Analysis apparatus, analysis method, program, and analysis system

Abstract

To provide an analysis apparatus, an analysis method, a program, and an analysis system capable of accurately analyzing by what kind of factors an opportunity loss is caused.SOLUTION: An analysis apparatus comprises: an acquisition unit for acquiring a plurality of area images obtained by capturing a plurality of areas that are different; a counting unit for outputting a counting result indicating a result of counting the number of people appearing in the area image for each of the areas; and an analysis unit for performing an analysis regarding opportunity loss in a specific area among the plurality of areas based on the relationship between the counting results in the plurality of areas.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an analysis device, an analysis method, a program, and an analysis system for performing analysis on opportunity losses. [Background technology]

[0002] In a store that sells products, for example, if sales of a product displayed in a specific location within the store are poor, it is considered that a sales opportunity loss for that product has occurred. Conventionally, technologies for reducing sales opportunity loss have been proposed in order to increase sales. For example, Patent Document 1 discloses an analysis system that uses a camera to capture a predetermined shooting range within a store, calculates the status of visits to a specific area based on the positions, attributes, dwell times, or movement lines of people captured within the shooting range, and analyzes sales opportunity loss based on the results. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5731766 Summary of the Invention [Problem to be solved by the invention]

[0004] For example, if a product displayed in a specific location in a store is experiencing a sales opportunity loss, there may be several factors that could be the cause. Specific examples of factors include the following: · Customers are not coming to a particular location. The product does not match the customer. · There are customers but no products on display.

[0005] Each of the above-mentioned factors is thought to be caused by multiple additional factors. For example, one example of an additional factor that can cause the factor "customers are not coming to a particular location" is that the particular location is located in a secluded area of ​​the store, making it difficult for customers to reach.

[0006] As described above, sales opportunity losses are caused by many factors. The present disclosure aims to provide an analysis device, an analysis method, a program, and an analysis system that can accurately analyze the factors that are causing the opportunity losses. [Means for solving the problem]

[0007] An analysis device according to one aspect of the present disclosure includes an acquisition unit that acquires a plurality of area images obtained by photographing a plurality of different areas, a counting unit that outputs a counting result indicating the result of counting the number of people appearing in the area image for each of the areas, and an analysis unit that performs an analysis regarding opportunity loss in a specific area among the plurality of areas based on the relationship between the counting results in the plurality of areas. [Effects of the Invention]

[0008] According to the present disclosure, it is possible to accurately analyze what factors are causing opportunity losses. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram illustrating an example of the overall configuration of an analysis system according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a schematic diagram showing a shopping mall as a first application example of the analysis system. [Figure 3] FIG. 10 is a diagram showing a specific example of analyzing the causes of sales opportunity losses at store A in a shopping mall according to application example 1. [Figure 4] A diagram showing an example of one city block as application example 3 of the analysis system being applied to urban development. [Figure 5] FIG. 1 is a diagram illustrating an example of the operation of an analysis device. [Figure 6] Block diagram showing an example of the hardware configuration of an analysis device DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0011] [Summary of this disclosure] The present disclosure relates to an analysis device, an analysis method, a program, and an analysis system for analyzing opportunity losses. The analysis device of the present disclosure includes an acquisition unit that acquires multiple area images obtained by capturing multiple different areas, a counting unit that counts the number of people appearing in the area images for each area and outputs a counting result indicating the result, and an analysis unit that performs an analysis of opportunity losses in a specific area among the multiple areas based on the relationship between the counting results for the multiple areas.

[0012] The analysis device of the present disclosure derives the relationship between counting results in multiple areas and analyzes opportunity losses based on the relationship, thereby enabling accurate analysis of the causes of opportunity losses in a specific area.

[0013] [Overall configuration] 1 is a block diagram showing an example of the overall configuration of an analysis system 100 according to an embodiment of the present disclosure. As shown in FIG. 1, the analysis system 100 includes a plurality of cameras 1 and an analysis device 2.

[0014] The cameras 1 each capture an image of a different area to generate a plurality of area images, and the cameras 1 transmit the generated area images to the analysis device 2 via a wired or wireless network.

[0015] The analysis device 2 uses a plurality of area images acquired from a plurality of cameras 1 to perform an analysis of opportunity loss in a specific area among the plurality of areas.

[0016] The analysis device 2 is a computer such as a personal computer (PC), a workstation, or a tablet terminal. The analysis device 2 has a plurality of functional blocks as a functional configuration. In the example shown in Fig. 1, the analysis device 2 includes an acquisition unit 21, a counting unit 22, a trajectory detection unit 23, an analysis unit 24, a notification unit 25, an improvement processing unit 26, an attribute information generation unit 27, and a joint position information generation unit 28.

[0017] The acquisition unit 21 acquires, from the camera 1 via a network, a plurality of area images obtained by capturing a plurality of different areas.

[0018] The counting unit 22 counts the number of people appearing in the region image for each region, and outputs a counting result indicating the counting result.

[0019] The trajectory detection unit 23 detects the trajectory of a person who appears in area images captured during a predetermined period of time, as the person moves over time. The trajectory detection unit 23 may use a known technique such as optical flow as a method for detecting the trajectory of the person.

[0020] The counting unit 22 may use the movement trajectories detected by the trajectory detection unit 23 to count the movement trajectories that are similar to each other within the region image for each region, and output the result as the counting result.

[0021] The analysis unit 24 performs an analysis of opportunity loss in a specific area among the multiple areas based on the relationship between the counting results in the multiple areas. For example, the analysis unit 24 performs the analysis based on a comparison result obtained by comparing a first counting result in an area image of a first area among the multiple areas with a second counting result in an area image of a second area other than the first area. Here, the first area or the second area may be the same area as the specific area that is the target of the opportunity loss analysis, or may be a different area.

[0022] It should be noted that which of the multiple regions is to be the specific region may be determined in advance by the user of analysis system 100 before analysis by analysis unit 24.

[0023] Notification unit 25 notifies the user of analysis system 100 of the analysis results of analysis by analysis unit 24. Notification unit 25 is, for example, a display device, and notifies the analysis results in various formats such as text, figures, and tables.

[0024] The improvement processing unit 26 executes improvement processing to improve opportunity losses in specific areas based on the analysis results of the analysis performed by the analysis unit 24.

[0025] The attribute information generation unit 27 generates attribute information indicating the attributes of a person appearing in the area image. In this specification, the attribute of a person refers to at least one of the gender and age (generation) of the person. The attribute information generation unit 27 generates the attribute information of the person appearing in the area image, for example, using a trained machine learning model. In this example, the trained machine learning model is trained using, as training data, a plurality of training images in which people appear and correct labels indicating the attributes of the people appearing in each of the training images. When a region image is input, the trained machine learning model outputs attribute information of the person appearing in the region image.

[0026] The counting unit 22 outputs the counting results of counting the number of people for each region image and for each attribute based on the attribute information output by the attribute information generating unit 27. In this case, the analysis unit 24 performs analysis based on the counting results for each region image and for each attribute.

[0027] The joint position information generation unit 28 generates joint position information indicating the joint positions of a person appearing in the region image. The joint position information generation unit may estimate the joint positions of the person using, for example, a known person posture estimation method, and generate the joint position information based on the estimated joint positions. Alternatively, the joint position information generation unit 28 may generate the joint position information of the person appearing in the region image using, for example, a trained machine learning model.

[0028] Further based on the joint position information output by the joint position information generating unit 28, the analyzing unit 24 analyzes opportunity losses in a specific region.

[0029] [Application example] The detailed operation of the analysis system 100 will be described below using application examples in which the analysis system 100 is applied to various facilities.

[0030] (Application example 1) Application example 1 is an example in which analysis system 100 is applied to a shopping mall. Fig. 2 is a schematic diagram showing a shopping mall as application example 1 of analysis system 100. In application example 1, the shopping mall is located in a three-story building. Escalators are provided between the first and second floors, and between the second and third floors.

[0031] Each floor has multiple stores. In the example shown in Figure 2, six stores A to F are located on the third floor, six stores G to L are located on the second floor, and three stores M to O are located on the first floor. There is an entrance on the first floor.

[0032] Multiple cameras 1 are installed inside the shopping mall. The multiple cameras 1 capture images of different areas within the shopping mall and generate area images. The areas are preferably areas within the shopping mall through which people visiting the shopping mall, i.e., customers, pass. Examples of such areas include the entrance to the shopping mall building, the entrances to each store in the shopping mall, passageways for moving between stores on each floor, and routes between floors. In the example shown in FIG. 2, an escalator is shown as an example of a route between floors, but other examples may include stairs or an elevator.

[0033] The area images generated by the cameras 1 are transmitted to the analysis device 2 via a network. The analysis device 2 performs various analyses using the area images captured over a predetermined period of time. The predetermined period may be, for example, one hour, one day, one week, or one month, and is set in advance by a shopping mall operator or other user of the analysis system 100.

[0034] A specific example of the analysis that can be performed by the analysis device 2 will be described.

[0035] The analysis device 2 can use area images of multiple areas included in the route from the entrance of the shopping mall to a specific store to perform analysis to identify issues that need to be resolved in order to reduce lost sales opportunities at the specific store.

[0036] For example, if the specific store is store A shown in FIG. 2, the analysis device 2 performs analysis using area images of at least the following areas included in the travel route from the entrance to store A. Entrance to the entire shopping mall Inside the escalator going from the first floor to the second floor Inside the escalator going from the second floor to the third floor Entrance to Store A In addition to these, the analysis device 2 may also perform analysis using, for example, the passage on the first floor from the entrance to the escalator entrance, or the passage on the third floor from the escalator exit on the third floor to store A. Furthermore, if the entire shopping mall has multiple entrances, the analysis may be performed using area images of all of the entrances.

[0037] For example, the analysis device 2 counts the number of customers for each attribute based on an area image of the entrance of a shopping mall. The analysis device 2 can analyze whether or not the number of customers of the gender or age group that the operator of the shopping mall expects as customers are visiting the shopping mall.

[0038] Here, the analysis device 2 can count customers who enter through the entrance separately from customers who exit through the entrance by detecting the movement trajectory of customers based on multiple area images taken within a predetermined period of time.

[0039] Furthermore, the analysis device 2 counts the number of people who have visited the second floor, for example, based on an image of the area inside an escalator going from the first floor to the second floor. Here, by capturing images of the ascending escalator and the descending escalator with different cameras 1, it is possible to count customers moving from the first floor to the second floor separately from customers moving from the second floor to the first floor.

[0040] Based on the number of people who have visited the second floor, analysis device 2 can analyze whether a sufficient number of people have visited the second floor. Similarly, analysis device 2 can analyze whether a sufficient number of people have visited the third floor, for example, based on an image of the area inside an escalator going from the second floor to the third floor.

[0041] Furthermore, the analysis device 2 counts the number of customers who visit the store A, for example, based on an area image of the entrance of the store A. This makes it possible to analyze whether a sufficient number of people are visiting the store A.

[0042] Furthermore, the analysis device 2 can perform a more detailed analysis based on the counting results of area images of multiple areas included in the movement route from the entrance to the store A.

[0043] For example, the analysis device 2 can calculate the number or percentage of customers who visited the shopping mall but did not visit the second floor based on the counting results of the area image of the entrance and the area image inside the escalator going up from the first floor to the second floor. In the following explanation, the number of customers who visited the shopping mall but did not visit the second floor, in other words, the number of customers who decreased from the entrance to the second floor, is referred to as the decrease number N to the second floor. dec_2F The percentage of customers who did not visit the second floor among those who visited the shopping mall, in other words, the percentage of customers who decreased from the entrance to the second floor, is called the decrease rate to the second floor R dec_2F It is written as follows.

[0044] The total number of customers who visited the shopping mall is N Total The number of customers who visited the second floor is N 1F→2F If there are people, the number of reductions is Ndec_2F can be calculated using equation (1). N dec_2F =N Total -N 1F→2F (1)

[0045] In addition, the reduction rate R dec_2F can be calculated using equation (2). R dec_2F =(N Total -N 1F→2F ) / N Total (2)

[0046] The analysis device 2 can calculate the number or percentage of customers who visited the second floor but did not visit the third floor based on the area image inside the escalator going up from the second floor to the third floor. In the following description, the number of customers who visited the second floor but did not visit the third floor, in other words, the decrease in the number of customers who visited the second floor until they reached the third floor, is referred to as the decrease in the number of customers to the third floor, N dec_3F The percentage of customers who visited the second floor who did not visit the third floor, in other words, the percentage of customers who decreased from the second floor to the third floor, is called the decrease rate to the third floor R. dec_3F It is written as follows.

[0047] The number of customers who visited the third floor is N 2F→3F If there are people, the number of reductions is N dec_3F can be calculated using equation (3). N dec_3F =N 1F→2F -N 2F→3F (3)

[0048] In addition, the reduction rate R dec_3F can be calculated using equation (4). R dec_3F =(N 1F→2F -N 2F→3F ) / N 1F→2F (4)

[0049] The analysis device 2 can calculate the number or percentage of customers who visited the third floor but did not visit store A, based on the area image of the entrance to store A. In the following description, the number of customers who visited the third floor but did not visit store A, in other words, the number of customers who decreased from visiting the third floor until they reached store A, is referred to as the decrease in number N dec_StoreA The percentage of customers who visited the third floor but did not visit store A, in other words, the percentage of customers who decreased between visiting the third floor and store A, is the decrease rate to store A R dec_StoreA It is written as follows.

[0050] The number of customers who visited store A is N StoreA If there are people, the number of reductions is N dec_StoreA can be calculated using equation (5). N dec_StoreA =N 2F→3F -N StoreA (5)

[0051] In addition, the reduction rate R dec_StoreA can be calculated using equation (6). R dec_3F =(N 2F→3F -N StoreA ) / N 2F→3F (6)

[0052] In this way, the analysis device 2 performs analysis based on the first counting result for the first region that is relatively close to store A and the second counting result for the second region that is relatively close to the entrance, within the travel route from the entrance of the shopping mall to store A as the specific region. In the above example, if the inside of the escalator that goes from the first floor to the second floor is the first region, then the entrance to the entire shopping mall is the second region. If the inside of the escalator that goes from the second floor to the third floor is the first region, then the adjacent regions, the inside of the escalator that goes from the first floor to the second floor, is the second region. If the entrance to store A is the first region, then the adjacent regions, the inside of the escalator that goes from the second floor to the third floor, is the second region.

[0053] The analysis device 2 then calculates the number of decreases or the rate of decrease between adjacent areas. This makes it possible to analyze in which areas customers who visit the shopping mall but do not visit store A occur. The number of decreases corresponds to the difference value in the present disclosure. The rate of decrease corresponds to the rate of change in the number of people in the present disclosure.

[0054] In the analysis device 2, for example, a threshold value for determining the number of decreases or the rate of decrease is set in advance. In the following description, the threshold value for the number of decreases is referred to as Th Ndec , the threshold for the number of decreases is Th Rdec It is written as follows.

[0055] Analysis device 2 can analyze which area is the cause of lost sales opportunities in store A, a specific area, by comparing the number of decreases or the rate of decrease in each area included in the travel route to store A with a threshold. When the number of decreases or the rate of decrease in a certain area is equal to or greater than the threshold, analysis device 2 analyzes that the area is at least one of the causes of lost sales opportunities in store A.

[0056] A more specific explanation will be given using numerical values. Fig. 3 is a diagram showing a specific example of analyzing the causes of sales opportunity losses at store A in the shopping mall of application example 1.

[0057] Suppose the total number of customers who visit the shopping mall per hour is 1,000. Of these, 500 customers visit the second floor. Of these, 50 customers visit the third floor. Of these, 10 customers visit store A.

[0058] In this case, the number of reductions to the second floor is N dec_2F is 1000-500=500. The reduction rate to the second floor R dec_2F is (1000-500) / 1000=0.5. The number of reductions to the third floor, N dec_3F is 500-50=450. The reduction rate to the third floor R dec_3F is (500-50) / 500=0.9. The number of reductions to store A is Ndec_StoreA The reduction rate for store A is R. dec_StoreA is (50-10) / 50=0.8.

[0059] Here, the threshold value of the decrease number Th Ndec is 300, the number of reductions to the second floor N dec_2F and the number of reductions to the third floor, N dec_3F is greater than or equal to the threshold value. Rdec is 0.7, the reduction rate to the third floor R dec_3F and the reduction rate R for store A dec_StoreA is greater than or equal to the threshold. In FIG. 3, values ​​that are greater than or equal to the threshold are shown surrounded by dashed lines.

[0060] In this case, the analysis device 2 analyzes, based on the number of decreases, that the fact that few customers who visited the shopping mall visited the second floor and that few customers who visited the second floor visited the third floor are factors contributing to lost sales opportunities at store A. Furthermore, based on the rate of decrease, the analysis device 2 analyzes, based on the rate of decrease, that the fact that few customers who visited the second floor visited the third floor and that few customers who visited the third floor visited store A are factors contributing to lost sales opportunities at store A. The analysis device 2 may perform analysis based on either the number of decreases or the rate of decrease, or may perform analysis based on both. In the example of FIG. 3 , when the analysis device 2 performs analysis based on both, it may analyze that the fact that both the number of decreases and the rate of decrease are above a threshold, and that there is little movement of customers from the second floor to the third floor, is a factor contributing to lost sales opportunities at store A. Alternatively, the analysis device 2 may analyze an area where either the number of decreases or the rate of decrease is above a threshold, as a factor contributing to lost sales opportunities at store A.

[0061] The analysis device 2 notifies the user of the analysis system 100 of the analysis results. Specifically, the analysis device 2 displays the analysis results on a display device or the like. Alternatively, the analysis device 2 may transmit the analysis results as factors behind the sales opportunity loss at store A to a PC or mobile terminal device used by the user. This allows the user to develop measures to efficiently improve opportunity loss in a specific area.

[0062] Furthermore, based on the analysis results, the analysis device 2 executes an improvement process to reduce lost sales opportunities in the specific area, namely, store A. The improvement process is performed, for example, by the analysis device 2 executing various applications for the improvement process. Note that the application for the improvement process may be executed by the analysis device 2 or another computer communicably connected to the analysis device 2.

[0063] A specific example will be given below. For example, if it is analyzed that the reason for the loss of sales opportunities is that few customers who visit the second floor also visit the third floor, the analysis device 2 executes an application that controls the display content of an electronic bulletin board (signage) in a shopping mall. In this case, the display content controlled by the analysis device 2 is, for example, content that guides customers on the second floor to the third floor.

[0064] The analysis device 2 may also execute an application that controls the content of the audio played from speakers in the shopping mall. In this case, the content of the audio controlled by the analysis device 2 guides customers on the second floor to the third floor.

[0065] (Application example 2) Application example 2 is an example in which analysis system 100 is applied to one store.

[0066] A store is equipped with a number of fixtures, each displaying merchandise. A number of cameras 1 are installed inside the store. The cameras 1 capture images of different areas within the store and generate area images. The areas are preferably areas within the store where customers pass through. Examples of such areas include aisles within the store, product viewing spaces in front of display shelves, and cash registers.

[0067] The analysis device 2 can perform an analysis to identify issues that need to be resolved to reduce sales opportunity losses in the specific product viewing space, using area images of multiple areas included in the movement route from the store entrance to the specific product viewing space. Specifically, the analysis device 2 performs the analysis using area images of at least the store entrance, the specific product viewing space, and the aisle connecting them. If there are multiple movement routes from the store entrance to the specific product viewing space, the analysis device 2 can perform the analysis using area images of the aisles included in all of the movement routes.

[0068] Based on the attribute information of customers who have visited a specific product viewing space, the analysis device 2 can analyze whether customers with attributes that match the products displayed on the display shelves corresponding to the specific product viewing space are visiting. Specifically, if the products displayed on the display shelves corresponding to the specific product viewing space are boys' toys, the analysis device 2 counts the number of male customers of the child age group or customers of the parent age group who have children, among the customers who have visited the specific product viewing space. This allows the analysis device 2 to analyze whether a sufficient number of customers who match the products are visiting the product viewing space corresponding to boys' toys.

[0069] If the analysis device 2 analyzes that customers who match the product are not visiting a specific product viewing space sufficiently, it may execute an application that guides customers in the store to move to that product viewing space.

[0070] Furthermore, the analysis device 2 may calculate the number or rate of decrease in each area based on the counting results for each area included in the movement path from the store entrance to the specific product viewing space. This makes it possible to analyze whether customers who visit the store are able to reach the specific product viewing space sufficiently.

[0071] When the analysis device 2 analyzes that a customer who has visited the store has not been able to reach a specific product viewing space sufficiently, the analysis device 2 may execute an application that guides the customer in the store to the product viewing space.

[0072] The analysis device 2 may also generate joint position information of customers who visit a specific product viewing space and analyze whether the customers are picking up and browsing products based on the joint position information. The analysis device 2 may determine whether the customers are picking up and browsing products based on, for example, the position of the customers' hands or elbows indicated by the joint position information. When a customer is picking up and browsing products, it is considered that the customer is sufficiently interested in the products. Therefore, the analysis device 2 can analyze whether the products displayed on the shelves corresponding to a specific product viewing space are sufficiently matched to the customers visiting the product viewing space, based on the number of customers picking up and browsing products.

[0073] When the analysis device 2 analyzes that the products displayed on the shelves corresponding to a specific product viewing space are not sufficiently matched to the customers visiting that product viewing space, the analysis device 2 may execute an application that automatically places an order to replace the products displayed on the corresponding shelves with more suitable products.

[0074] (Application example 3) Application example 3 is an example in which analysis system 100 is applied to urban development.

[0075] FIG. 4 is a diagram showing an example of one city block as an application example 3 in which the analysis system 100 is applied to city development. In the example shown in FIG. 4, the analysis system 100 is applied to one city block including a station and a popular facility. In this case, the users of the analysis system 100 are the person in charge of the city development of the block, the manager of the local shopping district, etc.

[0076] In Application Example 3, multiple cameras 1 are placed within one city block. The multiple cameras 1 capture images of different areas within the block, and generate area images. An example of an area is a road leading from a station to a popular facility.

[0077] For example, if there are multiple travel routes from a station to a popular facility, the analysis device 2 acquires area images for each road that makes up the travel route. Then, analysis is performed based on the counting results of the multiple areas included in each travel route. In the example shown in Figure 4, three travel routes, travel routes 1 to 3, are possible.

[0078] For example, the analysis device 2 counts the number of people who travel to a popular facility via each travel route, thereby making it possible to identify travel routes that are frequently used to travel from a station to a popular facility.

[0079] In this case, the analysis device 2 can inform the user that it is possible to disperse the movement of people from the station to the popular facility, for example, by attracting stores with high customer attraction along a route with fewer people moving around.

[0080] [Example of operation] The following describes an example of the operation of the analysis device 2. FIG.

[0081] In step S1, the acquisition unit 21 of the analysis device 2 acquires a plurality of area images obtained by photographing a plurality of areas.

[0082] In step S2, the counting unit 22 counts the number of people appearing in the region image for each region and outputs the counting result. Note that in step S2, the counting unit 22 may generate the counting result by counting trajectories similar to each other within the region image using trajectories that have moved within the region and that have been detected by the trajectory detection unit 23.

[0083] In step S3, the analysis unit 24 analyzes opportunity loss in a specific area among the multiple areas based on the relationship between the counting results in the multiple area images. In step S3, the analysis unit 24 may also perform analysis based on a comparison result obtained by comparing a first counting result in an area image capturing a first area among the multiple areas with a second counting result in an area image capturing a second area other than the first area. The comparison result is, for example, a difference value (decrease value) between the first counting result and the second counting result, or a headcount fluctuation rate (decrease rate) obtained by dividing the difference value by the second counting result. This allows for accurate analysis of which area among the multiple areas included in the movement route to the specific area is the cause of opportunity loss in the specific area.

[0084] In step S3, the analysis unit 24 may perform analysis based on the attribute information of the person appearing in the region image generated by the attribute information generation unit 27. This allows for more accurate analysis of the factors behind opportunity loss in the specific region.

[0085] In step S3, the analysis unit 24 may perform the analysis based on the joint position information of the person appearing in the region image generated by the joint position information generation unit 28. This allows for a more accurate analysis of the causes of opportunity loss in the specific region.

[0086] In step S4, the notification unit 25 notifies the user of the analysis system 100 of the analysis results of the analysis by the analysis unit 24. Note that in step S4, instead of notifying the analysis results by the notification unit 25, improvement processing may be performed by the improvement processing unit 26. As described above, the improvement processing is various processing for improving opportunity loss in a specific area that is estimated based on the analysis results.

[0087] <Actions and Effects> As described above, the analysis device 2 according to an embodiment of the present disclosure includes an acquisition unit 21 that acquires a plurality of area images obtained by photographing a plurality of different areas, a counting unit 22 that outputs a counting result indicating the result of counting the number of people appearing in the area image for each area, and an analysis unit 24 that performs an analysis regarding opportunity loss in a specific area among the plurality of areas based on the relationship between the counting results in the plurality of areas.

[0088] According to the analysis device 2 according to the embodiment of the present disclosure, it is possible to accurately analyze which area is the cause of opportunity loss in a specific area.

[0089] [Example of hardware configuration for analyzer 2] FIG. 6 is a block diagram showing an example of a hardware configuration of the analysis device 2 according to the embodiment of the present disclosure.

[0090] The analysis device 2 is realized by various types of computers 300, such as a server device, a personal computer (PC), a workstation, a smartphone, or a tablet terminal. The computer 300 has a drive device 101, a storage device 102, a memory device 103, a processor 104, a user interface (UI) device 105, and a communication device 106, which are interconnected via a bus B.

[0091] The programs or instructions that realize the various functions and processes of the analysis device 2 may be stored in a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or flash memory. When the storage medium is set in the drive device 101, the programs or instructions are installed from the storage medium to the storage device 102 or memory device 103 via the drive device 101. However, the programs or instructions do not necessarily have to be installed from the storage medium, and may be downloaded from any external device via a network or the like.

[0092] The storage device 102 is realized by a storage device such as an HDD (Hard Disk Drive) or an SSD. The storage device 102 stores installed programs or instructions, as well as files, data, etc. used to execute the programs or instructions.

[0093] The memory device 103 is realized by a random access memory, a static memory, etc. When a program or an instruction is activated, the memory device 103 reads and stores the program or instruction, data, etc. from the storage device 102. The storage device 102, the memory device 103, and the removable storage medium may be collectively referred to as a non-transitory storage medium.

[0094] The processor 104 may be realized by one or more CPUs, which may be configured with one or more processor cores, GPUs (Graphics Processing Units), processing circuits, etc. The processor 104 executes various functions and processes of the analysis device 2 in accordance with programs, instructions, and data such as parameters required to execute the programs or instructions stored in the memory device 103.

[0095] The user interface (UI) device 105 may be composed of input devices such as a keyboard, mouse, camera, and microphone, output devices such as a display, speaker, headset, and printer, and input / output devices such as a touch panel. The UI device 105 provides an interface between the user and the analysis device 2. For example, the user operates the analysis device 2 by manipulating a GUI (Graphical User Interface) displayed on a display or touch panel using a keyboard, mouse, and the like.

[0096] The communication device 106 is realized by various communication circuits that execute wired or wireless communication processing with external devices, the Internet, a LAN (Local Area Network), a cellular network, or other communication networks.

[0097] The hardware configuration illustrated in FIG. 6 is merely an example, and the analysis device according to the present disclosure may be realized by any other appropriate hardware configuration.

[0098] Although examples of the present disclosure have been described in detail above, the present disclosure is not limited to the specific embodiments described above, and various modifications and changes are possible within the scope of the gist of the present disclosure as set forth in the claims. [Explanation of symbols]

[0099] 100 Analysis Systems 1 camera 2 Analyzer 21 Acquisition Department 22 Counting Unit 23 Trajectory detection unit 24 Analysis Department 25. Information Department 26 Improvement Department 27 Attribute information generation section 28 Joint position information generation unit

Claims

1. an acquisition unit that acquires a plurality of area images obtained by capturing a plurality of different areas; a counting unit that outputs a counting result indicating a result of counting the number of people appearing in the region image for each of the regions; an analysis unit that performs an analysis regarding opportunity loss in a specific area among the plurality of areas based on the relationship between the counting results in the plurality of areas; An analytical device comprising:

2. the acquisition unit acquires area images obtained by capturing images of multiple areas inside a facility; the analysis unit performs the analysis regarding opportunity losses of product sales in the specific area within the facility; The analytical device of claim 1 .

3. a trajectory detection unit configured to detect a movement trajectory of the person appearing in the area image for a predetermined period of time for each of the areas; the counting unit counts, for each of the regions, movement trajectories that are similar to each other within the region image and outputs the counting result. The analytical device according to claim 2 .

4. The analysis unit performs the analysis based on a comparison result obtained by comparing a first counting result in the regional image obtained by capturing a first region among the plurality of regions with a second counting result in the regional image obtained by capturing a second region other than the first region. The analytical device according to claim 3 .

5. the analysis unit performs the analysis based on the comparison result indicating a difference value between the first counting result and the second counting result. The analytical device according to claim 4 .

6. the analysis unit performs the analysis based on the counting results for a plurality of area images captured of a plurality of areas included in a movement route from an entrance of the facility to the specific area. The analytical device according to claim 5 .

7. the analysis unit performs the analysis based on the first counting result for the first area of ​​the movement path that is relatively close to the specific area and the second counting result for the second area that is relatively close to the entrance. The analytical device according to claim 6 .

8. The analysis unit analyzes that the opportunity loss has occurred in the first area when the difference value is equal to or greater than a threshold value set in advance for the first area. The analytical device according to claim 7 .

9. The analysis unit performs the analysis based on a fluctuation rate of the number of people obtained by dividing a difference between the first counting result and the second counting result by the second counting result for the first region and the second region adjacent to each other. The analytical device according to claim 7 .

10. The analysis unit analyzes that the opportunity loss has occurred in the first area when the headcount fluctuation rate is equal to or greater than a predetermined threshold value for the first area. The analytical device according to claim 9.

11. further comprising a notification unit that issues a notification when the analysis unit analyzes that the opportunity loss has occurred in the specific area. The analytical device of claim 1 .

12. an improvement processing unit that executes a process to improve the opportunity loss when the analysis unit analyzes that the opportunity loss has occurred in the specific area, The analytical device of claim 1 .

13. an attribute information generating unit that generates attribute information indicating attributes of people appearing in the region image; the analysis unit performs the analysis based on the counting results obtained by counting for each of the region images and for each of the attributes. The analytical device of claim 1 .

14. a joint position information generating unit that generates joint position information indicating joint positions of a person appearing in the region image, the analysis unit performs the analysis further based on the joint position information. The analytical device of claim 1 .

15. An analysis method for an analysis device that performs an analysis regarding opportunity loss in a specific area among a plurality of different areas, comprising: acquiring a plurality of area images obtained by photographing the plurality of areas; outputting a counting result indicating the result of counting the number of people appearing in the region image for each region; performing the analysis based on a relationship between the counting results in the plurality of regions; Analysis method.

16. A program executed by a computer of an analysis device that performs an analysis on opportunity losses in a specific area among a plurality of different areas, acquiring a plurality of area images by photographing the plurality of areas; a step of outputting a counting result indicating a result of counting the number of people appearing in the region image for each of the regions; performing the analysis based on the relationship between the counting results in the plurality of regions; A program that causes the computer to execute the above.

17. an acquisition unit that acquires a plurality of area images obtained by capturing a plurality of different areas; a counting unit that outputs a counting result indicating a result of counting the number of people appearing in the region image for each of the regions; an analysis unit that performs an analysis regarding opportunity loss in a specific area among the plurality of areas based on the relationship between the counting results in the plurality of areas; An analysis system comprising:

Images