Generation program, generation method and information processing device

Abstract

To analyze the flow lines of users in a store at low cost.SOLUTION: A generation program according to an embodiment causes a computer to execute a setting process and a generation process. The setting process includes setting weights for respective combinations of article categories of purchased articles based upon sale information on the articles. The generation process includes synthesizing, based upon a set weight, base visualization information stored in a storage part, and visualizing and showing user action histories in a store for each of a plurality of purchase patterns differing in the combination of article categories of purchased articles so as to generate visualization information visualizing and showing user action histories corresponding to the sale information.SELECTED DRAWING: Figure 9

Description

[Technical field]

[0001] An embodiment of the present invention relates to a generating program, a generating method, and an information processing device. [Background technology]

[0002] In the field of marketing for retail stores such as supermarkets and convenience stores, there is a conventional technology that generates a heat map that displays the cumulative time spent by customers at each point in the store overlaid on a map of the store. This heat map is a very useful visualization and analysis tool for analyzing the flow and movement of customers (hereinafter referred to as movement analysis) and analyzing the efficiency of the store, such as reducing congestion, and for improving access and sales. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] US Patent Application Publication No. 2016 / 0253740 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology has a problem in that it is very costly to generate a heat map, making it difficult to perform customer movement analysis at low cost.

[0005] For example, when creating a heat map by measuring the actual movements of customers, it is necessary to prepare equipment to identify the coordinates of customers within the store at each time, using radio communication technology for positioning or images taken by a camera that can observe the entire store.

[0006] In addition, when a heat map is generated by simulating the movement of customers in a store using an agent simulation based on POS (Point Of Sale) data, a huge calculation cost is incurred because each customer included in the POS data is simulated by an agent. In addition, in retail stores where the customer demographics differ depending on the time of day (morning, afternoon, and night), multiple heat maps corresponding to each time period are generated to analyze the movement lines for each time period. This results in long calculation times because an agent simulation for each time period is performed based on the POS data collected for each time period.

[0007] In one aspect, an object of the present invention is to provide a generation program, a generation method, and an information processing device that enable a customer movement line analysis within a store to be performed at low cost. [Means for solving the problem]

[0008] In one proposal, the generation program causes a computer to execute a setting process and a generating process. The setting process sets weights for each combination of product categories of purchased products based on product sales information. The generating process synthesizes, based on the set weights, base visualization information that visualizes and shows the behavioral history of users in a store for each of a plurality of purchase patterns with different combinations of product categories of purchased products, which is stored in a storage unit, to generate visualization information that visualizes and shows the behavioral history of users corresponding to the sales information. Effect of the Invention

[0009] According to one embodiment, it is possible to perform analysis of customer movement within a store at low cost. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment. [Diagram 2] FIG. 2 is an explanatory diagram illustrating an example of a store layout. [Diagram 3] FIG. 3 is an explanatory diagram illustrating an example of the POS data. [Figure 4] FIG. 4 is a flowchart showing an example of the base map generation process. [Diagram 5] FIG. 5 is an explanatory diagram illustrating an example of the base map. [Figure 6A] FIG. 6A is a flowchart (1) illustrating a processing example of generating a heat map in the information processing device according to the embodiment. [Figure 6B] FIG. 6B is a flowchart (2) illustrating a processing example of generating a heat map in the information processing device according to the embodiment. [Figure 7] FIG. 7 is an explanatory diagram showing an example of a receipt that appears in the POS data. [Figure 8] FIG. 8 is an explanatory diagram illustrating an example of a histogram. [Figure 9] FIG. 9 is an explanatory diagram showing an example of the generated heat map. [Figure 10] FIG. 10 is an explanatory diagram illustrating an example of a computer configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, a generating program, a generating method, and an information processing device according to the embodiments will be described with reference to the drawings. Configurations having the same functions in the embodiments are given the same reference numerals, and duplicated descriptions will be omitted. Note that the generating program, the generating method, and the information processing device described in the following embodiments are merely examples, and do not limit the embodiments. In addition, the following embodiments may be appropriately combined within a range that does not contradict each other.

[0012] Fig. 1 is a block diagram showing an example of a functional configuration of an information processing device according to an embodiment. As shown in Fig. 1, the information processing device 1 includes a communication unit 10, an input unit 20, a display unit 30, a storage unit 40, and a control unit 50. For example, a PC (Personal Computer) can be used as the information processing device 1. Based on sales information (POS data 42) of products in a store, the information processing device 1 generates visualization information such as a heat map that visualizes the behavioral history in the store of a user who purchased a product indicated by the POS data 42.

[0013] The communication unit 10 executes data communication with external devices, etc., via a network. For example, under the control of the control unit 50, the communication unit 10 acquires store information 41 related to the store, POS data 42 related to sales of products in the store, etc., from a server device, etc., which manages store data. The communication unit 10 stores the acquired store information 41 and POS data 42 in the storage unit 40.

[0014] The input unit 20 accepts operations from a user. For example, the input unit 20 accepts an instruction from a user to modify the store information 41 in accordance with a change in the layout within the store (e.g., a change in the display position of products). Based on this modification instruction, the store information 41 is modified to match the layout change.

[0015] The display unit 30 displays the processing results of the control unit 50. For example, the display unit 30 displays visualization information such as a heat map generated by the control unit 50 on a display.

[0016] The storage unit 40 has store information 41, POS data 42, base map data 43, and heat map data 44. For example, the storage unit 40 is realized by a memory or the like.

[0017] The store information 41 is information that indicates the layout of a store. For example, the store information 41 includes map (position) information of the entrance and exit for customers in the store, the aisles where product display shelves are lined up, the cash register, etc. The store information 41 also includes information that indicates the display positions of products by product category (ice cream, bread, confectionery, dessert, instant food, non-food, etc.) in the store.

[0018] Fig. 2 is an explanatory diagram for explaining an example of a store layout. Specifically, Fig. 2 shows an example of a planar layout of a store ST1 that is the subject of customer movement line analysis.

[0019] 2, the layout of the store ST1 starts from the entrance ST10, passes through aisles ST11 to ST15 where product display shelves are lined, and ends at the cash register ST16. The store information 41 includes map information showing such a layout of the store ST1.

[0020] The store information 41 also includes information on the products arranged on the shelves of each of the aisles ST11 to ST15, and the product categories CAT01 to CAT05 corresponding to the products. For example, if the product category CAT01 is ice cream bread, the store information 41 indicates that the ice cream bread is arranged on the shelves of the aisle ST11. If the product category CAT02 is confectionery, the store information 41 indicates that the confectionery is arranged on the shelves of the aisle ST12. If the product category CAT03 is dessert, the store information 41 indicates that the dessert is arranged on the shelves of the aisle ST13. If the product category CAT04 is non-food, the store information 41 indicates that the non-food is arranged on the shelves of the aisle ST14. If the product category CAT05 is instant food, the store information 41 indicates that the instant food is arranged on the shelves of the aisle ST15.

[0021] It is assumed that the information on the product categories CAT01 to CAT05 of the products arranged on the shelves of the passages ST11 to ST15 is updated by the user of the information processing device 1 at the timing of rearrangement of the products.

[0022] Returning to Fig. 1, the POS data 42 is an example of sales information indicating sales of products in the store ST1. Fig. 3 is an explanatory diagram for explaining an example of the POS data 42.

[0023] 3, the POS data 42 stores information on each item sold. Specifically, the POS data 42 has information on each item sold, such as "date," "time," "register number," "receipt number," "JAN code," "major category," "category name," "item name," "unit price," "quantity," and "sales amount."

[0024] "Date" indicates the date of the sale. "Time" indicates the time of the sale. "Cash register number" indicates the identification number of the cash register ST16 that recorded the sale. "Receipt number" indicates the identification number of the receipt that recorded the sale. For example, in the illustrated example, the six sales data items with "receipt number" "3395" indicate sales registered on a single receipt identified by that number.

[0025] "JAN code" indicates the JAN (Japanese Article Number) that identifies the product for which sales have been recorded. "Major category" indicates the major category of the product for which sales have been recorded (e.g. food, non-food, beverage, frozen, etc.). "Category name" indicates the category of the product for which sales have been recorded (vegetables, daily necessities, detergent, confectionery, etc.). "Product name" indicates the name of the product for which sales have been recorded. "Unit price" indicates the unit price of the product for which sales have been recorded. "Quantity" indicates the quantity of the product for which sales have been recorded. "Sales amount" indicates the amount of sales.

[0026] Returning to FIG. 1, the base map data 43 is information that visualizes the behavior history of users in the store ST1 for each of a plurality of purchase patterns in which the combinations of product categories CAT01 to CAT05 of purchased products are different. For example, the base map data 43 includes a heat map (base map) in which the behavior history of users is superimposed on a planar map of the store ST1 for each of a plurality of purchase patterns (bases) and the degree of density of the accumulated stay time of users is expressed by shading. In other words, the base map data 43 is an example of base visualization information.

[0027] The heat map data 44 is data related to a heat map that visualizes and shows the behavior history of a user corresponding to the POS data 42. In other words, the heat map data 44 is an example of visualized information.

[0028] Specifically, the heat map data 44 is data of a heat map generated by synthesizing a base map included in the base map data 43 based on the POS data 42 (details will be described later).

[0029] The control unit 50 includes a base map generating unit 51, a weight setting unit 52, and a heat map generating unit 53. For example, the control unit 50 is realized by a processor.

[0030] The base map generation unit 51 is a processing unit that generates a heat map (base map) that visualizes the behavioral history of users in the store ST1 for multiple purchasing patterns (bases) that have different combinations of product categories of purchased products, based on store information 41 that indicates the layout of each product category within the store.

[0031] Fig. 4 is a flowchart showing an example of a base map generation process. As shown in Fig. 4, the base map generation unit 51 acquires store information 41 related to the store ST1. As a result, the base map generation unit 51 acquires the position of the cash register ST16 in the store ST1, the positions of the aisles ST11-ST15 (display shelves), and the products and product categories CAT01-CAT05 arranged on the display shelves in the aisles ST11-ST15. Next, the base map generation unit 51 acquires the total number (ncat) of the product categories CAT01-CAT05 from the store information 41 (S1).

[0032] Next, the base map generation unit 51 obtains the total number of base maps (nd=2^ncat-1) based on the total number (ncat) of product categories CAT01 to CAT05 (S2). For example, if the total number (ncat) of product categories CAT01 to CAT05 is 5, the total number of base maps is nd=2^5-1=31. That is, in S2, the base map generation unit 51 obtains the total number (nd) of multiple purchasing patterns with different combinations of product categories.

[0033] Next, the base map generating unit 51 creates nd types of virtual POS corresponding to a plurality of purchasing patterns with different combinations of product categories (S3).

[0034] Specifically, the base map generating unit 51 creates virtual POSs corresponding to purchasing patterns starting from a combination of stopping at one product category (purchasing a product in the product category) to a final combination of stopping at ncat product categories.

[0035] For example, the base map generating unit 51 first creates ncat POSs that visit one product category (purchase a product of the product category) among the product categories CAT01 to CAT05 (the visit probability is 1). Similarly, the base map generating unit 51 creates ncat POSs that visit two product categories among the product categories CAT01 to CAT05. ncat Then, the base map generating unit 51 creates POSs that visit k product categories among the product categories CAT01 to CAT05.ncat C k create C (the stop - by probability is 1 / k for each). Finally, the base map generation unit 51 creates POSs that stop by ncat product categories out of product categories CAT01 to CAT05 ncat C ncat create C (the stop - by probability is 1 / ncat for each).

[0036] Next, the base map generation unit 51 initializes the process number (id) to id = 0 (S4), and determines whether id < nd (S5).

[0037] If id < nd (S5: Yes), the base map generation unit 51 increments id (S6). Next, the base map generation unit 51 reads the id - th virtual POS and executes an agent simulation based on the virtual POS (S7). Specifically, the base map generation unit 51 executes a known agent simulation on the premise of passing through the product category of the product that stops by (purchases) at the virtual POS.

[0038] Next, the base map generation unit 51 obtains the id - th base map based on the result of the agent simulation in S7 (S8), and returns the process to S5.

[0039] If id < nd is not satisfied (S5: No), the base map generation unit 51 obtains nd base maps by repeating S5 to S8 (S9). Next, the base map generation unit 51 stores the obtained base maps in the base map data 43 together with the identification information (id) indicating the combination of the product categories where the base maps stopped by, and ends the process.

[0040] Fig. 5 is an explanatory diagram explaining an example of a base map. As shown in Fig. 5, the base map generating unit 51 generates base maps BM1, BM2, BM3 ... BMn by agent simulation for a plurality of purchasing patterns with different combinations of product categories CAT01 to CAT05. Next, the base map generating unit 51 assigns identification information indicating the purchasing pattern (combination of product categories) to each of the generated base maps BM1, BM2, BM3 ... BMn, and stores them in the base map data 43.

[0041] The generation of the base map data 43 by the base map generating unit 51 described above may be performed once when updating the product layout (product categories corresponding to display shelves) in the store information 41. In other words, the information processing device 1 can reuse the base map data 43 once generated unless the product layout in the store ST1 is updated.

[0042] Returning to FIG. 1, the weight setting unit 52 is a processing unit that sets a weight for each combination of product categories of purchased products based on the POS data 42.

[0043] The heat map generation unit 53 is a processing unit that synthesizes the base maps BM1, BM2, BM3, ... BMn contained in the base map data 43 based on the weights set by the weight setting unit 52, and generates heat map data 44 that visualizes the behavioral history of the user corresponding to the POS data 42.

[0044] Here, a detailed description will be given of the processing of the weight setting unit 52 and the heat map generating unit 53. Figures 6A and 6B are flowcharts showing an example of processing for generating a heat map in the information processing device 1 according to the embodiment.

[0045] 6A and 6B, when the process starts, the weight setting unit 52 reads the POS data 42 (S10). When generating a heat map for a specific time period (morning (6:00 to 10:00), afternoon (10:00 to 18:00), night (18:00 to 22:00)), the weight setting unit 52 reads the POS data 42 for the corresponding time period.

[0046] For example, when generating a heat map for the daytime (10:00-18:00), the sales data for "receipt numbers" of "3395," "3983," and "4011" are loaded in the example of Figure 3. Next, when generating a heat map for the evening (18:00-22:00), the sales data for "receipt number" of "4433" is loaded in the example of Figure 3.

[0047] Here, the weight setting unit 52 sets the number of receipts included in the read POS data 42 as npos for the read POS data 42. For example, if POS data 42 corresponding to the daytime time period (10:00-18:00) is read, there are three "receipt numbers", "3395", "3983", and "4011", so npos=3 is set. The weight setting unit 52 also sets the number of types of purchased items (number of product categories) listed on each receipt, in other words, the number of times the customer stopped, as nstop. The weight setting unit 52 also sets the product category associated with each purchased item as icat.

[0048] Next, the weight setting unit 52 initializes weights (histograms) for each combination of product categories of purchased products (S11). Specifically, the weight setting unit 52 sets the above histogram as hist(id) and a function that can be referenced by hist(1), hist(2), ..., hist(nd). As described above, id is identification information indicating a combination of product categories, and nd is the number of types of combinations. The weight setting unit 52 initializes this hist(id) as hist(1:nd)=0.

[0049] Next, the weight setting unit 52 determines whether npos>0 (S12). In the initial processing when the POS is read for the very first time, the number of receipts is npos, and in subsequent processing (S14), the value of npos is decremented by one each time a receipt is processed. Therefore, by continuing processing as long as the value of npos is positive, all receipts can be processed. If npos>0 is not true (S12: No), all receipts have been processed (weighted), and the weight setting unit 52 proceeds to S17.

[0050] If npos>0 (S12: Yes), the weight setting unit 52 creates a list (list array) of categories visited for each receipt with no duplicates. This list array is an integer array with a size of ncat. Here, the weight setting unit 52 sets list(1:ncat)=0, and initializes all values ​​in the list array to zero (S13). Next, the weight setting unit 52 decrements the value of npos by 1 (S14) and performs list creation processing (S15).

[0051] In the list creation process, the weight setting unit 52 determines whether the number of times the customer stopped, nstop, that can be read from each receipt is nstop>0 (S20). In the first process, the number of times the customer stopped is nstop, and in subsequent processes (S21), the value of nstop is decremented by one each time an item is processed. Therefore, by continuing the process as long as the value of nstop is positive, it is possible to process all items on the receipt. If nstop>0 is not true (S20: No), the weight setting unit 52 proceeds to S16, as this means that processing of all items on the receipt has been completed.

[0052] If nstop>0 (S20: Yes), the weight setting unit 52 identifies the category icat in which the purchase event (the purchased product listed on the receipt) occurred (S22).

[0053] Fig. 7 is an explanatory diagram showing an example of a receipt that appears in POS data. As shown in Fig. 7, receipts RE1, RE2, and RE3 have been read from the POS data 42. The weight setting unit 52 identifies the category icat in which a purchase event (a purchased item listed on the receipt) occurred for each of the receipts RE1, RE2, and RE3. For example, cat02, cat02, cat02, and cat04 are identified from receipt RE2.

[0054] Next, the weight setting unit 52 determines whether or not list(icat)=0 (S23), and if list(icat)=0 (S23: Yes), it sets list(icat)=1 (S24) and returns the process to S20. If list(icat)=0 is not (S23: No), the weight setting unit 52 returns the process to S20 without performing S24.

[0055] This allows the weight setting unit 52 to set a flag of list(icat) = 1 only for product categories for which shopping was performed. In other words, the weight setting unit 52 obtains a list (list array) of product categories for which shopping was performed on each receipt of the POS data 42.

[0056] After creating such a list, the weight setting unit 52 counts the weights (histograms) for each combination of product categories of purchased products based on the list (S16).

[0057] Specifically, the weight setting unit 52 performs the following addition. nsb=sum_{1≦id≦nd}list(id)*2^(id-1)

[0058] For example, if list(1) = 1, list(2) = 1, list(3) = 1, list(4) = 0, and list(5) = 1, nsb will have the following values: nsb=1*2^0+1*2^1+1*2^2+0*2^(3)+1*2^4 =1+2+4+0+16 =23

[0059] The numerical value nsb thus obtained takes all integer values ​​from 1 to nd, one by one, and the weight setting unit 52 can then use this value to search for id.

[0060] More specifically, the weight setting unit 52 initializes nsb=0; icat=0 (S30).

[0061] Next, the weight setting unit 52 judges whether or not list(icat+1)=0 (S31). If list(icat+1)=0 (S31: Yes), the weight setting unit 52 sets pbs=0 (S32) and proceeds to the process of S34. If list(icat+1)=0 is not (S31: No), the weight setting unit 52 sets pbs=2^icat (S33) and proceeds to the process of S34. In S34, the weight setting unit 52 sets nsb+=psb;icat++. In this way, the weight setting unit 52 adds up nsb.

[0062] Next, the weight setting unit 52 determines whether or not icat=ncat (S35), and if the determination is negative (No), the process returns to S31.

[0063] If the determination in S35 is positive (Yes), the weight setting unit 52 refers to a correspondence table between nsb and id, and determines the combination id of the product categories from the value of nsb (S36). Next, since the combination id of the product categories has been determined, the weight setting unit 52 adds the count to the histogram as hist(id)++ (S37), and returns the process to S12.

[0064] Fig. 8 is an explanatory diagram showing an example of a histogram. By counting as hist(id)++, a histogram G1 can be obtained for each combination {1}, {2} ... {1, 2, 3, 4} of product categories (1 to 4), as shown in Fig. 8.

[0065] In S17 after all receipts have been processed (weighted), the heat map generator 53 creates a heat map by combining the base maps BM1, BM2, . . . BMn contained in the base map data 43 based on the weights set by the weight setting unit 52.

[0066] Specifically, the heat map generation unit 53 acquires a histogram hist(:) (S40). Next, the heat map generation unit 53 multiplies the base maps BM1, BM2...BMn prepared for each combination id of product categories by hist(id) and adds them together (S41). Next, the heat map generation unit 53 outputs the heat map synthesized by the addition in S41 as heat map data 44 (S42), and ends the process.

[0067] Fig. 9 is an explanatory diagram showing an example of a generated heat map. In Fig. 9, heat map HM1 is a heat map generated by the information processing device 1 based on the POS data 42. Heat map HM2 is a heat map obtained by measuring the actual movements of customers when the POS data 42 was obtained, that is, a heat map based on actual measured values.

[0068] As shown in FIG. 9, the heat map HM1 generated by the information processing device 1 is almost the same as the heat map HM2 based on actual measured values, and it is clear that a highly accurate result has been obtained.

[0069] This can be said to be because the heat map output is less affected by interactions between agents, and the superposition of the basis maps BM1, BM2, ..., BMn is effective.

[0070] For example, interactions among customers in store ST1 include waiting at the register, waiting, congestion, avoiding passing each other, etc. However, in reality, cases where such interactions occur are extremely rare. As an example, waiting and congestion occur only for a very limited period of time during business hours, and interactions during such a short period of time can be fully ignored. Therefore, the heat map HM1 generated by combining the basis maps BM1, BM2, ..., BMn with weights based on the POS data 42 accurately represents the flow of people.

[0071] As described above, the information processing device 1 sets a weight for each combination of product categories of purchased products based on the POS data 42. The information processing device 1 synthesizes, based on the set weights, base maps BM1, BM2...BMn that visualize and show the behavior history of users in the store ST1 for multiple purchase patterns with different combinations of product categories of purchased products, which are stored in the storage unit 40. By synthesizing the base maps BM1, BM2...BMn, the information processing device 1 generates a heat map HM1 that visualizes and shows the behavior history of users corresponding to the POS data 42.

[0072] As a result, the information processing device 1 can obtain a heat map HM1 that visualizes and shows the behavior history of users corresponding to the POS data 42, without measuring the movements of users within the store ST1 or reproducing the movements of users by agent simulation. Therefore, the information processing device 1 can perform the analysis of the movement lines of users within the store ST1 at low cost.

[0073] Furthermore, the information processing device 1 generates basis maps BM1, BM1, BM2...BMn by simulating the movement of agents corresponding to users in the store for each of a plurality of purchasing patterns, based on store information 41 indicating the layout of each product category in the store. This enables the information processing device 1 to easily obtain basis maps BM1, BM1, BM2...BMn for each of a plurality of purchasing patterns corresponding to the layout of each product category in the store, without having to measure the movement of users every time the product layout is changed.

[0074] Furthermore, the information processing device 1 generates a heat map HM1 for each time period by combining the basis maps BM1, BM1, BM2...BMn based on the weights for each time period set based on the POS data 42 for each time period. This allows the information processing device 1 to easily obtain a heat map HM1 corresponding to the POS data 42 for each time period without measuring the movements of users in the store ST1 or reproducing the movements of users by agent simulation for each time period.

[0075] Note that each component of each device shown in the figure does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0076] Furthermore, the various processing functions of the basis map generating unit 51, the weight setting unit 52 and the heat map generating unit 53 performed by the control unit 50 of the information processing device 1 may be executed in whole or in part on a CPU (or a microcomputer such as an MPU or an MCU (Micro Controller Unit)). Needless to say, the various processing functions may be executed in whole or in part on a program analyzed and executed by the CPU (or a microcomputer such as an MPU or an MCU), or on hardware using wired logic. The various processing functions performed by the information processing device 1 may be executed by multiple computers working together using cloud computing.

[0077] The various processes described in the above embodiment can be realized by executing a program prepared in advance on a computer. Therefore, an example of a computer configuration (hardware) that executes a program having the same functions as those in the above embodiment will be described below. Figure 10 is an explanatory diagram for explaining an example of a computer configuration.

[0078] 10, computer 200 has CPU 201 for executing various arithmetic processes, input device 202 for receiving data input, monitor 203, and speaker 204. Computer 200 also has medium reading device 205 for reading programs and the like from a storage medium, interface device 206 for connecting with various devices, and communication device 207 for connecting to external devices for wired or wireless communication. Computer 200 also has RAM 208 for temporarily storing various information, and hard disk device 209. Each unit (201 to 209) in computer 200 is connected to bus 210.

[0079] The hard disk drive 209 stores a program 211 for executing various processes in the functional configuration (e.g., the base map generating unit 51, the weight setting unit 52, and the heat map generating unit 53) described in the above embodiment. The hard disk drive 209 also stores various data 212 referenced by the program 211. The input device 202, for example, accepts input of operation information from an operator. The monitor 203, for example, displays various screens operated by the operator. The interface device 206 is connected to, for example, a printing device. The communication device 207 is connected to a communication network such as a LAN (Local Area Network), and exchanges various information with external devices via the communication network.

[0080] The CPU 201 reads out the program 211 stored in the hard disk drive 209, expands it in the RAM 208, and executes it to perform various processes related to the above-mentioned functional configuration (for example, the basis map generating unit 51, the weight setting unit 52, and the heat map generating unit 53). The program 211 does not have to be stored in the hard disk drive 209. For example, the program 211 stored in a storage medium readable by the computer 200 may be read out and executed. The storage medium readable by the computer 200 corresponds to, for example, a portable storage medium such as a CD-ROM or a DVD disk, a USB (Universal Serial Bus) memory, a semiconductor memory such as a flash memory, a hard disk drive, etc. Also, the program 211 may be stored in a device connected to a public line, the Internet, a LAN, etc., and the computer 200 may read out and execute the program 211 from the device.

[0081] Regarding the above embodiment, the following supplementary notes are further disclosed.

[0082] (Appendix 1) Based on the sales information of products, weights are set for each combination of product categories of purchased products, synthesizing, based on the set weights, basis visualization information showing a visualization of the behavioral history of the user in the store for each of a plurality of purchase patterns having different combinations of product categories of purchased products, which is stored in a storage unit, to generate visualization information showing a visualization of the behavioral history of the user corresponding to the sales information; A generating program that causes a computer to execute a process.

[0083] (Note 2) The computer is further caused to execute a process of simulating movement of an agent corresponding to a user in the store for each of the plurality of purchase patterns based on store information indicating a layout of the product categories in the store, and generating the base visualization information. 2. The generating program according to claim 1 .

[0084] (Additional Note 3) The process of generating the visualization information includes synthesizing the base visualization information based on the weight for each time period set based on the sales information for each time period, and generating the visualization information for each time period. 2. The generating program according to claim 1 .

[0085] (Appendix 4) Based on the sales information of the products, weights are set for each combination of product categories of purchased products, synthesizing, based on the set weights, basis visualization information showing a visualization of the behavioral history of the user in the store for each of a plurality of purchase patterns having different combinations of product categories of purchased products, which is stored in a storage unit, to generate visualization information showing a visualization of the behavioral history of the user corresponding to the sales information; A generating method characterized in that the processing is executed by a computer.

[0086] (Additional Note 5) The computer further executes a process of simulating movement of an agent corresponding to a user in the store for each of the plurality of purchase patterns based on store information indicating a layout of the product categories in the store, and generating the base visualization information. 5. The method of generating a signal according to claim 4.

[0087] (Additional Note 6) The process of generating the visualization information includes synthesizing the base visualization information based on the weight for each time period set based on the sales information for each time period, and generating the visualization information for each time period. 5. The method of generating a signal according to claim 4.

[0088] (Appendix 7) Based on the sales information of the products, weights are set for each combination of product categories of purchased products, synthesizing, based on the set weights, basis visualization information showing a visualization of the behavioral history of the user in the store for each of a plurality of purchase patterns having different combinations of product categories of purchased products, which is stored in a storage unit, to generate visualization information showing a visualization of the behavioral history of the user corresponding to the sales information; 1. An information processing device comprising: a control unit that executes processing.

[0089] (Additional Note 8) The control unit further executes a process of simulating a movement of an agent corresponding to a user in the store for each of the plurality of purchase patterns based on store information indicating a layout of the product categories in the store, and generating the base visualization information. 8. The information processing device according to claim 7,

[0090] (Additional Note 9) The process of generating the visualization information includes synthesizing the base visualization information based on the weight for each time period set based on the sales information for each time period, and generating the visualization information for each time period. 8. The information processing device according to claim 7, [Explanation of symbols]

[0091] 1...Information processing device 10. Communications Department 20...Input section 30…Display section 40...Storage section 41…Store information 42…POS data 43...Base map data 44…Heat map data 50...Control unit 51...Base map generator 52...Weight setting section 53…Heat map generation section 200…Computer 201...CPU 202...Input device 203…Monitor 204…Speaker 205... Media reader 206...Interface device 207...Communication equipment 208…RAM 209...Hard disk drive 210…Bus 211…Program 212...Various data BM1~BMn...Basal map CAT01~CAT05...Product Category G1…Histogram HM1, HM2…Heatmap RE1~RE3...Receipt ST1…Store ST10…Entrance / Exit ST11~ST15…passageway ST16…Register

Claims

1. Based on the sales information of the products, weights are set for each combination of product categories of purchased products, generating visualization information that visualizes and indicates the behavioral history of the user in the store for each of a plurality of purchase patterns, each of which has a different combination of product categories of purchased products, based on the weights that have been set, and that corresponds to the sales information; A generating program that causes a computer to execute a process.

2. and further causing the computer to execute a process of simulating movement of an agent corresponding to a user in the store for each of the plurality of purchase patterns based on store information indicating an arrangement of the product categories in the store, thereby generating the base visualization information.

2. The generating program according to claim 1 .

3. The process of generating the visualization information includes synthesizing the base visualization information based on the weight for each time period set based on the sales information for each time period, and generating the visualization information for each time period.

2. The generating program according to claim 1 .

4. Based on the sales information of the products, weights are set for each combination of product categories of purchased products, generating visualization information that visualizes and indicates the behavioral history of the user in the store for each of a plurality of purchase patterns, each of which has a different combination of product categories of purchased products, based on the weights that have been set, and that corresponds to the sales information; A generating method characterized in that the processing is executed by a computer.

5. Based on the sales information of the products, weights are set for each combination of product categories of purchased products, generating visualization information that visualizes and indicates the behavioral history of the user in the store for each of a plurality of purchase patterns, each of which has a different combination of product categories of purchased products, based on the weights that have been set, and that corresponds to the sales information; 1. An information processing device comprising: a control unit that executes processing.

Images