JP6793535B2 - Activity base estimation device, activity base estimation method and activity base estimation program - Google Patents

Description

The present invention relates to an activity base estimation device for estimating an individual activity base, an activity base estimation method, and an activity base estimation program.

There is an existing system that promotes purchasing activities by using the attribute data and sales data of credit card members and conducting advertisements that depend on them.

For example, Patent Document 1 discloses a credit card system for the purpose of providing comprehensive services to card member stores and cardholders. This credit card system includes a host computer system and a second computer system connected to it. The host computer system includes a customer service management system that obtains marketing data related to the credit card usage of credit card members based on attribute data and sales data for each credit card member, and an advertisement that advertises to credit card members based on the marketing data. It is equipped with a distribution system. Credit card members can view news and card usage statements on the advertisement distribution system after taking predetermined procedures. The advertisement distribution system carries out advertisements by e-mail or direct mail. When the second computer system receives an advertisement request from the member store terminal device, it entrusts the advertisement to the host computer system, and when it receives a marketing data output request, it acquires the customer service management system marketing data and sends it to the member store terminal device. Output.

Japanese Unexamined Patent Publication No. 2001-357297

In paragraph 0024 of Cited Document 1, "In the host computer system, the customer data is analyzed in the customer service management system. That is, the data in the attribute data bank and the sales data bank is used to segment and purchase the customer. Customer analysis data, sales analysis data, operation analysis data, trade area analysis data, effect analysis data, etc. are obtained by performing behavior measurement and effect measurement. Then, using these analysis data (hereinafter referred to as marketing data), the host In the computer system, target customer extraction, new customer acquisition, and existing customer incentive are performed. That is, as described later, in the advertisement distribution system, Web usage bill distribution, e-mail (E-Mail) distribution, and Execute contract direct mail (contract DM) shipping, etc. By doing so, repeat customers, impulsive purchase / parallel purchase, and retain customers. In this way, advertisement distribution is performed to acquire customers, etc. It will perform FSP services such as customer management, sales management, and point management. "

However, in Patent Document 1, customer segmentation, purchasing behavior measurement, and effect measurement are performed using the data in the attribute data bank and the sales data bank, and the customer analysis data, sales analysis data, operation analysis data, and so on. There is no explanation on how to obtain trade area analysis data, effect analysis data, etc.

The sales databank typically contains purchasing information that represents each purchase by each individual. In addition, purchasing behavior measurement may include those related to individual activity bases. Also, in general, information about individual activity bases is useful for marketing.

Therefore, the present invention provides an activity base estimation device, an activity base estimation method, and an activity base estimation program that enable an individual's activity base to be estimated based on purchase information representing each purchase by the individual. The purpose is.

According to the present invention
An activity base estimation device that estimates one or more areas that are the target person's activity bases based on purchase information that represents multiple purchases by the target person.
Based on the life zone distance and geographical positions of the plurality of purchase points to perform the plurality of purchase, the Living distance 1 or more to form a Group 1 or more so as to include a purchase point for the circular close to the radius , A group forming means that uses the geographical position of the purchasing point and the living area distance, and further sets a reference point at the center of the circle in order to create the circular area .
Group / region mapping means that associates each group with a region,
Based on the area to which any group is associated, an estimation means for estimating one or more areas that are the activity bases of the target person , based on the number of purchasing points included in the area, Bei example,
The group forming means forms each group so as to include a purchasing point defined as a reference purchasing point of each group and a purchasing point existing within the living area distance from the purchasing point.
Said estimating means, a corresponding predetermined number of local number of high-level in the order of purchase, activity base estimating apparatus is provided which is characterized that you estimated as one or more areas as the activity base of the subject To.

Further, according to the present invention,
It is an activity base estimation method that estimates one or more areas that are the target person's activity bases based on purchase information that represents multiple purchases by the target person.
Based on the life zone distance and geographical positions of the plurality of purchase points to perform the plurality of purchase, the Living distance 1 or more to form a Group 1 or more so as to include a purchase point for the circular close to the radius , A group formation step that uses the geographical position of the purchasing point and the living area distance, and further sets a reference point that is the center of the circle to create the circular area .
Group / region mapping steps that associate each group with a region,
Based on the area to which any group is associated, the estimation step of estimating one or more areas that will be the activity bases of the target person , based on the number of purchasing points included in the area, Bei example,
The group formation step forms each group so as to include a purchasing point defined as a reference purchasing point of each group and a purchasing point existing within the living area distance from the purchasing point.
Said estimating step, the corresponding predetermined number of local number of high-level in the order of purchase, activity base estimation method is provided which is characterized that you estimated as one or more areas as the activity base of the subject To.

Further, according to the present invention, an activity base estimation program for making a computer function as the activity base estimation device is provided.

According to the present invention, it is possible to estimate an individual's activity base based on purchase information representing each purchase by the individual.

It is a functional block diagram which shows the structure of the activity base estimation apparatus by embodiment of this invention. It is a flowchart (1/3) for demonstrating the operation of the activity base estimation apparatus by embodiment of this invention. It is a flowchart (2/3) for demonstrating operation of the activity base estimation apparatus by embodiment of this invention. It is a flowchart (3/3) for demonstrating operation of the activity base estimation apparatus by embodiment of this invention. It is a figure for demonstrating the living area distance by embodiment of this invention. It is a figure which shows the group and area which corresponded one-to-one in embodiment of this invention. (A) is a diagram showing a group and a region corresponding to one-to-many in the embodiment of the present invention, and (b) is a pair by modification to (a) by the first amendment according to the embodiment of the present invention. It is a figure which shows the group and area which came to correspond to 1. (A) is a diagram showing groups and regions corresponding to many-to-one in the embodiment of the present invention, and (b) is a pair by modification to (a) by the second amendment according to the embodiment of the present invention. It is a figure which shows the group and area which came to correspond to 1. It is a figure which shows a plurality of predetermined periods in embodiment of this invention. It is a figure which shows the relationship between the group and the purchase point in embodiment of this invention. It is a figure which shows the transition of the group which a part is formed in each different period by embodiment of this invention.

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

[First Embodiment]
The activity base estimation device according to the embodiment of the present invention has one or more activity bases for each credit card user to carry out purchasing activities based on the purchase information indicating the purchase history of the user. presume. FIG. 1 is a functional block diagram showing a configuration of an activity base estimation device according to an embodiment of the present invention.

Referring to FIG. 1, the activity base estimation device 100 includes a statistical information database 101, a living area distance calculation unit 103, a living area distance storage unit 105, a purchasing information database 107, a group forming unit 109, and a group / region association unit 111. , The estimation unit 113, the second estimation unit 115, and the information generation unit 117. Further, the group / region association unit 111 includes an allocation unit 111-1, a first correction unit 111-3, a second correction unit 111-5, and a third correction unit 111-7.

The statistical information database 101 stores, for example, the "main statistical table by municipality" and the "statistical database by region" published by the Statistics Bureau of the Ministry of Internal Affairs and Communications for 1921 municipalities nationwide.

The living area distance calculation unit 103 is based on the "main statistical table by city, ward, town, and village" and the "statistical database by region" stored in the statistical information database 101, as shown in FIG. 5, "city" and "region". , "Country town", "depopulated area", etc., the living area distance is calculated for each area classification. Specifically, the living area distance calculation unit 103 acquires and acquires the average distance between predetermined facilities of the same type in each of a plurality of randomly selected areas for each type of facility. Based on the average distance for each area and each type of facility, different living area distances are calculated for each area classification. Here, the types of facilities include supermarkets, grocery stores, types related to daily life including general stores, types related to medical care including hospitals and clinics, types related to entertainment including game centers, karaoke stores, and pachinko stores, and small. Types related to education including junior high school can be mentioned.

The living area distance storage unit 105 stores the living area distance calculated by the living area distance calculation unit 103 for each area classification.

The purchase information database 107 stores purchase information representing each purchase for each credit card user. The purchase information database 107 stores a usage statement table that stores the settlement method, purchase amount, purchase date and time, purchase day, and purchase store name in association with each purchase, and a store that stores the name of the purchase store and the address of the purchase store in association with each other. It includes a table, a position table that holds the address of the purchase shop in association with the latitude and longitude of the purchase store, and a user attribute table that holds the age of the purchaser and the gender of the purchaser in association with each other. Purchasing information includes all or part of the contents stored in these tables. Therefore, the name and geographical position (represented by latitude and longitude) of each purchasing point can be known from the purchasing information.

The group forming unit 109 forms one or more groups based on the living area distance for each classification of the area stored in the living area distance storage unit 105 and the purchasing information stored in the purchasing information database 107. Specifically, the group forming unit 109 forms one or more groups based on the geographical position of each purchasing point acquired from the purchasing information and the living area distance acquired from the living area distance storage unit 105. Here, as shown in FIG. 10, the group includes one or more stores in a circular area having a living area distance as a radius. As mentioned above, the living area distance is calculated for each regional classification. The group forming unit 109 examines the classification of the area where the group is formed when forming the group, and applies the living area distance corresponding to the classification.

As shown in FIG. 6, the group / region association unit 111 mainly has a function of associating a group and an region with a one-to-one relationship. Here, the area is taken in units of municipalities such as XX city, XX ward, XX town, XX village, but for example, XX city XX town, XX ward. It may be a part of a city, a part of a ward, etc., such as a town.

The allocation unit 111-1 allocates any area to each group formed by the group formation unit 109. Specifically, for example, the area where the geographical position (represented by latitude, longitude or area name) of the center of the group exists is assigned. Further, for example, the average of one or more purchasing points belonging to the group is calculated, and the area where this average exists is assigned.

Here, the living area distance applied to the group by the group forming unit 109 corresponds to the classification of the area where the purchasing point belonging to the group exists, and the allocation unit 111-1 allocates the area to the group. Immediately after that, it has not changed. Then, depending on the size relationship between the area of the group and the area of the area, there are the following groups. When a certain area is assigned to a certain group and the area of the group is larger than the area of the area assigned to the group, as shown in FIG. 7A, a plurality of areas are assigned to the area of the group. Will be included. Also, if you have assigned a certain area to a group, but the area of that group is smaller than the area of the area assigned to it, other groups may also be assigned to that area, and in fact If so assigned, a plurality of groups will correspond to the area, as shown in FIG. 8 (a). Assuming these cases, the first correction unit 111-3 and the second correction unit 111-5 are provided, respectively.

If there is a group associated with a plurality of regions as shown in FIG. 7 (a), the first correction unit 111-3 has only one group in the group as shown in FIG. 7 (b). Modify so that the regions are associated. That is, if there is a group corresponding to a plurality of regions by the allocation unit 111-1 among one or more groups formed by the group forming unit 10, the first correction unit 111-3 is assigned to that group. Correct the number of regions corresponding to the group to one based on the number of purchasing points for each corresponding region.

If there is an area associated with a plurality of groups as shown in FIG. 8A, the second correction unit 111-5 has only one area in that area as shown in FIG. 8B. Modify so that the groups are associated. That is, the second correction unit 111-5 has a plurality of groups if there is an area corresponding to a plurality of groups by the allocation unit 111-1 among one or more areas formed by the group formation unit 109. One group formed by merging is associated with one region. At the time of merging, the total number of purchases of each of the plurality of groups is set as the number of purchases of one group after merging.

The third correction unit 111-7 deletes a group in which the number of purchases corresponding to one group is less than a predetermined number.

The estimation unit 113 estimates one or more areas to be the activity bases of the target person based on the areas to which any group is associated by the group / area association unit 111. Specifically, if the number of activity bases is specified by an external application program (not shown) or the like, the estimation unit 113 is among a plurality of areas output from the group / region association unit 111. , The area of the number of cases specified from the top in the order of the number of purchases corresponding to the own area is output as the estimated activity base together with the ranking. However, the number of cases does not have to be specified from the outside, may be a predetermined number, or may be a changeable number determined by the activity base estimation device. Moreover, it is not necessary to output the ranking.

As shown in FIG. 9, for example, the secondary estimation unit 115 changes the place of residence of the target person or the occurrence, change, or disappearance of the place of employment based on one or more activity bases estimated for each predetermined period. In addition, estimate the activity base where the place of residence or place of employment exists before and after these changes.

The information generation unit 117 generates information that contributes to sales promotion at the activity bases based on one or more activity bases estimated by the estimation unit 113.

Next, the activity base estimation method performed by the activity base estimation device 100 according to the embodiment of the present invention will be described with reference to FIGS. 2 to 4.

The activity base estimation device 100 estimates one or more activity bases for each target person, targeting one or more designated purchasers, using purchase information related to a plurality of purchases in a designated period. However, in that case, a plurality of purchases are sorted for each target person in a specified order (for example, ascending order of date and time). Referring to FIG. 2, the activity base estimation device first inputs the designation of one or more target persons, the designation of the period, and the designation of the order via the user interface (step S201). Here, each target person can be specified by name, date of birth, gender, and the like. The target person may be specified by other personal identification information such as a membership number. In addition, a person who satisfies a specific condition may be extracted from the outside, and such a person may be targeted. The period is specified, for example, from XX month XX day to XX month XX day to △△△△ year △△ month △△ day. The order is usually specified in chronological order.

Next, the activity base estimation device 100 selects the first target person from one or more target persons designated in step S201 (step S203). Further, in step S203, the target person number is set to zero.

Next, the purchase information for the period specified in step S201 of the currently selected target person among the target persons specified in step S201 is sorted in the order specified in step S201 (step S205). As a result, the purchase information for the period specified in step S201 of the currently selected target person among the target persons specified in step S201 can be read in the order specified in step S201. Further, in step S205, the group number is set to zero.

Next, the purchase information corresponding to the first purchase is read (step S207).

Next, if the purchase information can be read in step S207 (YES in step S209), it is determined whether or not the purchase point indicated by the purchase information belongs to any group already formed (step). S211), if it does not belong (NO in step S211), the purchase point indicated by the most recently read purchase information (the purchase information read in step S207 or the latest step S213) is designated as the reference purchase point (step). S215). The purchasing point designated as the reference purchasing point in step S215 becomes the central point of the newly formed group.

Next, in step S217, the area (city, ward, town, village, etc.) to which the purchasing point designated as the reference purchasing point belongs is specified, what kind of area this area belongs to, and the specified type of area. Set the living area distance corresponding to.

Next, the purchase information corresponding to the next purchase is read (step S219).

Next, if the purchase information can be read in step S219 (YES in step S221), it is determined whether or not the purchase point indicated by the purchase information read in step S219 already belongs to any group (YES). Step S223). In essence, it is determined whether or not the group belongs to a group centered on the purchase point designated as the reference purchase point in step S215 executed before that step S215, not the most recently executed step S215. It becomes.

If the purchasing point indicated by the purchasing information read in step S219 does not belong to any existing group (NO in step S223), this purchasing point is selected as the reference purchasing point in step S215. From (step S225), it is determined whether or not the object exists within the range of the living area distance set in step S217 or less (step S225). If this determination is affirmative (YES in step S225), the purchasing point indicated by the purchasing information read in step S219 belongs to the group (step S225). In step S227
Number of points purchased (group number, target person number)
= Number of points purchased (group number, target person number) + 1
It also processes.

If it is NO in step S209, it means that the formation of the group has been completed for the currently selected target person. In this case, the process proceeds to step S231S.

If YES in step S211, the process proceeds to step S213 in order to read the purchase information corresponding to the next purchase for the purpose of searching for the purchase point that becomes the reference purchase point of the new group.

A NO in step S221 indicates that there are no additional purchasing points in the currently formed group, so the group number is incremented by 1 (step S229) to step S207. Go back and start forming the next group.

If YES in step S223, the process returns to step S219 in order to prevent the same purchasing point from belonging to a plurality of groups.

If NO in step S225, the purchase point indicated by the purchase read in step S219 cannot be added to the group currently being formed, so the process returns to step S219.

The above steps are executed by the group forming unit 109.

Next, referring to FIG. 3, the allocation unit 111-1 allocates an area to all the groups generated by the time the current target person reaches step S231S (steps S231S, S233, S231E).

Next, the first correction unit 111-3 is one in each group if there is a group associated with a plurality of regions for all the groups allocated to the area by the allocation unit 111-1. The processes from steps S237 to S245, which are processes for modifying so that only regions are associated with each other, are repeated for all the groups to which the areas are allocated (steps S235S and S235E).

In step S237, it is determined whether or not there are a plurality of areas within the current group. This can be done by comparing on a map. In the example of FIG. 6, the judgment is NO because there is one area within the group, but in the example of FIG. 7A, the judgment is YES because there are three areas within the group. .. In the example of FIG. 8A, the judgment is NO because there are not a plurality of areas within the group.

If so (YES in step S237), the number of purchases is counted for all areas existing within the current group (step S239). Here, in order to count the number of purchases for all areas, the number of purchases for each purchase point belonging to each area is totaled by referring to the purchase information again. The number of purchase points corresponding to the area and the number of purchases corresponding to the area may be different. For example, if there are two purchases at all purchasing points belonging to the area, the number of purchases is twice the number of purchasing points. In order to know the activity base, the frequency of purchasing at a certain point or area is important.

Next, if there are a plurality of areas having the largest number of purchases (YES in step S241), the process proceeds to step 243, and if there is only one area having the largest number of purchases (NO in step S241). The process proceeds to step S245.

In step S243, the daytime population ratio is acquired from the main statistical table by city, ward, town, and village, and the area with the highest ratio (city, ward, town, and village, etc.) is set as the area corresponding to the current group (city, ward, town, and village, etc.).

In step S245, the area with the largest number of purchases (city, ward, town, village, etc.) is set as the area corresponding to the current group (city, ward, town, village, etc.). In step S245, for example, the correspondence in FIG. 7A is modified to the correspondence in FIG. 7B.

In step S243 and step S245, the sum of the number of purchases corresponding to each of the plurality of areas within the group is set as the number of purchases corresponding to the area corresponding to the group.

When the repetition of steps S235S to S235E is completed, the second correction unit 111-5 modifies so that if there is an area to which a plurality of groups are associated, only one group is associated with that area. The processes from steps S249 to S251, which are the processes for performing the above, are repeated for all the areas to which the group is assigned (steps S247S, S247E).

In step S249, it is determined whether or not a plurality of groups are assigned to one area (city, ward, town, village, etc.). This can be done by comparing on a map. In the example of FIG. 6, the judgment is NO because one group exists in one region, but in the example of FIG. 8A, the judgment is YES because a plurality of groups exist in one region. .. In the example of FIG. 7A, the judgment is NO because a plurality of groups do not exist in one area. However, the correspondence as shown in FIG. 7A has already been corrected by the first correction unit 111-3 to the correspondence as shown in FIG. 7B.

If so (YES in step S249), the plurality of groups (associated) assigned to the area are merged into one group (step S251). Here, the total number of purchases corresponding to each of the plurality of groups is set to the number of purchases corresponding to one group obtained by merging the plurality of groups. In step S251, for example, the correspondence relationship in FIG. 8A is modified to the correspondence relationship in FIG. 8B.

If the number of purchases corresponding to the group (which is equal to the number of purchases corresponding to the group) is less than a predetermined value (YES in step S263), the third correction unit 111-7 deletes the group (YES in step S263). The process for step S265) is repeated for all groups (steps S261S, S261E).

When this is completed, the estimation unit 113 rearranges the areas in descending order of the number of purchases (step S267), and selects the number (area) specified from the top as the activity base (step S269).

This completes the processing for the current target person.

If there is a next target person (YES in step S271), the target person number is increased by 1 (step S272), and then the process returns to step S205 to process the next target person. If there is no next target person, the entire process ends.

Next, a specific example will be described with reference to FIG.

S215: Purchasing point 1: Group 1
S227: Purchasing point 2: Group 1
S227: Purchasing point 3: Group 1
S215: Purchasing point 4: Group 2
S227: Purchasing point 5: Group 2
S215: Purchasing point 6: Group 3
S227: Purchasing point 7: Group 3
S215: Purchasing point 8: Group 4
Groups 1 to 4 are formed in the order of.

FIG. 11 is a diagram showing the transition of a group in which a part is formed at different periods according to the embodiment of the present invention. 11 (a), (b) and (c) correspond to the period 1, period 2 and period 3 shown in FIG. 9, respectively. In period 1, group 1, group 2, group 3 and group 4 are formed in this order. In period 2, group 2, group 3, group 4 and group 5 are formed in this order. In period 3, group 3, group 4, group 5 and group 6 are formed in this order. Therefore, even if the periods are different from each other, if some parts overlap, it can be seen that the groups corresponding to the overlapping parts are common. In other words, it can be seen that it is possible to avoid unnecessary fluctuations in group formation. Therefore, it is possible to accurately distinguish and grasp the common part and the variable part of the activity base due to the transition of the period. This is because the group forming unit 109 performs the processing as shown in FIG.

However, although it is not always effective with the period transition, the purchase may be rearranged according to another criterion in step S205. For example, the items may be sorted in order of purchase amount at each purchase point or in order of number of purchases at each purchase point.

Next, a specific example of the secondary estimation performed by the secondary estimation unit 115 will be described.

For example, if a certain subject's activity base becomes a completely different activity base at a certain time and continues, there is a possibility that a major change in life has occurred, such as moving from the current place of residence to a distant place. It can be estimated to be high. In addition, if part of the activity base changes or other part changes, moving, changing jobs, graduating from school by comparing with the attribute value, employment, school address of the customer information registered in advance. It is highly probable that there was a change in lifestyle, such as getting a job or having a lover or friend. In determining the above change, the accuracy is estimated as much as possible depending on the day of the week when the card is used and the type of business of the store where the card is used.

As described above, the information generation unit 117 generates information that contributes to sales promotion in the region based on one or more regions estimated by the estimation unit 113.

Taking the information for a company that has only one store as an example, the target person is a person who is registered as a member who purchases products from the company, and the activity base estimated for that target person. If there is that store in, issue a coupon to guide you to that store. If more than one activity base is inferred, do this for each activity base. This can be done by an operating company that has a contract with such a store.

According to this embodiment, it is possible to know the activity bases that are likely to carry out purchasing activities without relying on the home address and work address obtained from the target person. Therefore, for example, it is possible to carry out accurate sales promotion activities even for a target person who has changed his / her home address due to moving but has not notified it. Therefore, it can be operated even in a system that does not require registration of a home address or a work address.

The activity base estimation device can be realized by hardware, software, or a combination thereof. Further, the activity base estimation method performed by the activity base estimation device described above can also be realized by hardware, software, or a combination thereof. Here, what is realized by software means that it is realized by a computer reading and executing a program.

Programs can be stored and supplied to a computer using various types of non-transitory computer readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (eg, magneto-optical disks), CD-ROMs (Read Only Memory), CD- It includes R, CD-R / W, and semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)). The program may also be supplied to the computer by various types of transient computer readable media. Examples of temporary computer-readable media include electrical, optical, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

The present invention can be used to estimate the activity base of the subject.

101 Statistical information database 103 Living area distance calculation unit 105 Living area distance storage unit 107 Purchasing information database 109 Group forming unit 111 Group / region mapping unit 113 Estimating unit 115 Secondary estimation unit 117 Information generation unit 111-1 Allocation unit 111 -3 1st correction part 111-5 2nd correction part 111-7 3rd correction part

Claims (14)

An activity base estimation device that estimates one or more areas that are the target person's activity bases based on purchase information that represents multiple purchases by the target person.
Based on the life zone distance and geographical positions of the plurality of purchase points to perform the plurality of purchase, the Living distance 1 or more to form a Group 1 or more so as to include a purchase point for the circular close to the radius , A group forming means that uses the geographical position of the purchasing point and the living area distance, and further sets a reference point at the center of the circle in order to create the circular area .
Group / region mapping means that associates each group with a region,
Based on the area to which any group is associated, an estimation means for estimating one or more areas that are the activity bases of the target person , based on the number of purchasing points included in the area, Bei example,
The group forming means forms each group so as to include a purchasing point defined as a reference purchasing point of each group and a purchasing point existing within the living area distance from the purchasing point.
It said estimating means, a corresponding predetermined number of local number of high-level in the order of purchase, activity base estimating apparatus characterized that you estimated as one or more areas as the activity base of the subject. The activity base estimation device according to claim 1 .
The group forming means is an activity base estimation device characterized in that one or more groups are formed according to a priority based on a predetermined criterion of purchase. The activity base estimation device according to claim 2 .
The group forming means arranges the plurality of purchases according to the priority order, excludes the purchase corresponding to the purchase point already belonging to any group, and then gives the first priority among the remaining purchases. If there is another purchase point within the range of the living area distance from the standard purchase point, the other purchase point is set as the standard purchase point belonging to the new group. An activity base estimation device, characterized in that one or more groups are formed by repeating the formation of the new group one or more times by belonging to the new group. The activity base estimation device according to claim 2 or 3 .
The predetermined standard is an activity base estimation device characterized in that it is a standard based on the ascending order of the date and time when the purchase was made, the order of the purchase amount at each purchase point, or the order of the number of purchases at each purchase point. The activity base estimation device according to any one of claims 1 to 4 .
The group forming means is an activity base estimation device characterized by using a different living area distance for each type of the area as the living area distance. The activity base estimation device according to claim 5 .
The average distance between the specified facilities of the same type in each of the multiple regions randomly selected for each region type is acquired for multiple types of facilities, and the average distance for each region and each type of facility acquired. An activity base estimation device, further comprising a living area distance calculating means for calculating the living area distance, which is different for each type of the area. A activity base estimating apparatus according to any one of claims 1乃Itaru 6,
The group / area association means is an activity base estimation device characterized in that the group and the area are associated with each other in a one-to-one relationship. The activity base estimation device according to claim 7 .
The group / region association means
An allocation means for assigning to each group the area where the position based on the purchase point belonging to the group exists.
If there is a group corresponding to a plurality of regions by the allocation means among the one or more groups formed by the group forming means, the group is selected based on a predetermined criterion among the plurality of regions. The first amendment to make any one of the areas correspond to that group,
If there is an area corresponding to a plurality of groups by the allocation means among the one or more areas formed by the group forming means, one group obtained by merging the plurality of groups will be obtained. A second amendment to modify to correspond to the area,
An activity base estimation device characterized by being equipped with. The activity base estimation device according to claim 8 .
The group / region associating means is an activity base estimation device further comprising a third correction means for deleting an area in which the number of corresponding purchases is less than a predetermined number. The activity base estimation device according to claim 9 .
The estimation means is an activity base estimation device characterized in that the activity bases are ranked in descending order of the number of corresponding purchases. The activity base estimation device according to any one of claims 1 to 10 .
Based on the one or more activity bases estimated for each of a plurality of predetermined periods, the change of residence or place of employment of the target person occurs, changes or disappears, and the place of residence or place of employment exists before and after these changes. An activity base estimation device characterized by further comprising a secondary estimation means for estimating an activity base to be performed. The activity base estimation device according to any one of claims 1 to 11 .
An activity base estimation device, further comprising an information generation means for generating information that contributes to sales promotion at the activity base based on the estimated one or more activity bases. It is an activity base estimation method that estimates one or more areas that are the target person's activity bases based on purchase information that represents multiple purchases by the target person.
Based on the life zone distance and geographical positions of the plurality of purchase points to perform the plurality of purchase, the Living distance 1 or more to form a Group 1 or more so as to include a purchase point for the circular close to the radius , A group formation step that uses the geographical position of the purchasing point and the living area distance, and further sets a reference point that is the center of the circle to create the circular area .
Group / region mapping steps that associate each group with a region,
Based on the area to which any group is associated, the estimation step of estimating one or more areas that will be the activity bases of the target person , based on the number of purchasing points included in the area, Bei example,
The group formation step forms each group so as to include a purchasing point defined as a reference purchasing point of each group and a purchasing point existing within the living area distance from the purchasing point.
Said estimating step, the corresponding predetermined number of local number of high-level in the order of purchase, activity base estimation method characterized that you estimated as one or more areas as the activity base of the subject. It is an activity base estimation program that estimates one or more areas that are the target person's activity bases based on purchase information that represents multiple purchases by the target person.
On the computer
To form one or more groups so as to include one or more purchasing points in a circular area whose radius is the living area distance, based on the geographical position and living area distance of the plurality of purchasing points for making the plurality of purchases. , A group formation process that uses the geographical position of the purchase point and the living area distance, and further sets a reference point that is the center of the circle in order to create the circular area.
Group / region mapping processing that associates each group with a region,
Based on the area to which any group is associated, the estimation process that estimates one or more areas that will be the activity bases of the target person based on the number of purchasing points included in that area. Let it run
The group formation process forms each group so as to include a purchasing point defined as a reference purchasing point of each group and a purchasing point existing within the living area distance from the purchasing point.
The estimation process is an activity base estimation program characterized in that a predetermined number of regions in the order of the number of corresponding purchases are estimated as one or more regions to be the activity bases of the target person .

Images