattern type of the user's future period based on a time-series life pattern type in a past period (> unit period).

Images