Information processing device, information processing method, and information processing program

Abstract

This can provide useful information for marketing within the facility. [Solution] The information processing device according to the present invention comprises: a purchase information acquisition unit that acquires purchase information relating to the purchase of goods at a facility; a video acquisition unit that acquires video data captured by cameras installed at the facility; an estimation unit that estimates movement estimation data showing the trajectory of a person's movement related to the purchase information based on the video data; a calculation unit that calculates movement count information showing the number of times a person moves in each passage of the facility and dwelling information showing the dwelling status of a person in each area of ​​the facility based on the movement count estimation data; and a linking unit that links the purchase information, the movement count information and the dwelling information.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, in marketing at facilities such as stores, a technique is known that uses purchase information related to product purchases acquired from POS (Point Of Sales) terminals of the facility (hereinafter sometimes referred to as POS data). For example, by performing image recognition processing on video captured by a camera installed in a store, first data related to customer behavior is created, second data related to product purchases is acquired from a POS terminal, and a technique for performing processing to associate the second data with the first data is known.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Means for Solving the Problems

[0004] An information processing apparatus according to the present application includes a purchase information acquisition unit that acquires purchase information related to product purchases at a facility, a video acquisition unit that acquires video data captured by a camera installed in the facility, an estimation unit that estimates flow line estimation data indicating a movement trajectory of a person associated with the purchase information based on the video data, a calculation unit that calculates movement count information indicating the number of movements of the person in each passage of the facility and stay information indicating the stay status of the person in each area of the facility based on the flow line estimation data, and an association unit that associates the purchase information, the movement count information, and the stay information with one another.

Brief Description of the Drawings

[0005] [Figure 1] Figure 1 illustrates an example of useful information that cannot be obtained from POS data. [Figure 2] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of data linked to POS data according to this embodiment. [Figure 5] Figure 5 illustrates an example of movement path estimation data according to this embodiment. [Figure 6] Figure 6 is a diagram illustrating an example of a method for calculating movement count information according to the embodiment. [Figure 7] Figure 7 is a diagram illustrating an example of a method for calculating movement count information according to the embodiment. [Figure 8] Figure 8 is a diagram illustrating an example of a method for calculating dwell time information according to the embodiment. [Figure 9] Figure 9 is a diagram illustrating an example of a method for calculating dwell time information according to the embodiment. [Figure 10] Figure 10 is a diagram illustrating an example of a method for calculating dwell time information according to the embodiment. [Figure 11] Figure 11 is a diagram illustrating an example of a method for calculating dwell time information according to an embodiment. [Figure 12] Figure 12 is a diagram illustrating an example of a method for calculating dwell time information according to the embodiment. [Figure 13] Figure 13 is a diagram illustrating an example of a method for calculating dwell time information according to the embodiment. [Figure 14] Figure 14 is a flowchart showing an example of information processing by the information processing device according to the embodiment. [Figure 15A] Figure 15A is a diagram illustrating the different types of probability distributions. [Figure 15B]Figure 15B is a diagram illustrating the different types of probability distributions. [Figure 16] Figure 16 shows an example of a UI screen related to a modified example. [Figure 17] Figure 17 is a diagram illustrating use case (1). [Figure 18] Figure 18 is a diagram illustrating use case (1). [Figure 19] Figure 19 is a diagram illustrating use case (2). [Figure 20] Figure 20 is a diagram illustrating use case (2). [Figure 21] Figure 21 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0006] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0007] (Embodiment) [1. Introduction] Traditionally, in marketing at stores and other facilities, there is a known technique of using purchase information (hereinafter sometimes referred to as POS data) obtained from the facility's POS (Point of Sale) terminals. However, there is useful information in marketing that cannot be obtained from POS data.

[0008] An example of useful information that cannot be acquired from POS data will be described with reference to Figure 1. Figure 1 is a diagram for describing an example of useful information that cannot be acquired from POS data. For example, as an example of useful information that cannot be acquired from POS data, there is customer attribute information such as the customer's age and gender. Note that when the customer is a point card user, the customer attribute information registered in advance by the customer may be acquired in some cases. In addition, as an example of useful information that cannot be acquired from POS data, there is information related to accompanying persons. For example, a customer may purchase a product not for themselves, but for an accompanying person who is accompanying the customer. For example, there is a case where a father (customer) who comes shopping with his family purchases child products (products for the child who is the accompanying person).

[0009] In addition, POS data is information indicating the action of a customer purchasing a product. In contrast, information related to the actions of a customer up to the point of purchasing a product is information that cannot be obtained from POS data. For example, as examples of useful information that cannot be acquired from POS data, there is recognition information indicating whether or not a product in a facility has been recognized by a customer, and interest level information indicating to what extent the customer has interest in the product in the facility. The recognition information can be rephrased as information related to the customer's recognition of the product in the facility. In addition, the interest level information can be rephrased as information related to the degree of the customer's interest in the product in the facility.

[0010] In contrast, the information processing apparatus according to the present embodiment acquires purchase information related to the purchase of products in a facility. The information processing apparatus also acquires video data captured by a camera provided in the facility. Further, the information processing apparatus estimates movement line estimation data indicating the movement trajectory of a person associated with the purchase information, based on the video data. The information processing apparatus further calculates movement count information indicating the number of movements of a person in each aisle of the facility, and stay information indicating the stay status of a person in each area of the facility, based on the movement line estimation data. The information processing apparatus also associates the purchase information, the movement count information, and the stay information. Here, the purchase information is, for example, POS data. The movement count information is information used to determine whether or not a product arranged in each aisle of the facility has been recognized by a customer who passed through the aisle. The stay information is information used to determine the degree of the customer's interest in and concern for the products arranged in each area of the facility. As a result, the information processing apparatus can provide information related to the customer's recognition of products in the facility, and information related to the degree of the customer's interest in and concern for products in the facility. Therefore, the information processing apparatus can provide useful information for marketing in the facility.

[0011] [2. Configuration of Information Processing System] A configuration example of the information processing system 1 according to the embodiment will be described using FIG. 2. FIG. 2 is a diagram illustrating a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 2, the information processing system 1 includes a POS terminal 10, an imaging apparatus 20, and an information processing apparatus 100. The POS terminal 10, the imaging apparatus 20, and the information processing apparatus 100 are communicably connected via a predetermined communication network (network N) by wire or wirelessly.

[0012] The POS terminal 10 is a POS terminal provided at a checkout location (for example, a cash register) for products in a facility. The POS terminal 10 generates purchase information related to the purchase of products in the facility. For example, the POS terminal 10 generates, as the purchase information, information in which the purchase date and time of a product is associated with information capable of identifying the purchased product.

[0013] The imaging device 20 is a camera installed in the facility. The imaging device 20 generates video data captured inside the facility. For example, the imaging device 20 may be a security camera installed in the facility. Alternatively, the imaging device 20 may be an information processing device in which a camera and an edge device are integrated. For example, the imaging device 20 performs image analysis (e.g., object detection) on the video data captured by the camera and transmits the results of the image analysis (e.g., the detection result of object detection) to the information processing device 100. In the following description, the case where the imaging device 20 is a standalone camera will be explained.

[0014] The information processing device 100 acquires purchase information related to the purchase of goods at the facility from the POS terminal 10. The information processing device 100 also acquires video data captured by cameras installed in the facility from the imaging device 20. Based on the video data, the information processing device 100 estimates movement estimation data that shows the trajectory of people's movements related to the purchase information. Based on the movement estimation data, the information processing device 100 calculates movement count information that shows the number of times a person moves in each passage of the facility, and dwell time information that shows the dwell time of people in each area of ​​the facility. The information processing device 100 also links the purchase information, movement count information, and dwell time information.

[0015] [3. Configuration of the Information Processing Device] An example of the configuration of the information processing device 100 according to the embodiment will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. The information processing device 100 has a communication unit 110, a storage unit 120, an input unit 130, an output unit 140, and a control unit 150.

[0016] (Communications Department 110) The communication unit 110 is implemented using a NIC (Network Interface Card), an antenna, etc. The communication unit 110 is connected to various networks by wired or wireless means, and transmits and receives information with, for example, a POS terminal 10 or an imaging device 20.

[0017] (Storage unit 120) The storage unit 120 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. Specifically, the storage unit 120 stores the information processing program according to the embodiment. The storage unit 120 also has a marketing information storage unit 121. However, the storage unit 120 is not limited to the above and may store various kinds of information.

[0018] (Marketing Information Storage Unit 121) The marketing information storage unit 121 stores various types of information related to marketing information. Here, marketing information is information used for marketing. Specifically, marketing information is information that links purchase information, movement frequency information, and dwell time information. More specifically, marketing information is information that links purchase information, attribute information, information about accompanying persons, movement path estimation data, movement frequency information, and dwell time information.

[0019] (Input section 130) The input unit 130 is an input device that receives various inputs from the outside. The input unit 130 is equipped with an operating device that receives input operations from the user. The operating device is, for example, a keyboard, mouse, or operation keys, a device for the user to perform various operations. If the information processing device 100 employs a touch panel, the touch panel is also included as an operating device. In this case, the user performs various operations by touching the screen with their finger or stylus. Alternatively, the operating device may be a voice input device (for example, a microphone) that receives input operations from the user's voice.

[0020] (Output section 140) The output unit 140 is a display device that displays various types of information. The output unit 140 may be, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display. If a touch panel is used in the information processing device 100, the output unit 140 may be an integrated device with the operating device of the input unit 130. The output unit 140 displays various types of information and provides it to the user. In the following description, the output unit 140 may be referred to as the screen.

[0021] (Control unit 150) The control unit 150 is a controller, and is implemented, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 150 is a controller and can be implemented, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0022] The control unit 150 has a purchase information acquisition unit 151, an image acquisition unit 152, an estimation unit 153, a calculation unit 154, and a linking unit 155 as functional units, and may realize or execute the information processing operations described below. Note that the internal configuration of the control unit 150 is not limited to the configuration shown in Figure 3, and other configurations are also acceptable as long as they perform the information processing described later. Furthermore, each functional unit represents the function of the control unit 150 and does not necessarily have to be physically separated.

[0023] (Purchase information acquisition unit 151) The purchase information acquisition unit 151 acquires purchase information related to the purchase of goods at the facility. For example, the purchase information acquisition unit 151 acquires purchase information from the POS terminal 10. For example, the purchase information acquisition unit 151 acquires information that associates the date and time of purchase of the goods with information that can identify the purchased goods (e.g., the name of the goods). For example, the purchase information acquisition unit 151 acquires POS data as purchase information. Also, if the purchase information acquisition unit 151 acquires POS data, it generates new purchase information that associates the POS data with information that can identify the facility (e.g., the name of the facility). The purchase information acquisition unit 151 acquires new purchase information. Hereafter, new purchase information may be referred to simply as purchase information.

[0024] (Video acquisition unit 152) The video acquisition unit 152 acquires video data captured by cameras installed in the facility. For example, the video acquisition unit 152 acquires video data from the imaging device 20. For example, the video acquisition unit 152 acquires video data of people located in the facility.

[0025] (Estimation part 153) The estimation unit 153 estimates a person associated with the purchase information based on the purchase information acquired by the purchase information acquisition unit 151 and the video data acquired by the video acquisition unit 152. For example, the estimation unit 153 detects a person included in the video data using a known object detection technique. The estimation unit 153 also estimates that the person who was at the register at the time of purchase of the product included in the purchase information is the person associated with the purchase information. Hereafter, the person estimated to be associated with the purchase information may be referred to as the "person associated with the purchase information."

[0026] Furthermore, the estimation unit 153 estimates attribute information of the person associated with the purchase information based on the video data. For example, the estimation unit 153 uses known attribute recognition technology to estimate attribute information such as the age and gender of the person associated with the purchase information.

[0027] Furthermore, the estimation unit 153 estimates information about companions of the person associated with the purchase information based on the video data. For example, the estimation unit 153 estimates that a person who has been within a predetermined range for a predetermined time or longer from the person associated with the purchase information is a companion. The estimation unit 153 estimates attribute information such as the age and gender of the companion as information about the companion.

[0028] Furthermore, the estimation unit 153 estimates movement trajectory data showing the movement trajectory of persons associated with purchase information based on the video data. For example, the estimation unit 153 tracks persons associated with purchase information in the video data using known tracking techniques. The estimation unit 153 also acquires time-series data of coordinates indicating the position of persons associated with purchase information in the video data by tracking persons associated with purchase information in the video data. In other words, the estimation unit 153 acquires coordinate data indicating the position of persons associated with purchase information in the video data at predetermined time intervals by tracking persons associated with purchase information in the video data. For example, the estimation unit 153 acquires coordinate data indicating the position of persons associated with purchase information in the video data at time intervals shorter than 10 FPS. For example, the estimation unit 153 acquires time-series data of coordinates indicating the 2D position of persons associated with purchase information in the video data. The estimation unit 153 also projects the time-series data of coordinates indicating the position of persons associated with purchase information in the video data onto a 2D map of the facility. The estimation unit 153 estimates the time-series data of coordinates projected onto a two-dimensional map of the facility as movement estimation data that shows the trajectory of people associated with purchase information.

[0029] Furthermore, when the estimation unit 153 estimates attribute information of a person associated with the purchase information, information about accompanying persons, and movement estimation data, it generates information linking the purchase information, attribute information of the person associated with the purchase information, information about accompanying persons, and movement estimation data. Figure 4 is a diagram showing an example of data linked to POS data according to the embodiment. In Figure 4, the estimation unit 153 generates information linking POS data, attribute information of a person associated with the POS data, information about accompanying persons, and movement estimation data as an example of purchase information. For example, the POS data in the first row of Figure 4 shows that the purchase date and time is "March 1, 2024, 09:10:34" and the purchased items are "beer" and "snacks". Also, the attribute information of the person associated with the POS data in the first row of Figure 4 shows that the person's age is "23" and their gender is "male". Furthermore, Figure 4 shows that the POS data in the first row is linked to information about the accompanying person, indicating that there was no accompanying person. It also shows that the movement estimation data #1 is linked to the movement data of the person associated with the POS data in the first row of Figure 4.

[0030] Furthermore, the POS data in the second row of Figure 4 indicates that the purchase date and time was "March 1, 2024, 09:12:34" and the purchased item was "bread". Also, the attribute information of the person associated with the POS data in the second row of Figure 4 indicates that the person is "42" years old and "male". Additionally, the information of the accompanying person associated with the POS data in the second row of Figure 4 indicates that the attribute of the first accompanying person is a 2-year-old male, and the attribute of the second accompanying person is a 35-year-old female. Finally, the movement data of the person associated with the POS data in the second row of Figure 4 is linked to movement estimation data #2.

[0031] Furthermore, the POS data in the third row of Figure 4 indicates that the purchase date and time was "March 31, 2024, 14:57:34," and the purchased items were "beer" and "books." Also, the attribute information of the person associated with the POS data in the third row of Figure 4 indicates that the person is "26" years old and "female." Additionally, the information regarding the accompanying person associated with the POS data in the third row of Figure 4 indicates that there were no accompanying persons. Finally, the movement data of the person associated with the POS data in the third row of Figure 4 is linked to movement estimation data #3.

[0032] Furthermore, if the estimation unit 153 generates information linking purchase information, attribute information of persons associated with the purchase information, information about accompanying persons, and movement estimation data, it stores this linked information in the marketing information storage unit 121. In the following, the information linking purchase information, attribute information of persons associated with the purchase information, information about accompanying persons, and movement estimation data may be referred to as "movement estimation data related information." The estimation unit 153 generates movement estimation data related information. If the estimation unit 153 generates movement estimation data related information, it stores this information in the marketing information storage unit 121.

[0033] Figure 5 illustrates an example of movement estimation data according to the embodiment. On the left side of Figure 5, an imaging device 20 is installed in facility FA1. The imaging device 20 generates video data of a person U1 located within facility FA1. The estimation unit 153 estimates the person U1 associated with the purchase information based on the purchase information and the video data. The estimation unit 153 also tracks the person U1 associated with the purchase information in the video data. Furthermore, by tracking the person U1 associated with the purchase information in the video data, the estimation unit 153 acquires time-series data of coordinates indicating the position of the person U1 associated with the purchase information in the video data. The estimation unit 153 acquires coordinate data indicating the position of the person U1 at each time point in the video data by tracking the person U1 associated with the purchase information in the video data. For example, the estimation unit 153 acquires time-series data of coordinates indicating the two-dimensional position of the person U1 associated with the purchase information in the video data.

[0034] Furthermore, the estimation unit 153 projects the time-series data of coordinates indicating the position of person U1 in the video data associated with the purchase information onto the 2D map MP1 of facility FA1. The estimation unit 153 estimates the time-series data of coordinates projected onto the 2D map MP1 of facility FA1 as movement estimation data FL1, which shows the trajectory of movement of person U1 associated with the purchase information.

[0035] Furthermore, the output unit 140 outputs the facility map and the estimated movement data in a visually associated manner. On the right side of Figure 5, the output unit 140 outputs the facility map MP1 and the estimated movement data FL1 in a visually associated manner. The output unit 140 displays image G1, which shows the estimated movement data FL1 superimposed on the facility map MP1. From image G1 on the right side of Figure 5, it can be seen that person U1, associated with the purchase information, entered the facility FA1 from the entrance, passed in front of the main section and ATM, then passed in front of the sweets section and prepared food section, stopped by the beverage section, and then stopped by the cash register.

[0036] (Calculation section 154) The calculation unit 154 calculates movement count information, which indicates the number of times a person moves through each passage in the facility, and dwell time information, which indicates the dwell time of a person in each area of ​​the facility, based on the movement path estimation data. For example, the calculation unit 154 calculates movement count information for each area of ​​the facility based on the number of times a person passes through each area provided in each passage in the facility. Figures 6 and 7 are diagrams illustrating an example of a method for calculating movement count information according to the embodiment. In Figure 6, the calculation unit 154 divides each passage in facility FA1 into areas AR1 to AR18, according to sections corresponding to the sales area in facility FA1. In Figure 7, the calculation unit 154 calculates the number of times a person passes through each of areas AR1 to AR18 provided in each passage in the facility, based on the movement path estimation data. For example, based on the movement path estimation data, the calculation unit 154 counts the number of times a person moves from a predetermined area provided in each passage in the facility to an adjacent area adjacent to that predetermined area as 1. Furthermore, the calculation unit 154 calculates the total number of times multiple people move from a predetermined area in each passage of the facility to an adjacent area, based on the estimated movement data of multiple people, as movement count information.

[0037] In Figure 7, the direction of movement of a person is indicated by the direction of the arrow. The number of movements is represented by the number shown near the arrow. For example, in Figure 7, the calculation unit 154 calculates that the total number of movements a person made from area AR1 to area AR6, as shown in Figure 6, is 16, and the total number of movements a person made from area AR6 to area AR1 is 1, as the movement count information MV1. Also in Figure 7, the calculation unit 154 calculates that the total number of movements a person made from area AR6 to area AR9, as shown in Figure 6, is 16, and the total number of movements a person made from area AR9 to area AR6 is 1, as the movement count information MV2.

[0038] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of movements a person made from area AR9 to area AR10 as 15, and the total number of movements a person made from area AR10 to area AR9 as 1, as movement count information MV3. Also in Figure 7, the calculation unit 154 calculates the total number of movements a person made from area AR9 to area AR12 as 3, and the total number of movements a person made from area AR12 to area AR9 as 2, as movement count information MV4.

[0039] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR12 to area AR14 as 3, and the total number of times a person moves from area AR14 to area AR12 as 2, as movement count information MV5. Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR14 to area AR15 as 3, and the total number of times a person moves from area AR15 to area AR14 as 2, as movement count information MV6.

[0040] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR15 to area AR16 as 3, and the total number of times a person moves from area AR16 to area AR15 as 2, as movement count information MV7. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR16 to area AR17 as 13, and the total number of times a person moves from area AR17 to area AR16 as 1, as movement count information MV8.

[0041] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR17 to area AR18 as 13 times, and the total number of times a person moves from area AR18 to area AR17 as 1 time, as movement count information MV9. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR18 to area AR8 as 14 times, and the total number of times a person moves from area AR8 to area AR18 as 2 times, as movement count information MV10.

[0042] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moved from area AR13 to area AR16 as 13, and the total number of times a person moved from area AR16 to area AR13 as 2, as movement count information MV11. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moved from area AR11 to area AR13 as 13, and the total number of times a person moved from area AR13 to area AR11 as 2, as movement count information MV12.

[0043] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR10 to area AR11 as 15 times, and the total number of times a person moves from area AR11 to area AR10 as 1 time, as movement count information MV13. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR11 to area AR7 as 4 times, and the total number of times a person moves from area AR7 to area AR11 as 1 time, as movement count information MV14.

[0044] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR11 to area AR7 as 4, and the total number of times a person moves from area AR7 to area AR11 as 1, as movement count information MV14. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR8 to area AR5 as 14, and the total number of times a person moves from area AR5 to area AR8 as 2, as movement count information MV15.

[0045] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moved from area AR5 to area AR4 as 14, and the total number of times a person moved from area AR4 to area AR5 as 2, as movement count information MV16. Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moved from area AR4 to area AR3 as 14, and the total number of times a person moved from area AR3 to area AR4 as 2, as movement count information MV17.

[0046] Furthermore, in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR7 to area AR3 as 4, and the total number of times a person moves from area AR3 to area AR7 as 1, as movement count information MV18. Also in Figure 7, the calculation unit 154 calculates the total number of times a person moves from area AR3 to area AR2 as 16, and the total number of times a person moves from area AR2 to area AR3 as 1, as movement count information MV19.

[0047] Furthermore, the output unit 140 outputs the facility map and the movement count information in a visually associated manner. In Figure 7, the output unit 140 outputs the map MP1 of facility FA1 and the movement count information MV1 to MV19 in a visually associated manner. The output unit 140 displays image G2, which superimposes the movement count information MV1 to MV19 onto the map MP1 of facility FA1. The output unit 140 displays image G2, which superimposes the movement count information MV1 to MV19, which includes arrows indicating the direction of movement of people and numbers indicating the number of moves, onto the map MP1 of facility FA1.

[0048] Figures 8 to 13 illustrate an example of a method for calculating dwell time information according to an embodiment. The calculation unit 154 calculates the average of the coordinates of the movement estimation data for predetermined time intervals and calculates dwell time information by summing the probability distributions centered on the calculated average. For example, the probability distribution is a normal distribution. In Figure 8, the plane corresponding to the facility is considered as a two-dimensional xy plane, and the dwell time information indicating the dwell time of people in each area of ​​the facility is taken in the z-axis direction as the value of a probability density function such as a normal distribution.

[0049] Figure 9 illustrates the case where the movement path estimation data is one-dimensional for simplicity. The lines shown in the upper part of Figure 9 conceptually represent the movement path estimation data, which is one-dimensional data. Each of the multiple points shown in the upper part of Figure 9 represents the x-coordinate value of the movement path estimation data for a predetermined time interval. First, the calculation unit 154 averages the x-coordinate values ​​of the movement path estimation data in groups of n points (for example, n=5). In the upper part of Figure 9, the calculation unit 154 averages the x-coordinate values ​​of the movement path estimation data in groups of five points. In other words, the calculation unit 154 calculates the average of the x-coordinate values ​​of the movement path estimation data for predetermined intervals. In the upper part of Figure 9, the average of the x-coordinate values ​​of the movement path estimation data is calculated for every five points (Step 1). In the middle part of Figure 9, the calculation unit 154 generates a normal distribution with the averaged x-coordinate values ​​from Step 1 as the mean (Step 2). In the lower part of Figure 9, the calculation unit 154 calculates the dwell time information by summing the normal distributions generated in Step 2.

[0050] The left side of Figure 10 shows the case where a person is staying in a predetermined location. When a person is staying in a predetermined location, the distance between the x-coordinates of adjacent movement estimation data is small. Therefore, the distance between the x-coordinates averaged over a predetermined number of data points is also small. Furthermore, because the distance between the averaged x-coordinates is small, the distance between adjacent normal distributions is also small. Moreover, because the distance between adjacent normal distributions is small, when adjacent normal distributions are superimposed, the degree of overlap between the normal distributions is large. Furthermore, because the degree of overlap between the normal distributions is large, it indicates that the peak height of the superimposed normal distribution is large.

[0051] The right side of Figure 10 shows the case where no person is staying at the designated location (they are passing through). When no person is staying at the designated location, the distance between the x coordinates of adjacent movement estimation data is larger compared to when a person is staying at the designated location. Therefore, the distance between the x coordinates averaged for each predetermined number is also larger compared to when a person is staying at the designated location. Furthermore, because the distance between the averaged x coordinates is large, the distance between adjacent normal distributions is also large. Moreover, because the distance between adjacent normal distributions is large, when adjacent normal distributions are superimposed, the degree of overlap between the normal distributions is small. Furthermore, because the degree of overlap between the normal distributions is small, the height of the peak of the superimposed normal distribution is small, indicating that it is flattened.

[0052] Figure 11 shows estimated movement data for multiple individuals #1 to #N (where N is a natural number). Figure 11 shows the case where each of the multiple individuals #1 to #N passes through the snack food section, then the prepared food section, and then the beverage section. In Figure 11, the calculation unit 154 calculates the average of the coordinates of the estimated movement data for each of the multiple individuals #1 to #N at predetermined time intervals, and calculates the dwell time information corresponding to each of the multiple individuals #1 to #N by summing the probability distributions centered on the calculated average. The calculation unit 154 also calculates dwell time information for the multiple individuals #1 to #N by summing the dwell time information corresponding to each of the multiple individuals #1 to #N.

[0053] Figure 11 shows that in the snack and beverage section, the peak of the superimposed normal distribution for multiple individuals #1 to #N is high, indicating that many people linger in the snack and beverage section. On the other hand, in the prepared food section, the peak of the superimposed normal distribution for multiple individuals #1 to #N is low, indicating that many people pass through the prepared food section without stopping.

[0054] Figures 9 to 11 illustrate the case where the movement estimation data is one-dimensional for simplicity, but actual movement estimation data is two-dimensional. In Figure 12, instead of representing the height of the peak of the normal distribution indicating dwell time with a value in the z-axis direction, the height of the peak of the normal distribution is represented on a two-dimensional plane by making the color darker as the height of the peak of the normal distribution increases.

[0055] Figure 12 shows that the calculation unit 154 calculates the average of the (x, y) coordinate values ​​of the movement estimation data for person #1 at predetermined intervals. The calculation unit 154 also generates a normal distribution with the averaged (x, y) coordinate values ​​as the mean. Furthermore, the calculation unit 154 calculates the dwell time information RE1 corresponding to person #1 by summing the generated normal distributions.

[0056] Furthermore, the calculation unit 154 calculates the average of the (x, y) coordinate values ​​of the movement estimation data for person #2 at predetermined intervals. The calculation unit 154 also generates a normal distribution with the averaged (x, y) coordinate values ​​as the mean. Finally, the calculation unit 154 calculates the dwell time information RE2 corresponding to person #2 by summing the generated normal distributions.

[0057] Similarly, the calculation unit 154 calculates the average of the (x, y) coordinate values ​​of the movement estimation data for person #N at predetermined intervals. The calculation unit 154 also generates a normal distribution with the averaged (x, y) coordinate values ​​as its mean. The calculation unit 154 then calculates the dwell time information REN corresponding to person #N by summing the generated normal distributions.

[0058] In this way, the calculation unit 154 generates a normal distribution for each of the multiple people #1 to #N, using the average of the two-dimensional coordinate values ​​of the movement estimation data averaged at predetermined intervals. The calculation unit 154 also generates a normal distribution for each of the multiple people #1 to #N, using the average of the two-dimensional coordinate values ​​of the movement estimation data. The calculation unit 154 also calculates the dwell information RE1 to REN corresponding to each of the multiple people #1 to #N by summing the generated normal distributions for each of the multiple people #1 to #N. The calculation unit 154 also calculates the dwell information REA corresponding to the group of multiple people #1 to #N by summing the dwell information RE1 to REN corresponding to each of the multiple people #1 to #N.

[0059] In Figure 13, the calculation unit 154 calculates the dwelling information REA corresponding to the group of multiple people #1 to #N by adding up the dwelling information RE1 to REN corresponding to each of the multiple people #1 to #N as explained in Figure 12. The output unit 140 also outputs the facility map and the dwelling information in a visually associated manner. In Figure 13, the output unit 140 outputs the map MP1 of facility FA1 and the dwelling information REA corresponding to the group of multiple people #1 to #N in a visually associated manner. The output unit 140 displays image G3, which shows the dwelling information REA superimposed on the map MP1 of facility FA1.

[0060] For example, in Figure 13, the dwell time information REA1 in the area between the sweets and instant noodles in the lower left of map MP1 is the darkest in color in image G3, indicating that the most people lingered in this area. Similarly, the dwell time information REA2 in the area between the instant noodles and prepared food at the bottom of map MP1, and the dwell time information RE3 in the area between the prepared food and ice cream, are slightly lighter in color than REA1, but still show a dark color, indicating that many people lingered in these areas as well. Furthermore, the dwell time information REA4 in the area between the ice cream and drinks on the right side of map MP1 is lighter in color than REA2 to RE3, indicating that fewer people lingered in this area compared to the area between the instant noodles and prepared food, and the area between the prepared food and ice cream. Furthermore, the dwell time information REA5 in the area between frozen foods and ice cream in the upper right of map MP1 is lighter in color than dwell time information REA4, indicating that even fewer people lingered there than in the area between ice cream and drinks. Also, the dwell time information REA6 in the area between the cash register and baked goods in map MP1 is lighter in color than dwell time information REA5, indicating that even fewer people lingered there than in the area between frozen foods and ice cream.

[0061] (String attachment part 155) The linking unit 155 links purchase information, movement count information, and dwell time information. The linking unit 155 generates marketing information by linking purchase information, movement count information, and dwell time information. For example, the linking unit 155 generates marketing information by linking movement path estimation data-related information, movement count information, and dwell time information. The linking unit 155 generates marketing information by linking purchase information, attribute information of persons related to the purchase information, information about accompanying persons, movement path estimation data, movement count information, and dwell time information. When the linking unit 155 generates marketing information, it stores the marketing information in the marketing information storage unit 121.

[0062] [4. Information Processing Procedures] Next, an example of information processing by the information processing device according to the embodiment will be described using Figure 14. Figure 14 is a flowchart showing an example of information processing by the information processing device according to the embodiment. In Figure 14, the purchase information acquisition unit 151 of the information processing device 100 acquires purchase information related to the purchase of goods at the facility (step S101).

[0063] Furthermore, the video acquisition unit 152 of the information processing device 100 acquires video data captured by cameras installed in the facility (step S102). Also, the estimation unit 153 of the information processing device 100 estimates movement trajectory data that shows the movement trajectory of a person related to the purchase information, based on the video data (step S103).

[0064] Furthermore, the calculation unit 154 of the information processing device 100 calculates movement count information, which indicates the number of times a person moves in each passage of the facility, and dwell time information, which indicates the dwell time of a person in each area of ​​the facility, based on the movement estimation data (step S104). In addition, the linking unit 155 of the information processing device 100 links the purchase information, movement count information, and dwell time information (step S105).

[0065] [5. Variations] The embodiments described above explained the case where the probability distribution is a normal distribution, but the probability distribution is not limited to a normal distribution. For example, the probability distribution may be a uniform distribution. Also, the probability distribution may be a hemispherical distribution. Also, the probability distribution may be a pyramidal distribution. Figures 15A to 15B are diagrams for explaining the types of probability distributions. The upper part of Figures 15A to 15B shows the cases where the probability distribution is a normal distribution, a uniform distribution, a hemispherical distribution, and a pyramidal distribution. The lower part of Figures 15A to 15B shows the stagnation information calculated for each of the cases where the probability distribution is a normal distribution, a uniform distribution, a hemispherical distribution, and a pyramidal distribution. Depending on the type of probability distribution used in the calculation, the appearance of the stagnation information has the following characteristics. As shown in the lower part of Figures 15A to 15B, when the probability distribution is a normal distribution, the stagnation range tends to be wide. When the probability distribution is a uniform distribution, the stagnation range tends to be wide, second only to when the probability distribution is a normal distribution. In contrast, when the probability distribution is a triangular pyramidal distribution, the range of stagnation tends to be narrower. When the probability distribution is a hemispherical distribution, the range of stagnation tends to be narrower, second only to when the probability distribution is a triangular pyramidal distribution.

[0066] Figure 16 shows an example of a UI screen related to a modified example. The output unit 140 displays a UI screen G4 that includes an area where the extraction conditions for movement estimation data can be entered. The input unit 130 accepts input of condition information indicating the extraction conditions for movement estimation data. For example, the condition information includes at least one of the following: information that can identify a product, information about the date and time of purchase of a product, information that can identify a facility, information about the age of a person, information about the gender of a person, or information about a person's companion. The calculation unit 154 also calculates movement count information and dwell time information based on the movement estimation data corresponding to the condition information. For example, when the input unit 130 accepts input of condition information, the calculation unit 154 refers to the marketing information storage unit 121 and obtains movement estimation data linked to the condition information. The calculation unit 154 also calculates movement count information and dwell time information based on the movement estimation data linked to the condition information.

[0067] The output unit 140 displays a UI screen G4 that includes an area where the user can input a period corresponding to the product purchase date. In Figure 16, the output unit 140 displays a UI screen G4 that includes an area F11 where the user can input the start date of the product purchase and an area F12 where the user can input the end date of the product purchase. The input unit 130 accepts the product purchase date entered in area F11 by the user as the start date of the product purchase. In Figure 16, the input unit 130 accepts "April 1, 2025" as the start date of the product purchase. The input unit 130 also accepts the product purchase date entered in area F12 by the user as the end date of the product purchase. In Figure 16, the input unit 130 accepts "April 30, 2025" as the end date of the product purchase. Furthermore, when the input unit 130 accepts the input of a period for the product purchase, the calculation unit 154 refers to the marketing information storage unit 121. Furthermore, the calculation unit 154 refers to the marketing information storage unit 121 and obtains estimated movement data linked to purchase information corresponding to the purchase date of the products included in the period received by the input unit 130.

[0068] Furthermore, in Figure 16, the output unit 140 displays a UI screen G4 that includes an area F2 into which information that can identify a store (an example of a facility) can be entered. For example, the information that can identify a store (an example of a facility) may be the name of the store. For example, when the user selects area F2, the output unit 140 displays a pull-down menu into which the user can select a desired store name from a list of multiple store names. The input unit 130 accepts the input of the store name selected by the user from the pull-down menu. In addition, when the input unit 130 accepts the input of a store name, the calculation unit 154 refers to the marketing information storage unit 121. The calculation unit 154 also refers to the marketing information storage unit 121 to obtain estimated movement data linked to purchase information corresponding to the store name accepted by the input unit 130.

[0069] Furthermore, in Figure 16, the output unit 140 displays a UI screen G4 that includes an area F3 where information that can identify a product can be entered. For example, the information that can identify a product may be the product name (product name). For example, when the user selects area F3, the output unit 140 displays a pull-down menu that allows the user to select a desired product name from a list of multiple product names. The input unit 130 accepts the input of the product name selected by the user from the pull-down menu. In addition, when the input unit 130 accepts the input of a product name, the calculation unit 154 refers to the marketing information storage unit 121. The calculation unit 154 also refers to the marketing information storage unit 121 and obtains estimated movement data linked to purchase information corresponding to the product name accepted by the input unit 130.

[0070] In Figure 16, the output unit 140 displays a UI screen G4 that includes an area F4 where information about a person's age can be entered. For example, the information about a person's age may be in their teens, twenties, thirties, forties, etc. For example, when the user selects area F4, the output unit 140 displays a pull-down menu that allows the user to select a desired age from a list of multiple ages. The input unit 130 accepts the age selected by the user from the pull-down menu. The calculation unit 154 also refers to the marketing information storage unit 121 when the input unit 130 accepts the age input. The calculation unit 154 also refers to the marketing information storage unit 121 to obtain movement estimation data linked to attribute information corresponding to the age accepted by the input unit 130.

[0071] Furthermore, in Figure 16, the output unit 140 displays a UI screen G4 that includes an area F5 where information about a person's gender can be entered. For example, the information about a person's gender may be information indicating whether they are male or female. For example, the output unit 140 displays radio buttons to select male or female. The input unit 130 accepts the gender selected by the user from among the radio buttons. In addition, when the input unit 130 accepts the gender input, the calculation unit 154 refers to the marketing information storage unit 121. The calculation unit 154 also refers to the marketing information storage unit 121 and obtains movement estimation data linked to attribute information corresponding to the gender accepted by the input unit 130.

[0072] Furthermore, in Figure 16, the output unit 140 displays a UI screen G4 that includes an area F6 where information about a person's companions can be entered. For example, the information about a person's companions may be information indicating whether or not there are companions or the number of companions. For example, when the user selects area F6, the output unit 140 displays a pull-down menu in which the user can select information indicating whether or not there are companions (for example, "none" if there are no companions, "yes" if there are companions, etc.). The input unit 130 accepts the input of information indicating whether or not there are companions selected by the user from the pull-down menu. In addition, when the input unit 130 accepts the input of information indicating whether or not there are companions, the calculation unit 154 refers to the marketing information storage unit 121. The calculation unit 154 also refers to the marketing information storage unit 121 and obtains movement estimation data linked to the information about companions corresponding to the information indicating whether or not there are companions accepted by the input unit 130.

[0073] Furthermore, in Figure 16, the output unit 140 displays a UI screen G4 that includes an area F7 where the type of probability distribution can be entered. The input unit 130 accepts input of the type of probability distribution. For example, when the user selects area F7, the output unit 140 displays a pull-down menu that allows the user to select the desired probability distribution from among the normal distribution, uniform distribution, hemispherical distribution, or pyramidal distribution. The input unit 130 accepts input of the type of probability distribution selected by the user from the pull-down menu. The calculation unit 154 calculates dwell time information by summing up the types of probability distributions accepted by the input unit 130. For example, when the input unit 130 accepts input of the type of probability distribution, the calculation unit 154 calculates dwell time information by summing up the types of probability distributions accepted by the input unit 130 based on the movement estimation data linked to the condition information.

[0074] In Figure 16, the output unit 140 displays a UI screen G4 that includes an area F8 where the variance value can be entered when the probability distribution is a normal distribution. The input unit 130 accepts the input of the variance value. The calculation unit 154 calculates the dwell time information by summing the normal distributions corresponding to the variance values ​​received by the input unit 130.

[0075] [6. Use Cases] Figures 17 and 18 are diagrams illustrating use case (1). Figures 17 and 18 provide considerations for when you want to sell related products to a customer who has purchased beer. In Figures 17 and 18, the calculation unit 154 calculates movement count information, which shows the number of times a person moves in each aisle of a store, and dwell time information, which shows the dwell time of a person in each area of ​​a store, based on estimated movement data of a customer who purchased beer in a store.

[0076] For example, the movement data shown in Figure 17 reveals that many customers who purchased beer passed through the area between the snack food and bread sections. Furthermore, since many of these customers passed through this area, it can be inferred that many of them became aware of the products placed in the snack food and bread section. Therefore, a marketing strategy could be considered in which the products to be sold (related products) are placed in the area between the snack food and bread sections, which was frequently visited by customers who purchased beer.

[0077] Furthermore, the dwell time information shown in Figure 18 reveals that many customers who purchased beer lingered in the area between the sweets and prepared foods and the instant noodles. This suggests that many of these customers were interested in the products located in the sweets and prepared foods and instant noodle sections. Therefore, a possible marketing strategy could be to sell products from the sweets and prepared foods and instant noodle sections as related items to customers who purchased beer.

[0078] Figures 19 and 20 illustrate use case (2). For example, suppose that POS data from all stores shows that beer and snacks are often purchased together. In other words, POS data from all stores shows a strong correlation between beer and snacks. Furthermore, analysis of POS data from a particular store reveals a tendency for customers who purchase beer not to purchase snacks. In this case, Figures 19 and 20 provide information for investigating the reasons why customers who purchase beer at a particular store do not purchase snacks. In Figures 19 and 20, the calculation unit 154 calculates movement count information, which shows the number of times a person moves in each aisle of a particular store, and dwell time information, which shows the dwell time of people in each area of ​​a particular store, based on estimated movement data of customers who purchased beer at that store.

[0079] For example, the movement frequency information shown in Figure 19 reveals that in a certain store, customers who purchase beer do not pass through the area where snacks are placed (the area between the snack foods and bread in Figure 19). Therefore, a marketing strategy could be considered, for example, to revise the store layout. Alternatively, a marketing strategy could be considered to place snacks in the area that customers who purchase beer pass through most frequently.

[0080] Furthermore, let's say that the dwelling information shown in Figure 20 reveals that in one store, customers were lingering in the area where snacks are displayed. In this case, it's possible that the customers were trying to buy snacks, but they were out of stock. Conversely, let's say that in another store, it's found that no customers were lingering in the area where snacks are displayed. In this case, it can be analyzed that something unusual is happening in that store, as customers who purchased beer are not trying to buy snacks.

[0081] Furthermore, the calculation unit 154 performs at least one of the following analyses based on the purchase information, movement count information, and dwell time information linked by the linking unit 155: product awareness analysis, product purchasing trend analysis, or analysis related to the optimization of product placement in the facility. For example, the calculation unit 154 analyzes product awareness using a first machine learning model trained to output information indicating product awareness when purchase information, movement count information, and dwell time information are input. For example, the calculation unit 154 inputs purchase information, movement count information, and dwell time information into the first machine learning model to generate information indicating product awareness. Furthermore, the calculation unit 154 analyzes product purchasing trends using a second machine learning model trained to output information indicating product purchasing trends when purchase information, movement count information, and dwell time information are input. For example, the calculation unit 154 inputs purchase information, movement count information, and dwell time information into the second machine learning model to generate information indicating product purchasing trends. Furthermore, the calculation unit 154, upon receiving purchase information, movement count information, and dwell time information, uses a third machine learning model trained to output information regarding the optimization of product placement within the facility to perform an analysis on optimizing product placement within the facility. For example, the calculation unit 154 inputs purchase information, movement count information, and dwell time information into the third machine learning model to generate information regarding the optimization of product placement within the facility.

[0082] [7. Effects] As described above, the information processing device 100 according to the embodiment includes a purchase information acquisition unit 151, a video acquisition unit 152, an estimation unit 153, a calculation unit 154, and a linking unit 155. The purchase information acquisition unit 151 acquires purchase information related to the purchase of goods at the facility. The video acquisition unit 152 acquires video data captured by cameras installed at the facility. The estimation unit 153 estimates movement estimation data that shows the trajectory of people's movements related to the purchase information based on the video data. The calculation unit 154 calculates movement count information that shows the number of times a person moves in each passage of the facility, and dwelling information that shows the dwelling status of people in each area of ​​the facility, based on the movement estimation data. The linking unit 155 links the purchase information, the movement count information, and the dwelling information.

[0083] Here, movement frequency information is used to determine whether or not products placed in each aisle of the facility were noticed by customers passing through the aisle. In addition, dwell time information is used to determine the degree of customer interest or concern towards products placed in each area of ​​the facility. As a result, the information processing device 100 can provide information on customer awareness of products in the facility, and information on the degree of customer interest or concern towards products in the facility. Therefore, the information processing device 100 can provide useful information for marketing in the facility. Furthermore, because the information processing device 100 can provide useful information for marketing in the facility, it can contribute to achieving Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0084] Furthermore, the calculation unit 154 calculates movement count information for each area of ​​the facility based on the number of times a person passes through each area provided in each passageway of the facility.

[0085] This allows the information processing device 100 to provide information regarding customer awareness of products in each area located in each passageway of the facility.

[0086] Furthermore, the calculation unit 154 calculates the average of the coordinates of the movement estimation data for each predetermined time period, and calculates dwell time information by summing up the probability distributions centered on the calculated average.

[0087] As a result, the information processing device 100 can provide dwelling information that visually and appropriately represents the dwelling status of people.

[0088] Furthermore, the probability distribution is a normal distribution.

[0089] As a result, the information processing device 100 can provide dwelling information that visually and appropriately represents the dwelling status of people.

[0090] Furthermore, the information processing device 100 includes an input unit 130 that accepts input of the type of probability distribution. The calculation unit 154 calculates dwell time information by summing up the types of probability distributions accepted by the input unit 130.

[0091] As a result, the information processing device 100 can provide dwelling information that visually and appropriately represents the dwelling status of people in a manner desired by the user.

[0092] Furthermore, the information processing device 100 includes an input unit 130 that receives input of condition information indicating the conditions for extracting movement estimation data. The calculation unit 154 calculates movement count information and dwell time information based on the movement estimation data according to the condition information.

[0093] As a result, the information processing device 100 can provide movement count information and dwell time information according to the extraction conditions desired by the user.

[0094] Furthermore, the conditional information includes at least one of the following: information that can identify a product, information about the date and time of purchase of a product, information that can identify a facility, information about a person's age, information about a person's gender, or information about a person's companions.

[0095] As a result, the information processing device 100 can provide information on the number of movements and dwell time corresponding to at least one of the following: information that can identify a product, information that can identify a product and the date and time of purchase of the product, information that can identify a facility, information that can identify a person's age, information that can identify a person's gender, or information that can identify a person's companions.

[0096] Furthermore, the information processing device 100 is further equipped with an output unit 140 that outputs a visually associated map of the facility and information on the number of moves.

[0097] This makes it easy for the information processing device 100 to visually grasp information such as which areas of the facility have a lot of or little movement of people.

[0098] Furthermore, the information processing device 100 is equipped with an output unit 140 that outputs a visually associated map of the facility and dwell time information.

[0099] This makes it easy for the information processing device 100 to visually grasp information such as which areas of the facility have a high or low concentration of people.

[0100] [8. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 21. The following explanation will use the information processing device 100 as an example. Figure 21 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0101] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The arithmetic unit 1030 can be implemented using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array).

[0102] The primary storage device 1040 is a memory device, such as RAM (Random Access Memory), that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and can be implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. The secondary storage device 1050 may also be a removable storage medium such as USB (Universal Serial Bus) memory or SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), NAS (Network Attached Storage), file server, etc.

[0103] The output I / F 1060 is an interface for transmitting information to be output to output devices 1010, such as displays, projectors, and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input I / F 1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, keypads, buttons, and scanners, and is implemented using, for example, USB.

[0104] Furthermore, the output interface 1060 and input interface 1070 may be wirelessly connected to the output device 1010 and input device 1020, respectively. In other words, the output device 1010 and input device 1020 may be wireless devices.

[0105] Furthermore, the output device 1010 and the input device 1020 may be integrated as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as an input / output I / F.

[0106] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0107] The network interface 1080 receives data from other devices via network N and sends it to the computing unit 1030, and also transmits data generated by the computing unit 1030 to other devices via network N.

[0108] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output interface 1060 and the input interface 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0109] For example, when computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 150 by executing a program loaded onto the primary storage device 1040. Alternatively, the arithmetic unit 1030 of computer 1000 may load a program obtained from another device via the network interface 1080 onto the primary storage device 1040 and execute the loaded program. Furthermore, the arithmetic unit 1030 of computer 1000 may cooperate with other devices via the network interface 1080 and call and use program functions, data, etc., from other programs on other devices.

[0110] [9. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0111] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0112] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0113] For example, the information processing device 100 described above may be implemented using multiple server computers, and depending on the function, it may be implemented by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, allowing for flexible configuration changes.

[0114] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent. [Explanation of Symbols]

[0115] 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Marketing Information Storage Unit 130 Input section 140 Output section 150 Control Unit 151 Purchase Information Acquisition Section 152 Video Acquisition Unit 153 Estimation Department 154 Calculation Unit 155 String attachment part

Claims

1. A purchase information acquisition unit that acquires purchase information regarding the purchase of goods at the facility, A video acquisition unit that acquires video data captured by a camera installed in the aforementioned facility, Based on the aforementioned video data, an estimation unit estimates movement path estimation data that shows the trajectory of the person's movements related to the purchase information, Based on the aforementioned movement estimation data, a calculation unit calculates movement count information indicating the number of times the person moves in each passage of the facility, and dwell time information indicating the dwell time of the person in each area of ​​the facility. A linking unit that links the aforementioned purchase information, the aforementioned number of movements information, and the aforementioned dwell time information, Equipped with, The calculation unit described above, Based on the number of times the person passes through each area provided in each passage of the facility, the movement count information in each area of ​​the facility is calculated, and the average of the coordinates of the movement estimation data for predetermined time intervals is calculated, and the dwell time information is calculated by summing the probability distributions centered on the calculated average. Information processing device.

2. The aforementioned probability distribution is a normal distribution. The information processing apparatus according to claim 1.

3. The system further includes an input unit that accepts input of the type of probability distribution, The calculation unit described above, The dwell time information is calculated by summing the probability distributions of the types received by the input unit. The information processing apparatus according to claim 1.

4. The system further includes an input unit that accepts input of conditional information indicating the extraction conditions for the aforementioned movement path estimation data, The calculation unit described above, Based on the movement estimation data corresponding to the condition information, the number of movements and the dwell time information are calculated. The information processing apparatus according to claim 1.

5. The aforementioned conditional information includes at least one of the following: information that can identify the product, information regarding the date and time of purchase of the product, information that can identify the facility, information regarding the age of the person, information regarding the gender of the person, or information regarding the person's companions. The information processing apparatus according to claim 4.

6. Output unit that outputs a visual correspondence between the map of the facility and the travel count information. The information processing apparatus according to claim 1, further comprising:

7. Output unit that outputs a visual correspondence between the map of the facility and the dwell information. The information processing apparatus according to claim 1, further comprising:

8. The calculation unit described above, Based on the purchase information, movement frequency information, and dwell time information linked by the linking unit, at least one of the following is performed: an analysis of the awareness level of the product, an analysis of the purchasing trend of the product, or an analysis related to the optimization of the placement of the product in the facility. The information processing apparatus according to claim 1.

9. An information processing method implemented by a program executed by an information processing device, A purchase information acquisition process that acquires purchase information regarding the purchase of goods at a facility, A video acquisition process for acquiring video data captured by a camera installed in the aforementioned facility, An estimation step is performed to estimate movement data showing the trajectory of the person's movements related to the purchase information, based on the aforementioned video data. A calculation process that calculates movement count information indicating the number of times the person moves in each passage of the facility, and dwelling information indicating the dwelling status of the person in each area of ​​the facility, based on the movement estimation data. A linking process that links the aforementioned purchase information, the aforementioned number of movements information, and the aforementioned dwell time information, Includes, The calculation process described above is: Based on the number of times the person passes through each area provided in each passage of the facility, the movement count information in each area of ​​the facility is calculated, and the average of the coordinates of the movement estimation data for predetermined time intervals is calculated, and the dwell time information is calculated by summing the probability distributions centered on the calculated average. Information processing methods.

10. Procedure for obtaining purchase information regarding the purchase of goods at a facility, A video acquisition procedure for acquiring video data captured by a camera installed in the aforementioned facility, An estimation procedure for estimating movement data showing the trajectory of a person associated with the purchase information, based on the aforementioned video data, A calculation procedure for calculating movement count information indicating the number of times the person moves in each passage of the facility, and dwelling information indicating the dwelling status of the person in each area of ​​the facility, based on the aforementioned movement path estimation data, A linking procedure for linking the aforementioned purchase information, the aforementioned number of movements information, and the aforementioned dwell time information, Have the computer run it, The above calculation procedure is: Based on the number of times the person passes through each area provided in each passage of the facility, the movement count information in each area of ​​the facility is calculated, and the average of the coordinates of the movement estimation data for predetermined time intervals is calculated, and the dwell time information is calculated by summing the probability distributions centered on the calculated average. Information processing program.

Images