JP5731766B2 - Loss opportunity analysis system and analysis method - Google Patents

Loss opportunity analysis system and analysis method Download PDF

Info

Publication number
JP5731766B2
JP5731766B2 JP2010159962A JP2010159962A JP5731766B2 JP 5731766 B2 JP5731766 B2 JP 5731766B2 JP 2010159962 A JP2010159962 A JP 2010159962A JP 2010159962 A JP2010159962 A JP 2010159962A JP 5731766 B2 JP5731766 B2 JP 5731766B2
Authority
JP
Japan
Prior art keywords
analysis
store
information
opportunity loss
sales opportunity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2010159962A
Other languages
Japanese (ja)
Other versions
JP2012022528A (en
Inventor
昌徳 小林
昌徳 小林
Original Assignee
株式会社野村総合研究所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社野村総合研究所 filed Critical 株式会社野村総合研究所
Priority to JP2010159962A priority Critical patent/JP5731766B2/en
Publication of JP2012022528A publication Critical patent/JP2012022528A/en
Application granted granted Critical
Publication of JP5731766B2 publication Critical patent/JP5731766B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Description

  The present invention relates to a technology such as data information processing for analyzing the situation of visitors (such as customers) of a facility such as a store, and in particular, a captured video of a monitoring camera installed in a retail store or the like or image analysis information thereof. The present invention relates to a technology that is effective when applied to a system for analyzing sales opportunity loss and the like.

  At present, surveillance cameras and surveillance camera systems (hereinafter sometimes simply referred to as “surveillance cameras”) are installed and used for crime prevention purposes in various facilities such as retail stores such as supermarkets and convenience stores. Yes. Surveillance cameras continue to be highly functional and high performance, and cameras having various functions are provided to the market.

  As a function of the surveillance camera, in addition to the basic function of shooting and recording images inside and outside the facility (moving images), as an additional function, a moving object is selected based on image analysis processing on the captured moving images. There are a function to detect and a function to detect an object such as a person or a face based on the detected feature of the moving object. Furthermore, there are some which have a function of detecting each part such as a person's face and estimating attributes such as the sex and age of the person from the features.

  How to use the data information obtained by using the surveillance camera for purposes other than crime prevention depends on the needs of the installation facility. For example, it is conceivable to use the data information obtained from the monitoring camera for the purpose of business management, marketing, advertising, etc. for retail stores. In particular, it is conceivable to utilize the data information from the monitoring camera in comparison with data of a POS (Point of Sales) system such as merchandise inventory management information and sales performance information.

  For example, retail stores require judgment and decision-making related to product inventory management, such as the content and timing of product purchase / display (additional replenishment), and the timing of such sales. There is a need to optimize in balance with opportunity loss. Therefore, it is conceivable that the sales information loss (or potential demand) is quantified by using data information obtained from the monitoring camera and used for store management and the like.

  JP-A-2001-331875 (Patent Document 1) (consumer behavior monitor device, etc.) is an example of the prior art relating to the estimation of the above-mentioned loss of merchandise sales. This consumer behavior monitoring device is based on a drop-in detection device that detects a customer's visit to the sales floor, a POS terminal that manages customer purchase information, and purchases products even if the customer visits the sales floor based on the drop-in information and purchase information. And an analysis terminal that measures the sales opportunity loss that has not been performed (claim 1). Further, it is described that the stop detection device is a camera, a weight sensor, an infrared sensor, or an ultrasonic sensor attached to a sales floor (claim 2). Further, it is described that the loss of sales opportunity is determined by collating face images from the camera (claim 4).

JP 2001-331875 A

  In retail stores and the like, there are occasions when the store inventory (number of displays) of products is too small or too large. If it is too small, it will lead to problems such as loss of sales opportunities (decrease in sales). If the amount is too large, it may lead to problems such as inventory holding costs and product disposal (for example, food disposal). A sales opportunity loss is typically a case where, for example, there is a customer who stops by a specific aisle or product shelf in the store, but the product desired by the customer is not purchased because it is out of stock. Is mentioned. In particular, even if merchandise is displayed at the storefront, there is data that the sales opportunity loss is increased by that amount if a certain quantity or more is not secured. On the other hand, if a large number of products are purchased and displayed in order to eliminate / reduce the sales opportunity loss, the consumer can naturally purchase with sufficient margin, but this leads to problems such as disposal due to unsold products. It is also required to reduce this value using the discard rate (the number of discards) as one criterion.

  In conventional retail stores, etc., the above-mentioned judgment regarding product inventory management (balance and optimization of merchandise inventory and sales opportunity loss) depends primarily on empirical and vague judgments by store staff and other people. The part was big. On the other hand, secondly, in the case where the above-mentioned determination is supported or automated using a computer system, conventionally, the determination has been made mainly based on product sales performance information (POS data, etc.) by a POS system or a product inventory management system. It was broken. By referring to and analyzing the POS data and the like, it is possible to obtain information such as what products are sold well to what kind of customers at what timing. Such information is effective for making the above-described determination of merchandise inventory management.

  However, in the prior art, there is room for improvement with respect to the loss of sales opportunities and the problem of disposal, in any of the above-mentioned human / computer judgments.

  In the case of using the above computer (POS system etc.), it is only possible to grasp the information (such as the number of products purchased) by the customer who purchased the product, and not the case where the customer did not purchase the product. It was. That is, it was impossible to accurately analyze the situation of sales opportunity loss including cases where customers did not purchase products.

  In Patent Document 1, a stop detection device (camera, sensor, etc.) detects a stop of a consumer (customer) at a store by signal processing (paragraph 0013). When detecting with a camera as a stop detection device, a general method using a background difference / interframe difference or a person detection method is used (paragraph 0020). Further, the value of the opportunity loss is calculated based on the difference between the number of people visiting the store (product shelf) and the number of product purchases (paragraph 0023, FIG. 2). It also describes that a consumer's face image is taken with a camera in the vicinity of the POS terminal, and is transmitted to the analysis terminal via the network and stored together with information (gender, age, etc.) input at the POS terminal (paragraph). 0025 etc.).

  In Patent Document 1, there is a lack of specific explanation for realizing an effective and problem-free form when measuring a loss of opportunity using a camera. There is also a problem with respect to handling of shooting data information by the camera from the viewpoint of privacy and the like. For example, it is necessary to pay attention to transmission of shooting data (such as a person's face image) and POS terminal input information on a network and storage in a database. In addition, in the case of detection using a sensor, there is a high possibility that the number of persons is erroneously detected when there are a plurality of people, such as at the time of congestion. Moreover, in patent document 1 etc., viewpoints, such as merchandise disposal, are not described in detail.

  In view of the above, an object of the present invention is to provide product inventory related to product inventory management (store management management, etc.) using data captured by a surveillance camera in a facility such as a store or data analysis information thereof. To provide a system and the like that can obtain useful indexes (index values related to sales opportunity loss, etc.) with respect to the balance between sales loss and sales opportunity loss and optimization decisions in a form that is accurate and has no problem in terms of privacy, etc. is there. The above and other objects and novel features of the present invention will be apparent from the description of this specification and the accompanying drawings.

  In order to achieve the above object, a representative embodiment of the present invention is built in or connected to a surveillance camera system including a surveillance camera for photographing a predetermined photographing range of a store (facility), and sales opportunities for products in the store It is a sales opportunity loss analysis system having an analysis server for analyzing loss, and has the following characteristics.

  For example, the surveillance camera system includes an analysis unit that outputs analysis information including information on the position of a person in a frame region corresponding to the imaging range, by analysis processing of a moving image to be analyzed captured by the surveillance camera. For example, the analysis unit or the analysis server includes a drop-in situation calculation unit that performs a process of calculating the number of drop-off persons for each region unit and time unit in the frame region using the analysis information. For example, an information processing system including a terminal device (POS register, etc.) in a store holds management information (POS data, etc.) indicating the inventory and sales status of merchandise in the store. For example, the analysis server includes: a collection unit that collects information including analysis information including the number of visitors from the surveillance camera system; and management information from the information processing system of the store; And an analysis unit that performs an analysis process on the sales opportunity loss of the product in the store and outputs analysis result information including an index value of the sales opportunity loss.

  According to a typical embodiment of the present invention, for product inventory management (store management management, etc.) using data information obtained from a video captured by a monitoring camera in a facility such as a store or analysis information thereof. It is possible to obtain a useful index (index value related to loss of sales opportunity, etc.) relating to the balance between the merchandise inventory and the sales opportunity loss and the optimization decision (index value related to loss of sales opportunity, etc.) with high accuracy and without any problem from the viewpoint of privacy.

It is the figure which showed the outline | summary about the structural example of the sales opportunity loss analysis system which is one embodiment of this invention. It is the figure shown about the calculation formula of various data information and sales opportunity loss in one embodiment of this invention. It is the figure which showed the example of the graph of various data information as an analysis result in one embodiment of this invention. It is a figure for demonstrating the calculation method of the number of people in a stop in one embodiment of this invention. It is a figure for demonstrating the calculation methods, such as a stand-by degree and a stand-by location, in one embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the sales opportunity loss analysis system 100 (FIG. 1) according to an embodiment of the present invention, (A) analysis of a person (customer) in the video of the shooting range 35 of the surveillance camera system (30, 20) of the store 50. Loss of sales opportunity related to products in the shooting range 35 of the store 50 using the information (24, 61) and (B) data (41, 62) corresponding to the POS system (POS register 40) of the store 50 Analytical processing is performed, and the index value of sales opportunity loss is calculated with high accuracy.

  Specifically, (A) is information such as the number of customers visiting the area (sections, etc.) associated with the product. (B) is information such as the number of stocks, the number of sales, the number of purchasers (actual results), etc., related to the product associated with the area (section, etc.). In (C), an index value of sales opportunity loss is obtained by a predetermined calculation based on the relevance of each information of (A) and (B) (FIG. 2).

[System configuration]
FIG. 1 shows an outline of a configuration example of an analysis system 100 according to an embodiment of the present invention. The analysis system 100 includes an analysis server 10 connected to a network 90 such as the Internet, and an information processing system for each of a plurality of stores 50. The information processing system of each store 50 includes a surveillance camera system (surveillance camera server 20, surveillance camera 30), a POS register 40, and the like.

  One or more surveillance cameras 30 are installed in the store 50. The surveillance camera 30 captures a predetermined capturing range 35. Each surveillance camera 30 is connected to the surveillance camera server 20. The monitoring camera server 20 may be configured inside the store 50 or may be configured outside the store 50 via the network 90 or the like. The store 50 has a POS cash register 40. The analysis server 10 is connected to the monitoring camera server 20 and the POS register 40 via the network 90. The analysis server 10 is configured as a system on the network 90, and a plurality of stores 50 can be analyzed. The analysis server 10 is shown as being implemented as a device / system independent of the information processing system such as the monitoring camera server 20 of each store 50. It may be mounted integrally.

  The store 50 is, for example, a supermarket or a convenience store store. The plurality of stores 50 are, for example, the same type of facility, such as a chain store. The imaging range 35 of the monitoring camera 30 is for a predetermined fixed space area in the store 50, for example. In the present embodiment, the imaging range 35 is a three-dimensional area including passages, product shelves, etc. (sections) in the store 50 (FIG. 4, 301). A moving image shot for the shooting range 35 by the monitoring camera 30 is recorded in the monitoring camera server 20 as moving image data 23.

  The monitoring camera server 20 includes, for example, a computer system and each unit of the monitoring camera control unit 21 and the image analysis unit 22 implemented by a software program, and each data or database of the moving image data 23 and the analysis information 24. The monitoring camera server 20 has a function of recording a moving image taken by the monitoring camera 30 as moving image data 23. Further, the surveillance camera server 20 performs image analysis processing by the image analysis unit 22 based on the moving image data 23, so that a moving person, its face and other objects in the area of the shooting range 35, and its moving image. It has a known function (person detection function and flow line detection function) that can detect a line (trajectory) or the like. The processing content of the image analysis unit 22 and the like can be variably set based on the setting information. Analysis information 24 by the image analysis unit 22 (person detection function and flow line detection function) is recorded in the monitoring camera server 20. Furthermore, the image analysis unit 22 may have a known function for estimating the attributes (gender, age group, etc.) of the detected person. In this case, the attribute information is included in the analysis information 24.

  The monitoring camera server 20 controls the monitoring camera 30 by the monitoring camera control unit 21. This control may include, for example, execution / stop of photographing by the monitoring camera 30, setting or changing the photographing range 35, changing photographing conditions such as exposure. In particular, it is possible to set a desired shooting range 35 by changing the orientation of the monitoring camera 30 or the like.

  In the present embodiment, the image analysis unit 22 includes a drop-in situation calculation unit 25. As a part of the detection function, the drop-in situation calculation unit 25 is based on information such as a person and a flow line as a result of the detection function, and the person (store visitor) in the area (division etc.) of the shooting range 35 A process of calculating the situation such as the number of people on the stop (d) is performed. Information such as the number of visitors (d) of the processing result is included in the analysis information 24.

  In the image analysis unit 22 (stopping state calculation unit 25), from the captured video (moving image data 23) of the surveillance camera 30, a trend / situation such as a person's stoppage / leaving, etc. As such information, it has a function to analyze and detect with high accuracy. The analysis information 24 including the detected person information (date and time, place (sections, etc.), number of people (stop number (d)), attributes, etc.) is utilized as text data. For example, it is possible to determine the number of visitors (d) and the like for a plurality of customers who are concentrated on a specific product shelf or section at the time of congestion without erroneous detection.

  In the present embodiment, the monitoring camera server 20 is provided with the above-described person / flow line detection function, a stop-by state calculation function, and the like, and the analysis server 10 (analysis unit 12) has the above function (analysis information 24). Use it to realize sales opportunity loss analysis. As another embodiment, the analysis server 10 may be provided with the above-described function (particularly, the drop-in situation calculation unit 25) and may be realized in the same manner. In this case, for example, the analysis information 61 to be exchanged includes person / flow line information and the like, and the drop-in situation calculation unit on the analysis server 10 side processes the analysis information 61 to obtain the drop-in number (d) and the like. It becomes.

  The surveillance camera server 20 has a function of transmitting a part of data (analysis information 61) in a text data format to the analysis server 10 via the network 90 based on the analysis information 24 held. At this time, the moving image data 23 and the like are not transmitted. The analysis information 61 does not include customer visitor personal information.

  The POS register 40 is a cash register device having a function corresponding to the POS system, and records / holds information on merchandise accounting (at the time of sale) as POS data 41. The POS cash register 40 differs depending on the corresponding POS system / model, etc., but has a function (recording management function) for recording / managing product sales (purchase) results (sales information (b)), product inventory information (stock information). (A)) a function to record / manage (inventory management function), a function to input and record purchaser attribute information (gender, age group, etc.) by a store clerk (attribute management function) (not required), etc. Have. The POS register 40 of the store 50 may be an information processing system including a store computer, a network communication device, etc., or connected to an external inventory management system, an electronic money system (for example, a system using an IC card), or the like. -It may be a linked system. For example, the point-of-sale information may be recorded as the POS data 41 in accordance with an accounting operation and processing using an IC card.

  The POS data 41 is realized by a database or the like, and has inventory information (a), sales information (b), disposal information (c), and the like in this embodiment. The sales information (b) may include attribute information of the purchaser.

  The POS cash register 40 has the above-mentioned sales management function and attribute management function such as information such as store, date / time (time zone), product, quantity, customer group (attribute), etc. b)) is recorded as a part of the POS data 41.

  As the inventory management function (or inventory management system or the like), the POS register 40 records information (stock information (a)) such as the quantity of goods purchased and displayed in the store 50 as part of the POS data 41. Further, the present function or system may determine information (stock information (a)) such as the quantity of goods purchased or displayed based on the sales information (b). As this function or system, it is desirable to grasp the display quantity of merchandise (store inventory) in the store 50.

  As the disposal information (c), information such as date and quantity in the case of disposal of merchandise is managed. The discard information (c) may be managed by another information processing system, or may not be managed for the purpose of calculating the sales opportunity loss only.

  The POS register 40 has a function of transmitting a part of data (POS data 62) in the text data format to the analysis server 10 via the network 90 based on the stored POS data 41. At this time, the POS data 62 does not include personal information of customers.

  The analysis server 10 is configured by, for example, a computer system, and includes each unit of the collection unit 11 and the analysis unit 12 implemented by a software program, and each data or database of the collection information 13 and the analysis result 14. As a result, the analysis system 100 has a function of calculating information (71) on the loss of sales opportunity of the product in the area of the shooting range 35 from the moving image taken by the monitoring camera system (30, 20). Although not shown, the analysis server 10 includes setting means for setting various types of information by operations of an administrator or the like, and can set a processing target frame, time, determination threshold value, and the like.

  The collection unit 11 collects and acquires various data information (61, 62) necessary for processing in the analysis unit 12 from the monitoring camera server 20 and the POS register 40 of each store 50 via the network 90, Aggregated in units such as date and time and stored as collected information 13. The information to be collected includes, for example, a store, date and time, person / flow line (stopping situation such as the number of people (d) visiting), person attributes (sex, age group, etc.), POS system related information, and the like. In particular, the collection unit 11 receives the text data of the analysis information 61 (including the number of visitors (d)) from the monitoring camera server 20, and the POS data 62 (stock information (a), sales) from the POS register 40. Text data (including information (b), discard information (c), etc.) is received.

  This analysis system 100 has a mechanism that takes into account the privacy of customers (consumers) and portrait rights. In the surveillance camera system (30, 20), the captured moving image data 23 is deleted without being stored for a long time by real-time processing, and the analysis information 24 (not including information infringing on privacy, etc.) of the moving image data 23 is also included. In addition, text data (analysis information 61) is exchanged on the network 90. The data (analysis information 61) does not include information infringing on privacy, such as an image of a person (store visitor). In addition, the same information (POS data 62) as the conventional one is exchanged from the POS register 40. The data (POS data 62) also does not include information infringing on privacy, such as an image of a person (purchaser).

  The analysis unit 12 uses the collected information 13 (a, b, c, d, etc.) to perform analysis / calculation processing on the sales opportunity loss index value (f), the disposal index value (g), etc. 2), and store and output the result as the analysis result 14. The analysis result 14 includes information on an index value (f) for sales opportunity loss (sales opportunity loss information 71), information on an index value for disposal (discard information 72), and the like. Further, the analysis unit 12 may create a graph in which various data information including the index value (f) of the sales opportunity loss is collected and may include it as the analysis result 14 (described later, FIG. 3).

  The processing content of the analysis unit 12 can be variably designated and set by an administrator or the like. For example, an analysis unit (one hour unit, one product unit, one section unit, etc.), a determination condition, a threshold value, or the like can be designated. The analysis server 10 (analysis unit 12 or the like) may perform statistical processing based on the collected information 13. That is, the information of each of the plurality of stores 50 may be statistically processed and analyzed. For example, an administrator or the like may designate a store, date and time, a product (section), a customer segment (attribute), and the like as an analysis target.

  The analysis result 14 has a format that can be browsed by, for example, an administrator of the corresponding store 50. The analysis result 14 can be acquired, for example, by being transmitted to the information processing system or the like of the corresponding store 50 or accessed from the information processing system or the like of the corresponding store 50.

  Depending on the facility such as the store 50, the POS cash register 40 (function of the POS system or the like) may not be provided. In that case, the analysis server 10 cannot acquire the POS data 62, but from the function obtained by calculating the equivalent of the POS data 62 by the predetermined information processing on the collected information 13 or the other information processing system on the analysis server 10 side. This can be realized by providing a function for acquiring the POS data 62 equivalent.

[Various data information and calculation formulas]
FIG. 2 shows an example of calculation formulas for various data information (a to g) and a sales opportunity loss index value (f) in the present embodiment. The unit of each numerical value is per predetermined time (for example, 1 hour) and per product (corresponding area unit).

  a is the number of items in stock (the number of store stock, the number of displays, etc.). Corresponding is the inventory information (a) of the POS data 41 of FIG.

  b is the number of products sold (number of purchases) or the number of purchasers (actual value). Corresponding is the sales information (b) of the POS data 41 of FIG.

  c is the number of discarded products. Corresponding is the discard information (c) of the POS data 41 in FIG. In general, c can be calculated from the difference (ab) between a and b.

  d is the number of people to drop by. d is calculated by the drop-in situation calculation unit 25 and included in the analysis information 24 (61). Based on the analysis / detection of the person / flow line in the image analysis unit 22, it can be calculated by determining / counting the number of persons coming and going in / out of the region associated with the product (described later).

  e is a purchase rate of goods. e can be calculated from the POS data 41 (a, b, etc.) and the number of visitors (d).

  f is an index value of sales opportunity loss. f is included in the opportunity loss information 71. Basically, in a certain product (corresponding region) and a certain time zone, if the number of stocks (a) or the number of purchasers (b) is small and the number of people visiting (d) is large, it is considered that the sales opportunity loss increases.

  g is an index value of the discard rate. g is included in the discard information 72. Basically, in a certain product (corresponding region) and a certain time zone, if the number of inventory (a) is large and the number of visitors (d) is small, the discard rate (inventory holding cost etc.) is considered to be large.

  An example of the calculation formula for the index value (f) of the sales opportunity loss is as follows.

  (1) As a first calculation formula, [Opportunity loss (f)] = [Number of people on the way (d)] × [Purchase rate (e)]. As a condition, it is calculated when [the number of stocks (a)] = 0 (or less than a predetermined threshold at) and (AND) and [the number of visitors (d)]> 0 (or more than a predetermined threshold dt). To do.

  The above condition is, for example, the case where the number of store inventory (display) is 0 and the number of people in the store (d) is one or more for the product on the product shelf in the target section in the store 50. . As an example of calculation, in the case of selling a specific product P in the target section K, the number of visitors (d) is 10 per hour, and the purchase rate (e) of the product P is 20%. In some cases, the sales opportunity loss index value (f) is 10 × (1−0.2) = 8.

  As a second calculation formula, the calculation can be roughly made from the difference (d−a) between the number of people visiting (d) and the number of purchasers (b). As an example of calculation, in the case of selling a specific product P in the target section K, the number of visitors (d) is 10 people per hour, and the number of purchasers (b) of the product P is 2 people. In this case, the index value (f) of the sales opportunity loss is 10−2 = 8.

[Example of analysis]
FIG. 3 shows an example of analysis performed by the analysis unit 12 with respect to a certain store 50, a certain date (24 hours), a certain product (area unit such as a corresponding section), and various data information (a, The example of a graph which calculated b, c, d, f) is shown. In the graph example of FIG. 3, the horizontal axis is in units of 1 hour (h). Each value is converted per hour and per product (corresponding area).

  In FIG. 3, it can be seen that the sales opportunity loss (f) is large in a time zone (timing) such as 9 o'clock to 10 o'clock and 12 o'clock to 15 o'clock. That is, at this timing, there is no or little stock quantity (a) in the product (region) even though there is a visitor visit to the product (region) (the number of visitors (d)> 0). Not connected to purchase (sales volume (b) is low).

  In addition to the example of FIG. 3, it is also possible to specify the AND conditions such as “Monday”, “20's”, and “male” using the attribute information and the like, and perform the same analysis.

[Calculation of the number of people on the stop]
FIG. 4 is an explanatory diagram illustrating an example of a method for calculating the number of people in the stop (d) in the stop state calculation unit 25. In the present analysis system 100, based on the moving image data 23 (analysis information 24), for each area unit such as a section K corresponding to the arrangement configuration such as the product P and the shelf E in the store 50, and for each time zone, Determine and count the number of people (customers) visiting (d). The section K (its boundary line) and the like can be variably set by the analysis system 100 (setting means).

  301 is an example of a frame area corresponding to the photographing range 35, and K (K1 to K3) is a section such as a passage, and E (E1 to E4) is a shelf (commodity shelf) as a background area (in the absence of a person). , P (P2) is an example of a product. A broken line indicates a boundary line of the section K. Note that the section K may be set uniformly without distinguishing the shelf E or the passage in the frame area.

  Reference numeral 310 denotes an example of a flow line indicating a change in a time series (frame time or the like) of the position of a person on the background area. A triangular mark indicated by 311 on the flow line 310 indicates an example of the current position (coordinates) of the person on the frame image. The flow line information is, for example, coordinate information indicating the position of a person for each predetermined frame unit in time series.

  The drop-in situation calculation unit 25 uses information on the person's flow line (coordinate information, etc.) obtained based on the person's analysis / detection in the frame area of the shooting range 35 for each section K unit indicated by the boundary line. The entry / exit and retention of the person is determined, and the number of people on the stop (d) is counted. For example, the intersection between the boundary line and the flow line, or the overlap between the current person position (coordinates) and the region unit is determined by geometric calculation. Furthermore, it is possible to determine and calculate the stop time and the degree of stop (degree of congestion and quietness). In the frame region of the shooting range 35, the section K having a large number of people on the stop (d) indicates a portion with a high degree of stop.

  Reference numeral 302 denotes a region in a two-dimensional space associated with a frame region 301 in the case of a three-dimensional space. The arrangement configuration in the store 50 is looked down on from above, and information such as flow lines are superimposed. Depending on the installation of the monitoring camera 30 and the setting of the shooting range 35, the target can be made two-dimensional in this way. For example, the shooting range 35 may be set in a direction in which the product shelf is viewed from the front. Further, a predetermined association / conversion process may be performed between the three-dimensional information and the two-dimensional information. By making it two-dimensional, for example, it is possible to make information easy for an administrator or the like to see when outputting.

[Calculation of degree of drop-off / stop-point]
FIG. 5 is an explanatory diagram showing an example of the method of calculating the degree of stop and the location of the stop in the stop state calculation unit 25. In this example, the frame area is divided into units such as a plurality of rectangular blocks as in 501, and the degree of falling is determined and calculated for each divided area unit. Reference numeral 501 denotes an example in which a frame area 301 is divided into 64 blocks 510 of 8 × 8 in the vertical and horizontal directions. In place of the section K, the number of people to stop by (d) is calculated in block 510 units.

  For example, 511 indicates an example in which a block with a high degree of stop is extracted as a result of calculation. The method of calculating the degree of drop-in is, for example, using the information of the flow line 310 illustrated in FIG. 4 to determine the overlap between the flow line (current position coordinates) of each person in the target frame group and the block 510. Then, for the overlapping blocks, the numerical value related to the stop-by degree is counted. Then, for example, based on a comparison between the value of the degree of stop and a predetermined threshold, a block having a large value of the degree of stop is extracted.

  Further, when there are a large number of the extracted blocks, clustering processing may be performed to collect the extracted blocks. As a clustering method, a known technique such as a K-average method can be used. By collecting the cluster set, it becomes easy for a human to identify a portion where the degree of falling in the frame region of the shooting range 35 is high.

  Reference numeral 502 denotes a case where the above-described extracted block or cluster set is displayed in a circle as a location with a high degree of stoppage (stoppage portion). The extracted block, cluster set, or drop-in place (circle) is associated with a specific section K, shelf E, product P, or the like in the frame area of the shooting range 35.

[Effects]
As described above, according to the present embodiment, the information obtained from the captured moving image data 23 or the analysis information 24 of the monitoring camera 30 in the facility such as the store 50, the POS register 40, and the like. Use data information to provide accurate and useful information on the balance between product inventory and loss of sales opportunities related to business management of stores 50 and optimization decisions (index values related to loss of sales opportunities, etc.) From the point of view, it can be obtained without any problem.

  As a result, the analysis result 14 can be reflected in the business management of the store 50 (product inventory management, etc.). For example, it can be used for examination of the arrangement of products and advertisements in the store 50. Alternatively, data may be automatically input to a POS system or an inventory management system to adjust the quantity of goods purchased / displayed. Thereby, an increase in sales and a reduction in the discard rate can be realized.

  In the present embodiment, unlike the prior art disclosed in Patent Document 1 and the like, information used for analysis (information exchanged via the network) does not include data captured by the camera, but only includes information on the position of a person. Since the analysis information (text data) is used, there is no problem in terms of privacy.

  As mentioned above, the invention made by the present inventor has been specifically described based on the embodiment. However, the present invention is not limited to the embodiment, and various modifications can be made without departing from the scope of the invention. Needless to say.

  The present invention is particularly applicable to a fixed camera system for the purpose of store management and the like.

DESCRIPTION OF SYMBOLS 10 ... Analysis server, 11 ... Collection part, 12 ... Analysis part, 13 ... Collection information, 14 ... Analysis result,
20 ... Surveillance camera server, 21 ... Surveillance camera control unit, 22 ... Image analysis unit, 23 ... Moving image data, 24 ... Analysis information, 25 ... Stopping state calculation unit,
30 ... surveillance camera, 35 ... shooting range,
40 ... POS cash register, 41 ... POS data,
50 ... store,
61 ... analysis information, 62 ... POS data,
71 ... opportunity loss information, 72 ... discard information,
100: Analysis system.

Claims (11)

  1. A sales opportunity loss analysis system that is built in or connected to a camera system that includes a camera that captures a predetermined shooting range of a store, and that analyzes a sales opportunity loss of store products,
    The information including at least one of the position, attribute, dwell time, or flow line of the person in the frame region corresponding to the shooting range is obtained by the analysis processing of the moving image to be analyzed shot by the camera. An analysis unit that performs a process of calculating the situation of the person's stop in the frame region, and outputs analysis information including the state of the stop;
    Using analysis information including the state of the stop which is data in a format not including the personal information of the person, and POS data of the product of the store which is data in a format not including the personal information of the person, A sales opportunity loss analysis system comprising: an analysis unit that performs an analysis process on a sales opportunity loss of a product in a store and outputs analysis result information including an index value of the sales opportunity loss.
  2. A system having an analysis server that is built in or connected to a camera system that includes a camera that captures a predetermined shooting range of a store, is connected to an information processing system that includes a terminal device of the store, and analyzes a loss in sales opportunities of the products in the store A sales opportunity loss analysis system,
    The camera system or the analysis server obtains at least one of a position, an attribute, a residence time, or a flow line of a person in a frame area corresponding to the shooting range by analyzing a moving image to be analyzed shot by the camera. obtaining information including, based on the information, performs a process of calculating the status of visiting of a person in the frame area, has an analysis unit which outputs the analysis information including the status of the stop-off Ri,
    An information processing system including the terminal device of the store holds POS data of the product of the store,
    The analysis server
    A collection unit that collects information including the analysis information including the drop-in status and POS data of the merchandise of the store in a format not including personal information regarding the person;
    Using the collected information, an analysis unit that performs an analysis process on a sales opportunity loss of the product of the store and outputs analysis result information including an index value of the sales opportunity loss. Opportunity loss analysis system.
  3. In the sales opportunity loss analysis system according to claim 1 or 2,
    The analysis unit performs a process of calculating the number of people approaching in at least one unit for each region unit or for each time unit in the frame region,
    The analysis unit performs an analysis process on a sales opportunity loss of the product of the store, including a calculation using the number of people at the stop and a numerical value based on the POS data of the product of the store as a variable. A sales opportunity loss analysis system characterized by outputting analysis result information including an index value.
  4. In the sales opportunity loss analysis system according to claim 1,
    The analysis unit calculates the number of people in the stop as the stop state,
    The analyzing unit, the store and shopper times of the analyte, with respect to the analyzed items and area unit to be associated to the product, using the number (d) of the stop by, the purchase rate (e), (F) = (d) × (e) to calculate the sales opportunity loss index value (f).
  5. In the sales opportunity loss analysis system according to claim 1,
    The analysis unit calculates the number of people in the stop as the stop state,
    The analyzing unit, the store and shopper times of the analyte, with respect to the analyzed items and area unit to be associated to the product, using the number (d) of the stop by the buyer number and (b) , (F) = (d) − (b) to calculate the index value (f) of the sales opportunity loss, the sales opportunity loss analysis system.
  6. In the sales opportunity loss analysis system according to claim 1,
    Wherein the analysis unit uses the information including the position or the flow line before Symbol human product, determining the least and out of the one unit or overlapping person area unit or time unit in the frame region of the image capturing range in counting the number of visiting in person the unit, the analysis system sales opportunities loss to output the status of the stop by containing the number of visiting in the unit, characterized by.
  7. In the sales opportunity loss analysis system according to claim 6,
    Wherein the analysis unit, in the frame region of the image capturing range, corresponding to the arrangement of the store, for each partition units arbitrarily set, the number of the visiting calculated, including the number of visiting in the partition units Output the status of the stop,
    The analysis unit of the sales opportunity loss, wherein the analysis unit calculates an index value of the sales opportunity loss for each of the division units.
  8. In the sales opportunity loss analysis system according to claim 6,
    The analysis unit, in the frame region of the image capturing range, for each block divided into a plurality, the number of the visiting calculated, and outputs the status of the stop by containing the number of visiting in the block,
    The analysis unit for sales opportunity loss, wherein the analysis unit calculates an index value of the sales opportunity loss for each block unit.
  9. In the sales opportunity loss analysis system according to claim 1,
    Connected to an information processing system including the terminal device of the store,
    An information processing system including a terminal device of the store, and manage the POS data items from previous SL store,
    The analyzing unit analyzes the system sales opportunity loss, characterized in that, using the POS data of an information processing system including the in the form of data that does not include personal information of the person, the terminal apparatus of the store.
  10. A sales opportunity loss analysis method that analyzes sales opportunity loss of store products by information processing of a computer built in or connected to a camera system including a camera that captures a predetermined shooting range of the store,
    As a step executed by information processing of the computer,
    The information including at least one of the position, attribute, dwell time, or flow line of the person in the frame region corresponding to the shooting range is obtained by the analysis processing of the moving image to be analyzed shot by the camera. Based on the analysis step of calculating the situation of the person's stop in the frame region, and outputting analysis information including the stop situation;
    Using analysis information including the state of the stop which is data in a format not including the personal information of the person, and POS data of the product of the store which is data in a format not including the personal information of the person, A sales opportunity loss analysis method comprising: an analysis step of performing an analysis process on a sales opportunity loss of a product in a store and outputting analysis result information including an index value of the sales opportunity loss.
  11. Loss of opportunity for sales of merchandise at stores due to information processing by a computer that includes an analysis server that is built in or connected to a camera system that includes a camera that captures a predetermined shooting range of the store and that is connected to an information processing system that includes the terminal device A sales opportunity loss analysis method,
    As a step executed by information processing of the computer,
    The information including at least one of the position, attribute, dwell time, or flow line of the person in the frame region corresponding to the shooting range is obtained by the analysis processing of the moving image to be analyzed shot by the camera. based on an analysis step of said performs a process of calculating the status of visiting of a person in a frame region, and outputs the analysis information including the status of the stop-off Ri,
    A first collection step for collecting the analysis information including the situation of the drop-in in a form not including personal information about the person;
    A second collection step of collecting the POS data of the store product in a format not including personal information about the person from an information processing system including a terminal device of the store that holds the POS data of the store product; ,
    Using the collected information, an analysis step of performing an analysis process on a sales opportunity loss of the product of the store and outputting analysis result information including an index value of the sales opportunity loss, Opportunity loss analysis method.
JP2010159962A 2010-07-14 2010-07-14 Loss opportunity analysis system and analysis method Active JP5731766B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2010159962A JP5731766B2 (en) 2010-07-14 2010-07-14 Loss opportunity analysis system and analysis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2010159962A JP5731766B2 (en) 2010-07-14 2010-07-14 Loss opportunity analysis system and analysis method

Publications (2)

Publication Number Publication Date
JP2012022528A JP2012022528A (en) 2012-02-02
JP5731766B2 true JP5731766B2 (en) 2015-06-10

Family

ID=45776769

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2010159962A Active JP5731766B2 (en) 2010-07-14 2010-07-14 Loss opportunity analysis system and analysis method

Country Status (1)

Country Link
JP (1) JP5731766B2 (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5356615B1 (en) 2013-02-01 2013-12-04 パナソニック株式会社 Customer behavior analysis device, customer behavior analysis system, and customer behavior analysis method
JP6261197B2 (en) * 2013-06-17 2018-01-17 キヤノン株式会社 Display control apparatus, display control method, and program
US10163115B2 (en) 2013-09-19 2018-12-25 Panasonic Intellectual Property Corporation Of America Control method for displaying merchandising information on information terminal
US9799044B2 (en) * 2013-12-26 2017-10-24 Panasonic Intellectual Property Corporation Of America Control method, and control system
WO2015162723A1 (en) * 2014-04-23 2015-10-29 株式会社日立製作所 Behavior analysis device
JP5881022B1 (en) * 2014-09-11 2016-03-09 パナソニックIpマネジメント株式会社 Product monitoring device, product monitoring system and product monitoring method
JP5942173B2 (en) * 2014-11-05 2016-06-29 パナソニックIpマネジメント株式会社 Product monitoring device, product monitoring system and product monitoring method
JP6161011B2 (en) * 2015-08-04 2017-07-12 パナソニックIpマネジメント株式会社 Facility management support apparatus, facility management support system, and facility management support method
IT201700017690A1 (en) * 2017-02-17 2018-08-17 Centro Studi S R L PROCESS TOOL Intelligent system for controlling processes that govern the sale of goods and services

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0652191A (en) * 1992-08-03 1994-02-25 Hitachi Ltd Device and method for analyzing commodity data
JP2001331875A (en) * 2000-05-24 2001-11-30 Nec Corp Consumer behavior monitoring device and consumer behavior monitoring method used for the device
JP2003256843A (en) * 2002-02-26 2003-09-12 Oki Electric Ind Co Ltd Measurement system
JP2003256720A (en) * 2002-03-06 2003-09-12 Masatoshi Shoji Sales promotion method and sales promotion system
JP2009265830A (en) * 2008-04-23 2009-11-12 Toshiba Corp In-store behavior analyzing device and method

Also Published As

Publication number Publication date
JP2012022528A (en) 2012-02-02

Similar Documents

Publication Publication Date Title
US7933797B2 (en) Purchase selection behavior analysis system and method
US7100824B2 (en) System and methods for merchandise checkout
US9262832B2 (en) Cart inspection for suspicious items
US9740937B2 (en) System and method for monitoring a retail environment using video content analysis with depth sensing
US8009863B1 (en) Method and system for analyzing shopping behavior using multiple sensor tracking
US20070067220A1 (en) System and methods for tracking consumers in a store environment
US20080114633A1 (en) Method and Apparatus for Analyzing Activity in a Space
US8189926B2 (en) Method and system for automatically analyzing categories in a physical space based on the visual characterization of people
US8229781B2 (en) Systems and apparatus to determine shopper traffic in retail environments
US9418352B2 (en) Image-augmented inventory management and wayfinding
US7474330B2 (en) System and method for integrating and characterizing data from multiple electronic systems
US20090083121A1 (en) Method and apparatus for determining profitability of customer groups identified from a continuous video stream
US9076149B2 (en) Shopper view tracking and analysis system and method
WO2010044338A1 (en) Information providing device, information providing method, and recording medium
US7617981B2 (en) Method and system for targeted marketing by leveraging video-based demographic insights
WO2015033577A1 (en) Customer behavior analysis system, customer behavior analysis method, non-temporary computer-readable medium, and shelf system
US7652687B2 (en) Still image queue analysis system and method
TW200841737A (en) Video analytics for banking business process monitoring
JP4621716B2 (en) Human behavior analysis apparatus, method and program
JP2016184410A (en) Ordering method and processing method
US8560357B2 (en) Retail model optimization through video data capture and analytics
US20140043162A1 (en) Inventory system for the prevention of tobacco product theft
US20130030875A1 (en) System and method for site abnormality recording and notification
US20060259346A1 (en) Trolley tracker
US20140100916A1 (en) Allocating commodity shelves in a supermarket

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20130607

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20140715

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20140722

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20140912

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20141007

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20141125

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20141216

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20150227

A911 Transfer of reconsideration by examiner before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20150309

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20150331

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20150410

R150 Certificate of patent or registration of utility model

Ref document number: 5731766

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250