JP2008204370A - Customer inducing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a customer inducing method for efficiently inducing customers by selecting customers capable of changing a store visiting tendency based on a predicted congestion occurrence condition and giving a notification only to the selected customers. <P>SOLUTION: In this customer inducing method for inducing a store visiting tendency of a customer, a computer device executes a candidate retrieval procedure and a transmission procedure. In the candidate retrieval procedure, store visiting prediction information predicting the number of persons below a maximum number of treatable persons stored in a predicted number of excessive/shortage persons table, which shows the number of excessive/shortage persons with respect to a predetermined number of treatable persons predicted for each store identifier identifying a store, is retrieved in a predetermined retrieval order of candidates, in which a part of store visiting tendency information of a customer database storing store visiting information in association with a customer identifier for each customer identifier identifying a customer purchasing a commodity at a store over a predetermined number of treatable persons is varied. In the transmission procedure, recommended store visiting information is transmitted to customer terminals of the customers by using the store visiting prediction information retrieved by the candidate retrieval procedure. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a customer guidance method for guiding customer visit tendency.

  Traditionally, using customer purchase history to analyze purchase trends to promote product sales, analyzing product sales in the market to study product development directions, and trends in store visits It is performed to analyze the store and operate the store efficiently.

  In Patent Document 1, visitors to a store are represented using a Bayesian network showing a probability model based on a graph structure in which random variables are represented by nodes and linked between variables indicating causal relationships and correlations. It has been proposed to make a prediction.

  In Patent Document 2, the customer's current trends are divided into cell groups so that the customer's current trends can be accurately grasped from the store visit date / time, store visit frequency and usage amount, and the location of the customer's current cell group is grasped or the cell group is moved By grasping the actual situation, a customer management system based on numerical values has been proposed in which data contributing to the identification of good customers, the prediction of customer departure and the effective identification of advertising targets can be obtained.

Patent Document 3 proposes a one-to-one business support system for facilitating a process of analyzing a customer using information about the customer and formulating an appropriate action for each customer using the analysis result.
JP 2005-228014 A JP 2002-259667 A JP 2004-185598 A

  In a retail store, if there are customers exceeding the number of customers that can be handled in the store (a state in which there is no queue at the cash register more than a predetermined number of people / a customer who cannot be handled by the sales clerk), the customer service Has declined significantly, leading to lost sales opportunities. In order to prevent such a chance loss due to congestion, there may be a method of increasing the number of cash registers or the number of sales staff, but there is a problem that a large amount of investment is required.

  An object of the present invention is to provide a customer guidance method for efficiently guiding a customer by selecting a customer whose store visit tendency can be changed based on a predicted congestion occurrence situation and notifying only that customer. It is.

  In order to solve the above-mentioned problem, the present invention is a program for causing a computer device to perform processing in a customer guidance method for guiding the customer's store visit tendency, which corresponds to a store identifier for identifying a store. In addition, from the store prediction database storing store prediction information as the store visit prediction information for the predetermined process number that is the number of people that can be handled per hour in the store, records with the predicted store visit number exceeding the predetermined process number are stored. The customer identifier associated with the purchase record that matches the store identifier indicated in the referenced record is extracted from the POS information database that stores information related to the purchase procedure and the past purchase record in association with the customer identifier. The store visit prediction data in a predetermined candidate search order in which a part of the store visit tendency of the extracted customer identifier differs. The recommended store visit information is generated using a procedure for searching for a record in which the predicted number of store visits does not exceed the predetermined number of processing persons and a record searched by the search procedure, and is transmitted to the customer terminal of the customer Configured to execute the procedure.

  In a computer device that operates according to such a program, a store visit is provided by providing recommended store visit information to a customer who tends to purchase a product at a store that is expected to be crowded, in which the store visit tendency is partially changed. Customers can be guided so that the level of concentration is leveled. Since only a part of the store visit tendency is changed, it is possible to provide recommended store visit information that does not cause discomfort to the customer (that is, the customer can easily visit the store).

  As means for solving the above-described problems, the present invention may be a customer guidance program that causes a computer device to execute the processing procedure according to the customer guidance method, and a storage medium that stores the customer guidance program.

  In the present invention, the concentration of store visits is leveled by providing recommended store visit information in which the customer's store visit tendency is partially changed to customers who tend to purchase products at stores where congestion is expected. So that customers can be guided. Since only part of the store visit tendency is changed, it is possible to provide recommended store visit information that does not cause discomfort to the customer.

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

  FIG. 1 is a diagram showing a configuration of a customer guidance system according to an embodiment of the present invention. In FIG. 1, a customer guidance system 100 mainly includes an over-capacity calculation unit 20, a segmentation processing unit 30, and a customer guidance processing unit 40. The customer guidance system 100 includes a customer personal computer, a portable terminal, and the like via the network 2. Connected to the customer terminal 3.

  The overcapacity calculation unit 20 is a processing unit that predicts the number of customers who visit the store and calculates a difference from the maximum number of customers that can handle each store, and includes a store visit prediction processing unit 21, a POS information DB 22, The store master DB 23, the prediction parameter table 24, and the store visit prediction DB 25 are included.

  The segmentation processing unit 30 is a processing unit that segments customers and obtains customer attributes based on purchase time zones and purchase price trends, and includes a customer attribute determination unit 31, a member information DB 32, and a segmentation DB 33.

  The customer guidance processing unit 40 is a processing unit that transmits guidance information for guiding customers to a store exceeding the maximum number of customers via the network 2 to the customer who is the guidance target. The product master DB 42 and the promotion information DB 43 are included.

  The customer guidance system 100 may be realized by one computer device, or the over-capacity calculation unit 20, the segmentation processing unit 30, and the customer guidance processing unit 40 are realized by different computer devices and connected by a network. It is good also as a structure to be performed.

  The computer device that implements the customer guidance system 100 has a hardware configuration as shown in FIG. FIG. 2 is a diagram illustrating a hardware configuration of a computer device that realizes a customer guidance system according to an embodiment of the present invention.

  In FIG. 2, a computer device 100 a that implements the customer guidance system 100 is a device controlled by a computer, and includes a CPU (Central Processing Unit) 11, a memory unit 12, a display unit 13, an output unit 14, The input unit 15, the communication unit 16, the storage device 17, and the driver 18 are configured and connected to the system bus B.

  The CPU 11 controls the computer device 100 a according to a program stored in the memory unit 12. The memory unit 12 includes a RAM (Random Access Memory), a ROM (Read-Only Memory), and the like, and is obtained by a program executed by the CPU 11, data necessary for processing by the CPU 11, and processing by the CPU 11. Stored data. A part of the memory unit 12 is allocated as a work area used for processing by the CPU 11.

  The display unit 13 displays various information required under the control of the CPU 11. The output unit 14 has a printer or the like, and is used for outputting various types of information in accordance with instructions from the user. The input unit 15 includes a mouse, a keyboard, and the like, and is used for a user to input various information necessary for the simulation system 100 to perform processing.

  The communication unit 16 is a device for the computer device 100a to control communication via a network such as the Internet or a LAN (Local Area Network).

  The storage device 17 is composed of, for example, a hard disk unit, and stores data such as programs for executing various processes.

  A program that realizes processing performed by the computer apparatus 100a is provided to the computer apparatus 100a by a storage medium 19 such as a CD-ROM (Compact Disk Read-Only Memory). That is, when the storage medium 19 storing the program is set in the driver 18, the driver 18 reads the program from the storage medium 19, and the read program is installed in the storage device 17 via the system bus B. . When the program is activated, the CPU 11 starts its processing according to the program installed in the storage device 17.

  The medium for storing the program is not limited to a CD-ROM, and any medium that can be read by a computer is acceptable. The program for realizing the processing according to the present invention may be downloaded via the network by the communication unit 16 and installed in the storage device 17. When the computer apparatus 100a has an interface such as a USB (Universal Serial Bus) for connecting to the outside, the program may be read from an external storage medium by USB connection.

  Processing by the store visit prediction processing unit 21 of the overcapacity calculation unit 20 will be described with reference to FIGS. 3 and 4. FIG. 3 is a diagram for explaining processing in the store visit prediction processing unit. In FIG. 3, the store visit prediction processing unit 21 reads the POS information DB 22 (step S201), acquires the cash register processing start time and cash register processing end time recorded at the cash register when the customer purchases the product, The number of cash register processing cases per day (that is, the number of customers) is calculated (step S202).

  The store visit prediction processing unit 21 acquires the number of store cashiers from the store master DB 23 (step S203), average cashier processing time, the number of cashiers processed per hour, and the maximum number of cashiers processed per hour (in the store being processed) (Predetermined number of processing persons) is calculated (step S204). For example, the average cashier processing time “60 seconds” per customer, the cashier processing number of people per hour “120 people” per store cashier, and the maximum number of people processing “360 people” per hour of the stores being processed ( = 120 people × 3 units). Steps S201 to S204 are executed for each store.

  On the other hand, the store visit prediction processing unit 21 calculates the number of customers who visit the store every hour of each day of the week from past performance data read from the POS information DB 22 (step S211). In addition, the store visit prediction processing unit 21 reads parameter information including weather forecast, location conditions, season, event, day of the week, and time zone (step S212), and refers to the prediction parameter table 24 for each hour of each day of the week. A weighting coefficient is calculated (step S213).

  Referring to FIG. 4, the prediction parameter table 24 includes parameter items, parameter values, conditions, and parameter indices. As the parameter items, weather forecast, location conditions, season, event, day of the week, and time zone are shown, and the parameter index is obtained by multiplying the value of the condition corresponding to each item and the parameter value. After calculating the parameter index for all the parameter items, the total parameter index becomes a weighting coefficient for predicting the number of customers visiting the store.

  According to the parameter information, if the weather is “Sunny”, the location condition is “In front of the station (open type)”, the season is “Summer”, and the event is “Yes”, the parameter index for the day of the week at a certain store on Friday night Becomes “0.4” by multiplying the parameter value “0.2” by the value “2” of the condition “Friday”. By the same calculation, the time zone parameter index is “0.16”, the weather parameter index is “0.3”, the location condition parameter index is “0.07”, and the season parameter index is “0.15”. The event parameter index is “0.36”. Then, a weighting coefficient “1.44” obtained by adding these parameter indexes is acquired.

  Returning to FIG. 3, the store visit prediction processing unit 21 predicts the number of customers visiting the store every hour of each day of the week in units of one week (step S214). A value (number of customers visiting the store) obtained by multiplying the number of customers visiting the store predicted by a predetermined algorithm using past performance data (the number of customers visiting the store) is obtained as a prediction result. When the number of customers visiting the store predicted by the predetermined algorithm is “300”, the prediction result is “432” (= 300 × 1.44).

  Further, the store visit prediction processing unit 21 calculates the over capacity per hour for every hour of each day of the week using the maximum number of persons processed per hour calculated in step S204 (step S220).

  If the value obtained by subtracting the maximum processing number from the prediction result calculated in step S214 (over or shortage number) is less than or equal to zero (zero or negative), it is determined that the predicted number of customers visiting the store is within the processable range, The time of day of the week is not targeted for guidance (step S221). The store visit prediction processing unit 21 sets the prediction result calculated in step S214, the excess / shortage number, and the guidance target flag in correspondence with each store ID, date, day of the week, and time zone being processed, and the store visit prediction DB 25. To store. In this case, the store visit prediction processing unit 21 turns off the guidance target flag and indicates that it is below the maximum processing number of people.

  On the other hand, when the value obtained by subtracting the maximum number of processed persons from the prediction result calculated in step S214 (the number of excess / deficient persons) is positive, the predicted number of customers visiting the store exceeds the processable range, that is, for example, waiting for cashiers or sales to customers. Since it can be inferred that there may be a problem such as a shortage of staff, in order to alleviate such a situation, the excess number of customers on that day of the processing day is the number of customers who are guided to other stores (Step S222). The store visit prediction processing unit 21 sets the prediction result calculated in step S214, the number of surpluses and deficiencies, and the guidance target flag corresponding to each store ID, date, day of the week, and time zone being processed, and the store visit prediction DB 25 To store. In this case, the store visit prediction processing unit 21 turns on the guidance target flag to indicate that the number is equal to or greater than the maximum processing number.

  Processing performed by the customer attribute determination unit 31 of the segmentation processing unit 30 will be described with reference to FIGS. 5, 6, and 7. FIG. 5 is a diagram for explaining processing in the customer attribute determination unit. In FIG. 5, the customer attribute determination unit 31 reads the past performance data 22d from the POS information DB 22 (step S301), and reads the member information data 32d from the member information DB 32 (step S302). The past performance data 22d read from the POS information DB 22 includes, for example, as shown in FIG. 6, the product name of the product purchased by the member as a customer, the product code of the product, the product category indicating the price range of the product, the purchase It includes items such as the number of purchased products, date of purchase, day of the week, customer ID for identifying the member, time of purchase, degree of discount (%) at the time of purchase, premium product, and the like. In the product master DB 42 of the customer guidance processing unit 40, the product name belonging to each product category and the price of the product are defined.

  The member information data 32d read from the member information DB 32 includes, for example, as shown in FIG. 7, the name and customer ID of a customer registered as a member, the member registration date registered as a member, gender, age, address, Includes items such as email addresses and phone numbers.

  The customer attribute determination unit 31 associates the past performance data 22d and the member information data 32d with the customer ID, and determines the price sensitivity of each member (step S303). That is, the customer attribute determination unit 31 determines the price range in which the member tends to purchase using the product category of the product purchased by the member. Also, the purchase tendency for discounted products is analyzed.

  Price sensitivity refers to the importance of the purchaser (member) on the price, whether it tends to buy low-priced products, intermediate-priced products, or high-priced products (that is, quality-oriented) It is made up of segments that indicate the tendency to purchase.

  Subsequently, the customer attribute determination unit 31 determines time sensitivity regarding the purchase time of each member (step S304). That is, the customer attribute determination unit 31 reads the day of the week and the time from the past record data 22d and determines the degree of concentration of the day of the week and the time at the time of purchase. Further, the customer attribute determination unit 31 determines whether the purchase time is concentrated after the evening (for example, after 18:00) or the purchase time is concentrated on the weekend (Saturday or Sunday) from the degree of concentration of the day of the week and time. And determine the type of member. For example, if the purchase time is concentrated after the evening or on the weekend, the member is determined to be a worker.

  Time sensitivity indicates the degree of time the customer visits the store. Is the time zone fixed (for example, the customer visits the store at 90% or more in the same time zone)? Consists of segments that indicate whether they are scattered (for example, visiting 60% or more and less than 90% in the same time zone), or whether the time zone to visit is not specified (for example, coming in less than 60% in the same time zone) Is done. Due to the combination of price sensitivity and time sensitivity, the segmentation 38 is composed of 9 segments.

  Further, the customer attribute determination unit 31 uses the segmentation 38 representing a plurality of segments by the price sensitivity and the time sensitivity divided for each predetermined range, and the price sensitivity obtained in step S303 and the step S304. A segment to be plotted for each member is determined based on the obtained time sensitivity (step S305). The customer attribute determination unit 31 stores customer segment information 33d in which a segment is associated with each customer ID in the segmentation DB 33.

  Processing performed by the promotion execution unit 41 of the customer guidance processing unit 40 will be described with reference to FIG. FIG. 8 is a diagram for explaining processing in the promotion execution unit. In FIG. 8, the promotion execution unit 41 reads the POS information DB 22, the store visit prediction DB 25, the member information DB 32, and the segmentation DB 33 (step S401).

  And the promotion execution part 41 extracts the customer which belongs to one of the segments D, E, G, and H from the customers who have purchased in the past on the day of the week and the time zone of the store exceeding the maximum processing number (step) S402). The extracted customer information is stored in the assumed customer DB 41c.

  As shown in the segmentation 38, customers belonging to the segments D, E, G, and H are customers that do not have high time sensitivity and price sensitivity. Such customers are considered to be customers who are easy to be guided to a time zone that is different from the time zone where they normally do shopping because they tend to be flexible during the time they visit the store and are more price-oriented. Can do.

  The process in step S402 will be described with reference to FIG. In FIG. 9, first, the promotion execution unit 41 searches the POS information DB 22 for records having the same combination of store ID, date, and day of week for records in which the guidance target flag of the store visit prediction DB 25 is on (the maximum number of users is exceeded). The customer ID, the store ID, the date, the day of the week, and the time zone are read out from each extracted record, and the first work table 47a is created.

  Next, promotion execution part 41 acquires store ID of three stores in order with the frequency of purchasing goods for every customer ID using the 1st work table 47a, and purchases goods in each store. Get the day of the week and the time of day. Then, for each customer ID, a second work table 47b composed of store ID 1, trend 1, store ID 2, trend 2, store ID 3, and trend 3 is created. For example, trend 1, trend 2 and trend 3 are indicated by information combining days of the week and times of day with a high purchase frequency at each store.

  Then, the promotion execution unit 41 acquires a segment that matches the customer ID stored in the second work table 47b from the segmentation DB 33, and records the value in the second work table 47b in association with the customer ID. Thereafter, only the records with the segments D, E, G, and H are extracted from the second work table 47b to which the segments are added to create the assumed customer DB 41c.

  Returning to FIG. 8, the promotion execution unit 41 guides, in the order of (1) different days of the week, (2) different time zones, and (3) different stores, from the stores exceeding the maximum number of processing persons according to the customer's tendency to visit A destination is searched and a guidance destination candidate is created for each customer who is a guidance target (step S403). In this case, when a guidance destination candidate is not searched, the process by the promotion execution part 41 is complete | finished.

  The processing in step S403 will be described with reference to FIGS. In FIG. 10, the promotion execution unit 41 extracts records from the visitor prediction DB 25 using items of store ID, date, day of the week, time zone, and excess / deficiency number, and creates a third work table 47c as shown in FIG. (Step S431). And the promotion execution part 41 reads the record of the first customer ID from assumption customer DB41c (step S432).

  For each store and trend with a high purchase frequency in the assumed customer DB 41c, the promotion execution unit 41 stores information from the third work table 47c in the order of (1) different day of the week, (2) different time zone, and (3) different store candidate search order. A guide destination candidate having a negative number of deficient persons is searched (step S433).

  The third work table 47c is searched in the candidate search order of (1) using the combination of the store ID 1 and the trend 1 of the assumed customer DB 41c. If there is no guide destination candidate, the search is performed in the candidate search order of (2). If there is no candidate, the search is further performed in the candidate search order of (3). If the guide destination candidate is searched in the candidate search order of (1), the search in the candidate search order of (2) and (3) is not necessary, and the search is similarly performed with the combination of the store ID 2 and the trend 2 of the assumed customer DB 41c. To do. Even if the guide destination candidate is not searched in the candidate search order of (1), if the guide destination candidate is searched in the candidate search order of (2), the search in the candidate search order of (3) becomes unnecessary. When the guide destination candidate is not searched in the candidate search order of (1) to (3) for the combination of the store ID 1 and the trend 1, the search is similarly performed with the combination of the store ID 2 and the trend 2. Alternatively, if a predetermined number of candidates (for example, three candidates) can be searched by searching in the candidate search order of (1) to (3) with the combination of the store ID 1 and the trend 1 of the assumed customer DB 41c, the next store ID 2 and the trend You may make it complete | finish, without searching by the combination of two.

  The promotion execution unit 41 determines whether one or more guide destination candidates have been searched (step S434). If no guidance destination candidate has been found, the promotion execution unit 41 proceeds to step S437.

  When one or more guide destination candidates can be searched, the promotion execution unit 41 creates the fourth work table 47d indicating the guide destination candidates for which candidate stores and candidate dates and times are set in correspondence with the customer ID (step S435). When three candidates are searched, the candidate store and the candidate date and time are set in candidate store ID1 and candidate date and time 1, candidate store ID2 and candidate date and time 2, candidate store ID3 and candidate date and time 3, respectively. A segment is also set. Thereafter, the promotion execution unit 41 subtracts 1 from the excess or deficiency number of records of candidate stores and candidate dates (step S436).

  And the promotion execution part 41 judges whether the process was complete | finished about all the customer IDs of assumption customer DB41c (step S437). If not completed, the promotion execution unit 41 reads the record of the next customer ID from the assumed customer DB 41c (step S438), returns to step S433, and repeats the same processing as described above. On the other hand, if it has been completed, the promotion execution unit 41 ends the process in step S403 of FIG.

  Returning to FIG. 8, the promotion execution unit 41 determines whether or not a fourth work table 47d indicating a guide destination candidate has been created (step S404). If not created, the processing by the promotion execution unit 41 ends. If created, the promotion target product for the current month is determined for each of the customer segments D, E, G, and H using the product master DB 42 and the promotion DB 43 (step S405). The promotion execution part 41 adds and sets the information regarding the determined promotion goods to guidance customer DB41d.

  The processing in step S405 will be described with reference to FIGS. As shown in FIG. 12, in the embodiment of the present application, each promotion target product is grouped into nine segments formed by three price categories and product freshness. The price category is divided into 3 from low price to high price, and the product freshness is divided into 3 from standard products to new products.

  Each product plotted in the segmentation for such promotional products is promoted by items such as a product code identifying the product and a coupon indicating coupon information when purchasing the product for each month targeted for promotion. It is recorded and managed in the information DB 43.

  In this embodiment, when the segment on which the customer is plotted is G, the products of the segments D ′, E ′, G ′, and H ′ are specifically selected as the promotion target products, and when the segment on which the customer is plotted is D, When the products of segments A ′, B ′, D ′, E ′ are selected as the products to be promoted in particular and the segment on which the customer is plotted is E, the products of segments B ′, C ′, E ′, F ′ are particularly When the segment in which the customer is plotted is H and the segment on which the customer is plotted is H, the products in the segments E ′, F ′, H ′, and I ′ are specifically selected as the promotion target products.

  As shown in FIG. 13, the promotion execution unit 41 acquires the product code and coupon of the promotion target product from the promotion information DB 42 for each of the customer segments D, E, G, and H, and the product name necessary as the promotion information. , Get price etc. using product code.

  The promotion execution unit 41 creates promotion information by a predetermined process using the product name, price, and coupon, and sets the promotion information corresponding to the customer segment as the promotion value in the guided customer DB 41d. Here, the price indicates a standard price, but for example, information such as a discount rate is included in the value of the coupon, so that a cheap feeling can be given to the customer.

  Returning to FIG. 8, next, the promotion execution unit 41 transmits the promotion information to the customer identified by the customer ID stored in the guidance customer DB 41d via the network 2 (step S405). As illustrated in FIG. 13, the promotion execution unit 41 reads records one by one from the guidance customer DB 41 d in order, searches the member information DB 32 for a record with a matching customer ID, and acquires a name and an email address. And the promotion execution part 41 produces a predetermined greeting using the customer's name acquired from member information DB32.

  Moreover, the promotion execution part 41 acquires a store name, an address, and a telephone number from store information DB44 with respect to each of candidate store ID1 and tendency 1, candidate store ID2 and trend 2, candidate store ID3, and trend 3, The recommended store visit information is created based on the information on the store location and the recommended day of the week and time. Furthermore, the promotion execution part 41 produces the advertisement information as a bargain product from the value of promotion.

  The promotion execution part 41 transmits the content of the e-mail composed of the greeting text, the recommended store visit information, and the advertisement information created in this way to the e-mail address acquired from the member information DB 32.

  As described above, for customers who have a strong tendency to purchase products at stores that are predicted to exceed the maximum processing capacity, to induce customers to visit other stores on different days of the week, at different times, and at different stores By providing the promotion information, for example, as shown in FIG. 14, it is possible to adjust so as to relax the customer's visit concentration. FIG. 14 is a diagram illustrating a state example of the number of customers visiting the store before and after guidance. In FIG. 14, the time axis or day of the week is shown in the x-axis direction, and the number of customers visiting the store before guidance is shown in the y-axis direction.

  FIG. 14 (A) shows a state in which the number of customers visiting the store before guidance exceeds the maximum number of customers in a certain time zone or day of the week and the customers are concentrated. FIG. 14B shows the transition of the number of store visits when a customer who has received an e-mail with recommended store visit information visits the store after changing the time zone or day of the week. In this case, it can be seen that the concentration of customer visits has been moderate. By making the degree of congestion gradually change in this way, store salespersons can uniformly explain products to customers regardless of time of day or day of the week. A sense of trust can be enhanced. Thereby, sales loss due to congestion can be reduced.

  As described above, in the invention of the present application, it is possible to reduce sales loss due to congestion by guiding customers to different time zones, different days of the week, different stores, etc. We can expect sales to increase without doing so.

  In addition, customers can receive incentives such as discounts on prices and better services from the store by purchasing products using coupons received by e-mail at specified times, days of the week, or at other stores. Can do.

  Furthermore, the congestion mitigation can be adjusted effectively by targeting customers who tend to be flexible in time and tend to be sensitive to prices. Further, by specifying the guidance target, it is possible to prevent the customer from feeling uncomfortable due to the e-mail for guidance. Normally, customers hate crowds, but they have no way of knowing which hours, which days of the week, and which stores are easy to use. Customers who tend to be flexible in time and price-sensitive (buy low-priced products) have a tendency to use the contents of e-mails because they are less likely to feel uncomfortable with the contents of e-mails to guide It is judged that

  In addition, in order to provide recommended store visit information that changes the customer's store visit tendency to customers who tend to purchase products at stores that are expected to be crowded, the customer visit level is leveled out. Can be induced. Since only part of the store visit tendency is changed, it is possible to provide recommended store visit information that does not cause discomfort to the customer.

Regarding the above description, the following items are further disclosed.
(Appendix 1)
A program for causing a computer device to perform processing in a customer guidance method for inducing customer visit tendency,
Corresponding to the store identifier that identifies the store, the predicted number of store visits is calculated from the store prediction database that stores the number of store visit predictions with respect to the predetermined processing number of people that can be handled per hour at the store as store visit prediction information. A procedure for referring to a record exceeding the predetermined processing number;
A procedure for extracting a customer identifier associated with the purchase record that matches the store identifier indicated in the referenced record from a POS information database that stores information on the past purchase record associated with the customer identifier;
In a predetermined candidate search order in which a part of the store visit tendency of the extracted customer identifier is different, a procedure for searching for records in which the predicted number of store visits does not exceed the predetermined processing number in the store visit prediction database;
A program for generating recommended store visit information using a record searched by the searching procedure and transmitting the information to the customer terminal of the customer.
(Appendix 2)
The store visit prediction information includes information indicating a store identifier, a day of the week, and a time zone,
The program according to appendix 1, wherein the predetermined candidate search order is an order of different time zones, different days of the week, and different store identifiers.
(Appendix 3)
In addition to the computer device,
Using past performance data in which the product name of the product sold, the price of the product, the time of purchase, and the customer identifier of the customer who has purchased are recorded in association with each other, the degree of importance for the price for each customer identifier And a procedure to determine the segment by the combination with the fixed degree for the time zone to visit,
The program according to appendix 1 or 2, wherein the transmitting step is configured to cause the customer terminal to transmit the recommended store information and promotional product information related to a product promoted according to the segment.
(Appendix 4)
In addition to the computer device,
A procedure for making a prediction result a value obtained by multiplying the number of customers visiting the store predicted for each day of the week and each time zone using the past performance data by a weighting coefficient calculated using a plurality of parameters;
A value obtained by subtracting the predetermined processing number from the prediction result is set as the excess / deficiency number, and the store visit prediction information including at least a day of the week, a time zone, the prediction result, and the excess / deficiency number is recorded in the store visit prediction database. The program according to appendix 3, wherein the management procedure is executed.
(Appendix 5)
A customer guidance method for guiding customer visit tendency, wherein a computer device is
Corresponding to the store identifier that identifies the store, the predicted number of store visits is calculated from the store prediction database that stores the number of store visit predictions with respect to the predetermined processing number of people that can be handled per hour at the store as store visit prediction information. A procedure for referring to a record exceeding the predetermined processing number;
A procedure for extracting a customer identifier associated with the purchase record that matches the store identifier indicated in the referenced record from a POS information database that stores information on the past purchase record associated with the customer identifier;
In a predetermined candidate search order in which a part of the store visit tendency of the extracted customer identifier is different, a procedure for searching for records in which the predicted number of store visits does not exceed the predetermined processing number in the store visit prediction database;
A customer guidance method for executing a procedure of generating recommended store visit information using a record searched by the candidate search procedure and transmitting the information to the customer terminal of the customer.
(Appendix 6)
A customer guidance device for generating information for inducing customer visit tendency,
Corresponding to the store identifier that identifies the store, the predicted number of store visits is calculated from the store prediction database that stores the number of store visit predictions with respect to the predetermined processing number of people that can be handled per hour at the store as store visit prediction information. Means for referring to a record exceeding the predetermined processing number;
Means for extracting a customer identifier associated with the purchase record that matches the store identifier indicated in the referenced record from a POS information database that stores information on the past purchase record in association with the customer identifier;
Means for searching for records in which the predicted number of store visits does not exceed the predetermined processing number in the store prediction database in a predetermined candidate search order in which a part of the store visit tendency of the extracted customer identifier is different;
A customer guidance device that executes means for generating recommended store visit information using a record searched by the searching means and transmitting the information to the customer terminal of the customer.

  The present invention is not limited to the specifically disclosed embodiments, and various modifications and changes can be made without departing from the scope of the claims.

It is a figure which shows the structure of the customer guidance system which concerns on one Example of this invention. It is a figure which shows the hardware constitutions of the computer apparatus which implement | achieves the customer guidance system which concerns on one Example of this invention. It is a figure for demonstrating the process in a store visit prediction process part. It is a figure which shows the example of a prediction parameter table. It is a figure for demonstrating the process in a customer attribute determination part. It is a figure which shows the example of purchase history data. It is a figure which shows the example of member information data. It is a figure for demonstrating the process in a promotion execution part. It is a figure for demonstrating the process in step S402 of FIG. It is a figure for demonstrating in detail the process by FIG.8 S403. It is a figure for demonstrating the process in step S403 of FIG. It is a figure which shows the example of the segment of promotion object goods. It is a figure for demonstrating the process in step S405 of FIG. It is a figure which shows the example of a state of the store visitor number before and behind guidance.

Explanation of symbols

2 Network 3 Customer terminal 11 CPU
DESCRIPTION OF SYMBOLS 12 Memory unit 13 Display unit 14 Output unit 15 Input unit 16 Communication unit 17 Storage device 18 Driver 19 Storage medium 20 Overcapacity calculation part 21 Store visit prediction process part 22 POS information DB
22d Past performance data 23 Store master DB
24 Prediction parameter table 25 Store visit prediction DB
30 Segmentation Processing Unit 31 Customer Attribute Determination Unit 32 Member Information DB
32d Member information data 33 Segmentation DB
33d Customer segment information 38 Segmentation 40 Customer guidance processing part 41 Promotion execution part 42 Goods master DB
43 Promotion Information DB
100 Customer Guidance System 100a Computer Device

Claims (4)

A program for causing a computer device to perform processing in a customer guidance method for inducing customer visit tendency,
Corresponding to the store identifier that identifies the store, the predicted number of store visits is calculated from the store prediction database that stores the number of store visit predictions with respect to the predetermined processing number of people that can be handled per hour at the store as store visit prediction information. A procedure for referring to a record exceeding the predetermined processing number;
A procedure for extracting a customer identifier associated with the purchase record that matches the store identifier indicated in the referenced record from a POS information database that stores information on the past purchase record associated with the customer identifier;
In a predetermined candidate search order in which a part of the store visit tendency of the extracted customer identifier is different, a procedure for searching for records in which the predicted number of store visits does not exceed the predetermined processing number in the store visit prediction database;
A program for generating recommended store visit information using a record searched by the searching procedure and transmitting the information to the customer terminal of the customer. The store visit prediction information includes information indicating a store identifier, a day of the week, and a time zone,
The program according to claim 1, wherein the predetermined candidate search order is an order of different time zones, different days of the week, and different store identifiers. In addition to the computer device,
Using past performance data in which the product name of the product sold, the price of the product, the time of purchase, and the customer identifier of the customer who has purchased are recorded in association with each other, the degree of importance for the price for each customer identifier And a procedure to determine the segment by the combination with the fixed degree for the time zone to visit,
The program according to claim 1, wherein the transmitting procedure causes the recommended terminal visit information and promotional product information relating to a product to be promoted according to the segment to be transmitted to the customer terminal. In addition to the computer device,
A procedure for making a prediction result a value obtained by multiplying the number of customers visiting the store predicted for each day of the week and each time zone using the past performance data by a weighting coefficient calculated using a plurality of parameters;
A value obtained by subtracting the predetermined processing number from the prediction result is set as the excess / deficiency number, and the store visit prediction information including at least a day of the week, a time zone, the prediction result, and the excess / deficiency number is recorded in the store visit prediction database. The program according to claim 3, wherein a management procedure is executed.

Images