JP2016207059A - Behavior analysis system and behavior analysis method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide useful information for examining measures for store improvement.SOLUTION: This behavior analysis system has a behavior visualization unit that can access traffic line information that includes a history of human movements measured by a position measurement device, transaction information that includes information on settlements of commodity transactions, passage area information that includes a condition for determining stoppage in a prescribed area, and shelving allocation information in which commodities displayed in each compartment defined for a store shelf are recorded. The behavior visualization unit analyzes the traffic line information referring to the passage area information, determines stoppage for each area in the store, totalizes the number or the amount of purchased commodities for each compartment of the store shelf referring to the transaction information and the shelving allocation information, and outputs screen data for schematically displaying the number of stoppages per area and the totalized number of amount of purchased commodities on top of a store layout.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a behavior analysis system that analyzes flow line information and visualizes human behavior.

  In recent years, with the price reduction of various sensors and the evolution of networks, information on customers traveling around the store has been installed in order to take measures to increase store sales and reduce costs by installing cameras and position measurement devices in the store. Analyzing.

  2. Description of the Related Art Conventionally, a method for tracking a person's movement using a laser beam emitted from a range sensor installed in a store is known. Thereby, it is possible to obtain the movement (flow line) of the person hitting the laser beam. On the other hand, in a store, customer transaction information at a cash register or the like is stored in a database. By associating the above-described flow line information and transaction information, it is possible to obtain information on what kind of customers have made a round trip in the store and what kind of products have been purchased. Furthermore, there is known a technique for estimating an attribute (age and gender) of a customer using a face image of the customer who passed in front of the camera using a camera or the like installed in the store. By associating the attribute information with the flow line information, it is possible to analyze how a customer with which attribute has visited the store, what product has been purchased, what has not been purchased, or the like.

  As a background art of this technique, there is JP 2009-134688 A (Patent Document 1). Patent Document 1 discloses a technique for calculating a stop state in a store from flow line information, creating a stop state heat map, and displaying the heat map on a display device.

JP 2009-134688 A

"Pedestrian tracking using multiple laser range scanners and its reliability evaluation", Katsuyuki Nakamura et al., IEICE Transactions D-II VOL. J88-D-II, pp1143-1152, July 1, 2005

  However, the flow line information has a large amount of data, and it is difficult to obtain an indication of store operation from the individual flow line information. Further, in the technique described in Patent Document 1, store sales information does not correspond to a heat map, and it is impossible to obtain suggestions such as improvement points of a store layout, for example, only by looking at the screen.

  The present invention has been made in view of such circumstances, and examines measures for store improvement by combining information obtained by processing flow line information with sales information and the like and displaying them on a screen. An object is to provide an action visualization device that provides useful information.

  A typical example of the invention disclosed in the present application is as follows. That is, a behavior analysis system comprising a computer having a processor and a memory, flow line information including a history of movement of a person measured by a position measuring device, and transaction information including information on settlement of a product transaction The passage area information including a condition for determining a stop in a predetermined area and the shelf allocation information in which products displayed for each section defined in the product shelf are recorded, and the flow line information A behavior visualization unit that generates information visualizing human behavior from the behavior visualization unit, analyzing the flow line information with reference to the passage area information, and determining a stop for each area in the store Then, referring to the transaction information and the shelf allocation information, the number of purchases or purchase price of the product is totaled for each section of the product shelf, and the number of stops for each area and the total number of purchases or the purchase price And it outputs the screen data to graphically superimposed and displayed on the store layout.

  According to a typical embodiment of the present invention, information obtained from flow line information and transaction information can be viewed in association with each other. Problems, configurations, and effects other than those described above will become apparent from the description of the following embodiments.

It is a figure which shows the logical structure of the action visualization apparatus of this embodiment. It is a block diagram which shows the physical structure of the action visualization apparatus of this embodiment. It is a figure which shows the structural example of the flow line information of this embodiment. It is a figure which shows the structural example of the store layout information of this embodiment. It is a figure which shows the structural example of the transaction information of this embodiment. It is a figure which shows the structural example of the passage area information of this embodiment. It is a figure which shows the structural example of the shelf allocation information of this embodiment. It is a figure which shows the structural example of the inventory information of this embodiment. It is a figure which shows an example of the screen which the action visualization apparatus of 1st Example produces | generates. It is a flowchart of the screen generation process of 1st Example. It is a figure which shows an example of the screen which the action visualization apparatus of 2nd Example produces | generates. It is a flowchart of the screen generation process of 2nd Example.

  FIG. 1 is a diagram illustrating a logical configuration of the behavior visualization apparatus 101 according to the embodiment of this invention.

  The behavior visualization device 101 includes a display device 102, a behavior visualization unit 103, an instruction device 104, a network connection unit 105, and a storage unit 106.

  The storage unit 106 stores flow line information 107, store layout information 108, transaction information 109, passage area information 110, shelf allocation information 111, inventory information 112, and the like.

  The behavior visualization apparatus 101 according to the present embodiment can be configured by a computer such as a smartphone, a tablet terminal, a business terminal, a PC, or a virtual machine. Further, FIG. 1 shows the configuration of the behavior visualization device 101, but each component may be mounted on a different behavior visualization device 101. For example, in the case of a tablet terminal, necessary information may be received via the network connection unit 105 and displayed on the display device 102 (for example, the screen of the tablet terminal).

  FIG. 2 is a block diagram illustrating a physical configuration of the behavior visualization apparatus 101.

  The behavior visualization device 101 of this embodiment is configured by a computer having a processor (CPU) 1, a memory 2, an auxiliary storage device 3, and a communication interface 4.

  The processor 1 executes a program stored in the memory 2. The memory 2 includes a ROM that is a nonvolatile storage element and a RAM that is a volatile storage element. The ROM stores an immutable program (for example, BIOS). The RAM is a high-speed and volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 1 and data used when the program is executed.

  The auxiliary storage device 3 constitutes the storage unit 106 and is, for example, a large-capacity and nonvolatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The program executed by the processor 1 and execution of the program Stores data used at times. That is, the program is read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1.

  The communication interface 4 is a network interface device that constitutes the network connection unit 105 and controls communication with other devices according to a predetermined protocol.

  The behavior visualization apparatus 101 includes an input interface 5 and an output interface 8. The input interface 5 constitutes the pointing device 104 and is an interface that receives input from an operator. Specifically, the input interface 5 is a mouse, a keyboard, a touch panel, a pen, an acceleration sensor, a microphone, or the like. For example, when the behavior visualization device 101 is a smartphone, the acceleration sensor can input information by vibrating the smartphone in a specific pattern. The microphone can input information according to the voice of the user. The output interface 8 is a display device 9 or a printer, and is an interface that outputs the execution result of the program in a format that can be visually recognized by the operator.

  A program executed by the processor 1 is provided to the behavior visualization device 101 via a removable medium (CD-ROM, flash memory, etc.) or a network, and is stored in the nonvolatile auxiliary storage device 3 which is a non-temporary storage medium. . For this reason, the behavior visualization apparatus 101 may have an interface for reading data from a removable medium.

  The behavior visualization apparatus 101 is a computer system configured on a single physical computer or a plurality of logically or physically configured computers, and operates in a separate thread on the same computer. It may be possible to operate on a virtual machine constructed on a plurality of physical computer resources. Moreover, each function part of the behavior visualization apparatus 101 may be implement | achieved on a different computer.

<Configuration example of flow line information>
FIG. 3 is a diagram illustrating a configuration example of the flow line information 107.

  The flow line information 107 shown in FIG. 3 can be obtained by using the technique disclosed in Non-Patent Document 1, for example. In the example shown in FIG. 3, the flow line information 107 includes a customer ID 201 for uniquely identifying a customer, a time 202 when the customer's position is measured, and a two-dimensional position (x coordinate 203 in the customer's store). , Y-coordinates 204) are stored, for example, in time series.

  Therefore, by selecting the data of the same customer ID 201 from the flow line information 107 and arranging them in time series, a series of information relating to which position in the store at which time one customer existed, that is, the flow line Information is obtained.

  Although illustration is omitted, the flow line information 107 may include customer attributes (for example, gender, age). For example, the attribute of a customer can obtain a gender and age by analyzing a face image taken at the entrance of a store. Alternatively, the gender and age registered on the store membership card can be used.

<Configuration example of store layout information>
FIG. 4 is a diagram illustrating a configuration example of the store layout information 108.

  The store layout information 108 is information in which locations such as the store entrance / exit 302, the passage 301, the product shelf 304, and the cash register 303 are recorded, and is in the form of an image file, for example.

<Configuration example of transaction information>
FIG. 5 is a diagram illustrating a configuration example of the transaction information 109.

  The transaction information 109 records the content of a transaction created when a customer purchases a product at a cash register or the like. The transaction information 109 includes a transaction date and time 401, a transaction number 402, a cash register number 403, and a total amount 404 for each record. One record includes data of one or more purchased products, that is, product ID 405, product name 406, product classification ID 407, product classification name 408, quantity 409, and unit price 410.

  The transaction date 401 records the date and time when the transaction was made at a cash register or the like. In the illustrated example, it is 11:22 on February 10, 2015, and the time is recorded in units of minutes. This is because, depending on the cash register, the transaction date and time may be recorded only up to the minute unit, so the transaction information may be recorded in time according to the cash register recording unit. Note that the time recording unit may be not a minute but a time of seconds or less.

  The transaction number 402 is a number for distinguishing a plurality of transactions, and is 1234 in the illustrated example. For example, the transaction number 402 may be incremented by 1 for each transaction starting from 1, but the transaction number 402 may be determined by other rules.

  The cash register number 403 is an identifier for identifying the cash register. In the illustrated example, it is 1.

  The total amount 404 is the total price of purchased products.

  The product ID 405 is an identifier for identifying the purchased product. In the illustrated example, P0001, P0002, and P0003 are recorded for each purchased product.

  The product name 406 is the name of the purchased product. In the illustrated example, rice balls A, tea, and rice balls B are used.

  The product classification ID 407 is an identifier for classifying products according to the characteristics of the products. In the illustrated example, “rice ball A” and “rice ball B” can be classified as “rice cooked rice”, and therefore both have the same product classification ID 407 “C00A”.

  The product category name 408 is the name of the product category. In the illustrated example, it is cooked rice and beverages.

  The quantity 409 is the number of items purchased. The unit price 410 is a price per product.

  Although not shown, the transaction information 109 may include a customer membership number. For example, a customer who presents a membership card (for example, a point card) at a cash register can know its attributes (for example, gender, age, place of residence).

<Configuration example of passage area information>
FIG. 6 is a diagram illustrating a configuration example of the passage area information 110.

  The passage area information 110 includes passage location information and information for determining whether the vehicle has stopped in the passage, and includes a passage area name 501, a passage area area 502, and a stop determination condition 503.

  The passage area name 501 is a name of the passage area. The passage area area 502 is an area for determining stoppage. The stop determination condition 503 is a condition for determining whether the flow line existing in the passage area 502 is stopped.

  A specific description will be given by taking the data in the first row of FIG. 6 as an example. The passage area name 501 is “area 1”, and the passage area area 502 is a rectangular area (X1, Y1) − (X2, Y2) indicating “area 1”. The passage area region 502 is not rectangular and may have any shape. Also, a stop determination condition 503 for determining a stop is defined as “stay in area 1 for 5 seconds or longer”.

  The passage area information 110 may include a condition for determining a stop at the lowest speed in the area in addition to the illustrated information. Moreover, you may use the information which the sensor provided in the merchandise shelf acquired together, and that the customer is facing the shelf may be used for the determination criterion of a stop.

<Configuration example of shelf allocation information>
FIG. 7 is a diagram illustrating a configuration example of the shelf allocation information 111.

  The shelf allocation information 111 is information for associating the position of the section on the product shelf in the store with the product classification ID 407 of the product displayed in each product section, and stores the product section name 601, the product classification 602, and the product section area 603. Including.

  The product section name 601 is the name of the product section. The product category 602 is a product category ID 407 of a product displayed in the product section, and may include a plurality of product category IDs 407. The product division area 603 indicates the position of the product division in the store. Note that the product partition area 603 is not rectangular and may have any shape.

<Example configuration of inventory information>
FIG. 8 is a diagram illustrating a configuration example of the inventory information 112.

  The stock information 112 is information in which the number of products in stock is recorded at each time for each product, and includes a product ID 405, a date 1001, and a stock quantity by time 1002.

  A date 1001 is a date when the inventory quantity is recorded. The stock quantity by time 1002 indicates the stock quantity at each time of the product specified by the product ID 405. For example, the stock of the product whose product ID 405 is “P0001” is 1 at 0 and 5 at 1 o'clock. The increase in inventory from 1 to 5 indicates that the product has been delivered from 0 to 1 and the inventory has increased.

<First embodiment>
The first embodiment of the present invention will be described below.

<Description of Operation of Behavior Visualization Device 101>
The user starts processing of the behavior visualization unit 103 from an application, a web browser, or the like.

  The process of the behavior visualization unit 103 will be described using the flowchart of FIG. The display of the screen described in this specification is an example, and is not limited to the illustrated one. You may display so that it may overlap with the existing screen as needed. For example, since a smartphone has a low screen resolution, it may be difficult to display a plurality of screens side by side. For this reason, as described above, a plurality of screens may be displayed so as to overlap each other.

  FIG. 9 is a diagram illustrating an example of a screen generated by the behavior visualization unit 103.

  The screen example shown in FIG. 9 includes a gender selection area 701, an age selection area 702, a stay time selection area 703, a store layout information display area 704, a male / female ratio graph 709, average statistical information 710, and a stopped person / purchase rate graph 711. . In the store layout information display area 704, a heat map 705 using the total quantity or total amount, a heat map 706 using the number of people staying, an alert icon 707, and alert contents 708 are displayed. It should be noted that at least one of the gender ratio graph 709, the average statistical information 710, and the number of stopped persons / purchase rate graph 711 may be displayed even if not all are displayed.

  The gender selection area 701 is an area for selecting gender, that is, male or female. According to the selection result of the gender selection area 701, only information that matches the specified gender in the flow line information 107 is filtered. In addition, as an index for selecting a gender, options may be identified by an image or the like instead of characters such as “male” and “female”.

  The age selection area 702 is an area for selecting an age range, that is, “10s”, “20s”, “30s”, “40s”, “50s”, and “60 or more”. According to the selection result of the age selection area 702, only information that matches the age of the specified range in the flow line information 107 is filtered. In addition, as an index for selecting the age range, options may be identified by an image or the like instead of characters such as “teens”. Further, the age group may be arbitrarily changed other than that shown in the figure. For example, “under 20 years old”, “20 years old and under 40 years old”, and “40 years old and over” may be used.

  The stay time selection area 703 is an area for selecting a stay time in the store, that is, a customer who stayed in the store “less than 1 minute”, “less than 5 minutes”, and “5 minutes or more”. Based on the selection result of the stay time selection area 703, only information that matches the stay time in the specified range in the flow line information 107 is filtered. In addition, as an index for selecting the stay time, the option may be identified by an image or the like instead of characters such as “less than 1 minute”. Further, the stay time category may be arbitrarily changed from those shown in the figure. For example, “less than 3 minutes” or “more than 3 minutes” may be used.

  FIG. 10 is a flowchart of processing in which the behavior visualization unit 103 generates the screen in FIG. Note that the user can select the gender selection area 701, the age selection area 702, the stay time selection area 703, the alert icon 707, etc. at any time, and executes processing from an appropriate location at the selected timing.

  In step S <b> 901, the number of customers who have stopped is calculated for each passage area area 502 using the passage area information 110 and the flow line information 107, and displayed superimposed on the store layout information display area 704. At this time, customers who have stopped in accordance with the conditions set in the gender selection area 701, the age selection area 702, and the stay time selection area 703 are filtered, and only those who meet the conditions are displayed on the heat map 706. Specifically, the gender and age are not shown, but are specified in the gender and / or age (or age) included in the flow line information 107 and the gender and / or age selection area 702 specified in the gender selection area 701. Compare the generated ages and extract only the matching lines. As for the stay time, data for each customer ID 201 is extracted from the flow line information 107, and for each customer ID 201, the difference between the latest time and the earliest time of data appears as the stay time selection area 703. Compared with the staying time specified in step (1), only the data of the customer ID 201 that matches the conditions is extracted.

  In step S902, using the transaction information 109 and the shelf allocation information 111, the total quantity and the total amount of the products displayed in the product section area 603 are calculated for each product section area 603, and the store layout information It is displayed superimposed on the display area 704. The display may be both the total quantity and the total amount, or one of them. At this time, customers are filtered according to the conditions set in the gender selection area 701, the age selection area 702, and the stay time selection area 703, and only those who meet the conditions are displayed on the heat map 705. The filtering method may be the same as the processing described in step S901.

  In step S903, a heat map is created based on the information calculated in steps S901 and S902. In step S903, a heat map 705 using the total quantity or total amount and a heat map 706 using the number of people staying are created. As shown in the figure, the two created heat maps may be displayed in a superimposed manner, or may be switched and displayed.

  Hereinafter, an example of displaying a heat map of the number of people who are stopped will be described.

  For each aisle area 502, the display mode (for example, color, brightness, pattern, etc.) is changed according to the number of parked people. For example, the larger the number of stops, the blacker the color, and the smaller the number, the closer to white. Various colors may be used depending on a predetermined gradation.

  The heat map for each product partition area 603 can also be generated in the same manner as described above using the total quantity or the total amount.

In step S904, an index is calculated from the flow line information 107 and the transaction information 109 for each product segment area 603, and when the calculated index exceeds a predetermined threshold, the number of parked people is large and the number of product purchasers is small. Judgment is made and an alert for alerting the operator is displayed. Examples of indicators are shown below.
Purchase rate =% of the number of people who purchased the product out of the number of people in the stop area 502 set in the passage in front of the product

  For example, the alert displays an alert icon 707 superimposed on a position on the store layout information display area 704 corresponding to the display position of the product exceeding the threshold.

  Step S905 is executed when the user selects the alert icon 707, and displays the alert content 708. The alert content 708 may display the product for which the alert is displayed, the number of people in the passage area in front of the product, and the purchase rate of the product.

  In step S906, a gender ratio graph 709 is displayed. The gender ratio graph 709 is a graph showing the gender composition ratio of customers who have purchased products for which alerts are to be displayed based on the transaction information 109. In FIG. 9, it is represented by a pie chart, but it may be displayed by a graph or a numerical value in another format. At this time, customers are filtered according to the conditions set in the gender selection area 701, the age selection area 702, and the stay time selection area 703, and only those who meet the conditions are displayed in the gender ratio graph 709. The filtering method may be the same as the processing described in step S901.

  In step S907, the average statistical information 710 is displayed. The average statistical information 710 indicates the past purchase of the product, such as the average purchase price, average purchase points, average number of stops in the passage area in front of the product, average purchase rate, etc. It is a statistical value of data. At this time, customers are filtered according to the conditions set in the gender selection area 701, the age selection area 702, and the stay time selection area 703, and only the purchase data of people who meet the conditions are displayed in the average statistical information 710. The filtering method may be the same as the processing described in step S901.

  In step S908, a stop number / purchase rate graph 711 is displayed. The number of stops / purchase rate graph 711 is a graph showing the purchase rate for each day of the product for which the alert is displayed and the number of stops in the passage area in front of the product shelf of the product during a predetermined period. In FIG. 9, the bar graph and the line graph are shown, but other types of graphs and numerical values may be displayed. At this time, the customers are filtered according to the conditions set in the gender selection area 701, the age selection area 702, and the stay time selection area 703, and only those who meet the conditions are displayed in the stopped person / purchase rate graph 711. The filtering method may be the same as the processing described in step S901.

<Second embodiment>
The second embodiment of the present invention will be described below. In the second embodiment, only configurations and processes different from those of the first embodiment described above will be described, and descriptions of the same configurations and processes as those of the first embodiment will be omitted.

<Description of Operation of Behavior Visualization Device 101>
First, the user starts processing of the behavior visualization unit 103 from an application, a web browser, or the like.

  The process of the behavior visualization unit 103 will be described using the flowchart of FIG. The display of the screen described in this specification is an example, and is not limited to the illustrated one. You may display so that it may overlap with the existing screen as needed. For example, since a smartphone has a low screen resolution, it may be difficult to display a plurality of screens side by side. For this reason, as described above, a plurality of screens may be displayed so as to overlap each other.

  FIG. 11 is a diagram illustrating an example of an image generated by the behavior visualization unit 103.

  The screen example shown in FIG. 11 includes a gender selection area 701, an age selection area 702, and a store layout information display area 704. In the store layout information display area 704, an immediately leaving store flow line 801, an alert icon 707, and an immediately leaving store number / inventory amount graph 802 for each time zone are displayed. The immediate exit store flow line 801 and the immediately exit store number / inventory amount graph 802 may be displayed at least one, even if not all are displayed.

  Immediately leaving the store is a customer who has stopped by a specific product shelf but has not purchased the product and has not gone around the store. Whether it is determined that the circuit has been migrated is defined in advance according to store characteristics. Immediately leaving store flow lines 801A and 801B are flow lines in the store of the customer who has immediately left the store.

  FIG. 10 is a flowchart of processing in which the behavior visualization unit 103 generates the screen in FIG. Note that the user can select the gender selection area 701, the age selection area 702, the alert icon 707, etc. at any time, and executes processing from an appropriate location at the selected timing.

In step S1101, a store clerk is searched for based on the index calculated from the flow line information 107 for each product section. For example, by calculating the next index for each customer ID 201 of the flow line information 107 and comparing each calculated index with a predetermined threshold, it is possible to determine whether or not the store is immediately closed. At this time, the flow line information stopped according to the conditions set in the gender selection area 701 and the age selection area 702 is filtered to extract only the flow lines that match the conditions. Specifically, the gender and age are not shown, but are specified in the gender and / or age (or age) included in the flow line information 107 and the gender and / or age selection area 702 specified in the gender selection area 701. Compare the generated ages and extract only the matching lines.
(1) Time from entry to exit (2) Length of flow line (3) Number of parked areas (4) Is U-turn in front of a specific product shelf For example, from entry to exit If you know that the stay in the store is short, such as the time is less than 1 minute, the length of the flow line is 30 meters or less, and only stops in the area where the specific product is displayed, then return to the exit It can be determined that the customer has left the store without purchasing the product.

  In step S1102, a stock quantity is calculated for each product section area 603, a predetermined index is calculated by comparing the stock quantity and the number of shoppers in the product section area 603, and the calculated index is determined in advance. Based on the comparison result with the threshold value, an alert icon 707 for alerting the operator to the store layout information display area 704 is superimposed and displayed. For example, if the index is the number of immediately leaving stores ÷ the amount of inventory, the index increases when there are many immediately leaving stores and there are few products displayed on the product shelf. Therefore, the alert icon 707 is displayed when the index exceeds a predetermined threshold. Note that the alert icon 707 may be displayed when the inventory quantity is smaller than a predetermined threshold and the number of shoppers immediately exceeds a predetermined threshold.

  The stock quantity is calculated based on the stock information 112 in the product partition area 603, and the total number of stocks in the product partition area 603 is obtained for each time. It is good to define it by the ratio of the total number of inventory at each time. However, the definition of the inventory quantity described above is an example, and other definitions may be used. For example, when the same product is displayed in a plurality of columns of the product shelf, the inventory quantity may be added with a weight in consideration of the display area of the product.

  In step S <b> 1103, the process is executed when the user selects the alert icon 707, and some (or one) flow lines representative of the immediately leaving store in the product partition area 603 are displayed. For example, it is only necessary to extract and display a flow line (main flow line) having a lot of similarities among the flow lines of all immediately leaving stores. A typical flow line may be defined.

  In step S <b> 1104, the immediately leaving store number / inventory amount graph 802 for each time period is displayed superimposed on the store layout information display area 704. At this time, the flow line information is filtered in accordance with the conditions set in the gender selection area 701 and the age selection area 702, and only those who satisfy the conditions are displayed in the immediately-leaved shop number / inventory quantity graph 802. The filtering method may be the same as the processing described in step S1101. The number of immediately leaving stores and the stock quantity in the product section area 603 calculated in steps S1101 and S1102 are displayed on a graph with the time axis as the horizontal axis. In FIG. 11, it is represented by a line graph, but it may be displayed by other types of graphs or numerical values.

  As described above, when the user operates the screens shown in FIG. 9 and FIG. 11, it is possible to quantitatively grasp which product has an opportunity loss. Further, by knowing the route of the store clerk immediately, it is possible to obtain an indication regarding the reason for leaving the store, such as when the store of a specific product is out of stock without searching for alternative products. In this case, for example, it is possible to take measures such as avoiding opportunity loss by appropriately adjusting the order quantity so as not to cause out of stock.

  Specifically, according to the embodiment of the present invention, the behavior visualization unit 103 analyzes the flow line information 107 with reference to the passage area information 110, determines a stop for each area in the store, Referring to the shelf allocation information 111, the number of purchases or purchase price of each product shelf is totaled, and the number of stops for each area and the total number of purchases or purchase price of the product are superimposed on the store layout. Therefore, the information obtained from the flow line information and the transaction information can be viewed in association with each other. And measures for store improvement can be examined. Specifically, the following business value is born. (1) Reduce disposal costs by optimizing orders, (2) Increase sales by directing customers to places where customers can't get close to the store, (3) Increase sales by replacing dead products, ( 4) Reduced opportunity loss by avoiding out-of-stock conditions, (5) Increased sales by optimizing the amount of customers in the store, and (6) Improved store layout.

  Further, when receiving at least one filtering condition (701, 702, 703) of the gender, age, and store stay time of the person who has acted to generate the flow line information, the behavior visualization unit 103 sets the received filtering condition to the received filtering condition. Since the number of stops that match and the number of purchases or purchase price of the merchandise are displayed (FIG. 9), it is possible to analyze customer trends by narrowing down the target layer.

  Further, the behavior visualization unit 103 superimposes the alert icon 707 on the store layout when the number of stops before the product shelf section is large and the number of purchases or purchase price displayed on the product in the product shelf section is small. Are displayed (FIG. 9). In other words, if the purchase rate (number of sales divided by number of stops, amount of sales divided by number of stops) exceeds a certain threshold, it is determined that there are many stops but the number of sales and the amount of sales is small. Can be found.

  Further, when the alert icon is operated, the behavior visualization unit 103 displays the statistical information of the product (FIG. 9). That is, at least one of the ratio 709 of the purchaser of the product, the statistical value 710 of the past purchase data of the product, and the relationship between the number of purchases of the product and the number of stops before the product shelf of the product. Since the information is displayed, it is possible to obtain detailed information on the target product.

  In addition, the behavior visualization unit 103 extracts the immediately leaving store that matches the predetermined condition from the flow line information 107, and displays the extracted flow lines 801A and 801B of the immediately leaving store (FIG. 11). In other words, because the store's stay time from entering the store to leaving the store, the length of the flow line, the number of parked areas, and the combination of whether or not a specific product shelf is making a U-turn, the store exit is immediately determined. Information on shopkeepers who do not lead to sales can be obtained immediately.

  Further, the behavior visualization unit 103 refers to the inventory information 112 and, for each product shelf targeted by the immediately leaving store, the alert icon 707 when the number of immediately leaving stores and the inventory information 112 satisfy predetermined conditions. Is superimposed on the position of the product shelf in the store layout (FIG. 11). That is, since the inventory amount of the product is quantified and the alert is displayed by comparing the inventory amount with the number of shoppers immediately leaving, it is possible to reduce the opportunity loss due to avoiding the shortage condition.

  In addition, when the predetermined display is operated, the behavior visualization unit 103 operates the flow line of the immediately leaving store, the statistical value of past purchase data of the product, the number of purchases of the product and the product shelf of the product. Since at least one of the graphs showing the relationship with the number of stops before is displayed (FIG. 11), it is possible to obtain detailed information on the products related to the shopkeeper immediately.

  The present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. A part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Moreover, you may add the structure of another Example to the structure of a certain Example. In addition, for a part of the configuration of each embodiment, another configuration may be added, deleted, or replaced.

  In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, with an integrated circuit, and the processor realizes each function. It may be realized by software by interpreting and executing the program to be executed.

  Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

  Further, the control lines and the information lines are those that are considered necessary for the explanation, and not all the control lines and the information lines that are necessary for the mounting are shown. In practice, it can be considered that almost all the components are connected to each other.

101 behavior visualization device 102 display device 103 behavior visualization unit 104 instruction device 105 network connection unit 106 storage unit 107 flow line information 108 store layout information 109 transaction information 110 aisle area information 111 shelf allocation information 112 inventory information

Claims (9)

A behavior analysis system comprising a computer having a processor and a memory,
Flow line information including a history of movement of a person measured by the position measuring device, transaction information including information on settlement of merchandise transactions, passage area information including conditions for determining stopping in a predetermined area, Access to shelf allocation information in which products displayed for each section defined on the product shelf are recorded,
An action visualization unit for generating information that visualizes a person's action from the flow line information;
The behavior visualization unit
Analyzing the flow line information with reference to the passage area information, determining a stop for each area in the store,
Referring to the transaction information and the shelf allocation information, the number of purchases or the purchase price of the product is totaled for each section of the product shelf,
A behavior analysis system for outputting screen data for graphically displaying the number of stops for each area and the total number of purchases or the purchase price superimposed on a store layout. The behavior analysis system according to claim 1,
Accept at least one filtering condition of gender, age and store stay time of the person who has acted to generate the flow line information,
The behavior visualization system outputs the screen data for displaying the number of stops that match the filtering condition and the number of purchases or the purchase price of the product. The behavior analysis system according to claim 1 or 2,
The behavior visualization unit has a predetermined display for alerting an operator when the number of stops in front of the compartment of the product shelf is large and the number of purchases or the purchase price of the product displayed in the compartment of the product shelf is small. A behavior analysis system characterized by outputting screen data for displaying the image superimposed on the store layout. The behavior analysis system according to claim 3,
When the predetermined display is operated, the behavior visualization unit outputs screen data for displaying statistical information of the product. The behavior analysis system according to claim 1,
The behavior visualization unit extracts an immediately leaving store that matches a predetermined condition from the flow line information, and outputs screen data for displaying the extracted flow line of the immediately leaving store. Behavior analysis system. The behavior analysis system according to claim 5,
Access to inventory information that records the number of items in stock over time,
The behavior visualization unit refers to the inventory information, and for each product shelf intended by the immediately leaving store, if the number of immediately leaving stores and the inventory information satisfy a predetermined condition, pay attention to the operator. A behavior analysis system characterized by outputting screen data for displaying a predetermined display for prompting superimposed on a position of the product shelf in the store layout. The behavior analysis system according to claim 6,
When the predetermined display is operated, the behavior visualization unit is configured to display the flow line of the immediately leaving store, the statistical value of past purchase data of the product, and the number of purchases of the product and the product shelf of the product. A behavior analysis system characterized by outputting screen data for displaying at least one of graphs showing a relationship with the number of stops. A behavior analysis method executed by a computer having a processor and a memory,
The computer includes a flow path information including a history of movement of a person measured by the position measuring device, transaction information including settlement information of a commodity transaction, and a path including a condition for determining a stop in a predetermined area. Access to area information and shelf allocation information in which products displayed for each section defined on the product shelf are recorded;
The method
The processor analyzes the flow line information with reference to the passage area information, determines stopping for each area in the store, and stores the result of the determination in the memory;
The processor refers to the transaction information and the shelf allocation information, totals the number of purchased products or the purchase price for each section of the product shelf, and stores the result of the aggregation in the memory;
The processor includes a procedure for outputting screen data for graphically displaying the number of stops for each area and the aggregated number or amount on a store layout. The behavior analysis method according to claim 8,
The processor extracts from the flow line information an immediately leaving store that matches a predetermined condition, and stores the extracted immediately leaving store information in the memory;
The processor includes a procedure of outputting screen data for displaying the extracted flow line of the immediately leaving store.

Images