WO2011142471A1 - Dispositif d'extraction de caractéristiques d'actions, système d'extraction de caractéristiques d'actions, procédé d'extraction de caractéristiques d'actions et programme d'extraction de caractéristiques d'actions - Google Patents

Dispositif d'extraction de caractéristiques d'actions, système d'extraction de caractéristiques d'actions, procédé d'extraction de caractéristiques d'actions et programme d'extraction de caractéristiques d'actions Download PDF

Info

Publication number
WO2011142471A1
WO2011142471A1 PCT/JP2011/061126 JP2011061126W WO2011142471A1 WO 2011142471 A1 WO2011142471 A1 WO 2011142471A1 JP 2011061126 W JP2011061126 W JP 2011061126W WO 2011142471 A1 WO2011142471 A1 WO 2011142471A1
Authority
WO
WIPO (PCT)
Prior art keywords
point
stay
action
type
base type
Prior art date
Application number
PCT/JP2011/061126
Other languages
English (en)
Japanese (ja)
Inventor
岳夫 大野
Original Assignee
日本電気株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Priority to JP2012514855A priority Critical patent/JPWO2011142471A1/ja
Publication of WO2011142471A1 publication Critical patent/WO2011142471A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a behavior feature extraction device, a behavior feature extraction system, a behavior feature extraction method, and a behavior feature extraction program that extract feature information of user behavior.
  • Patent Literature 1 discloses a situation estimation device that defines a situation transition model of a behavioral state (sleeping, working, going out, etc.) and estimating a user's current situation from position information and time information. Yes.
  • Patent Document 2 discloses a method in which a user does not input an action type related to each staying place but automatically extracts an action type related to each staying place.
  • the behavior history analysis apparatus of Patent Literature 2 estimates a user's private related point and business related point based on a staying time zone, a noise level, and an illuminance level in the user's workplace.
  • the behavior history analysis device described in Patent Document 2 described above classifies whether the staying place is a private related point or a business related point based on the illuminance level and the noise level.
  • the behavior history analysis apparatus of Patent Document 2 in order to classify whether the staying place is a private-related point or a business-related point, information on illuminance or noise other than position information, and a user's working hours There was a problem of needing information about.
  • One object of the present invention is to provide a behavior feature extraction device, a behavior feature extraction system, a behavior feature extraction method, and a behavior feature extraction program that can extract the relationship between a user's staying location and a behavior type from a position information history. It is in.
  • the behavior feature extraction device is the behavior feature extraction device user who has stayed, the first behavior base type corresponding to the first behavior type and the second behavior type corresponding to the first behavior type.
  • action type storage means for storing stay point information including information indicating the order of stay at the stay point
  • the action type storage means The stay point information is acquired, and based on the stay point information, either the stay point of the first action base type or the stay point of the second action base type is set as a start point, and the first point Extracting the chain of stay points whose end point is the stay point of the action base type and the stay point of the second action base type, for each stay point included in the extracted chain
  • the start and end lines Based on the location type, a first degree of relevance indicating the degree of association between the stay point and the first action type, and a degree of association between the stay point and the second action type.
  • Action feature extracting means for calculating at least one of the two stay point relevances and outputting the calculated stay point relevance for each stay point included in the chain.
  • the behavior feature extraction system includes a first behavior base type corresponding to a first behavior type that the user has stayed on the basis of a positioning point indicating a user position and a positioning date and time.
  • an action of extracting stay point information including information indicating an order of staying at the stay point
  • the stay point information is acquired from the type extraction means and the behavior type extraction means, and based on the stay point information, the stay points of the first action base type and the stay points of the second action base type are obtained.
  • the chain of the staying points is extracted by extracting one of the starting points, and the staying point of the first action base type and the staying point of the second action base type as the end point.
  • the behavior feature extraction method includes a retention point of a first behavior base type corresponding to a first behavior type and a second behavior base corresponding to a second behavior type, where the user has stayed.
  • the stay point of the first action base type and the second point based on stay point information including information indicating the order of stay at the stay point
  • the chain of stay points starting from one of the stay points of the action base type and ending point of either the stay point of the first action base type or the stay point of the second action base type
  • the degree of association between the stay point and the first action type is determined based on the action base type of the start point and the end point.
  • Retention point relevance of 1 and the stay point and previous At least one of the second stay point relevance levels indicating the degree of association with the second action type is calculated, and the calculated stay point relevance level is output for each stay point included in the chain. .
  • the computer-readable recording medium corresponds to the stay point of the first action base type corresponding to the first action type and the second action type corresponding to the first action type in which the user stayed in the computer. For each of the plurality of stay points including the stay point of the second action base type, the stay point of the first action base type based on the stay point information including information indicating the order of staying at the stay point. And the stay point of the second action base type as the start point, and the stay point of the first action base type and the stay point of the second action base type as the end point.
  • the first indicating the degree of relevance At least one of the staying point relevance level and the second staying point relevance level indicating the degree of relevance between the staying point and the second action type is calculated, and for each staying point included in the chain
  • a behavior feature extraction program for executing a process of outputting the calculated staying point relevance is stored.
  • the effect of the present invention is that the relationship between the user's staying place and the action type can be extracted from the position information history.
  • the behavior type data 211 and the living behavior model in the embodiment of the present invention will be described.
  • the terminal 100 that moves together with the user periodically acquires position information.
  • the behavior type extraction device 200 extracts the stay point information 212 as the user's behavior type data 211 based on the acquired position information.
  • the staying point information 212 is information regarding a staying point (a staying place) where the user has visited and stayed.
  • the user's life behavior model is defined as follows. First, it is assumed that the user's behavior is classified into at least two behavior types, such as “work” (first behavior type) and “private” (second behavior type).
  • first action type the stay point of the workplace
  • second action base type “private” at the stay point of the home
  • an action belonging to each action type is performed at the stay point of the action base type corresponding to each action type, such as performing an action (private life) belonging to (second action type).
  • a staying point when a user goes out of the workplace and returns to the workplace a staying point when the user goes out of the home and returns to the home
  • a staying point when the user moves from the workplace to the home a staying point from the home
  • the stay points that stop when moving between the stay points of each action base type such as the stay points that stop when moving to, are related to one of the above action types.
  • the possibility that the stay point that stops when moving is related to any of the action types is determined by the start point of the move and the action base type of the stay point that is the arrival point.
  • a user's action is classified into two action types “work” and “private”, and the user works at a staying point at the workplace (workplace staying point) and at a staying point at home (home staying point). Live a private life.
  • the stay point is likely to be related to work (or may be related to private). Low).
  • the stay point is less likely to be related to work (or highly likely to be related to private).
  • the residence point that stops by the user is slightly more likely to be related to work (or may be related to private) Is a little low).
  • the stay point is slightly less likely to be related to work (or may be related to private) Is a little high).
  • the first action type is “work”
  • the first action base type corresponding to the first action type is “workplace”
  • the second action type is “private”.
  • the second action base type corresponding to the second action type is “home”. That is, the user's behavior is classified into two behavior types of “work” and “private”, and the user performs a job at the work staying point and a private behavior at the home staying point.
  • the behavior feature extraction system 1 extracts a chain of residence points having either a workplace residence point or a home residence point as a start point (start point) and an arrival point (end point), and is included in the extracted stay point chain.
  • FIG. 2 is a block diagram showing a configuration of the behavior feature extraction system 1 according to the first embodiment of the present invention.
  • the behavior feature extraction system 1 includes a terminal 100, a behavior type extraction device 200, a behavior feature extraction device 300, and a behavior feature reference device 400.
  • the terminal 100 and the behavior type extraction device 200, the behavior type extraction device 200 and the behavior feature extraction device 300, and the behavior feature extraction device 300 and the behavior feature reference device 400 are connected by a network (not shown) and can communicate with each other.
  • the terminal 100 is an information terminal that can move with the user.
  • the terminal 100 is a mobile phone terminal.
  • the terminal 100 may be an information terminal such as a PDA (Personal Data Assistant), a personal computer, or a car navigation system terminal, instead of a mobile phone terminal. Although only one terminal 100 is illustrated in FIG. 2, a plurality of terminals 100 may be provided.
  • the terminal 100 acquires the position information of the terminal 100 and outputs it as position information data 111.
  • the terminal 100 includes a position information acquisition unit 101.
  • the position information acquisition unit 101 acquires position information of the terminal 100 by GPS.
  • the terminal 100 includes an antenna and receives radio waves transmitted from a GPS satellite (not shown).
  • the position information acquisition unit 101 calculates the position (positioning point) of the terminal 100 based on the radio wave received from the satellite. Further, the position information acquisition unit 101 calculates a positioning point and simultaneously acquires a positioning time.
  • the positioning point calculated by the position information acquisition unit 101 is the position of the terminal 100.
  • the position information acquisition unit 101 acquires the positioning point from the information on the installation position of the reader attached to the reader of an RFID (Radio Frequency IDentification) installed in a specific place (store, etc.), for example, instead of the GPS. May be.
  • RFID Radio Frequency IDentification
  • the position information acquisition unit 101 may acquire a positioning point by estimating the moving distance of the terminal 100 using an acceleration sensor or a geomagnetic sensor. Further, the position information acquisition unit 101 may acquire other information related to the positioning point such as the positioning accuracy at the same time as calculating the positioning point.
  • the position information acquisition unit 101 periodically calculates a positioning point, and transmits position information data 111 including position information indicating the position of the positioning point, positioning time, and positioning accuracy information to the behavior type extraction device 200.
  • the time interval at which the positioning point is calculated by the position information acquisition unit 101 may be set in advance in the position information acquisition unit 101 by the administrator, or may be set in the position information acquisition unit 101 by the user.
  • the position information of the positioning point may be indicated on a predetermined coordinate axis, or may be indicated by latitude and longitude.
  • the behavior type extraction device 200 extracts the behavior type data 211 of the terminal 100 based on the position information data 111.
  • the behavior type extraction apparatus 200 includes a behavior type extraction unit 201 and a behavior type storage unit 202.
  • the behavior type extraction unit 201 receives the position information data 111 from the terminal 100, and extracts the stay point information 212 as the behavior type data 211 of the terminal 100 based on the received position information data 111.
  • the behavior type extraction unit 201 based on the position information data 111, for example, when the positions of a plurality of positioning points acquired within a predetermined time are included in a predetermined range, these positioning points Any one of the positions is defined as a stay point.
  • the behavior type extraction unit 201 stores the extracted behavior type data 211 in the behavior type storage unit 202 for each terminal 100. Furthermore, the behavior type extraction unit 201 transmits the behavior type data 211 to the behavior feature extraction device 300.
  • FIG. 6 is a diagram showing an example of the stay point information 212 in the first embodiment of the present invention.
  • the stay point information 212 includes a stay data identifier for identifying each stay, stay point identifiers s1 to s9 for identifying a stay point in each stay, position information of the stay point, and an order of staying at the stay point.
  • the stay point identifier is given to each stay point extracted by the behavior type extraction unit 201.
  • the information indicating the order may be any information as long as it indicates the staying order, and may be a staying start date and time and a staying end date and time as shown in FIG. Further, when the behavior type extraction unit 201 assigns the stay point identifier so as to indicate the stay order, the stay point identifier may be information indicating the order.
  • the behavior feature extraction apparatus 300 generates behavior feature data 311 of the terminal 100 based on the behavior type data 211.
  • the behavior feature extraction apparatus 300 includes a behavior type reference unit 301, a behavior feature extraction unit 302, and a behavior feature storage unit 303.
  • the behavior type reference unit 301 receives the behavior type data 211 from the behavior type extraction device 200.
  • the behavior feature extraction unit 302 extracts a stay point chain starting from one of the workplace stay point and the home stay point and arriving as either of the stay point at home, and is included in the extracted chain. For each stay point, the stay point relevance to “work” is calculated. Furthermore, the behavior feature extraction system 1 calculates a chain relevance level for “work” for each of the above-described chains.
  • the behavior feature extraction unit 302 stores the calculated stay point association degree in the behavior feature storage unit 303 as stay point association degree information 312. In addition, the behavior feature extraction unit 302 stores the calculated chain association degree as the chain association degree information 313 in the behavior feature storage unit 303. Furthermore, the behavior feature extraction unit 302 transmits behavior feature data 311 including the stay point association degree information 312 and the chain association degree information 313 to the behavior feature reference device 400.
  • FIG. 11 is a diagram showing an example of the stay point relevance information 312 in the first embodiment of the present invention.
  • the stay point relevance information 312 includes stay point relevance for each stay point.
  • FIG. 13 is a diagram illustrating an example of the chain association degree information 313 according to the first embodiment of this invention.
  • the chain association degree information 313 includes the chain association degree for each of the stay point chains.
  • the behavior feature reference device 400 is a server on which an application using the user behavior feature data 311 operates.
  • any application may be used as long as the behavior feature data 311 is used.
  • the application may be an application that provides an advertisement distribution service or the like based on the staying point relevance information 312 or the chain relevance information 313 included in the behavior characteristic data 311.
  • the terminal 100, the behavior type extraction device 200, the behavior feature extraction device 300, and the behavior feature reference device 400 may each be a computer that operates according to a program.
  • the terminal 100, the behavior type extraction device 200, the behavior feature extraction device 300, and the behavior feature reference device 400 include a storage unit, a processing unit, an input / output unit, and a communication unit (not shown), which are electrically connected by a common bus.
  • the storage unit includes a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, and the like, and stores programs and data for realizing the functions of each device.
  • the processing unit is configured by a CPU (Central Processing Unit), and executes the function of each device by reading the program in the storage unit and performing processing.
  • the input / output unit includes an LCD (Liquid Crystal Display), a keyboard, a mouse, a speaker, and the like, and is an input / output interface with an administrator of each device.
  • the communication unit performs communication with other devices by performing wireless communication or wired communication. In this way, the terminal 100, the behavior type extraction device 200, the behavior feature extraction device 300, and the behavior feature reference device 400 are realized.
  • the behavior feature extraction device 300 is different from the terminal 100, the behavior type extraction device 200, and the behavior feature reference device 400.
  • the behavior feature extraction device 300 and one or more of the terminal 100, the behavior type extraction device 200, and the behavior feature reference device 400 may constitute one device.
  • the behavior type extraction device 200 and the behavior feature extraction device 300 may constitute one device.
  • each component of the behavior feature extraction apparatus 300 may be disposed in a physically different place and connected via a network. That is, the configuration of the behavior feature extraction system 1 illustrated in FIG. 2 is merely an example, and the terminal 100, the behavior type extraction device 200, the behavior feature extraction device 300, and the behavior feature reference device 400 each include any component. Whether it is provided can be changed flexibly. Next, operation
  • FIG. 3 is a flowchart showing position information acquisition processing of the terminal 100 in the first embodiment of the present invention.
  • the position information acquisition unit 101 of the terminal 100 receives radio waves from the satellite and periodically calculates positioning points (step S101).
  • the position information acquisition unit 101 acquires the positioning accuracy information and the positioning time at the same time when calculating the positioning point (step S102).
  • the position information acquisition unit 101 transmits position information data 111 including a positioning point, positioning accuracy information, and positioning time to the behavior type extraction device 200 (step S103).
  • mold extraction apparatus 200 in 1st embodiment of this invention is demonstrated.
  • FIG. 4 is a flowchart showing the behavior type extraction process of the behavior type extraction device 200 according to the first embodiment of the present invention.
  • the behavior type extraction unit 201 of the behavior type extraction device 200 receives the position information data 111 from the terminal 100 (step S201).
  • the behavior type extraction unit 201 extracts the stay point information 212 from the position information data 111 transmitted from the terminal 100 (step S202).
  • the behavior type extraction unit 201 stores the extracted stay point information 212 in the behavior type storage unit 202 as behavior type data 211 (step S203).
  • the behavior type extraction device 200 transmits the behavior type data 211 to the behavior feature extraction device 300 (step S204).
  • FIG. 5 is a flowchart showing the behavior feature extraction process of the behavior feature extraction apparatus 300 according to the first embodiment of the present invention.
  • the behavior type reference unit 301 of the behavior feature extraction device 300 receives the behavior type data 211 from the behavior type extraction device 200 (step S301).
  • the behavior type reference unit 301 receives the stay point information 212 as illustrated in FIG. 6 as the behavior type data 211.
  • the behavior feature extraction unit 302 extracts a chain of residence points starting from one of the home residence point and the workplace residence point and ending from either one of the residence point information 212 received by the behavior type reference unit 301 ( Step S302).
  • the behavior feature extraction unit 302 acquires the stay point identifier of the home stay point and the work stay point based on the position information of the home and the work input in advance by the user or the administrator.
  • the behavior feature extraction unit 302 for example, if the input home position (position coordinates, latitude, longitude, etc.) is within a predetermined range from the position of the stay point included in the stay point information 212, Let the stay point identifier of the stay point be the stay point identifier of the home stay point. Similarly, when the input workplace position is within a predetermined range from the residence point position included in the residence point information 212, the residence point identifier of the residence point is set as the residence point identifier of the workplace residence point. For example, in the case of the stay point information 212 of FIG.
  • the behavior feature extraction unit 302 includes the home position information (position coordinates (x1, y1)) and the workplace position information (position coordinates (x5, y5)) input by the administrator. )), The residence point identifier s1 of the home residence point and the residence point identifier s5 of the workplace residence point are acquired.
  • FIG. 7 is a diagram illustrating an example of a result of extraction of a chain of stay points in the first embodiment of the present invention.
  • the behavior feature extraction unit 302 extracts chains (chain identifiers c1 to c4) as shown in FIG. 7 from the stay point information 212 of FIG.
  • the behavior feature extraction unit 302 may acquire the stay point identifiers of the home stay point and the workplace stay point by analyzing the stay point information 212. In this case, for example, in the stay point information 212, the behavior feature extraction unit 302 sets the stay point identifier of the stay point with the longest stay time as the stay point identifier of the home stay point, and stays at the stay point with the second stay time.
  • the point identifier may be the stay point identifier of the workplace stay point.
  • the behavior feature extraction unit 302 classifies each stay point other than the home stay point and workplace stay point on the extracted chain according to the stay point type, and assigns the stay point type to each stay point (step S303). .
  • the behavior feature extraction unit 302 sets the stay point type of the stay point, the start point of the chain including the stay point, and the action base type (“workplace” or “home”) of the stay point as the end point. It is determined by the start point of the chain including the stay point or the order of the stay point from the end point.
  • FIG. 8 is a diagram illustrating an example of the staying point type in the first embodiment of the present invention.
  • the behavior feature extraction unit 302 classifies each stay point other than the home stay point and the workplace stay point into 12 types of stay point types p1 to p6 and w1 to w6 as shown in FIG.
  • the stay point types p1 to p3 are stay points included in the chain starting from and staying at the home stay point, p1 is immediately after leaving the home stay point (next to the start point), and p3 arrives at the home stay point.
  • the retention point immediately before (before the end point) is shown.
  • p2 is a residence point that is not included in either p1 or p3, and a plurality of p2 exist.
  • the residence point applicable to both conditions of p1 and p3 may be classified into both p1 and p3, or any one.
  • the stay point types p4 to p6 are stay points included in the chain starting from the work stay point and ending at the home stay point, p4 is immediately after leaving the work stay point (next to the start point), and p6 is staying at home. Indicates the staying point immediately before arriving at the point (before the end point).
  • p5 is a residence point that is not included in either p4 or p6, and there are a plurality of p5.
  • the residence point applicable to both conditions of p4 and p6 may be classified into both of p4 and p6, or any one.
  • the stay point types w1 to w3 are the stay points included in the chain starting from and staying at the workplace, w1 is immediately after leaving the workplace stay point (next to the start point), and w3 arrives at the home stay point.
  • the retention point immediately before (before the end point) is shown.
  • w2 is a staying point not included in either w1 or w3, and there are a plurality of w2.
  • the stay points that apply to both the conditions of w1 and w3 may be classified into both or one of w1 and w3.
  • the stay point types w4 to w6 are stay points included in the chain starting at the home stay point and ending with the work stay point, w4 is immediately after leaving the home stay point (next to the start point), and w6 is staying at the work place. Indicates the staying point immediately before arriving at the point (before the end point).
  • w5 is a staying point not included in either w4 or w6, and there are a plurality of w5.
  • the stay point that applies to both the conditions of w4 and w6 may be classified into both or either of w4 and w6. When one stay point is included in a plurality of chains, the stay points are classified for each chain.
  • FIG. 9 is a diagram showing an example of the stay point classification result in the first embodiment of the present invention.
  • the behavior feature extraction unit 302 classifies each stay point other than the start point and end point on the chain (chain identifiers c1 to c4) in FIG. 7 according to the stay point type in FIG. The retention point type is assigned as follows.
  • the behavior feature extraction unit 302 calculates a stay point relevance level for each classified stay point, and stores it in the behavior feature storage unit 303 as stay point relevance information 312 (step S304).
  • FIG. 10 is a diagram showing an example of a calculation formula for the staying point relevance in the first embodiment of the present invention.
  • RSj is the staying point relevance of staying point identifier j
  • Nji is the staying point identifier.
  • the coefficient ⁇ i is set in advance by the administrator according to the above-mentioned user behavior model. For example, when the stay point types are classified as shown in FIG. 8, it can be estimated that the stay points of the stay point types w1 to w3 are likely to be related to work, so the coefficient ⁇ i for the stay point types w1 to w3 is set.
  • the coefficient ⁇ i for the stay point types p1 to p3 is set to a value close to zero.
  • the coefficient ⁇ i for the stay point types w4 to w6 is larger than the coefficient ⁇ i for p4 to p6 and w1 A value smaller than the coefficient ⁇ i for ⁇ w3 is set.
  • the coefficient ⁇ i for the stay point types p4 to p6 is smaller than the coefficient ⁇ i for w4 to w6 and p1 A value larger than the coefficient ⁇ i for ⁇ p3 is set. Furthermore, for the stay points of the stay point types w1 to w3, if it can be estimated that the stay point immediately after leaving the workplace is more likely to be related to the work than the stay point immediately before arriving at the workplace, the coefficient ⁇ i is , ⁇ w1> ⁇ w2> ⁇ w3.
  • the coefficient ⁇ i is set so as to satisfy ⁇ p1 ⁇ p2 ⁇ p3.
  • the coefficient ⁇ i is , ⁇ w4 ⁇ w5 ⁇ w6.
  • the coefficient ⁇ i is , ⁇ p4> ⁇ p5> ⁇ p6.
  • the behavior feature extraction unit 302 calculates the stay point association degree as shown in FIG. 11 according to the calculation formula of FIG. 10 and the coefficient ⁇ i. Note that the value of the coefficient ⁇ i is not limited to the set value described above (FIG. 10), and a value according to a different magnitude relationship or a different value may be set according to the living behavior model.
  • the value of the coefficient ⁇ i a value according to actual user behavior obtained by sampling survey or the like may be set.
  • the number of stay point types on the chain is not limited to the above-described classification (FIG. 8), and may be different depending on the living behavior model.
  • the stay point types on each chain may be classified into more types according to the order from the start point or end point of the stay point on the chain.
  • the behavior feature extraction unit 302 may determine whether the stay point is related to work based on the calculated stay point relevance level, and may include the stay point determination result in the stay point relevance level information 312. .
  • the behavior feature extraction unit 302 includes the stay point determination result as illustrated in FIG. Next, the behavior feature extraction unit 302 calculates a chain association degree for each chain based on the calculated stay point association degree, and stores it in the behavior feature storage unit 303 as the chain association degree information 313 (step S305). ).
  • FIG. 12 is a diagram illustrating an example of a calculation formula for the chain association degree according to the first embodiment of this invention.
  • RCk represents the chain relevance of the chain of the chain identifier k
  • Mkj represents the number of stay points of the stay point identifier j included in the chain of the chain identifier k.
  • the behavior feature extraction unit 302 uses the calculation formula in FIG. 12 for each chain (chain identifier c1 to c4) in FIG. Is calculated. Note that the behavior feature extraction unit 302 may determine whether the chain is related to work based on the calculated chain relevance, and may include the result in the chain relevance information 313 as a chain determination result.
  • the behavior feature extraction unit 302 uses FIG.
  • the chain determination result such as is included in the chain relevance information 313.
  • the behavior feature extraction unit 302 responds to the acquisition request for the behavior feature data 311 received from the behavior feature reference device 400, and the behavior feature includes the stay point association degree information 312 and the chain association degree information 313 in the behavior feature reference device 400.
  • Data 311 is transmitted (step S306).
  • the behavior feature extraction device 300 may periodically execute the processing from step S301 to step S306 at predetermined time intervals, or obtain behavior feature data 311 received from the behavior feature reference device 400.
  • the behavior feature extraction unit 302 calculates the stay point relevance using one or more stay point types assigned to each stay point. However, the behavior feature extraction unit 302 further divides the stay point according to the given stay point type, calculates the stay point relevance for each divided stay point, and calculates the stay point relation calculated for the divided stay point. The degree of linkage relevance may be calculated based on the degree.
  • FIG. 14 is a diagram showing an example of a stay point dividing method according to the first embodiment of the present invention.
  • the stay point relevance is calculated for the stay point of the stay point identifier s10 using the given stay point types w1, w1, p2, and p4 without dividing the stay point. did.
  • the behavior feature extraction unit 302 sets the stay point of the stay point identifier s10, as shown in FIG. 14, to the stay point identifier s10w to which the stay point relevance to work is high and to which the stay point types w1 to w6 are assigned.
  • FIG. 15 is a diagram showing another example of the stay point dividing method according to the first embodiment of the present invention.
  • the behavior feature extraction unit 302 divides the stay point of the stay point identifier s10 into three stay points of stay point identifiers s10w1, s10p2, and s10p4 according to each stay point type as shown in FIG. You may calculate a stay point relevance degree about a point. Further, in the first embodiment of the present invention, the behavior feature extraction system 1 sets the first behavior type as “work” and the second behavior type as “private”, and sets the first residence point of the user. Residence point association degree (first residence point association degree) with respect to action type ("work”), and linkage degree relation (first linkage association degree) with respect to the first action type ("work”) of the chain of residence points ) has been described.
  • the behavior feature extraction system 1 may use other behavior types as long as the behavior of the user can be classified. For example, if the user is a student, the behavior feature extraction system 1 sets the first behavior type as “study” and the second behavior type as “private”, and the degree of stay point relevance for the user ’s stay point “study”, In addition, the staying point relevance degree for the “study” of the staying point chain may be calculated. In this case, the behavior feature extraction system 1 calculates a staying point relevance level and a chain relevance level for “school work” by setting the first behavior base type as “school” and the second behavior base type as “home”. Further, the behavior feature extraction system 1 defines a stay point relevance calculation formula as shown in FIG. 10 and a chain relevance calculation formula as shown in FIG.
  • FIG. 1 is a block diagram showing a characteristic configuration of the first embodiment of the present invention. Referring to FIG.
  • the behavior feature extraction apparatus 300 includes a behavior type storage unit 202 and a behavior feature extraction unit 302.
  • the action type storage unit 202 stores the stay point of the first action base type corresponding to the first action type and the second action base type corresponding to the second action type, where the user has stayed.
  • the stay point information 212 including information indicating the order of staying at the stay point is stored.
  • the behavior feature extraction unit 302 starts from either the stay point of the first action base type or the stay point of the second action base type, A chain of staying points with either end point is extracted, and for each staying point included in the extracted chain, based on the action base type of the start point and the end point, the stay point and the first action type At least one of the first stay point relevance level indicating the relevance level and the second stay point relevance level indicating the relevance level between the stay point and the second action type is calculated and included in the chain. For each stay point, the calculated stay point related degree is output.
  • the relationship between the user's staying location and the action type can be extracted from the position information history.
  • the reason is that the behavior feature extraction unit 302 starts from the stay point of the first action base type and the stay point of the second action base type based on the stay point information 212, and ends either The stay point indicating the degree of association between the stay point and the action type for each stay point included in the extracted stay point chain based on the action base type of the start point and the end point This is for calculating the point relevance. Thereby, for example, information on whether the user's staying place is related to work or private can be extracted from the position information history. Further, according to the first embodiment of the present invention, the relationship between the chain of staying places of the user and the action type can be extracted from the position information history.
  • the behavior feature extraction unit 302 calculates the chain relevance indicating the degree of association between the stay point chain and the action type based on the stay point relevance of each stay point included in the stay point chain. It is to do. Thereby, for example, information on whether the chain of residence places of users is related to work or private (whether it is related to weekdays or holidays) can be extracted from the position information history.
  • the relationship between the staying place of the user and the action type, and the relationship between the chain of staying places and the action type, regardless of the time when the user performed the action. can be extracted.
  • the behavior feature extraction unit 302 calculates the stay point relevance based on the behavior base type of the start point and end point of the stay point chain, and based on the calculated stay point relevance level. In addition, this is for calculating the linkage relevance. As a result, for example, even when the time period in which an action is performed varies depending on the user, such as work, the relation between the staying place of the user and the work and the relation between the chain of staying places and the work can be extracted. (Second embodiment) Next, a second embodiment of the present invention will be described.
  • the behavior feature extraction unit 302 extracts the stay point chain with the staying place staying point as the home staying point, and calculates the staying point relevance level and the chain relevance level. However, it differs from the first embodiment of the present invention.
  • the configuration of the second embodiment of the present invention is the same as the configuration of the first embodiment of the present invention.
  • the operation of the behavior feature extraction system 1 according to the second embodiment of the present invention will be described. About operation
  • FIG. 16 is a flowchart showing a behavior feature extraction process of the behavior feature extraction apparatus 300 according to the second embodiment of the present invention.
  • the behavior type reference unit 301 of the behavior feature extraction device 300 receives the behavior type data 211 from the behavior type extraction device 200 (step S401).
  • FIG. 17 is a diagram illustrating an example of the stay point information 212 in the second embodiment of the present invention.
  • the behavior type reference unit 301 receives the stay point information 212 as shown in FIG. 17 as the behavior type data 211.
  • the behavior feature extraction unit 302 extracts a lodging place from the staying point information 212 received by the behavior type reference unit 301 (step S402).
  • the behavior feature extraction unit 302 extracts the staying point staying 24 hours after the predetermined time at which the user stayed at home as the staying destination staying point in accordance with the definition of the living behavior model.
  • the behavior feature extraction unit 302 uses the time when the user leaves the home, the time when the user arrives at the home, or an intermediate time between when the user arrives at the home and leaves The staying point staying 24 hours after that time is defined as the staying destination staying point.
  • the behavior feature extraction unit 302 extracts a staying point staying 24 hours after the predetermined time at which the staying at the extracted staying place staying point is extracted as the next staying place staying point, thereby different staying place staying points. Points may be extracted. For example, in the case of the stay point information 212 of FIG.
  • the behavior feature extraction unit 302 has previously acquired a stay point identifier s1 of the home stay point and a stay point identifier s5 of the work place stay point.
  • the behavior feature extraction unit 302 has an intermediate time (03/173 03) between the user's arrival at the home and the departure in the stay at the home stay point (stay data identifier 9) of the stay point information 212 in FIG. : 45) as a reference, the staying point of the staying point identifier s10 is extracted as the staying point staying point as the staying point stayed 24 hours after that time (03/18 03:45).
  • the behavior feature extraction unit 302 may use a staying point staying at a predetermined time in the middle of the night as an overnight stay.
  • the behavior feature extraction unit 302 sets the staying point information 212 received by the behavior type reference unit 301 as the home staying point for the extracted staying destination, and sets either the home staying point or the workplace staying point as the starting point and A chain of staying points as end points is extracted (step S403).
  • FIG. 18 is a diagram illustrating an example of a result of extraction of a chain of stay points in the second embodiment of the present invention.
  • the behavior feature extraction unit 302 extracts chains (chain identifiers c1 to c5) as illustrated in FIG. 18 from the stay point information 212 illustrated in FIG.
  • the behavior feature extraction unit 302 calculates the stay point relevance level and the chain relevance level after assigning the stay point type to each stay point and transmits the behavior point to the behavior feature reference device 400 (step S404).
  • ⁇ S407) are the same as those of the first embodiment of the present invention (FIG. 5, steps S303 to S306).
  • FIG. 19 is a diagram illustrating an example of a stay point classification result according to the second embodiment of the present invention.
  • the behavior feature extraction unit 302 classifies each stay point other than the start point and end point on the chain (chain identifiers c1 to c5) in FIG. 18 according to the stay point type in FIG.
  • the retention point type is assigned as follows.
  • FIG. 20 is a diagram showing the staying point relevance information 312 in the second embodiment of the present invention.
  • the behavior feature extraction unit 302 calculates the stay point relevance degree as shown in FIG. 20 according to the calculation formula of FIG.
  • FIG. 21 is a diagram showing the linkage relevance information 313 in the second embodiment of the present invention.
  • the behavior feature extraction unit 302 performs the chain relevance as shown in FIG. 21 for each of the chains (chain identifiers c1 to c5) in FIG. Is calculated.
  • the relationship between the stay location of the user and the action type, and the relationship between the stay location chain and the action type, even when the stay location of the user includes an overnight stay. Can be extracted.
  • the reason is that the behavior feature extraction unit 302 extracts the staying point stay point from the staying point information 212, extracts the staying point chain as the staying point staying point at home, the staying point relevance level, and the chain relation This is to calculate the degree.
  • the behavior type extraction device 200 extracts the behavior type data 211 based on the position information acquired by the terminal 100, and the behavior feature extraction device 300 uses the behavior type data 211 based on the behavior type data 211. 311 is extracted.
  • the behavior feature extraction device 300 may extract the behavior feature data 311 based on the behavior type data 211 manually input to the behavior feature extraction device 300.
  • a plurality of stay points including a stay point of the first action base type corresponding to the first action type and a stay point of the second action base type corresponding to the second action type where the user has stayed.
  • behavior type storage means for storing residence point information including information indicating the order of residence at the residence point;
  • the stay point information is acquired from the behavior type storage means, and based on the stay point information, either the stay point of the first action base type or the stay point of the second action base type is obtained.
  • a chain of stay points is extracted as a start point, and one of the stay points of the first action base type and the stay point of the second action base type is an end point, and is included in the extracted chain
  • For each stay point based on the action base type of the start point and the end point, a first stay point relevance level indicating the degree of association between the stay point and the first action type, and the stay point And at least one of the second residence point association degrees indicating the degree of association between the second action type and the calculated residence point association degree for each residence point included in the chain.
  • Action feature including action feature extracting means for outputting Detection device.
  • the behavior feature extraction means includes When calculating the first residence point relevance for each residence point included in the chain, In the first case where the action base type of the start point is the first action base type and the action base type of the end point is the first action base type, the first stay point relevance degree Is a predetermined value a, In the second case where the action base type at the start point is the second action base type and the action base type at the end point is the second action base type, the first dwell point relevance degree Less than the first residence point relevance in the first case, In the third case where the behavior base type at the start point is the second behavior base type and the behavior base type at the end point is the first behavior base type, the first dwell point relevance degree Less than the first residence point relevance in the first case and greater than the first residence point relevance in the fourth case, In the fourth case where the action base type of the start point is the first
  • the second residence point relevance is set to be equal to or lower than the second residence point relevance in the second case and larger than the second residence point relevance in the third case.
  • the behavior feature extraction device according to (Appendix 1). (Appendix 3) The behavior feature extraction means calculates the stay point relevance for each stay point included in the chain based on the behavior base type of the start point and the end point and the order of the stay point on the chain. The behavior feature extraction device according to (Appendix 1) or (Appendix 2) to be calculated. (Appendix 4)
  • the behavior feature extracting means further includes a first indicating a degree of association between the chain and the first action type based on the first stay point relevance of each stay point included in the chain.
  • the second chain association degree indicating the degree of association between the chain and the second action type based on the second association point and the second stay point association degree of each stay point included in the chain
  • the behavior feature extraction device according to any one of (Appendix 1) to (Appendix 3), which calculates at least one of them and outputs the calculated degree of linkage.
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the residence point information further includes a residence start time indicating a time when the residence at the residence point is started and a residence end time indicating a time when the residence at the residence point is finished
  • the behavior feature extraction means extracts the staying point of the user's staying place from the staying points based on the staying start time and the staying end time, and the staying point of the staying place is the home
  • the behavior feature extraction device according to any one of (Appendix 1) to (Appendix 4), wherein the stay point relevance is calculated as a stay point.
  • action type extracting means for extracting stay point information including information indicating the order of stay at the stay point;
  • the stay point information is acquired from the behavior type extracting means, and based on the stay point information, either the stay point of the first action base type or the stay point of the second action base type is obtained.
  • a chain of stay points is extracted as a start point, and one of the stay points of the first action base type and the stay point of the second action base type is an end point, and is included in the extracted chain
  • For each stay point based on the action base type of the start point and the end point, a first stay point relevance level indicating the degree of association between the stay point and the first action type, and the stay point And at least one of the second residence point association degrees indicating the degree of association between the second action type and the calculated residence point association degree for each residence point included in the chain.
  • Action feature including action feature extracting means for outputting Out system.
  • the behavior feature extraction means includes When calculating the first residence point relevance for each residence point included in the chain, In the first case where the action base type of the start point is the first action base type and the action base type of the end point is the first action base type, the first stay point relevance degree Is a predetermined value a, In the second case where the action base type at the start point is the second action base type and the action base type at the end point is the second action base type, the first dwell point relevance degree Less than the first residence point relevance in the first case, In the third case where the behavior base type at the start point is the second behavior base type and the behavior base type at the end point is the first behavior base type, the first dwell point relevance degree Less than the first residence point relevance in the first case and greater than the first residence point relevance in the fourth case, In the fourth case where the action base type of the start point is the
  • the second residence point relevance is set to be equal to or lower than the second residence point relevance in the second case and larger than the second residence point relevance in the third case.
  • the behavior feature extraction system according to (Appendix 6).
  • the behavior feature extraction means calculates the stay point relevance for each stay point included in the chain based on the behavior base type of the start point and the end point and the order of the stay point on the chain.
  • the behavior feature extracting means further includes a first indicating a degree of association between the chain and the first action type based on the first stay point relevance of each stay point included in the chain.
  • the second chain association degree indicating the degree of association between the chain and the second action type based on the second association point and the second stay point association degree of each stay point included in the chain
  • the behavior feature extraction system according to any one of (Appendix 6) to (Appendix 8), which calculates at least one of them and outputs the calculated degree of linkage.
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the residence point information further includes a residence start time indicating a time when the residence at the residence point is started and a residence end time indicating a time when the residence at the residence point is finished
  • the behavior feature extraction means extracts the staying point of the user's staying place from the staying points based on the staying start time and the staying end time, and the staying point of the staying place is the home
  • the behavior feature extraction system according to any one of (Appendix 6) to (Appendix 9) that calculates the stay point relevance as a stay point.
  • a plurality of stay points including a stay point of the first action base type corresponding to the first action type and a stay point of the second action base type corresponding to the second action type where the user has stayed. For each, based on stay point information including information indicating the order of stay at the stay point, either the stay point of the first action base type or the stay point of the second action base type As a starting point, extract the chain of staying points whose end point is either the staying point of the first action base type and the staying point of the second action base type, For each stay point included in the extracted chain, based on the action base type of the start point and the end point, a first stay point indicating the degree of association between the stay point and the first action type Calculating at least one of a relevance level and a second dwell point relevance level indicating a relevance level between the dwell point and the second action type; A behavior feature extraction method for outputting the calculated staying point relevance for each staying point included in the chain.
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the first stay point relevance degree Is a predetermined value a
  • the action base type at the start point is the second action base type and the action base type at the end point is the second action base type
  • the first dwell point relevance degree Less than the first residence point relevance in the first case
  • the behavior base type at the start point is the second behavior base type and the behavior base type at the end point is the first behavior base type
  • the first dwell point relevance degree Less than the first residence point relevance in the first case and greater than the first residence point relevance in the fourth case
  • the action base type of the start point is the first action base type and the
  • the second residence point relevance is set to be equal to or lower than the second residence point relevance in the second case and larger than the second residence point relevance in the third case.
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the residence point information further includes a residence start time indicating a time when the residence at the residence point is started and a residence end time indicating a time when the residence at the residence point is finished
  • the stay point of the user's staying place is extracted from the plurality of staying points, and the staying point of the staying place
  • the behavior feature extraction method according to any one of (Appendix 11) to (Appendix 14), wherein the residence point relevance is calculated using the home residence point.
  • a plurality of stay points including a stay point of the first action base type corresponding to the first action type and a stay point of the second action base type corresponding to the second action type where the user has stayed. For each, based on stay point information including information indicating the order of stay at the stay point, either the stay point of the first action base type or the stay point of the second action base type As a starting point, extract the chain of staying points whose end point is either the staying point of the first action base type and the staying point of the second action base type, For each stay point included in the extracted chain, based on the action base type of the start point and the end point, a first stay point indicating the degree of association between the stay point and the first action type Calculate at least one of the degree of association and the degree of association of the second stay point indicating the degree of association between the stay point and the second action type, and calculate for each stay point included in the chain
  • the computer-readable recording medium which stores the action feature extraction program which performs the process which outputs the said staying
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the first stay point relevance degree Is a predetermined value a
  • the action base type at the start point is the second action base type and the action base type at the end point is the second action base type
  • the first dwell point relevance degree Less than the first residence point relevance in the first case
  • the behavior base type at the start point is the second behavior base type and the behavior base type at the end point is the first behavior base type
  • the first dwell point relevance degree Less than the first residence point relevance in the first case and greater than the first residence point relevance in the fourth case
  • the action base type of the start point is the first action base type and the
  • the second residence point relevance is set to be equal to or lower than the second residence point relevance in the second case and larger than the second residence point relevance in the third case.
  • a computer-readable recording medium storing the behavior feature extraction program according to (Appendix 16).
  • (Appendix 18) When calculating the stay point relevance, for each stay point included in the chain, the stay point based on the action base type of the start point and the end point and the order of the stay point on the chain
  • a computer-readable recording medium storing the behavior feature extraction program according to (Appendix 16) or (Appendix 17) for calculating the degree of association.
  • the first action type is work or school
  • the first action base type is workplace or school
  • the second action type is private
  • the second action base type is a residence point at home
  • the residence point information further includes a residence start time indicating a time when the residence at the residence point is started and a residence end time indicating a time when the residence at the residence point is finished
  • the stay point of the user's staying place is extracted from the plurality of staying points, and the staying point of the staying place
  • the present invention can be applied not only to information distribution using user behavior characteristics but also to user probe data creation in a trade area survey or traffic volume survey.
  • Action feature extraction system 100 Terminal 101 Position information acquisition part 111 Position information data 200 Action type extraction apparatus 201 Action type extraction part 202 Action type storage part 211 Action type data 212 Staying point information 300 Action feature extraction apparatus 301 Action type reference part 302 Behavior feature extraction unit 303 Behavior feature storage unit 311 Behavior feature data 312 Residence point association degree information 313 Chain association degree information 400 Behavior feature reference device

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Le dispositif d'extraction de caractéristiques d'actions ci-décrit extrait d'un historique d'informations de position les relations existant entre les emplacements d'habitation des utilisateurs et des types d'actions. Ledit dispositif d'extraction de caractéristiques d'actions (300) contient une unité de mémorisation de types d'actions (202) et une unité d'extraction de caractéristiques d'actions (302). Ladite unité de mémorisation de types d'actions (202) mémorise des informations sur les points d'habitation (212) comprenant des informations indiquant dans quel ordre un utilisateur est resté dans une pluralité de points d'habitation incluant un point d'habitation d'un premier type de base d'action qui correspond à un premier type d'action ainsi qu'un point d'habitation d'un second type de base d'action qui correspond à un second type d'action. Grâce à ces informations sur les points d'habitation (212), l'unité d'extraction de caractéristiques d'actions (302) extrait une chaîne de points d'habitation dont le point d'habitation du premier type de base d'action ou le point d'habitation du second type de base d'action est le point de départ, et l'autre de ces deux points d'habitation est le point d'arrivée. Grâce aux types de bases d'actions dudit point de départ et dudit point d'arrivée, l'unité d'extraction de caractéristiques d'actions (302) calcule et émet, pour chaque point d'habitation de la chaîne de points d'habitation extraite, un degré d'association de point d'habitation qui indique le degré d'association entre ce point d'habitation et un type d'action.
PCT/JP2011/061126 2010-05-13 2011-05-10 Dispositif d'extraction de caractéristiques d'actions, système d'extraction de caractéristiques d'actions, procédé d'extraction de caractéristiques d'actions et programme d'extraction de caractéristiques d'actions WO2011142471A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2012514855A JPWO2011142471A1 (ja) 2010-05-13 2011-05-10 行動特徴抽出装置、行動特徴抽出システム、行動特徴抽出方法、及び行動特徴抽出プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2010111031 2010-05-13
JP2010-111031 2010-05-13

Publications (1)

Publication Number Publication Date
WO2011142471A1 true WO2011142471A1 (fr) 2011-11-17

Family

ID=44914520

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2011/061126 WO2011142471A1 (fr) 2010-05-13 2011-05-10 Dispositif d'extraction de caractéristiques d'actions, système d'extraction de caractéristiques d'actions, procédé d'extraction de caractéristiques d'actions et programme d'extraction de caractéristiques d'actions

Country Status (2)

Country Link
JP (1) JPWO2011142471A1 (fr)
WO (1) WO2011142471A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019204197A (ja) * 2018-05-22 2019-11-28 株式会社Ｎｔｔドコモ 行動推定装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146249A (ja) * 2006-12-07 2008-06-26 Nippon Telegraph & Telephone West Corp プローブデータ解析システム
JP2009043057A (ja) * 2007-08-09 2009-02-26 Nomura Research Institute Ltd 行動履歴分析装置及び方法
JP2010134762A (ja) * 2008-12-05 2010-06-17 Nec Corp 情報通知システム、情報通知方法およびプログラム
WO2011046113A1 (fr) * 2009-10-14 2011-04-21 日本電気株式会社 Système, dispositif, procédé et programme éducatif de type de comportement, et support d'enregistrement sur lequel ledit programme est enregistré

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146249A (ja) * 2006-12-07 2008-06-26 Nippon Telegraph & Telephone West Corp プローブデータ解析システム
JP2009043057A (ja) * 2007-08-09 2009-02-26 Nomura Research Institute Ltd 行動履歴分析装置及び方法
JP2010134762A (ja) * 2008-12-05 2010-06-17 Nec Corp 情報通知システム、情報通知方法およびプログラム
WO2011046113A1 (fr) * 2009-10-14 2011-04-21 日本電気株式会社 Système, dispositif, procédé et programme éducatif de type de comportement, et support d'enregistrement sur lequel ledit programme est enregistré

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019204197A (ja) * 2018-05-22 2019-11-28 株式会社Ｎｔｔドコモ 行動推定装置
JP7053371B2 (ja) 2018-05-22 2022-04-12 株式会社Ｎｔｔドコモ 行動推定装置

Also Published As

Publication number Publication date
JPWO2011142471A1 (ja) 2013-07-22

Similar Documents

Publication Publication Date Title
CN108765933B (zh) 一种推荐上车点的方法、装置、设备及存储介质
JP6904637B2 (ja) 輸送停車場ロケーションを決定するためのシステムと方法
WO2011102541A1 (fr) Dispositif d'extraction de caractéristiques de comportement, système d'extraction de caractéristiques de comportement, procédé d'extraction de caractéristiques de comportement et programme d'extraction de caractéristiques de comportement
WO2012018131A1 (fr) Dispositif d'extraction de caractéristique d'action, système d'extraction de caractéristique d'action, procédé d'extraction de caractéristique d'action et programme d'extraction de caractéristique d'action
US9301099B2 (en) Method of analyzing points of interest with probe data
CN104599002B (zh) 预测订单价值的方法及设备
CN108537352A (zh) 一种数据处理方法、装置和服务器
JP6396686B2 (ja) 行動判定装置、行動判定方法及びプログラム
JP2010271205A (ja) 経路検証システムにおける経路検証方法
JP2016143232A (ja) 位置情報管理装置及び位置情報管理方法
EP3425339A1 (fr) Dispositif d'estimation de position, procédé et programme d'estimation de position
CN108763374B (zh) 一种行驶路径展示方法、装置及设备
JP6982237B2 (ja) 候補位置評価プログラム、候補位置評価装置、及び候補位置評価方法
JP2020091681A (ja) データ分析装置、データ分析システム、データ分析方法およびデータ分析プログラム
US9702720B2 (en) Navigation server for determining location-based advertisement effectiveness
US20040111241A1 (en) Communication terminal and information processing apparatus of a payment system
US10145705B2 (en) Destination information provider server, destination information provider system and on-vehicle device
JP2018077756A (ja) 対象経路を含む移動位置範囲群に基づき通行量を推定する装置、プログラム及び方法
WO2011142471A1 (fr) Dispositif d'extraction de caractéristiques d'actions, système d'extraction de caractéristiques d'actions, procédé d'extraction de caractéristiques d'actions et programme d'extraction de caractéristiques d'actions
EP1388824A2 (fr) Terminal de communication et dispositif de traitement d'informations d'un système de paiement
CN114692968A (zh) 取号处理方法、装置以及电子设备
JP2019046347A (ja) 情報処理装置、情報処理システム、情報処理方法及びプログラム
JP6316597B2 (ja) 情報処理サーバ、情報処理方法及び情報処理プログラム
KR20130082672A (ko) 이동 통신 장치의 교통 정보 검색 방법
JP2017168040A (ja) 保険条件決定装置、保険条件決定方法、およびプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11780726

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2012514855

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 11780726

Country of ref document: EP

Kind code of ref document: A1