WO2013030942A1 - 行動履歴の管理システム及び行動履歴の管理方法 - Google Patents
行動履歴の管理システム及び行動履歴の管理方法 Download PDFInfo
- Publication number
- WO2013030942A1 WO2013030942A1 PCT/JP2011/069534 JP2011069534W WO2013030942A1 WO 2013030942 A1 WO2013030942 A1 WO 2013030942A1 JP 2011069534 W JP2011069534 W JP 2011069534W WO 2013030942 A1 WO2013030942 A1 WO 2013030942A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- history
- user
- point
- behavior
- action
- Prior art date
Links
- 238000007726 management method Methods 0.000 title claims description 109
- 238000012217 deletion Methods 0.000 claims abstract description 69
- 230000037430 deletion Effects 0.000 claims abstract description 69
- 238000013523 data management Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 12
- 230000000717 retained effect Effects 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 description 122
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Definitions
- the present invention relates to an action history management system and an action history management method for managing an action history of a user using a database.
- information terminals such as personal computers have stored user behavior histories, including the history of searches performed using an internetwork, in a database, and information to be recommended to users based on the stored behavior histories.
- There are services such as providing recommended information to users.
- an action history gradually increases as the user continues to use the information terminal, the amount of data that can be stored in a database that stores such an action history is finite. For this reason, such information terminals are usually managed by deleting the action history stored in the database in order from the oldest one so that the data amount does not exceed the storable capacity.
- Patent Document 1 describes a system for storing an action history when a user moves to a specific place in a database and managing the saved action history. Furthermore, in the system described in Patent Document 1, the action history to be stored in the database is limited to an extraordinary action that deviates from the average action. As a result, the database stores only the unusual behavior and a history of a part of all the behaviors, thereby reducing the amount of data stored in the database.
- the utility value may be higher than the new behavior history as data.
- the action history stored in the database is deleted from the oldest storage date and the newly acquired action history is left in the database, the action history having high utility value for the user is not necessarily stored as data. Is not limited. And even if there is a service provided based on the action history managed in such a database, such a service does not necessarily meet the user's request.
- the present invention has been made in view of such circumstances, and its purpose is to preferentially hold an action history having high utility value for the user when storing the action of the user as data in the database.
- an action history management system is an action history management system that manages an action history while storing the action history of the user in a database, and serves as a core of the action of the user.
- a point identifying unit for identifying a point and an action history having low relevance between the point specified by the point specifying unit are specified, and when the data is deleted from the database, the specified action history is preferentially deleted.
- a data management unit is an action history management system that manages an action history while storing the action history of the user in a database, and serves as a core of the action of the user.
- an action history management method is an action history management method for managing an action history while storing the action history of a user in a database, and is a core point of the action of the user And identifying a behavior history having low relevance to the identified point, and deleting the data from the database in preference to the identified behavior history.
- Such an action history can be used as an index when the user performs the next action, for example, by presenting the action history to the user.
- the action history that is highly related to the point that is the core of the user's action has a higher probability of matching with the action that the user will perform next, and its use value is also higher. Therefore, the action history having a higher relevance to the point that is the core of the user's action is more likely to be stored in the database in which the action history is stored.
- a point that is the core of the user's action is specified, and an action history that is less relevant to the specified point is specified.
- the action history having a low relevance to the point that is the core of the user's action is preferentially deleted from the action history stored in the list.
- an action history having high relevance with the point that is the core of the user's action is stably held, and the user's action history is appropriately stored, but it is useful for the user.
- a high action history can be stored in the database for a long time.
- the point that is the core of the user's behavior is specified separately for one or more categories based on the user's behavior history, and the point specifying unit is configured for the user according to the category.
- the point which becomes the core of this action is specified, and it is summarized that the database stores the action history according to the category.
- the point that is the core of the user's behavior is identified according to one or more categories based on the user's behavior history, and the point according to the identified category is The gist is to store the action history in the database.
- a predetermined search site or a predetermined site is the core of the user's behavior, and various searches are performed based on the core site. For example, a site that is frequently transferred from the core site or a site that has a long browsing time has a higher relevance to the core site and is highly available to the user.
- the user's action history (viewing history) on the site reflecting the location of the site with high availability and the content of the site is also highly useful to the user.
- the user's behavior is geographical movement
- the user's home is a point that becomes the core of the user's behavior.
- the movement history of the user who moves from this home is stored in the database as the action history of the user.
- the point that is the core of the user's action is specified for one or more categories based on the user's action history, and the user's action history is stored in the database for the specified category. To do.
- the point that becomes the core of the user's action differs for each category, the point that becomes the core of the user's action is specified for each category, and the action history highly related to the specified point is stored in the database. Precedence is retained. Therefore, even when action histories of a plurality of categories are to be stored in the database, various action histories having high utility values can be stably held in the database.
- the behavior history is a history indicating the behavior of the user each time the user heads to the destination, and the data management unit sets the destination with a low relevance to the identified point.
- the gist is to specify an action history when heading as a deletion target from the database.
- the behavior history is a history indicating the behavior of the user every time the user goes to the destination, and in the deleting step, the behavior history is directed to the destination having a low relevance to the identified point.
- the gist is to specify the action history at the time of deletion as the data to be deleted from the database.
- the latitude and longitude of the destination, the travel route to the destination, and data indicating the user's behavior at the destination are stored in the database as the user's behavior history.
- the action history when it heads for the destination with low relevance with the specified point among this action history is specified as a candidate for deletion from a database.
- the point that is the core of the user's behavior is the geographical base of the user
- the data management unit determines the low relevance between the identified point and the behavior history, The gist is to obtain it based on the distance from the geographical base of the user to the destination.
- a user's geographical base is specified as a point that is a core of the user's behavior
- the user's geographical base is The gist is to determine the low relevance between the identified point and the action history based on the distance to the destination.
- the distance from the geographical base to the destination is likely to be an index when the user selects the destination, and the relationship between the user's behavior history and the geographical base It is possible to use the distance from the user's geographical base to the destination as one of the judgment materials.
- the low relevance between the identified point and the action history is obtained based on the distance from the user's geographical base to the destination. This makes it possible to accurately specify the action history to be deleted based on the distance from the user's geographical base to the destination.
- the data management unit is directed to a destination that is relatively far from the geographical base of the user as an action history having a low relevance between the identified point and the action history.
- the gist is to identify the action history of the time.
- destinations closer to the user's home or the like tend to visit the destination in the near future. And the destination farther from home or the like tends to prevent the user from revisiting this destination.
- the closer the destination from the geographical base such as the user's home and the base the higher the relation between the base and the destination, and the geographical base such as the user's home and the base from the base. The farther away the destination, the lower the relationship between the base and the destination.
- the action history indicating the destination that is relatively far from the user's geographical base is specified as the action history having a low relevance between the point and the action history.
- the action history indicating a destination that is relatively far from the user's geographical base that is, the user visits again.
- Delete the action history indicating the destination with low possibility from the database As a result, the action history that is unlikely to be visited again by the user is preferentially deleted from the database, and conversely, the action history that is likely to be visited again by the user is retained in the database for a long time.
- the data management unit also manages the acquisition date and time of the user's action history, and takes the action history to be deleted preferentially from the database in consideration of the acquisition date and time of the action history.
- the gist is to specify.
- the method when the behavior history of the user is acquired, the method further includes the step of assigning the acquisition date and time to the behavior history, and in the step of specifying the behavior history, the acquisition date and time given to the behavior history is Taking this into consideration, the gist is to specify an action history to be deleted preferentially from the database.
- the user's behavior pattern also correlates with the date and time when the user performed various behaviors.
- a relatively new behavior history reflects the current behavior pattern of the user, and this behavior pattern may be performed in the future. There is a high possibility of being caught. That is, among the action histories that are acquired as appropriate, the action history with a relatively new acquisition date is more likely to reflect the current user action and has a higher utility value.
- the user's geographical base is a point that is the core of the user's behavior
- the behavior of the user from the geographical base toward the destination is managed as the behavior history
- the acquisition date is a relatively new action history
- the action history indicated by the action history indicates the user's action near the point
- the use value of this action history is extremely high.
- the action history will be stored in the database for a long time.
- the data management unit multiplies the element indicating the relationship between the identified point and the action history, and the acquisition date and time of the action history by a different coefficient, and by the multiplication
- the gist is to identify an action history to be deleted preferentially from the database based on two obtained multiplication values.
- the element indicating the relationship between the identified point and the action history and the acquisition date and time of the action history are multiplied by different coefficients, so that the element and the acquisition date and time are deleted. It is possible to change the degree of influence when specifying the action history to be performed. That is, by changing each coefficient, it is possible to dynamically change the influence degree of the acquisition date and the influence degree of the distance when deleting the action history.
- the coefficient by which the acquisition date is multiplied is decreased, and the coefficient by which the distance as the element is increased is increased. It is possible to manage action history with emphasis on. Therefore, it is possible to manage the action history with a higher degree of freedom.
- the data management unit determines a low or low relevance between the identified point and the behavior history as a common or similar behavior among behavior histories that diverge from the identified point.
- the gist is to determine the frequency based on at least one of the occurrence frequency of the action history to be shown and the user's stay time at the target point from the identified point.
- the actions that diverge from the core point and are repeatedly performed are actions unique to the user, and are likely to be continued in the future.
- history which shows such an action exists in the tendency for a user's use value to be high.
- a time when a certain user stays in a predetermined store and a browsing time (stay time) when browsing a predetermined site tend to reflect the user's preference, and stores that stay for a long time.
- the low relevance between the identified point and the action history is determined based on at least one of the occurrence frequency of the action history and the stay time of the user at the target point. In this case, it is possible to preferentially store an action history having a high utility value for the user in the database.
- the action history is a movement history of a vehicle operated by the user.
- the movement history of the vehicle acquired through the portable information terminal owned by the user or the in-vehicle information terminal mounted on the vehicle is stored in the database as the user's action history. Therefore, it is difficult to determine the use value only with the acquisition date and time, and the movement history of the vehicle used for transportation to various destinations from short distance to long distance is also highly useful for the user. Can be stably held in the database.
- This also creates a list of destinations that the user has headed in the past based on the travel history stored in the database and a route plan for travel routes that the user has used in the past. It is also possible to present the route plan to the user through a navigation system mounted on the vehicle, for example. At this time, the list of destinations and the route plan presented to the user are created based on an action history having high utility value for the user and high repeatability. A list of destinations with a high probability and a route plan are presented to the user.
- the point specifying unit learns information about departure / arrival points including a departure point where the user has departed and an arrival point where the user who has departed the departure point has arrived, and Among these, the gist is to estimate a departure point having a relatively large distribution of arrival points that diverge from a common departure point as a point that becomes the core of the user's behavior.
- a user's action history tends to go to various destinations such as a company or a store from his home, and the departure and arrival points are distributed in various directions and regions from the same departure point. And arrival point.
- the arrival point when the departure point is the same is likely to be a limited point, such as home, and variations in the arrival point with respect to the departure point Will be less.
- FIG. 1 is a block diagram showing a schematic configuration of a system to which the management system and the management method are applied according to a first embodiment of an action history management system and an action history management method according to the present invention.
- (A) is a figure which shows an example of the movement history preserve
- (B) is a figure which shows an example of the appropriateness of deletion about the movement history.
- the flowchart which shows an example of the deletion procedure of the movement history by the action history management system and action history management method of this Embodiment. It is an image figure of the movement history preserve
- (a)-(e) is a figure which shows an example of the deletion mode of the movement history by the action history management system and action history management method of this Embodiment.
- (A) is a figure which shows an example of the specific aspect of the movement history which should be made into the deletion target based only on the acquisition date of movement history.
- (B) is a figure which shows an example of the specific aspect of the movement history which should be made into the deletion object by the action history management system and action history management method of this Embodiment.
- the block diagram which shows schematic structure of the system by which the management system and the management method are applied about 2nd Embodiment of the management system of action history and the management method of action history concerning this invention.
- (A)-(c) is a figure which shows an example of the estimation aspect of the base by the point specific
- the block diagram which shows schematic structure of the system to which the management system and the management method are applied about 3rd Embodiment of the management system of behavior history and the management method of action history concerning this invention.
- the figure which shows an example of the specific aspect of the movement history which should be made into the deletion object by the action history management system and action history management method of this Embodiment.
- the block diagram which shows schematic structure of the system by which the management system and the management method are applied about 4th Embodiment of the management system of behavior history and the management method of action history concerning this invention.
- the figure which shows an example of the relevance with the homepage used as the core of a user's action, and the website utilized on the basis of the homepage.
- the figure which shows an example of the specific aspect of the movement history which should be made into the deletion object about other embodiment of the action history management system and action history management method concerning this invention The figure which shows an example of the specific aspect of the movement history which should be made into the deletion object about other embodiment of the action history management system and action history management method concerning this invention.
- a first embodiment embodying an action history management system and an action history management method according to the present invention will be described below with reference to FIGS.
- the action history management system and the action history management method of this embodiment manage, for example, the movement history of a vehicle moving from a driver's home or the like as a base.
- the behavior history management system and behavior history management method of the present embodiment the user's geographical base is targeted as a core point of the user's behavior, and the user's geography as the behavior history category. Bases and geographical movements are set up.
- the action history management system of the present embodiment is mounted on a vehicle C such as an automobile, for example, and is largely input to an input system to which various information is input, and this input system. And a management system (data management unit) that manages the information recorded in the recording system.
- a management system data management unit
- the input system is provided with an input unit 110 in which various operations are performed by a driver of the vehicle C or the like.
- the input unit 110 is used, for example, when information related to a driver's home address or the like is input as a core point of driver's action.
- the input unit 110 outputs the input information to the point specifying unit 120 that specifies the driver's geographical base based on the information.
- the input unit 110 is also used when route guidance to the destination is performed by the navigation system 400 mounted on the vehicle C. For example, the name, area name, address, etc. of the store as the destination are input.
- the input unit 110 outputs the input information regarding the destination to the navigation system 400.
- the point specifying unit 120 specifies the point indicating the absolute position indicated by the address or the like as the driver's geographical base. And the point specific
- a GPS 130 is provided in the input system.
- the GPS 130 receives a GPS satellite signal for detecting the absolute position of the vehicle C, and appropriately detects the position of the vehicle based on the received GPS satellite signal.
- the GPS 130 detects the position information of the vehicle C
- the GPS 130 outputs the detected position information to the behavior learning unit 140.
- the position information which shows the latitude longitude of the vehicle C which changes with driving
- the behavior learning unit 140 When the position information of the vehicle C is input from the GPS 130, the behavior learning unit 140, for example, the travel route from the departure point where the vehicle C departs to the arrival point (destination point) where the vehicle C arrives, the name of the arrival point, Learn latitude and longitude as appropriate. In addition, the behavior learning unit 140 calculates the distance from the geographical base of the vehicle C to the arrival point based on the positional information of the vehicle C input from the GPS 130 and the information about the geographical base input from the point specifying unit 120. learn. Furthermore, the behavior learning unit 140 according to the present embodiment also learns the date and time when the behavior of the vehicle C to be learned has occurred by giving the acquisition date and time of the information to the information to be learned. And the action learning part 140 outputs this learning result to the database 200 suitably as a movement history (action history) of the vehicle C.
- the database 200 registers this information as information indicating the geographical base of the driver.
- the database 200 appropriately stores the input movement history. Thereby, whenever the vehicle C arrives at the destination set by the driver, the movement history of the vehicle C is appropriately stored in the database 200, and the movement history of the vehicle C is accumulated.
- the movement history input from the behavior learning unit 140 is a history toward a destination that is common to the movement history already stored in the database 200, the movement history is already stored in the database 200. The movement history is overwritten on the movement history newly input from the behavior learning unit 140.
- the amount of movement history data that the database 200 can hold is finite in proportion to the capacity of the database 200.
- the management system that manages the database 200 includes a deletion necessity determination unit 310 that determines whether or not the data amount of the movement history accumulated in the database 200 has reached the data amount that can be stored in the database 200. It has been.
- the deletion necessity determination unit 310 monitors the data amount of the movement history accumulated in the database 200 and determines whether this data amount exceeds the capacity of the database 200.
- the deletion necessity determination unit 310 determines that the data amount of the movement history accumulated in the database 200 exceeds the capacity of the database 200 as the movement history of the vehicle C increases, the determination result is:
- the data is output to the deletion target data determination unit 320 that specifies the movement history to be deleted from the movement history stored in the database 200.
- the deletion target data determination unit 320 receives the geographical information of the driver of the vehicle C from the movement history registered in the database 200. A movement history related to a destination that is relatively far from the base is specified as a movement history to be deleted. Then, the deletion target data determination unit 320 outputs the identification result to the data deletion unit 330 that executes a movement history deletion process based on the identification result.
- the data deletion unit 330 extracts the movement history specified as the history to be deleted from the database 200 based on the identification result, and the extracted movement history is delete. Then, such movement history deletion processing is executed in accordance with the data amount of the movement history accumulated in the database 200, so that the data amount of movement history accumulated in the database 200 falls within the capacity range of the database 200. Maintained. As a result, the newly acquired movement history is stored in the database 200 in place of the deleted movement history.
- the navigation system 400 selects a destination by the driver of the vehicle C, for example, the movement history stored in the database 200 is displayed on the display device 410 configured by a liquid crystal display or the like. Specifically, for example, the navigation system 400 creates image data indicating a list of names and the like of arrival points where the vehicle C has traveled so far, based on the movement history accumulated in the database 200. The created image data is output to the display device 410. As a result, the display device 410 displays a list of information indicating the arrival points where the vehicle C has arrived, in other words, the names of the arrival points such as stores used by the driver of the vehicle C and the like.
- the navigation system 400 can reach the candidate points.
- Route guidance for Specifically, for example, the navigation system 400 displays, on the display device 410, the travel route that the vehicle C has used so far as a candidate route to the candidate point, based on the travel history stored in the database 200, for example. To do. As a result, a list screen of candidate points and a selection screen for candidate routes created based on the movement history of the vehicle C are displayed visually on the display device 410.
- the navigation system 400 selects a candidate point from the displayed candidate points by the driver, and when a candidate route is selected, the navigation system 400 provides route guidance to the candidate point on the candidate route through the display device 410. Performed by image guidance or voice guidance through a voice device (not shown).
- the movement histories 1 to 15 stored in the stream data management unit 200 are based on the relationship between the geographical base of the driver (user) and the destination.
- the movement history to be deleted is identified from the list. That is, normally, the farther the destination is from the geographical base, the farther from the geographical base of the user, the lower the probability that this destination will be used in the future.
- the movement history related to the destination that is far from the user's geographical base is less related to the user's geographical base.
- the movement history with the older acquisition date / time is less likely to match the current behavior pattern of the user, and the use value of the navigation system 400 as a candidate point or candidate route is lower. Therefore, the relevance with the user's geographical base is lower as the movement history is older.
- the movement history related to the destination that is closer to the user's geographical base is more relevant to the user's geographical base.
- the movement history having a new acquisition date / time is more likely to match the current behavior pattern of the user, and the use value as a candidate point or candidate route by the navigation system 400 is higher. Therefore, the relevance with the user's geographical base becomes higher as the movement history has a new acquisition date and time.
- the movement history related to the destination far from the geographical base, and the movement history with the older acquisition date / time is specified as the movement history to be deleted because it is less related to the geographical base. Is done.
- “deletion appropriateness” indicating whether or not it is appropriate to delete from the database 200 is used. This deletion appropriateness is calculated by, for example, the following equation (A), where “ ⁇ ” is the coefficient for the acquisition date and time of the movement history and “ ⁇ ” is the coefficient for the distance from the geographical base to the destination.
- Deletion appropriateness (calculation date / time-movement history acquisition date / time) x ⁇ + distance from the base x ⁇ (B)
- “calculation date / time” indicates the timing for calculating the appropriateness of deletion
- “movement history acquisition date / time” is obtained from the movement history that is the target for calculating the appropriateness of deletion.
- the date and time when it is possible to set arbitrary values for the coefficients “ ⁇ ” and “ ⁇ ”. For example, if the coefficient “ ⁇ ” is set larger than the coefficient “ ⁇ ”, the deletion appropriateness may be reduced. This increases the effect of the distance from the geographical base to the destination.
- the deletion appropriateness decreases as the movement history has a high relationship with the geographical base, and conversely increases as the movement history has a low relation with the geographical base.
- a part of the movement history stored in the database 200 based on these principles is appropriately deleted, so that the database 200 has high relevance to the user's geographical base, and the user has The movement history relating to the destination having a high probability of being used again is stably maintained. Accordingly, it is possible to secure a storage area necessary for storing the movement history when the movement history is newly acquired, while keeping the movement history having a high utility value in the database 200 for a long time. Become.
- step S100 when a movement history of the vehicle C is newly acquired as the vehicle C travels (step S100), the data amount of the movement history accumulated in the database 200 can be held in the database 200. It is determined whether or not an upper limit value has been reached (step S101).
- step S101 When the data amount of the movement history accumulated in the database 200 has reached the upper limit (step S101: YES), the relationship between each movement history accumulated in the database 200 and the user's geographical base is determined. Correlation deletion appropriateness is calculated (step S102). Thereby, as shown in FIG. 4A, each of the movement histories accumulated up to the upper limit value of the database 200 has an association with the geographical base of the user as shown in FIG. 4B, for example. “High”, “medium”, and “low” are specified, and the appropriateness of deletion is specified as “small”, “medium”, and “large”, respectively.
- the movement history that minimizes the relevance of the user to the geographical base in other words, the movement history that maximizes the appropriateness of deletion is specified.
- the identified movement history is extracted from the database 200 (step S104), and the extracted movement history is deleted from the database 200 (step S105).
- the movement history that has the minimum relevance to the user's geographical base is specified from the movement history accumulated in the database 200.
- FIG. As shown, this identified movement history is deleted from the database 200.
- step S106 in FIG. 3 the movement history acquired in step S100 is stored in the database 200.
- the newly acquired movement history is stored in the database 200 instead of the movement history having the relevance “small”.
- the movement history update mode managed by the behavior history management system and the behavior history management method of the present embodiment is compared with the movement history update mode managed by the conventional system. This will be described with reference to FIGS. 5 (a) and 5 (b).
- “1” is set for the coefficients “ ⁇ ” and “ ⁇ ”.
- the movement history when the vehicle C heads for “store B” located “4 km” away from the geographical base such as the user's home is “11 days ago”, for example.
- the movement history regarding this "store B” has the oldest acquisition date in the movement history shown in FIG. 5A
- the movement history regarding "store B” is specified as a deletion target in the conventional system.
- this “store B” is a destination that is closer to the user's geographical base than the other destinations “store A”, “facility A”, and “facility B”, and is used by the user. It is a highly likely destination.
- the deletion method based only on the acquisition date and time the movement history related to “Store B”, which is highly likely to be used by the user, is deleted preferentially.
- the movement history related to “facility B” existing at a position “50 km” away from the geographical base is specified as the deletion target. That is, the travel history related to “facility B” is acquired “seven days ago”, but other destinations “store A”, “store B”, “facility A”, “restaurant A”, “facility” C ". . It is predicted that the probability of being used again by the user is low because it is far from the geographical base than any of the above.
- the movement history related to “facility B” with low availability is deleted from the database 200 with priority.
- the movement history regarding the destination that is considered highly available based on the distance from the geographical base of the user is stably held in the database 200.
- a point that is the core of the user's action is specified, and a movement history that is not related to the specified point is specified. Then, when deleting the movement history from the database 200, the movement history having low relevance to the point that is the core of the user's action is preferentially deleted. For this reason, the database 200 can stably hold a movement history that is highly relevant to the point that is the core of the user's action. Thus, each time a user's movement history is acquired, the acquired movement history can be stored in the database 200 as appropriate, and a movement history having high utility value for the user can be preferentially held.
- the user's geographical base was identified as the core point of the user's behavior. Then, the low relevance between the point that is the core of the user's behavior and the movement history is determined based on the distance from the user's geographical base to the destination. Accordingly, it is possible to specify the movement history to be deleted based on an element that is different from the acquisition date and time of the movement history and can predict the probability that the user will use again.
- the movement history when the user is heading to a destination that is relatively far from the geographical base is identified.
- the movement history that is unlikely to be visited again by the user is preferentially deleted from the database 200, and the movement history that is likely to be visited again by the user is retained in the database 200 for a long period of time. It will be.
- the movement history related to the destination that is not highly available to general users is deleted from the database 200 with priority, and the versatility of the behavior history management system and the behavior history management method can be reduced. Enlargement can also be achieved.
- the movement history to be deleted preferentially from the database 200 is specified in consideration of the acquisition date and time included in the movement history. For this reason, it becomes possible to determine the necessity of data deletion from the viewpoint of both the relevance of the user to the moving base and the acquisition date and time, and it is possible to more accurately identify the movement history to be deleted. Become. Thereby, the necessity of storing in the database 200 is low from the viewpoint of the relevance of the user to the moving base, and the movement history having a low necessity of storing in the database 200 from the viewpoint of acquisition date is given priority from the database 200 It will be deleted. For this reason, the movement history related to the destination that has a very low probability of being used by the user is preferentially deleted, and the influence on the user due to the deletion of the movement history is minimized.
- the movement history of the vehicle C operated by the user is set as the category of the action history, and the movement history is managed.
- the history can be stably held in the database 200. This also makes it possible to present a candidate point and a candidate route to the destination based on the movement history held in the database 200 to the driver.
- the second embodiment of the action history management system and the action history management method according to the present invention is a diagram corresponding to FIG. 1 with a focus on differences from the first embodiment. This will be described with reference to FIG. 6 and FIG.
- the basic structure of the action history management system and the action history management method according to this embodiment is the same as that of the first embodiment, and FIG. 6 is substantially the same as that of the first embodiment.
- the same elements are denoted by the same reference numerals, and redundant descriptions are omitted.
- the point specifying unit 120A of the present embodiment records the information about the departure / arrival points including the departure point where the vehicle C started and the arrival point where the vehicle C departing from the departure point arrived.
- a point recording unit 121 is provided.
- the departure / arrival point recording unit 121 acquires information indicating the latitude and longitude when the accessory position (ACC) of the vehicle C in the stopped state is switched from the off state to the on state from the GPS 130. Then, the departure / arrival point recording unit 121 records the position of the vehicle C indicated by the acquired information as the departure point of the vehicle C.
- the departure / arrival point recording unit 121 also displays latitude and longitude information when the vehicle C stops from the departure point and arrives at the destination and the accessory position is switched from the on state to the off state. Obtained from GPS 130.
- the departure / arrival point recording unit 121 records the position of the vehicle C indicated by the acquired latitude / longitude information as an arrival point corresponding to the departure point.
- the departure / arrival point recording unit 121 associates the corresponding departure point and arrival point with each other, and records the associated departure point and arrival point as the departure / arrival point indicating the traveling history of the vehicle C.
- the point specifying unit 120A of the present embodiment includes a base estimation unit 122 that estimates the base of the vehicle C based on the departure / arrival points recorded by the departure / arrival point recording unit 121.
- the base estimation unit 122 obtains the frequency at which the vehicle C stays at each point based on the information about the departure / arrival points acquired from the vehicle C.
- required treats a predetermined area as one point like a radius of about "100 m", for example. That is, the site estimation unit 122 determines that the frequency at which the vehicle C stays at the same point increases as the number of start points of the vehicle C included in the predetermined area increases.
- the base estimation unit 122 identifies the top two representative points with the highest stay frequency when estimating the base of the vehicle C.
- the base location estimation unit 122 extracts information about the departure / arrival points including the departure points belonging to the predetermined area indicating the identified upper two points from the departure / arrival point recording unit 121. Thereafter, the base estimation unit 122 refers to each of the extracted arrival / departure points, and estimates a point having a relatively large distribution of arrival points that diverge from each of the top two points as a base of the vehicle C. .
- the point specifying unit 120A of the present embodiment outputs the base estimated as the base of the vehicle C by the base estimation unit 122 to the database 200 and the behavior learning unit 140 as the geographical base of the driver (user) of the vehicle C. .
- the behavior learning unit 140 learns the distance between the geographical base of the user estimated by the point specifying unit 120A and the movement history of the vehicle C, and outputs the learning result to the database 200.
- the base location estimation unit 122 first identifies the top two groups having the highest frequency of stay of the vehicle C among the groups G1 to Gn of the starting point groups.
- the group G1 in which the number of start points included in the circular area is the largest among the groups stored in the departure / arrival point recording unit 121 is specified.
- the group G2 having the largest number of start points included in the circular area next to the group G1 is specified.
- the difference in the number of start points included in the specified groups G1 and G2 is very small.
- the difference in the number of start points included in the groups G1 and G2 is 10% or less of the number of start points included in the group G1, The difference is determined to be minute.
- the base estimation part 122 diverges from each starting point included in these groups G1 and G2, when the difference of the number of each starting point included in each group G1 and G2 is a very small thing. Based on the distribution of arrival points, which representative point of each group G1 and G2 is determined as the base of the vehicle C.
- the majority of arrival point groups G1a to G1n corresponding to the departure point groups included in the group G1 having the highest stay frequency are representatives of the group G1. It tends to be distributed in a certain direction from the point Sg1. For this reason, variations such as directions and distances of arrival point groups G1a to G1n that diverge from the representative point Sg1 of the group G1 are also limited.
- the arrival point groups G2a to G2n corresponding to the departure point group included in the group G2 having the highest frequency of stay next to the group G1 are displayed from the representative point Sg2 of the group G2. It tends to be distributed in many directions. Various variations such as directions and distances of the arrival point groups G2a to G2n that diverge from the representative point Sg2 of the group G2 are diverse. Therefore, variations in the direction and distance of the arrival point groups G2a to G2n that diverge from the representative point Sg2 are more than variations in direction and distance of the arrival point groups G1a to G1n that diverge from the representative point Sg1 of the group G1. It is diverse.
- the base point estimation unit 122 of the present embodiment uses the representative point Sg2 of the group G2 in which the variation of the diverging arrival point group among the representative points Sg1 and Sg2 of the groups G1 and G2 is varied as the base point of the vehicle C.
- the base point estimation unit 122 of the present embodiment uses the representative point Sg2 of the group G2 in which the variation of the diverging arrival point group among the representative points Sg1 and Sg2 of the groups G1 and G2 is varied as the base point of the vehicle C.
- the start point group included in the group G1 indicates a parking lot of a company to which the driver of the vehicle C belongs
- the arrival point of the vehicle C starting the company is limited to the home. This indicates that there is less variation in arrival points than departure points.
- the starting point group included in the group G2 indicates the home where the driver of the vehicle C is based
- the arrival point of the vehicle C starting from the home is as in a company or each store.
- the tendency to become various points is strong, and it shows
- the effects (1) to (7) can be obtained, and the following effects can be further obtained. become.
- the point identification unit 120A is provided with a departure / arrival point recording unit 121 that learns information about departure / arrival points including a departure point from which the vehicle C has departed and an arrival point at which the user who has left the departure point has arrived. Then, in the point identifying unit 120A, among the departure / arrival points learned by the arrival / departure point recording unit 121, a departure point having a relatively large distribution of arrival points that diverge from a common departure point is set as a point serving as the core of the user's action. It was decided to estimate. Thereby, it becomes possible to specify the core point of the user's behavior from the user's behavior tendency with high accuracy, and based on the identified point, the relevance between the point and each movement history is obtained. It becomes possible.
- the third embodiment of the action history management system and action history management method according to the present invention is a diagram corresponding to FIG. 1 with a focus on differences from the first embodiment. This will be described with reference to FIG. 8 and FIG.
- the basic structure of the action history management system and the action history management method according to this embodiment is the same as that of the first embodiment, and FIG. 8 is substantially the same as that of the first embodiment.
- the same elements are denoted by the same reference numerals, and redundant descriptions are omitted.
- the behavior learning unit 140A of the present embodiment includes a stay frequency calculation unit 141 that calculates the stay frequency of each destination where the vehicle C stays. Whenever the vehicle C arrives at the destination, the stay frequency calculating unit 141 determines that the vehicle C is based on the location information of the destination that has arrived and the location information of the destination included in the movement history registered in the database 200. The stay frequency of the vehicle C at the arrival destination is calculated. Then, the behavior learning unit 140A outputs the information regarding the stay frequency calculated by the stay frequency calculating unit 141 to the database 200 as attached information of the movement history of the vehicle C.
- the deletion target data determination unit 320 obtains the appropriateness of deletion based on the following equation (b), and should be deleted preferentially from the database 200 according to the obtained appropriateness of deletion. Identify travel history.
- Deletion appropriateness (calculation date / time-movement history acquisition date / time) x ⁇ -stay count x ⁇ (b)
- the data deletion unit 330 deletes the movement history having the maximum deletion appropriateness from the database 200.
- the number of stays in the travel history regarding “Restaurant A” acquired “six days ago” is the smallest among the destinations. That is, of the movement histories that diverge from the user's geographical base as the departure point, the occurrence frequency of the movement history toward “Restaurant A” is the lowest.
- the deletion appropriateness obtained from the above formula (b) has the maximum deletion appropriateness of “restaurant A” among the destinations. Therefore, in the present embodiment, when the capacity of the database 200 is maintained, the movement history related to “Restaurant A” is preferentially deleted from the database 200.
- the effects (1), (2), (5) to (7) are obtained, and instead of the above (3) and (4), the following effects can be obtained.
- the fourth embodiment of the behavior history management system and behavior history management method according to the present invention is a diagram corresponding to FIG. 1 with a focus on differences from the first embodiment. This will be described with reference to FIG. 10 and FIG.
- the behavior history management system and behavior history management method of the present embodiment are applied to, for example, an information terminal such as a portable information terminal owned by a user, and the user's behavior history is classified into a plurality of categories. It is managed separately.
- the basic configuration of the system to which the action history management system and the action history management method of this embodiment is applied is the same as that of the first embodiment, and the first embodiment is also shown in FIG.
- the substantially same elements are denoted by the same reference numerals, and redundant descriptions are omitted.
- the input unit 110 is not limited to registration of a user's geographical base and selection of candidate points, but also, for example, when searching an internetwork that can be used through an information terminal. Used for input.
- the point specifying unit 120B is a category that specifies points that become the core of the user's behavior for each category based on the information input via the input unit 110 and the learning result of the behavior learning unit 140.
- a specifying unit 123 is provided.
- the category specifying unit 123 has a movement history category as a movement history, and the user's behavior in this category is Identify the core point as the user's geographic location.
- the category specifying unit 123 indicates that the category of the user's behavior history is the browsing history.
- the point that becomes the core of the user's action in this category is specified as, for example, a website set as a home page.
- the point specifying unit 120B records information on the specified point for each category in the database 200.
- the point identification unit 120B records information on the points identified by the category identification unit 123 in the database 200 for each category.
- the point specifying unit 120B outputs information related to the points specified by the category specifying unit 123 to the behavior learning unit 140.
- the behavior learning unit 140 of the present embodiment classifies whether the user's behavior is a behavior that diverges from any category of the points identified by the point identifying unit 120B. Thereby, the action history in which various actions of the user are reflected is classified as, for example, a movement history or a browsing history. And the action learning part 140 learns a user's action according to this classified category, and records the learning result in the database 200 according to the category.
- information on points that are the core of the user's behavior and the user's behavior history are stored for each category.
- the homepage 10 is set as a website that is activated when the web browser of the information terminal owned by the user is started up. Further, it is assumed that, for example, links 1 to 3 corresponding to websites 11 to 13 browsed so far by the user are pasted on the home page 10 and a search function is provided.
- the websites 11 to 13 are browsed through the links 1 to 3 with the homepage 10 as a core of action.
- information indicating a predetermined character is input through the input unit 110, information related to the input character is searched through the search function of the home page 10. Further, the browsing history and the search history are appropriately stored in the database 200 in this way.
- the relevance between the website 11 and the homepage 10 is high.
- the number of times of browsing the website 13 corresponding to the link 3 is the smallest or when the total browsing time of the website 11 is the shortest, the relevance between the website 13 and the homepage 10 is low.
- the browsing history of the website 13 having a low relevance to the home page 10 is preferentially deleted from the database 200.
- the browsing history of this website is stored in the database 200. For example, a link corresponding to this website is newly pasted on the homepage 10 instead of the link 3. Will be.
- the effects (1) to (7) can be obtained, and the following effects can be further obtained. become.
- Points that become the core of the user's behavior are specified for a plurality of categories based on the user's behavior history, and the user's behavior history is stored in the database 200 for each category.
- the behavior history that diverges from these different points is accurately stored in the database 200. It becomes possible to manage and it is possible to stably hold various action histories having high utility values in the database 200.
- various action histories stored for each category in the database 200 it is possible to present a candidate point for a destination when the user moves, a candidate link when using a web browser, and the like. It is possible to provide an accurate service according to the user's behavior.
- the low relevance between the homepage 10 and the websites 11 to 13 as a core point of the user's action is determined based on the number of browsing times and the browsing time of each of the websites 11 to 13. For this reason, even if a site has an old browsing date and time, it is possible to hold the browsing history of a site used frequently or a site browsed for a long time in the database 200 for a long time. This makes it possible to stably hold a browsing history having a high utility value for the user in the database 200.
- the action history when the amount of action history data stored in the database 200 reaches the upper limit that can be stored in the database 200, the action history is deleted.
- a threshold value smaller than the upper limit value that can be held in the database 200 may be set, and the action history may be deleted when the data amount of the action history exceeds the threshold value.
- the action history may be periodically deleted at a predetermined time interval. Even in these cases, an action history that has a low utility value for the user is preferentially deleted, so that an action history that has a high utility value for the user is stably held in the database 200, and an action that is stored in the database 200 is stored.
- the amount of history data can be managed.
- each coefficient “ ⁇ ” and “ ⁇ ” includes the movement history acquisition date and time, the distance between the user's geographical base and the destination, and the priority of the number of stays of the vehicle C (user) at the destination. It is possible to set an arbitrary value according to. Further, for example, “0” can be set to the coefficient “ ⁇ ” in the first embodiment, and “0” can be set to the coefficient “ ⁇ ” in the third embodiment. is there.
- the relationship between the user's geographical base and the movement history is determined based only on the distance between the user's geographical base and the destination, and the number of stays of the vehicle C (user) at the destination. It becomes.
- the appropriateness of deletion is obtained by the above formula (A) that adds the movement history acquisition time and the distance from the geographical base to the destination.
- the appropriateness of deletion is obtained by the above equation (b) in which the number of stays of the vehicle C at the destination is subtracted from the movement history acquisition time.
- the appropriateness of deletion of the movement history may be obtained by multiplying the movement history acquisition time and the distance from the geographical base to the destination.
- the appropriateness of deletion of the movement history may be obtained by dividing the acquisition time of the movement history by the number of stays of the vehicle C at the destination.
- the present invention is not limited to this, as long as the action history is deleted from the database 200 based on the relationship between the action history and the point that is the core of the user's action. For example, the distance from the geographical base to the destination is a predetermined value. You may make it delete from the database 200 preferentially the movement history when the threshold value is exceeded, and the movement history regarding the destination whose number of stays is a predetermined threshold value or less.
- the movement history when the user travels to a destination far from the geographical base of the user is specified as a history having low relevance to the geographical base of the user.
- the movement history when the user headed for a destination close to the geographical base based on the movement tendency May be specified as a history having a low relevance to the user's geographical base.
- the relationship between the user's geographical base and the movement history is obtained based on the distance between the user's geographical base and the destination.
- the relevance between the user's geographical base and the movement history is obtained based on the stay frequency (the number of stays) of the vehicle C at the destination.
- the geographical base of the user and the movement history based on the stay time of the vehicle C at the destination You may make it ask for the relevance of. In this case, for example, the shorter the travel history of the vehicle C at the destination, the lower the relevance to the user's geographical base, the higher the priority is deleted from the database 200. Further, as illustrated in FIG.
- each of the coefficients ⁇ 1 to ⁇ 3 may be multiplied by the distance from the geographical base to the destination, the stay frequency, and the stay time.
- the element for obtaining the relationship between the user's geographical base and the action history may be an element reflecting the user's action pattern emanating from the user's geographical base.
- the relationship between the user's geographical base and the travel history is obtained based on the distance from the user's geographical base to the destination, the stay frequency, the stay time, etc. did.
- the relevance between the home page 10 and the websites 11 to 13 as a core point of the user's action is obtained based on the number of browsing times and the browsing time of each of the websites 11 to 13. It was decided.
- the user's preference may be analyzed from the user's movement history or website browsing history, and the history to be deleted may be specified based on the analyzed preference. .
- a user who frequently uses a restaurant and has a low frequency of using a sports facility is learned from the movement history and the search history of the website that the restaurant preference is high. And the movement history and browsing history regarding the restaurant are preferentially stored in the database.
- the sports facility is learned that the user's preference is low because the use frequency is low. Then, the movement history and browsing history regarding the sports facility are deleted preferentially from the database. For this reason, for example, even if it is a movement history or a browsing history related to a restaurant that the user has used once in the past, the history is stably held in the database on the assumption that the use value of the history is high.
- a history reflecting the user's preference is held in the database, and the history is managed according to the user's preference.
- the home of the user is specified as the user's geographical base.
- the homepage 10 was set as a point used as the nucleus of a user's action.
- a website that is used most frequently or a website that is used most frequently may be identified as a point that is the core of the user's behavior.
- the point that is the core of the user's action may be any point that serves as a base when the user's action diverges, and can be changed as appropriate.
- the vehicle C is equipped with the recording system composed of the database 200 and the management system composed of the deletion necessity determination unit 310, the deletion target data determination unit 320, and the data deletion unit 330. It was decided to.
- the recording system and the management system are mounted on the information terminal owned by the user.
- the recording system and the management system may be provided in a center that manages the user's behavior history, and the user's behavior history may be collected by the center. And you may make it provide various services to a user based on the action history managed in this center.
- the behavior history management system is mounted on the vehicle C.
- the behavior history management system may be mounted on an information terminal owned by the user. Good.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
Description
以下、本発明にかかる行動履歴の管理システム及び行動履歴の管理方法を具体化した第1の実施の形態について図1~図5を参照して説明する。なお、本実施の形態の行動履歴の管理システム及び行動履歴の管理方法は、例えば、ドライバの自宅等を拠点として移動する車両の移動履歴を管理するものである。また、本実施の形態の行動履歴の管理システム及び行動履歴の管理方法では、ユーザの行動の核となるポイントとしてユーザの地理的な拠点が対象とされるとともに、行動履歴のカテゴリとしてユーザの地理的な拠点及び地理的な移動が設定されている。
削除適切度=(算出日時-移動履歴の取得日時)×α+拠点からの距離×β…(イ)
なお、上記式(イ)のうち、「算出日時」は、削除適切度を算出するタイミングを示しており、「移動履歴の取得日時」は、削除適切度の算出対象とされる移動履歴が取得された日時を示している。また、上記係数「α」及び「β」には、任意の値を設定することが可能であり、例えば、係数「α」よりも係数「β」が大きく設定されると、削除適切度に対して地理的拠点から目的地までの距離が及ぼす影響が増大する。逆に、例えば、係数「β」よりも係数「α」が大きく設定されると、削除適切度に対して移動履歴の取得日時が及ぼす影響が増大する。また、この削除適切度は、地理的拠点との関連性が高い移動履歴ほど小さくなり、逆に地理的拠点との関連性が低い移動履歴ほど大きくなる。そして、データベース200の容量の維持管理に際しては、図2(b)に示すように、削除適切度が大きい移動履歴(図2(a)移動履歴1)がデータベース200から優先して削除される。
次に、本発明にかかる行動履歴の管理システム及び行動履歴の管理方法の第2の実施の形態を、第1の実施の形態との相違点を中心に、先の図1に対応する図である図6、及び図7を参照して説明する。なお、本実施の形態にかかる行動履歴の管理システム及び行動履歴の管理方法も、その基本的な構成は第1の実施の形態と同等であり、図6においても第1の実施の形態と実質的に同一の要素にはそれぞれ同一の符号を付して示し、重複する説明は割愛する。
次に、本発明にかかる行動履歴の管理システム及び行動履歴の管理方法の第3の実施の形態を、第1の実施の形態との相違点を中心に、先の図1に対応する図である図8、及び図9を参照して説明する。なお、本実施の形態にかかる行動履歴の管理システム及び行動履歴の管理方法も、その基本的な構成は第1の実施の形態と同等であり、図8においても第1の実施の形態と実質的に同一の要素にはそれぞれ同一の符号を付して示し、重複する説明は割愛する。
削除適切度=(算出日時-移動履歴の取得日時)×α-滞在回数×β…(ロ)
こうして、削除対象データ判定部320により削除適切度が算出されると、データ削除部330は、この削除適切度が最大となる移動履歴をデータベース200から削除する。
」が設定されている。
次に、本発明にかかる行動履歴の管理システム及び行動履歴の管理方法の第4の実施の形態を、第1の実施の形態との相違点を中心に、先の図1に対応する図である図10、及び図11を参照して説明する。
なお、上記実施の形態は、以下のような形態をもって実施することもできる。
Claims (15)
- ユーザの行動履歴をデータベースに保存しつつ、その行動履歴を管理する行動履歴の管理システムであって、
ユーザの行動の核となるポイントを特定するポイント特定部と、
前記ポイント特定部により特定されたポイントとの関連性の低い行動履歴を特定し、前記データベースからのデータの削除に際してはこの特定した行動履歴を優先して削除するデータ管理部と、を備える
ことを特徴とする行動履歴の管理システム。 - 前記ユーザの行動の核となるポイントは、ユーザの行動履歴に基づく1ないし複数のカテゴリの別に特定されるものであって、前記ポイント特定部は、前記カテゴリの別にユーザの行動の核となるポイントを特定するものであり、
前記データベースは、前記行動履歴を前記カテゴリの別に保存する
請求項1に記載の行動履歴の管理システム。 - 前記行動履歴が、ユーザが目的地に向かう都度の同ユーザの行動を示す履歴であり、
前記データ管理部は、前記特定されたポイントとの関連性の低い目的地に向かったときの行動履歴を、前記データベースからの削除対象として特定する
請求項1または2に記載の行動履歴の管理システム。 - 前記ユーザの行動の核となるポイントが、ユーザの地理的拠点であり、
前記データ管理部は、前記特定されたポイントと前記行動履歴との関連性の低さを、前記ユーザの地理的拠点から前記目的地までの距離に基づいて求める
請求項3に記載の行動履歴の管理システム。 - 前記データ管理部は、前記特定されたポイントと行動履歴との関連性の低い行動履歴として、前記ユーザの地理的拠点からの距離が相対的に遠い目的地に向かったときの行動履歴を特定する
請求項4に記載の行動履歴の管理システム。 - 前記データ管理部は、前記ユーザの行動履歴の取得日時を併せて管理するとともに、この行動履歴の取得日時を加味して前記データベースから優先して削除すべき行動履歴を特定する
請求項1~5のいずれか一項に記載の行動履歴の管理システム。 - 前記データ管理部は、前記特定されたポイントと前記行動履歴との関連性を示す要素、及び前記行動履歴の取得日時に各別の係数を乗算するとともに、その乗算によって得られる2つの乗算値に基づいて前記データベースから優先して削除すべき行動履歴を特定する
請求項6に記載の行動履歴の管理システム。 - 前記データ管理部は、前記特定されたポイントと前記行動履歴との関連性の低さを、前記特定されたポイントから発散する行動履歴のうちの共通もしくは類似する行動を示す行動履歴の発生頻度の少なさ、及び、前記特定されたポイントから向かった目的ポイントにおけるユーザの滞在時間の少なくとも一方に基づいて定める
請求項1~7のいずれか一項に記載の行動履歴の管理システム。 - 前記行動履歴が、前記ユーザが操作する車両の移動履歴である
請求項1~8のいずれか一項に記載の行動履歴の管理システム。 - 前記ポイント特定部は、ユーザが出発した出発地点と該出発地点を出発したユーザが到着した到着地点とを含む発着ポイントに関する情報を学習するとともに、この学習した発着ポイントのうち、共通した出発地点から発散する到着地点の分布が相対的に多い出発地点を前記ユーザの行動の核となるポイントとして推定する
請求項1~9のいずれか一項に記載の行動履歴の管理システム。 - ユーザの行動履歴をデータベースに保存しつつその行動履歴を管理する行動履歴の管理方法であって、
ユーザの行動の核となるポイントを特定するステップと、
前記特定したポイントとの関連性の低い行動履歴を特定し、前記データベースからのデータの削除に際し、この特定した行動履歴を優先して削除ステップと、を含む
ことを特徴とする行動履歴の管理方法。 - 前記ポイントを特定するステップにおいて、前記ユーザの行動の核となるポイントを、ユーザの行動履歴に基づき1ないし複数のカテゴリの別に特定するとともに、この特定したカテゴリの別に前記行動履歴を前記データベースに保存する
請求項11に記載の行動履歴の管理方法。 - 前記行動履歴が、ユーザが目的地に向かう都度の同ユーザの行動を示す履歴であり、
前記削除するステップにおいて、前記特定したポイントとの関連性の低い目的地に向かったときの行動履歴を、前記データベースからのデータの削除対象として特定する
請求項11または12に記載の行動履歴の管理方法。 - 前記ポイントを特定するステップにおいて、ユーザの地理的拠点を前記ユーザの行動の核となるポイントとして特定し、
前記行動履歴を特定するステップにおいて、前記ユーザの地理的拠点から前記目的地までの距離に基づいて前記特定したポイントと行動履歴との関連性の低さを求める
請求項13に記載の行動履歴の管理方法。 - 請求項11~14のいずれか一項に記載の行動履歴の管理方法において、
前記ユーザの行動履歴を取得したとき、その取得日時を前記行動履歴に付与するステップをさらに含み、
前記行動履歴を特定するステップにおいて、前記行動履歴に付与した取得日時を加味して前記データベースから優先して削除すべき行動履歴を特定する
ことを特徴とする行動履歴の管理方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112014004047A BR112014004047A2 (pt) | 2011-08-30 | 2011-08-30 | sistema de gerenciamento de histórico de comportamento e método de gerenciamento de histórico de comportamento |
US14/239,948 US20140195467A1 (en) | 2011-08-30 | 2011-08-30 | Behavior history management system, and behavior history management method |
EP11871439.3A EP2752793A4 (en) | 2011-08-30 | 2011-08-30 | SYSTEM FOR ADMINISTERING A BEHAVIOR AND METHOD FOR MANAGING A BEHAVIOR |
JP2013530923A JP5708811B2 (ja) | 2011-08-30 | 2011-08-30 | 行動履歴の管理システム及び行動履歴の管理方法 |
PCT/JP2011/069534 WO2013030942A1 (ja) | 2011-08-30 | 2011-08-30 | 行動履歴の管理システム及び行動履歴の管理方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2011/069534 WO2013030942A1 (ja) | 2011-08-30 | 2011-08-30 | 行動履歴の管理システム及び行動履歴の管理方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013030942A1 true WO2013030942A1 (ja) | 2013-03-07 |
Family
ID=47755495
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/069534 WO2013030942A1 (ja) | 2011-08-30 | 2011-08-30 | 行動履歴の管理システム及び行動履歴の管理方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20140195467A1 (ja) |
EP (1) | EP2752793A4 (ja) |
JP (1) | JP5708811B2 (ja) |
BR (1) | BR112014004047A2 (ja) |
WO (1) | WO2013030942A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017059044A (ja) * | 2015-09-17 | 2017-03-23 | トヨタ自動車株式会社 | ライフログ記録システム |
JP2019066950A (ja) * | 2017-09-28 | 2019-04-25 | トヨタ自動車株式会社 | 車両管理システム |
KR20190138412A (ko) * | 2018-06-05 | 2019-12-13 | 에스케이플래닛 주식회사 | 고속 유사도 연산 기반의 상품에 대한 정보를 제공하기 위한 방법 및 이를 위한 장치 |
US10798219B2 (en) | 2015-12-22 | 2020-10-06 | Honda Motor Co., Ltd. | Server and server client system |
WO2022130467A1 (ja) * | 2020-12-14 | 2022-06-23 | 日本たばこ産業株式会社 | 端末装置、吸引装置、及びプログラム |
CN115203758A (zh) * | 2022-07-21 | 2022-10-18 | 莱阳市致睿电子科技有限公司 | 一种数据安全存储方法、系统及云平台 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9857195B2 (en) * | 2014-05-30 | 2018-01-02 | Google Inc. | Selection and presentation of geographic content in an automotive environment |
JP6191570B2 (ja) * | 2014-09-25 | 2017-09-06 | トヨタ自動車株式会社 | 車両の制御装置 |
JP6892570B2 (ja) * | 2019-06-06 | 2021-06-23 | 楽天グループ株式会社 | 推定システム、推定方法、及びプログラム |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1183531A (ja) * | 1997-09-12 | 1999-03-26 | Nippon Telegr & Teleph Corp <Ntt> | 情報提供装置及び情報提供プログラムを記録した記録媒体 |
JP2004524712A (ja) * | 1999-08-31 | 2004-08-12 | イスマイル,ラビーブ・ケイ | ターゲット決めされたビデオ番組編成の配送のための方法および装置 |
JP2011028436A (ja) | 2009-07-23 | 2011-02-10 | Nippon Telegr & Teleph Corp <Ntt> | 行動記録保存システム、サーバ装置、行動記録保存方法及びコンピュータプログラム |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4894546B2 (ja) * | 2007-02-14 | 2012-03-14 | 株式会社デンソー | 制御用情報記憶装置及びプログラム |
JP4900807B2 (ja) * | 2007-03-06 | 2012-03-21 | 株式会社日立製作所 | ストレージシステム及びデータ管理方法 |
US8065251B2 (en) * | 2007-09-28 | 2011-11-22 | Fisher-Rosemount Systems, Inc. | Dynamic management of a process model repository for a process control system |
KR20090054171A (ko) * | 2007-11-26 | 2009-05-29 | 한국전자통신연구원 | 차량 및 운전자 정보 관리 시스템 및 그 방법 |
JP5506252B2 (ja) * | 2009-06-08 | 2014-05-28 | クラリオン株式会社 | 経路探索装置および経路探索方法 |
WO2011046113A1 (ja) * | 2009-10-14 | 2011-04-21 | 日本電気株式会社 | 行動類型抽出システム、装置、方法、プログラムを記憶した記録媒体 |
US8612134B2 (en) * | 2010-02-23 | 2013-12-17 | Microsoft Corporation | Mining correlation between locations using location history |
US8498953B2 (en) * | 2010-03-30 | 2013-07-30 | Sap Ag | Method for allocating trip sharing |
US10163074B2 (en) * | 2010-07-07 | 2018-12-25 | Ford Global Technologies, Llc | Vehicle-based methods and systems for managing personal information and events |
-
2011
- 2011-08-30 BR BR112014004047A patent/BR112014004047A2/pt not_active IP Right Cessation
- 2011-08-30 US US14/239,948 patent/US20140195467A1/en not_active Abandoned
- 2011-08-30 WO PCT/JP2011/069534 patent/WO2013030942A1/ja active Application Filing
- 2011-08-30 EP EP11871439.3A patent/EP2752793A4/en not_active Withdrawn
- 2011-08-30 JP JP2013530923A patent/JP5708811B2/ja not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1183531A (ja) * | 1997-09-12 | 1999-03-26 | Nippon Telegr & Teleph Corp <Ntt> | 情報提供装置及び情報提供プログラムを記録した記録媒体 |
JP2004524712A (ja) * | 1999-08-31 | 2004-08-12 | イスマイル,ラビーブ・ケイ | ターゲット決めされたビデオ番組編成の配送のための方法および装置 |
JP2011028436A (ja) | 2009-07-23 | 2011-02-10 | Nippon Telegr & Teleph Corp <Ntt> | 行動記録保存システム、サーバ装置、行動記録保存方法及びコンピュータプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP2752793A4 |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017059044A (ja) * | 2015-09-17 | 2017-03-23 | トヨタ自動車株式会社 | ライフログ記録システム |
US10133917B2 (en) | 2015-09-17 | 2018-11-20 | Toyota Jidosha Kabushiki Kaisha | Lifelog recording system |
US10798219B2 (en) | 2015-12-22 | 2020-10-06 | Honda Motor Co., Ltd. | Server and server client system |
JP2019066950A (ja) * | 2017-09-28 | 2019-04-25 | トヨタ自動車株式会社 | 車両管理システム |
KR20190138412A (ko) * | 2018-06-05 | 2019-12-13 | 에스케이플래닛 주식회사 | 고속 유사도 연산 기반의 상품에 대한 정보를 제공하기 위한 방법 및 이를 위한 장치 |
KR102652416B1 (ko) * | 2018-06-05 | 2024-03-29 | 에스케이플래닛 주식회사 | 고속 유사도 연산 기반의 상품에 대한 정보를 제공하기 위한 방법 및 이를 위한 장치 |
WO2022130467A1 (ja) * | 2020-12-14 | 2022-06-23 | 日本たばこ産業株式会社 | 端末装置、吸引装置、及びプログラム |
CN115203758A (zh) * | 2022-07-21 | 2022-10-18 | 莱阳市致睿电子科技有限公司 | 一种数据安全存储方法、系统及云平台 |
CN115203758B (zh) * | 2022-07-21 | 2023-11-07 | 北京国联视讯信息技术股份有限公司 | 一种数据安全存储方法、系统及云平台 |
Also Published As
Publication number | Publication date |
---|---|
EP2752793A1 (en) | 2014-07-09 |
EP2752793A4 (en) | 2015-01-21 |
BR112014004047A2 (pt) | 2017-03-07 |
JP5708811B2 (ja) | 2015-04-30 |
JPWO2013030942A1 (ja) | 2015-03-23 |
US20140195467A1 (en) | 2014-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5708811B2 (ja) | 行動履歴の管理システム及び行動履歴の管理方法 | |
JP4130847B2 (ja) | 移動先予測装置およびその方法 | |
JP4283338B2 (ja) | 移動先予測装置、移動先予測方法、ナビゲーション装置及びプログラム | |
US7869942B2 (en) | Travel plan presenting apparatus and method thereof | |
JP3527505B2 (ja) | 情報提供方法 | |
JP3987877B2 (ja) | 地図情報更新装置および地図情報更新方法 | |
US8938358B1 (en) | System and method for suggesting alternative travel destinations | |
CN102147263A (zh) | 用于规划行程组合的装置及方法 | |
US10067985B2 (en) | Computing system with crowd-source mechanism and method of operation thereof | |
US20150330800A1 (en) | Systems and Methods for Personalized Multi-Destination Trip Planning | |
JP5527111B2 (ja) | ドライブ旅行計画作成システム | |
JP4045303B2 (ja) | 地図情報更新装置および地図情報更新方法 | |
WO2013192584A1 (en) | Automatically reexecuting a query | |
JP2008128659A (ja) | 情報提供システム | |
JP2008020334A (ja) | 車両用ナビゲーション装置、方法およびプログラム | |
JP6281767B2 (ja) | カーナビゲーションシステム、経路探索装置、カーナビゲーション装置、経路探索方法及びコンピュータプログラム | |
JPWO2009060537A1 (ja) | 立寄り場所情報提供装置、立寄り場所情報提供方法、立寄り場所情報提供プログラム及び記憶媒体 | |
JP7040355B2 (ja) | 情報処理装置及び情報処理方法、プログラム | |
Wei et al. | Discovering pattern-aware routes from trajectories | |
JP2019168277A (ja) | ナビゲーション装置およびナビゲーション方法、ならびにプログラム | |
JP2007218742A (ja) | 経路探索装置および経路探索システム | |
Neto et al. | Prediction of Destinations and Routes in Urban Trips with Automated Identification of Place Types and Stay Points. | |
US20190286296A1 (en) | Information presentation system, information presentation method, and non-transitory computer readable medium | |
JP4879803B2 (ja) | 地図情報更新装置および地図情報更新方法 | |
JP4045304B2 (ja) | 地図情報更新装置および地図情報更新方法 |
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: 11871439 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2013530923 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2011871439 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14239948 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112014004047 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112014004047 Country of ref document: BR Kind code of ref document: A2 Effective date: 20140221 |