JP2018169313A - Extraction device, charge control system, and method for extraction - Google Patents

Abstract

To provide an extraction device, a charge control system, and a method for extraction which can increase the accuracy of estimating a destination and a route to the destination.SOLUTION: An extraction device 1 includes a generation unit, an extraction unit, and a deletion unit. The generation unit generates event information, in which the travel from the start point where a vehicle starts travelling to the goal point where the vehicle is parked makes one event, and stores the event information into a storage unit 3 (S1). The extraction unit extracts the patterns of past actions on the basis of the histories of the event information stored in the storage unit 3 (S2). The deletion unit deletes the event information on the past action patterns extracted by the extraction unit from the storage unit 3 (S3).SELECTED DRAWING: Figure 1

Description

  The present invention relates to an extraction device, a charge control system, and an extraction method.

  Conventionally, there is an information processing apparatus that estimates a destination of a vehicle, a route to the destination, and the like. Such an information processing apparatus stores a travel history of a vehicle and estimates a destination and a route to the destination based on the travel history (see, for example, Patent Document 1).

JP 2017-21420 A

  However, in the prior art, since the destination and the route to the destination are estimated based on all the stored travel histories, there is a possibility that the estimation accuracy of the route to the destination and the destination may be lowered.

  This invention is made | formed in view of the above, Comprising: It aims at providing the extraction apparatus, charging control system, and extraction method which can improve the estimation precision of a path | route to the destination and the destination.

  According to the present invention, the extraction device includes a generation unit, an extraction unit, and a deletion unit. A generation part produces | generates the event information which makes driving | running | working from the start point which is the point where the vehicle started driving | running | working to the goal point which is the parked point one time, and memorize | stores it in a memory | storage part. The extraction unit extracts a past action pattern based on the history of the event information stored in the storage unit. The deletion unit deletes the event information related to the past behavior pattern extracted by the extraction unit from the storage unit.

  According to the present invention, it is possible to improve the route estimation accuracy to the destination and the destination.

FIG. 1 is a diagram showing an outline of the extraction method. FIG. 2 is a block diagram of the charge control system. FIG. 3A is a diagram (part 1) illustrating a specific example of processing by the extraction unit. FIG. 3B is a second diagram illustrating a specific example of processing performed by the extraction unit. FIG. 3C is a third diagram illustrating a specific example of the process performed by the extraction unit. FIG. 4A is a diagram (part 1) illustrating a specific example of processing by the estimation unit. FIG. 4B is a second diagram illustrating a specific example of the process performed by the estimation unit. FIG. 5 is a flowchart showing a processing procedure executed by the charge control system.

  Hereinafter, an extraction device, a charge control system, and an extraction method according to embodiments will be described in detail with reference to the accompanying drawings. In addition, this invention is not limited by this embodiment.

  First, the outline of the extraction method according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an outline of the extraction method. This extraction method is executed by the extraction apparatus 1 shown in FIG.

  As shown in FIG. 1, the extraction device 1 is mounted on a vehicle C. Moreover, the extraction apparatus 1 is provided with the control part 2 and the memory | storage part 3, for example. The control part 2 produces | generates the event information which makes driving | running | working from the start point where the vehicle C starts driving | running | working to the goal point which is the point where the vehicle C parks one time (step S1).

  For example, the start point corresponds to a point where an ignition power source (hereinafter referred to as IG power source) of the vehicle C is turned on, and the goal point corresponds to a point where the IG power source is turned off.

  The event information generated by the control unit 2 is stored in the storage unit 3. And the event information memorize | stored in the memory | storage part 3 can be used for the estimation of the route | route to the destination of the vehicle C and the destination.

  Here, in the prior art, the destination and the route to the destination are estimated based on all the event information stored in the storage unit. In other words, in the prior art, in addition to event information related to the destination A that is frequently used at present, the destination is estimated in consideration of event information related to the destination B that has been used in the past but is rarely used at present. It was broken.

  For this reason, in the prior art, for example, even when the vehicle C travels along the route A and is heading toward the destination A, the destination may be estimated as the destination B. In other words, since all event information is stored in the prior art, event information with high priority is buried in event information with low priority, and the estimation accuracy of the destination and the route to the destination may be reduced. was there.

  Therefore, in the extraction method according to the embodiment, the event estimation information related to the past behavior pattern is deleted to improve the destination estimation accuracy. In other words, in the extraction method according to the embodiment, the event information having a low priority is deleted to improve the estimation accuracy of the destination and the route to the destination.

  Specifically, in the extraction method according to the embodiment, a past action pattern is extracted based on the history of event information stored in the storage unit 3 (step S2). In this extraction method, for example, when a destination B that has been frequently used as a goal point in the past is almost no longer used, an event related to the destination B can be extracted as a past action pattern. .

  And in the extraction method which concerns on embodiment, the event information regarding the event extracted as a past action pattern is deleted from the memory | storage part 3 (step S3). That is, the event information related to the destination B is deleted.

  For this reason, in the extraction method according to the embodiment, it is possible to delete the history relating to the destination B having a low priority from the storage unit 3 and the route B that is the route to the destination B. In other words, in the extraction method according to the embodiment, event information with high priority can be extracted and stored in the storage unit 3.

  Thereby, in the extraction method according to the embodiment, the destination of the vehicle C and the route to the destination can be estimated based on the event information with high priority. For this reason, the estimation accuracy of the destination and the route to the destination can be improved.

  Further, in the extraction method according to the embodiment, by deleting event information with low priority, the amount of data stored in the storage unit 3 can be suppressed, and the storage capacity of the storage unit 3 can be suppressed. Thereby, an inexpensive storage medium having a small storage capacity can be used for the storage unit 3.

  In the extraction method according to the embodiment, it is possible to estimate the destination and the route to the destination with a small amount of data by deleting the event information. Thereby, it is possible to reduce the amount of calculation while improving the estimation accuracy when estimating the destination and the route to the destination.

  Note that the above-described extraction method can improve the fuel efficiency of the vehicle C by using it in a battery charge control system of the vehicle C, which is a hybrid vehicle or an electric vehicle, for example.

  Next, a configuration example of the charging control system 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a block diagram of the charging control system 100. 2 shows an ignition switch (hereinafter referred to as IG switch) 10, a navigation unit 11, an in-vehicle camera 12, and a battery B together.

  The IG switch 10 is a switch that receives start and stop of an electric system such as an engine or a motor. When the IG switch 10 is turned on, the IG power supply is started, for example, the charging control system 100 is started. Further, when the IG switch 10 is turned off, the charging control system 100 is stopped by stopping the IG power source. Note that the charging control system 100 may be operated using a power supply system other than the IG power supply.

  The navigation unit 11 includes a GPS (Global Positioning System), for example, and sequentially generates position information indicating the position of the vehicle C and outputs the position information to the extraction device 1.

  The in-vehicle camera 12 is a camera provided with an image sensor such as a complementary metal oxide semiconductor (CMOS) or a charge coupled device (CCD), for example, and is installed inside the vehicle C so as to capture an occupant of the vehicle C. A captured image captured by the in-vehicle camera 12 is output to the extraction device 1.

  The battery B is, for example, a secondary battery, and is a power source that drives a vehicle C that is an electric vehicle such as a hybrid vehicle or an electric vehicle. The battery B discharges to drive a motor (not shown) that drives the vehicle C.

  Further, the battery B can be charged by storing regenerative power generated by the motor. The battery B is, for example, a lithium ion secondary battery or a nickel hydride secondary battery. Battery B is an assembled battery, and is configured by connecting a plurality of battery blocks in series. Such a battery block includes a plurality of battery cells connected in series. Battery B may be configured by connecting a plurality of battery blocks in parallel.

  The charge control system 100 includes the extraction device 1, a charge control unit 25, and a calculation unit 26. The extraction device 1 includes a control unit 2 and a storage unit 3. The control unit 2 includes a generation unit 21, an extraction unit 22, a deletion unit 23, an estimation unit 24, a charge control unit 25, and a calculation unit 26.

  The control unit 2 includes, for example, a computer having a central processing unit (CPU), a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), an input / output port, and various circuits.

  The CPU of the computer reads out and executes a program stored in the ROM, for example, to generate the generation unit 21, the extraction unit 22, the deletion unit 23, the estimation unit 24, the charge control unit 25, and the calculation unit 26 of the control unit 2. Function.

  In addition, at least one or all of the generation unit 21, the extraction unit 22, the deletion unit 23, the estimation unit 24, the charge control unit 25, and the calculation unit 26 of the control unit 2 are connected to an ASIC (Application Specific Integrated Circuit) or an FPGA (Field It can also be configured with hardware such as a Programmable Gate Array.

  The storage unit 3 corresponds to, for example, a RAM or an HDD. The RAM and HDD can store event history information 31 and various program information. Note that the charging control system 100 may acquire the above-described program and various types of information via another computer or a portable recording medium connected via a wired or wireless network.

  The generation unit 21 of the control unit 2 generates the event information described above and stores the event information in the storage unit 3. The history of event information stored in the storage unit 3 becomes event history information 31. Specifically, for example, the generation unit 21 travels the vehicle C from the start point of the vehicle C (the point where the IG switch 10 is turned on) to the goal point (the point where the IG switch 10 is turned off again). Is obtained from the navigation unit 11.

  And the production | generation part 21 produces | generates the event information which made the start point, the goal point, and the travel route one event. At this time, when the parking time, that is, when the IG switch 10 is off is short (for example, within 10 minutes), the generation unit 21 does not determine that the period is parked, and the event continues. It can be determined as a thing.

  In other words, for example, when the vehicle C stops at a convenience store, a gas station, or the like, the generation unit 21 determines such a convenience store, a gas station, or the like as a transit point. Then, the production | generation part 21 can make the position which the vehicle C parked for a long time into a goal point.

  Thereby, the production | generation part 21 can determine the end point of an event correctly. The generation unit 21 may generate event information with the current location at the time when the IG switch 10 is turned off as the goal point regardless of the length of the parking time.

  Moreover, the production | generation part 21 can match | combine with the event information the time information which shows the time (a date, a day of the week etc. are included) which the event concerning event information generate | occur | produced, and the combination information which shows the passenger | crew combination of the vehicle C, for example. .

  Specifically, the generation unit 21 can generate time information by associating, for example, a time input from another device such as the navigation unit 11 with event information.

  Moreover, the production | generation part 21 can identify the passenger | crew of the vehicle C by analyzing the captured image input from the vehicle camera 12, for example, and can produce | generate above-described combination information. For example, the generation unit 21 may identify each occupant by performing biometric authentication such as fingerprint authentication of each occupant or communicating with a terminal device owned by the occupant such as a smartphone and authenticating the terminal device. Good.

  Furthermore, the generation unit 21 is not limited to time information and combination information, but can also associate weather information, traffic jam information, and the like with event information. Such traffic jam information can be acquired using, for example, VICS (Vehicle Information and Communication System; registered trademark) or vehicle-to-vehicle communication.

  That is, the generation unit 21 can generate not only the actual travel route of the vehicle C but also event information in which time information, combination information, weather information, and traffic jam information are associated with each other.

  The extraction unit 22 extracts past behavior patterns based on the history of event information, that is, the event history information 31 stored in the storage unit 3. And the extraction part 22 raises the past flag which shows that it is a past action pattern about the event information regarding the past action pattern from the event history information 31, for example. Details of the processing by the extraction unit 22 will be described later with reference to FIGS.

  The deletion unit 23 deletes the event information extracted as a past action pattern by the extraction unit 22 from the event history information 31 of the storage unit 3. Specifically, the deletion unit 23 refers to the event history information 31 and deletes the event information for which the past flag is set.

  As a result, event information relating to past behavior patterns is deleted from the event history information 31, and thus event information having a high priority at the present time is stored in the storage unit 3.

  Here, the specific example of the process by the extraction part 22 is demonstrated using FIG. 3A to 3C are diagrams illustrating specific examples of processing performed by the extraction unit 22.

  3A and 3B, the horizontal axis indicates the passage of time, and the occurrence of an event is indicated by “with event” and “without event”. As shown in FIG. 3A, for example, when the occurrence frequency decreases to a predetermined value or less like the period T2 following the period T1 in which a certain event frequently occurred, the extraction unit 22 selects the event as a past action. The pattern is determined.

  Specifically, for example, when the event that has occurred 20 times or more in one month in the period T1 becomes less than or equal to two times in one month in the period T2, the extraction unit 22 selects the event in the past. It can be extracted as an action pattern.

  Then, the extraction unit 22 sets the above-described past flag in the event information of the period T1, which is a past action pattern, at time t3 when the period T2 ends. Thereby, the deletion unit 23 deletes the event information for which the past flag of the period T1 is set at the time t3.

  For example, when the above condition is satisfied, the extraction unit 22 sets a past flag for all event information in the period T1 and the period T2, and the deletion unit 23 deletes all the event information. Also good. That is, the extraction unit 22 detects a change point of the behavior pattern, and the deletion unit 23 deletes event information before the change point.

  Furthermore, the extraction unit 22 can also set a past flag on event information related to an event that has never occurred retroactive to a predetermined period. The example shown in FIG. 3B shows a case where an event that has occurred at a predetermined frequency or more in the period T3 gradually decreases in the period T4 and never occurs in the period T5.

  In such a case, for example, the extraction unit 22 sets a past flag of the event information of the period T3 and the period T4 at time t7. Thereby, the deletion unit 23 deletes the event information at time t7.

  As described above, the extraction device 1 according to the embodiment can delete event information based on the transition of the occurrence frequency of events in a predetermined period. That is, the extraction apparatus 1 according to the embodiment can selectively delete event information having a low priority at the present time, instead of deleting the oldest event information in order.

  Thereby, event information with high priority is stored in the storage unit 3 at present, and the estimation accuracy of a destination and a route to the destination by the estimation unit 24 described later can be improved. Note that the extraction device 1 may delete event information regarding events that have never occurred in a predetermined period, regardless of the frequency of occurrence of past events.

  For example, as illustrated in FIG. 3C, the extraction unit 22 creates a ranking in which the number of occurrences of each event in a predetermined period (for example, one month) is tabulated, for example, and past action patterns based on the ranking Can be extracted.

  Specifically, as illustrated in FIG. 3C, the extraction unit 22 extracts, for example, event information related to an event lower than the threshold Th in the ranking as a past action pattern, and sets a past flag for the event information.

  The ranking order corresponds to the current priority of each event information. That is, the higher the ranking, the higher the current priority. For this reason, the deletion unit 23 can selectively delete event information having a low priority by deleting event information from the storage unit 3 based on the past flag.

  Although the case where the threshold Th is provided for the ranking order has been described here, a threshold may be provided for the number of occurrences. Moreover, the extraction part 22 can also extract the past action pattern based on the transition of the ranking in the ranking. Specifically, for example, the extraction unit 22 can extract an event whose rank gradually decreases as a past action pattern. In other words, the extraction unit 22 can extract event information whose priority gradually decreases as a past action pattern.

  Returning to the description of FIG. 2, the estimation unit 24 will be described. The estimation unit 24 estimates the destination of the vehicle C and a route to the destination based on the event history information 31, and outputs estimation information that is an estimation result to the charge control unit 25.

  Here, details of the processing by the estimation unit 24 will be described with reference to FIGS. 4A and 4B. 4A and 4B are diagrams illustrating specific examples of processing performed by the estimation unit 24. FIG.

  As shown in FIG. 4A, the estimation unit 24 starts estimation of a destination candidate when the IG switch 10 (see FIG. 2) is turned on, for example. In such a case, the estimation unit 24 can refer to the event history information 31 and estimate the goal point of the event information with the highest frequency among the event information having the current location as the start point as a destination candidate.

  Then, the estimation unit 24 estimates a route to the destination candidate based on the event history information 31. Moreover, as shown in FIG. 4A, the estimation unit 24 can update the destination candidate in accordance with the route on which the vehicle C actually travels.

  Specifically, the estimation unit 24 can update the ranks of the destination candidates when the vehicle C goes straight through the intersection I, makes a right turn, and makes a left turn. That is, the estimation unit 24 can estimate the destination with high accuracy by estimating the destination according to the actual travel route of the vehicle C.

  As illustrated in FIG. 4B, the estimation unit 24 can estimate different routes depending on the day of the week and the time zone, for example, even at the same destination. Specifically, the estimation unit 24 estimates a route to the destination A via the route C from Tuesday to Friday based on the event history information 31, and a route to the destination A via the route D on Monday. Can be estimated.

  That is, the estimation unit 24 can estimate an action pattern for each day of the week and estimate a route to the destination according to the action pattern. Although the case where the destination is the same place has been described here, the estimation unit 24 can also estimate a different destination according to the day of the week or the time zone. Here, although the case where the estimation unit 24 changes the route to be estimated according to the day of the week has been shown, the destination to be estimated can be changed according to the time zone.

  By the way, the destination and the travel route differ depending on the passenger of the vehicle C. For this reason, the estimation unit 24 can also estimate different destinations and routes to the destinations depending on the combination of passengers. Specifically, first, the estimation unit 24 extracts event information that most closely matches the current occupant combination of the vehicle C from the event history information 31.

  And the estimation part 24 can estimate the goal point of the event with the highest occurrence frequency among such event information as a destination, and can estimate the route to the goal point.

  That is, the estimation unit 24 estimates the route to the destination and the destination according to the combination of the occupants by estimating the destination and the route to the destination based on the combination of the occupants of the vehicle C. Can do. In other words, the destination and the route to the destination can be estimated more accurately. The estimation unit 24 can estimate the destination and the route to the destination more accurately by appropriately combining the above processes.

  Returning to the description of FIG. 2, the calculation unit 26 will be described. The calculation unit 26 detects an SOC (State of Charge) value indicating the state of charge of the battery B, and calculates a distance that the vehicle C can travel using the SOC value. Information regarding the travelable distance calculated by the calculation unit 26 is output to the charge control unit 25 as distance information. The SOC value is, for example, the charging rate (%) of the battery B, but may be the remaining capacity (Ah) of the battery B.

  The charging control unit 25 determines whether or not to charge the battery B based on the estimation information input from the estimation unit 24 and the distance information calculated by the calculation unit 26.

  Then, when the route to the destination included in the estimation information is less than the travelable distance included in the distance information, that is, when the battery B needs to be charged, the charging control unit 25 does not satisfy the required power. Is charged into the battery B.

  In other words, the charging control unit 25 charges the battery B with the minimum necessary power before the vehicle C reaches the destination estimated by the estimating unit 24. As a result, it is possible to suppress a decrease in fuel consumption of the vehicle C caused by charging the battery B more than necessary, and deterioration of the battery B due to repeated discharge and charge.

  Note that the charging control unit 25 adjusts the capacity to charge the battery B depending on, for example, the height difference of the route to the destination estimated by the estimation unit 24 or the use status of the air conditioner of the vehicle C. Good.

  Specifically, the charging control unit 25 can increase the capacity charged by the battery B when the vehicle C travels on an uphill as compared to traveling on a flat road. On the other hand, the charging control unit 25 can reduce the capacity charged by the battery B when the vehicle C travels a lot on the downhill.

  Moreover, the charge control part 25 can increase the capacity | capacitance charged to the battery B also when using the apparatus which consumes electric power, such as the air conditioner of a vehicle C, and an audio.

  Furthermore, the charge control unit 25 can adjust the capacity to charge the battery B based on the traffic jam information of the route estimated by the estimation unit 24, for example. For example, the charging control unit 25 can increase the capacity to be charged when the above route is congested compared to when the route is not congested.

  In this way, the charging control unit 25 can improve the fuel efficiency of the vehicle C by adjusting the capacity charged by the battery B in consideration of not only the route estimated by the estimation unit 24 but also the route. .

  Next, a processing procedure executed by the charging control system 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing a processing procedure executed by the charging control system 100. Note that this processing procedure is repeatedly executed by the control unit 2 of the charging control system 100.

  As shown in FIG. 5, first, the generation unit 21 of the control unit 2 generates event information (step S <b> 101), and then the extraction unit 22 is based on the event history information 31 stored in the storage unit 3. Past behavior patterns are extracted (step S102).

  Subsequently, the deletion unit 23 deletes event information related to past behavior patterns (step S103). Note that step S102 and step S103 described above are not necessarily performed every time, and may be performed at a predetermined cycle (for example, every two weeks).

  Subsequently, the estimation unit 24 estimates the destination and the route to the destination based on the event history information 31 (step S104). Thereafter, the calculation unit 26 calculates a travelable distance based on the state of charge of the battery B (step S105). Note that the control unit 2 may perform the processes of step S104 and step S105 in parallel at any time.

  And the charge control part 25 determines whether the distance which can drive | work is larger than the path | route to the destination (step S106). In this determination, when the travelable distance is less than the route to the destination (No at Step S106), the charging control unit 25 charges the battery B (Step S107) and ends the process.

  On the other hand, if the travelable distance is equal to or longer than the route to the destination (step S106, Yes), the charging control unit 25 does not charge the battery B and ends the process as it is.

  As described above, the extraction device 1 according to the embodiment includes the generation unit 21, the extraction unit 22, and the deletion unit 23. The generation unit 21 generates event information in which the traveling from the start point where the vehicle C starts traveling to the goal point where the vehicle C is parked is a single event, and stores the event information in the storage unit 3. The extraction unit 22 extracts past behavior patterns based on the history of event information stored in the storage unit 3. The deletion unit 23 deletes the history regarding the past behavior pattern extracted by the extraction unit 22 from the storage unit 3. Therefore, according to the extraction device 1 according to the embodiment, the estimation accuracy of the destination and the travel route to the destination can be improved.

  By the way, although embodiment mentioned above demonstrated the case where the extraction apparatus 1 was provided with the memory | storage part 3, the extraction apparatus 1 may memorize | store event information in an external storage device (for example, server etc.).

  Further, the extraction device 1 may store event information in a server, extract event information having high priority for the current occupant of the vehicle C, and store the event information in the storage unit 3. In such a case, even if the user purchases a new car, the extraction device 1 can estimate the destination and the route to the destination based on the event information with high priority.

  In the above-described embodiment, the case where the battery B is controlled based on the destination estimated by the extraction device 1 and the route to the destination has been described. However, the route to the destination and the destination is used for other services. You may decide to use it. For example, it is possible to calculate the required time to the destination estimated by the extraction device 1 and to provide the content in the vehicle at the required time.

  Further effects and modifications can be easily derived by those skilled in the art. Thus, the broader aspects of the present invention are not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications can be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents.

DESCRIPTION OF SYMBOLS 1 Extraction device 21 Generation part 22 Extraction part 23 Deletion part 24 Estimation part 25 Charging control part 26 Calculation part 31 Event history information B Battery C Vehicle

Claims (8)

A generation unit that generates event information that includes driving from a start point, which is a point where the vehicle starts to travel, to a goal point, which is a parked point, and stores it in a storage unit;
An extraction unit for extracting a past behavior pattern based on a history of the event information stored in the storage unit;
An extraction apparatus comprising: a deletion unit that deletes the event information related to the past behavior pattern extracted by the extraction unit from the storage unit. The extraction unit includes:
The extraction apparatus according to claim 1, wherein the event is extracted as the past action pattern when the occurrence frequency of the event that has occurred at a predetermined frequency or more in the past becomes a predetermined threshold value or less. The extraction unit includes:
The extraction according to claim 1 or 2, wherein a ranking representing the frequency of occurrence of the event in a predetermined period is created, and the event lower than a predetermined threshold in the ranking is extracted as the past action pattern. apparatus. The extraction device according to claim 1, 2, or 3, further comprising: an estimation unit that estimates a destination of the vehicle and a route to the destination based on the event information stored in the storage unit. The generator is
Generating the event information including time information indicating a time zone and a day of the week when the event occurred;
The estimation unit includes
The extraction device according to claim 4, wherein the destination and a route to the destination are estimated based on the time information. The generator is
Generating the event information including combination information indicating a combination of occupants of the vehicle;
The estimation unit includes
The extraction device according to claim 4 or 5, wherein the destination and a route to the destination are estimated based on the combination information. The extraction device according to claim 4, 5 or 6,
A calculation unit that detects a charged state of a battery that drives the vehicle and calculates a distance that the vehicle can travel in the charged state;
A charge control system comprising: a charge control unit that charges the battery with an amount of electric power that is not satisfied when the travelable distance calculated by the calculation unit is less than the route estimated by the estimation unit. A generation step of generating event information having a single event as a travel from a start point where the vehicle starts to travel to a goal point where the vehicle is parked;
An extraction step of extracting a past behavior pattern based on the history of the event information stored in the storage unit;
And a deletion step of deleting the event information relating to the past behavior pattern extracted by the extraction step from the storage unit.

Images