Information processing system, information processing method and program

Abstract

This information processing system comprises an attribute identifying unit and a statistical processing unit. The attribute identifying unit processes a video relating to a facility to identify a plurality of attributes relating to each of a plurality of customers. The statistical processing unit uses at least one attribute included in the identified plurality of attributes to perform statistical processing relating to the plurality of customers. The at least one attribute includes a group activity attribute relating to customers who act in groups of a plurality of people.

Description

Information processing system, information processing method, and recording medium

[0001] The present invention relates to an information processing system, an information processing method, and a recording medium.

[0002] For example, Patent Document 1 discloses a counting system that can count the characteristics of non-users who did not perform a specified use among visitors to a specified location. Also, for example, Patent Document 2 discloses a system that calculates the number of people staying on each floor of a building for each attribute of the people.

[0003] Patent Document 3 describes a technology that calculates the feature values ​​of each of multiple key points of a human body contained in an image, searches for images containing human bodies with similar postures or movements based on the calculated feature values, and classifies images with similar postures or movements together.

[0004] International Publication No. 2009 / 041242 Japanese Patent Application Laid-Open No. 2017-218248 International Publication No. 2021 / 084677

[0005] Among customers at a typical facility, some customers act in groups of several people, while others act alone. Whether customers act in groups or alone can lead to differences in their purchasing behavior and other aspects of their behavior at the facility.

[0006] However, Patent Documents 1 and 2 do not disclose a technology for distinguishing between customers who act in groups and customers who act alone, making it difficult to grasp customer behavior in a facility according to this distinction. Patent Document 3 also does not disclose a technology for distinguishing between customers who act in groups and customers who act alone.

[0007] One example of the object of the present invention is to provide, in consideration of the above-mentioned problems, an information processing system, an information processing method, a program, a recording medium, etc. that solves the problem of understanding customer behavior in a facility depending on whether the customer acts in a group or alone.

[0008] According to one aspect of the present invention, an information processing system is provided, comprising: an attribute identification means for processing video related to a facility and identifying a plurality of attributes relating to each of a plurality of customers; and a statistical processing means for performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes, wherein the at least one attribute includes a group behavior attribute relating to customers who act in groups of multiple people.

[0009] According to one aspect of the present invention, there is provided an information processing method, comprising: one or more computers processing video related to a facility to identify a plurality of attributes relating to each of a plurality of customers; and performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes, wherein the at least one attribute includes a group behavior attribute relating to customers who act in groups of multiple people.

[0010] According to one aspect of the present invention, a recording medium is provided having recorded thereon a program that causes one or more computers to process video related to a facility to identify multiple attributes related to each of multiple customers, and perform statistical processing on the multiple customers using at least one attribute included in the identified multiple attributes, and causes the at least one attribute to include a group behavior attribute related to customers who act in groups of multiple people.

[0011] According to one aspect of the present invention, it is possible to grasp the behavior of customers in a facility depending on whether the customers are acting in a group or acting alone.

[0012] 1 is a diagram illustrating an overview of an information processing system according to a first embodiment. 2 is a diagram illustrating an overview of an information processing method according to the first embodiment. 3 is a diagram illustrating an example of a configuration of an information processing system according to the first embodiment. 4 is a diagram illustrating an example of a functional configuration of a video analysis device according to the first embodiment. 5 is a diagram illustrating an example of a functional configuration of an attribute identification unit according to the first embodiment. 6 is a diagram illustrating an example of a functional configuration of a statistical processing device according to the first embodiment. 7 is a diagram illustrating an example of a physical configuration of a video analysis device according to the first embodiment. 8 is a flowchart illustrating an example of video analysis processing according to the first embodiment. 9 is a flowchart illustrating an example of customer statistical processing according to the first embodiment. 10 is a diagram illustrating an example of a functional configuration of a video analysis device according to a second embodiment. 11 is a diagram illustrating an example of a functional configuration of an attribute identification unit according to the second embodiment. 12 is a flowchart illustrating an example of video analysis processing according to the second embodiment. 13 is a diagram illustrating an example of a functional configuration of a video analysis device according to a third embodiment. 14 is a diagram illustrating an example of a functional configuration of an attribute identification unit according to the third embodiment. 15 is a flowchart illustrating an example of video analysis processing according to the third embodiment.

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, like components are designated by like reference numerals, and the description thereof will be omitted as appropriate.

[0014] First Embodiment (Overview) Fig. 1 is a diagram illustrating an overview of an information processing system 100 according to a first embodiment. The information processing system 100 includes an attribute identification unit 134 and a statistical processing unit 143. The attribute identification unit 134 processes video related to a facility to identify multiple attributes related to each of multiple customers. The statistical processing unit 143 performs statistical processing on the multiple customers using at least one attribute included in the identified multiple attributes. The at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people.

[0015] According to this information processing system 100, it is possible to grasp the behavior of customers in a facility depending on whether the customers are acting in a group or acting alone.

[0016] 2 is a diagram illustrating an overview of an information processing method according to embodiment 1. The information processing method includes one or more computers processing a video related to a facility to identify a plurality of attributes related to each of a plurality of customers (step S103), and performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes. The at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people.

[0017] According to this information processing method, it is possible to grasp the behavior of customers in a facility depending on whether the customers are acting in a group or alone.

[0018] A detailed example of the information processing system 100 according to the first embodiment will be described below.

[0019] 3 is a diagram illustrating an example of the configuration of the information processing system 100 according to embodiment 1. The information processing system 100 is a system that processes a video related to a facility and identifies a plurality of attributes related to each of a plurality of customers included in the video.

[0020] Examples of facilities include, but are not limited to, convenience stores, supermarkets, department stores, and commercial complexes.

[0021] The information processing system 100 includes, for example, one or more image capture devices 101_1 to 101_M (M is an integer of 1 or more), a video storage device 102, a video analysis device 103, and a statistical processing device 104.

[0022] The image capturing devices 101_1 to 101_M, the video storage device 102, the video analysis device 103, and the statistical processing device 104 are connected to one another via a network NT, and transmit and receive information to and from one another via the network NT. The network NT may be configured from wired, wireless, or an appropriate combination of these communication lines, a device (not shown) that relays information, and the like.

[0023] (Regarding the image capturing devices 101_1 to 101_M according to the first embodiment) Each of the image capturing devices 101_1 to 101_M is, for example, a camera. Each of the image capturing devices 101_1 to 101_M is installed in and around a facility so as to capture an image of an image capturing area related to the facility. Each of the image capturing devices 101_1 to 101_M generates a video of the image capturing area. The video is, for example, a moving image composed of a plurality of frame images.

[0024] Photography areas related to a facility include, for example, the entrances and exits of the facility, areas within the facility where customers pass through, parking lots on the facility's premises, and a predetermined range from the facility's payment device (so-called cash register).

[0025] The term "entrance / exit" includes not only entrances and exits that are used both as an exit from the facility and as an entrance to the facility, but also entrances and exits that are used only as an exit from the facility or as an entrance to the facility. The predetermined range from the payment device also includes, for example, an area where customers line up to pay.

[0026] The image capturing devices 101_1 to 101_M transmit the generated video to, for example, the video storage device 102. Each of the image capturing devices 101_1 to 101_M may transmit video in real time. Alternatively, each of the image capturing devices 101_1 to 101_M may store the captured video and transmit the video captured during a period corresponding to a predetermined transmission time, or may receive a request and transmit the video captured during a period corresponding to the request. This request may be transmitted from any of the video storage device 102, the video analysis device 103, the statistical processing device 104, etc., based on, for example, a user input.

[0027] The period according to the transmission time is, for example, the period from the previous transmission time to the current transmission time. The period according to the request may be the period specified in the request, or may be the period from the previous request to the current request.

[0028] The image capturing devices 101_1 to 101_M may transmit the captured video to the video analysis device 103 in addition to or instead of transmitting the captured video to the video storage device 102. The timing at which the image capturing devices 101_1 to 101_M transmit the video and the period during which the captured video is transmitted are not limited to those mentioned above.

[0029] (Functional Configuration of the Video Storage Device 102 According to the First Embodiment) The video storage device 102 is an information processing device that acquires videos captured by each of the image capturing devices 101_1 to 101_M and stores the acquired videos. The video storage device 102 transmits the stored videos to, for example, the video analysis device 103.

[0030] The video storage device 102 may receive a request based on a user's input to the video analysis device 103, the statistical processing device 104, etc., and transmit video captured during a period corresponding to the request. The period corresponding to the request may be a period specified in the request, or may be the period from the previous request to the current request.

[0031] The timing at which the video storage device 102 transmits video and the period during which the video was captured during the transmission period are not limited to these. For example, the video storage device 102 may transmit video in real time. Also, for example, the video storage device 102 may transmit video captured during a period corresponding to a predetermined transmission period. The period corresponding to the transmission period is, for example, the period from the previous transmission period to the current transmission period.

[0032] (Regarding the functional configuration of the video analysis device 103 according to the first embodiment) The video analysis device 103 is an information processing device that processes the video images captured by each of the image capture devices 101_1 to 101_M, i.e., the video images related to the facility, and identifies multiple attributes related to each of the multiple customers included in the video images.

[0033] 4 is a diagram illustrating an example of the functional configuration of the video analysis device 103 according to embodiment 1. The video analysis device 103 functionally includes, for example, a video acquisition unit 131, an analysis unit 132 including an object detection unit 133 and an attribute identification unit 134, an attribute information storage unit 135, and an attribute transmission unit 136.

[0034] The video acquisition unit 131 acquires video from the video storage device 102. Note that the video acquisition unit 131 may acquire video from each of the image capture devices 101_1 to 101_M, for example, in real time.

[0035] When the video acquisition unit 131 acquires a video, the analysis unit 132 processes the video to detect objects included in the video and identify attributes of the detected objects. Objects include people and objects.

[0036] The analysis unit 132 has one or more analysis functions for processing and analyzing video. The analysis functions of the analysis unit 111 include one or more of: (1) an object detection function, (2) a face analysis function, (3) a human figure analysis function, (4) a posture analysis function, (5) a behavior analysis function, (6) an appearance attribute analysis function, (7) a gradient feature analysis function, (8) a color feature analysis function, and (9) a movement line analysis function.

[0037] (1) The object detection function detects an object from an image. The object detection function can also determine the position of an object within an image. For example, YOLO (You Only Look Once) is a model that can be applied to the object detection process.

[0038] The people detected by the object detection function include, for example, customers. The objects detected by the object detection function include, for example, luggage carried by a person, and automobiles, bicycles, motorcycles, and the like that are used by people to visit a facility. Furthermore, the objects detected by the object detection function may include, for example, payment machines, delivery lockers, ATMs, objects that constitute entrances and exits to a facility, objects that constitute entrances and exits to a restroom, and the like. Furthermore, for example, the object detection function determines the positions of these objects within an image.

[0039] (2) The face analysis function detects human faces from images, extracts the features of the detected faces (facial feature values), and classifies the detected faces (classification). The face analysis function can also determine the position of the face within the image. The face analysis function can also determine the identity of people detected from different images based on the similarity between the facial feature values ​​of people detected from different images.

[0040] (3) The human morphology analysis function extracts the physical characteristics of people included in an image (for example, values ​​indicating overall characteristics such as whether they are fat or thin, their height, and their clothing), and classifies (classifies) people included in an image. The human morphology analysis function can also identify the position of a person within an image. The human morphology analysis function can also determine the identity of people included in different images based on the physical characteristics of the people included in different images.

[0041] (4) The posture analysis function detects the joint points of people from the image and creates a stick figure model by connecting the joint points. The posture analysis function then uses the information from the stick figure model to estimate the posture of the people, extract the feature values ​​of the estimated posture (posture feature values), and classify (classify) the people included in the image. The posture analysis function can also determine the identity of people included in different images based on the posture feature values ​​of the people included in different images.

[0042] For example, the technology disclosed in Patent Document 3 can be applied to the posture analysis function.

[0043] (5) The behavior analysis process can estimate a person's movements using information about the stick figure model, changes in posture, and the like, extract features of the person's movements (movement features), and classify (classify) people included in the image. The behavior analysis process can also estimate a person's height and identify the person's position in the image using information about the stick figure model. The behavior analysis process can estimate, for example, behaviors such as changes or transitions in posture and movements (changes or transitions in position) from the image and extract movement features of the behavior.

[0044] (6) The appearance attribute analysis function can recognize appearance attributes associated with a person. The appearance attribute analysis function extracts features (appearance attribute features) related to the recognized appearance attributes and classifies (classifies) people included in an image. Appearance attributes are attributes of a person's appearance. Appearance attributes include, for example, one or more of age group, gender, clothing type, color and pattern, shoe type, color and pattern, hairstyle, whether or not a hat is worn, whether or not a tie is worn, and whether or not glasses are worn. Clothing types include, for example, one or more of work clothes, uniforms, suits, etc.

[0045] (7) The gradient feature analysis function extracts gradient feature quantities (gradient feature quantities) in an image. For example, techniques such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied to the gradient feature detection process. SIFT is an abbreviation for Scale-Invariant Feature Transform. SURF is an abbreviation for Speeded-Up Robust Features. RIFF is an abbreviation for Rotation-Invariant Fast Feature. BRIEF is an abbreviation for Binary Robust Independent Elementary Features. ORB is an abbreviation for Oriented FAST and Rotated BRIEF. BRISK is an abbreviation for Binary Robust Invariant Scalable Keypoints. CARD is an abbreviation for Compact and Real-time Descriptors. HOG is an abbreviation for Histograms of Oriented Gradients.

[0046] (8) The color feature analysis function can detect objects from an image, extract color features of the detected objects, and classify the detected objects. The color features are, for example, color histograms.

[0047] (9) The flow line analysis function can determine the flow line (trajectory of movement) of a person included in a video, for example, using the result of the identity determination in any of the above-mentioned analysis functions (2) to (6). In more detail, for example, by connecting people determined to be the same in different images in a time series, the flow line of that person can be determined. Note that, in cases where video images captured by multiple image capture devices 101 capturing different shooting areas are acquired, the flow line analysis function can also determine the flow line spanning multiple videos captured in different shooting areas.

[0048] The analysis unit 132 detects an object included in the video and identifies the attributes of the detected object using, for example, the above-mentioned analysis functions (1) to (9). The analysis unit 132 can also identify other attributes using one or more identified attributes. Note that the analysis unit 132 is not limited to the above-mentioned analysis functions (1) to (9), and may also have analysis functions used in general image processing, image recognition, etc.

[0049] In this embodiment, the analysis unit 132 functionally includes, for example, an object detection unit 133 and an attribute identification unit 134 .

[0050] The object detection unit 133 processes video related to the facility and detects at least customers who are objects included in the video. The object detection unit 133 may detect objects that are objects included in the video. The object detection unit 133 generates attribute information including customer identification information for identifying the multiple detected customers, for example, based on the detection result. The object detection unit 133 may further include object identification information for identifying the multiple detected objects in the attribute information based on the detection result.

[0051] The attribute identification unit 134 processes the video related to the facility and identifies multiple attributes for each of the multiple customers included in the video. The attribute identification unit 134 generates attribute information including the multiple attributes for each of the multiple customers. The attribute information is, for example, information that associates the multiple customers included in the video related to the facility with the multiple attributes identified for each of the multiple customers.

[0052] It is preferable that the type of attribute to be used for each attribute relating to a customer be determined in advance as appropriate.

[0053] Examples of ways to represent attributes include codes and numerical values ​​that are predetermined according to the attribute. Codes for representing attributes are suitable for attributes in which multiple characteristic aspects, properties, etc., according to the attribute are predetermined, such as gender and age group. The code may be any one of numbers, alphabets, symbols, etc., or may be a combination of one or more of these in any number and order. Numeric values ​​for representing attributes are suitable for attributes expressed as continuous numerical values ​​according to size, degree, etc., such as position and distance.

[0054] Furthermore, an example of a method of expressing an attribute is identification information for identifying the attribute. The identification information for expressing the attribute is suitable for identifying attributes that are difficult to determine in advance, such as each person or each object, and may include, for example, the above-mentioned code that is assigned appropriately according to the attribute.

[0055] However, the way in which each attribute is expressed is not limited to these.

[0056] Examples of multiple attributes according to this embodiment and examples of how to express various attributes will be described below. Note that the multiple attributes according to this embodiment and how to express each attribute are not limited to the following examples.

[0057] In this embodiment, the plurality of attributes may include, for example, (1) a solo / group behavior attribute, and may further include, for example, at least one of (2) a purchase / non-purchase attribute and (3) a facility usage attribute.

[0058] (1) Examples of Solo / Group Behavior Attributes (Including Group Behavior Attributes) Solo / group behavior attributes are customer attributes relating to whether a customer is a solo customer or a group customer. Solo customers are customers who act alone. Group customers are customers who act in groups of multiple people.

[0059] The solo / group behavior attribute includes a group behavior attribute related to a group customer. The solo / group behavior attribute may further include a solo behavior attribute related to a solo customer. That is, the multiple attributes may include at least a group behavior attribute.

[0060] In this embodiment, the solo / group behavior attribute is represented by the code "0" and group identification information associated with solo customers and group customers, respectively. In this case, the code "0" of the solo / group behavior attribute is an attribute indicating a solo customer, i.e., an example of the solo behavior attribute. The group identification information is identification information for identifying the group to which the customer belongs. The group identification information is an attribute indicating a group customer, i.e., an example of the group behavior attribute. By setting the group identification information to the group behavior attribute, it is possible to indicate that the customer is a group customer and to identify the group to which the customer belongs.

[0061] In addition, when it is not necessary to identify a group, the group behavior attribute may be represented using a code indicating whether or not the customer is a group customer (e.g., "0" indicating an individual customer rather than a group customer and "1" indicating a group customer). Furthermore, the multiple attributes may individually include a solo behavior attribute and a group behavior attribute. At least one of the individually configured solo behavior attribute and group behavior attribute may be included as an element of the multiple attributes without using a comprehensive solo / group behavior attribute. In this case, the solo behavior attribute may be represented, for example, using a code indicating whether or not the customer is a solo customer (e.g., "0" and "1"). In this case, the group behavior attribute may be represented, for example, using a code indicating whether or not the customer is a group customer, group identification information, or the like. Similarly, for attributes other than the solo / group behavior attribute, the comprehensive attribute itself may not be included in the multiple attributes, but its subordinate attributes may be included as elements of the multiple attributes.

[0062] (2) Examples of purchasing / non-purchasing attributes (including non-purchasing attributes) The purchasing / non-purchasing attribute is an attribute relating to whether a customer is a purchasing customer or a non-purchasing customer. A purchasing customer is a customer who has purchased a product at a facility. A non-purchasing customer is a customer who has not purchased a product at a facility.

[0063] The purchasing / non-purchasing attribute includes at least one of a purchasing attribute and a non-purchasing attribute. The purchasing attribute is an attribute that indicates a purchasing customer. The non-purchasing attribute is an attribute that indicates a non-purchasing customer.

[0064] In this embodiment, the purchasing / non-purchasing attribute is represented by two codes "0" and "1" that are predetermined to correspond to purchasing customers and non-purchasing customers, respectively. In this case, the purchasing / non-purchasing attribute "0" is an example of the purchasing attribute. The purchasing / non-purchasing attribute "1" is an example of the non-purchasing attribute.

[0065] (3) The used facility attribute is an attribute related to the facility used by the customer. The facility facility is a facility provided in the facility, and includes, for example, at least one of a toilet, a delivery box, an ATM (Automated Teller Machine), etc. Note that the facility facility is not limited to these, and may also be a store within the facility if the facility is a commercial complex.

[0066] In this embodiment, the facility usage attribute is represented by a predetermined code "0" associated with a customer when the customer does not use the facility, and a predetermined code associated with the type of facility used by the customer. More specifically, in this embodiment, the facility types are a toilet, a delivery box, and an ATM, and the codes "1," "2," and "3" are associated with each of them, respectively.

[0067] 5 is a diagram illustrating an example of the functional configuration of the attribute specification unit 134 according to embodiment 1. The attribute specification unit 134 functionally includes, for example, a group specification unit 134a, a non-purchasing specification unit 134b, and a facility specification unit 134c.

[0068] The group identification unit 134a processes, for example, a video related to a facility and identifies a group behavior attribute for each of a plurality of customers included in the video. Based on the identification result, the group identification unit 134a associates, for example, a solo / group behavior attribute with each of the plurality of customers included in the attribute information.

[0069] In this embodiment, for example, the code "0" corresponding to a single customer is set as the initial value of the individual / group behavior attribute of the detected customer. The group identification unit 134a processes the video related to the facility and identifies a group customer from among the detected multiple customers. The group identification unit 134a sets the code "1" corresponding to a group customer as the individual / group behavior attribute of the identified group customer.

[0070] It should be noted that the group identification unit 134a only needs to be able to identify the group behavior attribute. The method by which the group identification unit 134a identifies the group behavior attribute is not limited to the example described here. The initial value of the individual / group behavior attribute of a customer may be set to the code "1" corresponding to a group customer, and the group identification unit 134a may identify an individual customer from among multiple customers and set the code "0" to the individual / group behavior attribute of the individual customer.

[0071] The non-purchasing identification unit 134b processes, for example, a video related to a facility to identify non-purchasing attributes for each of a plurality of customers included in the video. Based on the identification results, the non-purchasing identification unit 134b associates, for example, purchasing / non-purchasing attributes with each of the plurality of customers included in the attribute information.

[0072] In this embodiment, for example, the initial value of the purchasing / non-purchasing attribute of the detected customer is set to the code "1" corresponding to a non-purchasing customer. The non-purchasing identification unit 134b processes the video related to the facility and identifies purchasing customers from among the detected multiple customers. The non-purchasing identification unit 134b sets the purchasing / non-purchasing attribute of the identified purchasing customer to the code "0" corresponding to a purchasing customer.

[0073] It should be noted that the non-purchasing identification unit 134b only needs to be able to identify non-purchasing attributes. The method by which the non-purchasing identification unit 134b identifies non-purchasing attributes is not limited to the example described here. The initial value of the purchasing / non-purchasing attribute may be set to a code "0" corresponding to a purchasing customer, and the group identification unit 134a may identify a non-purchasing customer from among multiple customers and set a code "1" to the purchasing / non-purchasing attribute of the non-purchasing customer.

[0074] The facility-used identification unit 134c processes, for example, a video related to the facility to identify facility-used attributes for each of the multiple customers included in the video. Based on the identification result, the facility-used identification unit 134c associates the facility-used attributes with each of the multiple customers included in the attribute information.

[0075] In this embodiment, for example, the initial value of the facility-used attribute of the detected customer is set to the code "0" which corresponds to a customer who does not use the facility. The facility-used identification unit 134c processes the video related to the facility to identify a customer who has used the facility from among the detected customers, and also identifies the facility that has been used.

[0076] In order to identify the customer who used the equipment and the equipment used, the equipment-using identification unit 134c may store, for example, equipment information indicating the layout of the equipment in the facility in advance. Then, the equipment-using identification unit 134c may use the customer's location obtained by processing the video and the stored equipment information to determine whether the customer used the equipment, and if so, to identify the equipment (e.g., the type of equipment).

[0077] The facility-to-be-used identifying unit 134c sets one of the codes "1," "2," or "3" corresponding to the type of facility used as the facility-to-be-used attribute of the customer who used the facility. When a customer uses multiple types of facility, the facility-to-be-used identifying unit 134c may set multiple codes corresponding to the multiple types of facility used by the customer as the facility-to-be-used attribute of the customer.

[0078] The method by which the facility-to-be-used identifying unit 134c identifies the facility-to-be-used attribute is not limited to this.

[0079] The attribute identification unit 134 includes a group identification unit 134a, a non-purchasing identification unit 134b, and a facility-used identification unit 134c, which are identification units for identifying each of the multiple attributes. As a result, the attribute identification unit 134 can generate attribute information in which the multiple attributes identified by each of the identification units, namely, the solo / group behavior attribute, the purchasing / non-purchasing attribute, and the facility-used attribute, are associated with each of the multiple detected customers.

[0080] 4 again, the attribute information storage unit 135 is a storage unit for storing attribute information. For example, the attribute specification unit 134 stores the generated attribute information in the attribute information storage unit 135.

[0081] The attribute transmitting unit 136 transmits the attribute information generated by the attribute specifying unit 134. The attribute transmitting unit 136 transmits the attribute information stored in the attribute information storage unit 135 to the statistical processing device 104, for example.

[0082] (Functional Configuration of the Statistical Processing Device 104 According to the First Embodiment) The statistical processing device 104 is an information processing device that performs statistical processing on a plurality of customers included in a video related to a facility using attribute information. The statistical processing device 104 may perform statistical processing on a plurality of customers included in a video related to a facility using the attribute information and at least one attribute included in the plurality of attributes. The at least one attribute used in the statistical processing may include a group behavior attribute.

[0083] 6 is a diagram illustrating an example of the functional configuration of the statistical processing device 104 according to embodiment 1. The statistical processing device 104 functionally includes, for example, a selection receiving unit 141, an attribute information acquiring unit 142, a statistical processing unit 143, an output unit 144, and an output control unit 145.

[0084] The selection receiving unit 141 receives selection information indicating settings selected for statistical processing using attribute information.

[0085] The selection information includes a statistical processing attribute group consisting of at least one attribute used in statistical processing. The statistical processing attribute group may include at least one of a plurality of attributes identified for each of a plurality of customers.

[0086] In this embodiment, the statistical processing attribute group includes at least one attribute selected from a plurality of attributes included in the attribute information acquired by the attribute information acquisition unit 142. In detail, for example, the statistical processing attribute group may include at least one attribute selected from (1) a solo / group behavior attribute including at least a group behavior attribute, (2) a purchase / non-purchase attribute including at least one of a purchase attribute and a non-purchase attribute, and (3) a facility use attribute.

[0087] The selection information may further include settings regarding the target period for statistical processing, the statistical processing method (how to use attributes to perform statistical processing), and the format of the diagram to be used to represent the results of the statistical processing.

[0088] The target period is, for example, a period of time to be selected, such as a time slot, date, month, etc. Note that the selected period is not limited to this, and may be, for example, a point in time such as a selected time.

[0089] The statistical processing method may include, for example, counting the number of customers corresponding to one attribute or a combination of multiple attributes, calculating the percentage of the number of customers, etc. When calculating the percentage, the statistical processing method may include an attribute for counting the number of customers to be used as a population parameter.

[0090] Furthermore, the statistical processing method may include, for example, a classification of whether time-series processing is performed for the target period or whether processing is performed for the entire target period. When time-series processing is performed, the statistical processing method may include a time interval for performing the time-series processing. Note that general statistical methods may be used for the statistical processing, and the statistical processing method is not limited to these.

[0091] The diagram format may be, for example, a line graph, a pie chart, a bar graph, etc. However, the diagram format is not limited to these.

[0092] The attribute information acquisition unit 142 acquires the attribute information generated by the video analysis device 103. For example, the attribute information acquisition unit 142 acquires the attribute information generated based on the video captured during the target period.

[0093] The statistical processing unit 143 performs statistical processing on the multiple customers included in the video related to the facility, using at least one attribute included in the multiple attributes identified for each of the multiple customers. The statistical processing unit 143 generates a result of the statistical processing.

[0094] For example, the statistical processing unit 143 performs statistical processing using the attribute information acquired by the attribute information acquisition unit 142 and the selection information accepted by the selection acceptance unit 141. The results of the statistical processing may include at least one of a numerical value generated by the statistical processing, a diagram showing the numerical value in a format included in the selection information, etc. However, the results of the statistical processing are not limited to these.

[0095] In this embodiment, the group of attributes for statistical processing includes at least one of the following attributes, as described above: (1) solo / group behavior attributes including at least a group behavior attribute; (2) purchase / non-purchase attributes including at least one of a purchase attribute and a non-purchase attribute; and (3) facility usage attributes.

[0096] Using such attributes, the statistical processing unit 143 may, for example, calculate the respective proportions of purchasing customers and non-purchasing customers in a group of customers. Furthermore, for example, the statistical processing unit 143 may calculate the number of non-purchasing customers calculated for each of a plurality of attributes, or the proportion of the calculated number of non-purchasing customers to the total number of non-purchasing customers. In this case, the plurality of attributes may include a group behavior attribute.

[0097] Furthermore, for example, the statistical processing unit 143 may tally up customers who used the facilities by facility type, or may calculate the number of customers who used the facilities or the ratio of the number of customers of each type of facility used to all customers. The customers who used the facilities here may be customers belonging to other attributes, such as group customers or non-purchasing customers. Furthermore, for example, the statistical processing unit 143 may calculate the ratio of customers with other attributes among customers who used each type of facility. In this case, the other attributes may include group behavior attributes.

[0098] The statistical processing unit 143 may obtain the aggregated value or ratio in time series according to the selected information, for example, or may obtain the aggregated value or ratio as an index that collectively indicates the entire target period.

[0099] The output unit 144 outputs various information under the control of the output control unit 145 etc. The output control unit 145 causes the output unit 144 to output information. The output control unit 145 causes the output unit 144 to output, for example, the results of statistical processing generated by the statistical processing unit 143.

[0100] The output may be a display, a transmission, a recording, or the like. That is, the output control unit 145 may cause the output unit 144 to display as a display unit. The output control unit 145 may cause the output unit 144 to transmit data to a specified device as a transmission unit. The output control unit 145 may cause the output unit 144 to record data on a recording medium as a data writing unit. Note that the output method is not limited to these.

[0101] Up to this point, the functional configuration example of the information processing system 100 according to the first embodiment has been mainly described. From here, a physical configuration example of the information processing system 100 according to the first embodiment will be described.

[0102] (Example of physical configuration of information processing system 100 according to embodiment 1) The information processing system 100 is physically composed of a video storage device 102, a video analysis device 103, and a statistical processing device 104, which are connected via a network NT. Each of the video storage device 102, the video analysis device 103, and the statistical processing device 104 is composed of a single, physically separate device.

[0103] The functions of the image capture devices 101_1 to 101_M, the video storage device 102, the video analysis device 103, and the statistical processing device 104 may be provided by the entire information processing system 100. That is, for example, some or all of the functions of the image capture devices 101_1 to 101_M, the video storage device 102, the video analysis device 103, and the statistical processing device 104 may be physically configured as a single device. Also, for example, the image capture devices 101_1 to 101_M, the video storage device 102, the video analysis device 103, and the statistical processing device 104 may be configured as multiple different devices connected via an appropriate communication line such as a network N, for example, for each of one or more functions provided therein.

[0104] The video storage device 102, video analysis device 103, and statistical processing device 104 according to this embodiment may each have the same physical configuration. Here, an example of the physical configuration of the video analysis device 103 will be described with reference to the drawings.

[0105] 7 is a diagram showing an example of the physical configuration of the video analysis device 103 according to embodiment 1. The video analysis device 103 physically includes, for example, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070.

[0106] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0107] The processor 1020 is implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0108] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0109] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read-only memory (ROM), or the like. The storage device 1040 stores program modules for realizing the functions of the device that includes it (in the example of FIG. 7, the video analysis device 103). The processor 1020 reads each of these program modules into the memory 1030 and executes them, thereby realizing the function corresponding to that program module.

[0110] The network interface 1050 is an interface for connecting a device that includes it (the video analysis device 103 in the example of FIG. 7) to the network NT.

[0111] The input interface 1060 is an interface for the user to input information, and is configured from, for example, a touch panel, a keyboard, a mouse, and the like.

[0112] The output interface 1070 is an interface for presenting information to the user, and is configured, for example, by a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0113] So far, an example of the physical configuration of the information processing system 100 according to the first embodiment has been described. Next, an example of the operation of the information processing system 100 according to the first embodiment will be described.

[0114] (Example of Operation of Information Processing System 100 According to First Embodiment) The information processing system 100 executes information processing including, for example, video analysis processing and statistical processing. Each of the video analysis processing and customer statistical processing will be described with reference to the drawings.

[0115] (Example of Video Analysis Processing According to Embodiment 1) The video analysis processing according to this embodiment is processing video related to a facility to identify multiple attributes of each of multiple customers included in the video. The video analysis processing is started, for example, when the video analysis device 103 receives selection information, selection time, and the like from the statistical processing device 104. Note that the trigger for starting the video analysis processing is not limited to this, and the video analysis processing may be executed repeatedly, for example, when processing in real time.

[0116] FIG. 8 is a flowchart illustrating an example of a video analysis process according to the first embodiment.

[0117] The video acquisition unit 131 acquires video captured at the selection time included in the selection information received as a trigger or at a time corresponding to the selection time received as a trigger (step S101).

[0118] For example, the video acquisition unit 131 acquires from the video storage device 102 a video that was taken at a time corresponding to the selected time period.

[0119] The object detection unit 133 processes the video acquired in step S101 and detects an object included in the video (step S102).

[0120] For example, the object includes a customer and an object. When the object detection unit 133 processes the video and detects the customer and the object included in the video, it generates attribute information including the customer identification information and the object identification information of each of the customer and the object.

[0121] The attribute specification unit 134 processes the video acquired in step S101 and specifies a plurality of attributes related to each of a plurality of customers included in the video (step S103).

[0122] For example, the group identification unit 134a processes a video related to a facility to identify group behavior attributes for each of the multiple customers included in the video (step S103a). The non-purchasing identification unit 134b processes a video related to a facility to identify non-purchasing attributes for each of the multiple customers included in the video (step S103b). The facility-used identification unit 134c processes a video related to a facility to identify facility-used attributes for each of the multiple customers included in the video (step S103c).

[0123] The attribute identification unit 134 generates attribute information that associates the identified multiple attributes (in this embodiment, solo / group behavior attribute, purchasing / non-purchasing attribute, and facility usage attribute) with each of the multiple customers detected in step S102.

[0124] The attribute identification unit 134 stores the attribute information generated in step S103 in the attribute information storage unit 135 (step S104), and ends the video analysis process.

[0125] The order of steps S103a to S103c may be changed as appropriate. However, when identifying an attribute using the results of identifying other attributes, the identification of the attribute may be performed after the other attributes necessary for identifying the attribute have been identified.

[0126] (Example of Customer Statistical Processing According to Embodiment 1) The customer statistical processing according to this embodiment is processing for performing statistical processing on multiple customers using at least one attribute included in the multiple identified attributes. The customer statistical processing is started, for example, when the selection receiving unit 141 receives selection information according to a user selection. Note that the trigger for starting the customer statistical processing is not limited to this, and may include, for example,

[0127] FIG. 9 is a flowchart illustrating an example of customer statistical processing according to the first embodiment.

[0128] The attribute information acquisition unit 142 acquires attribute information generated by executing a video analysis process (step S201).

[0129] For example, the attribute information acquisition unit 142 requests video that was shot during the target period included in the selection information received as a trigger from the video analysis device 103. Upon receiving this request, the attribute transmission unit 136 acquires and transmits the video that was shot during the target period included in the request from the attribute information storage unit 135. The attribute information acquisition unit 142 acquires the video that has been transmitted from the attribute transmission unit 136.

[0130] The statistical processing unit 143 performs statistical processing using the selection information received as a trigger for starting customer statistical processing and the attribute information acquired in step S201 (step S202).

[0131] The output control unit 145 causes the output unit 144 to output the statistical processing results generated in step S202 (step S203), and then ends the process.

[0132] Multiple customers who visit a facility are included in the video related to the facility. Therefore, by performing video analysis processing and customer statistical processing, statistical processing can be performed using the attributes of multiple customers who visit the facility.

[0133] (Actions and Effects) As described above, according to this embodiment, the information processing system 100 includes the attribute identification unit 134 and the statistical processing unit 143. The attribute identification unit 134 processes video related to the facility to identify multiple attributes related to each of the multiple customers. The statistical processing unit 143 performs statistical processing on the multiple customers using at least one attribute included in the identified multiple attributes. The at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people.

[0134] This allows for identifying multiple attributes for each of multiple customers who visit a facility, and performing statistical processing on the multiple customers using at least one of the identified attributes. The at least one attribute includes a group behavior attribute for customers who visit in groups of multiple people. This makes it possible to understand customer behavior at a facility depending on whether the customers visit in groups or alone.

[0135] According to this embodiment, the attributes further include non-purchasing attributes relating to customers who do not purchase merchandise at the establishment.

[0136] This allows statistical processing of multiple customers using non-purchasing attributes, making it possible to understand customer behavior in a facility depending on whether the customers are in groups or alone.

[0137] (Embodiment 2) The multiple attributes are not limited to the solo / group behavior attribute, purchase / non-purchase attribute, and facility usage attribute described in embodiment 1. In embodiment 2, an example will be described in which the multiple attributes include at least one of a group attribute, an age group, a distance attribute relating to the distance between customers, a store visit time attribute relating to the time of customer visit, a store visit means attribute relating to the means by which the customer visits, and a clothing attribute relating to the clothing of the customer. In addition, an example of a method for identifying a group behavior attribute and a group type (family, coworkers, sports buddies, friends, etc.) will also be described.

[0138] In this embodiment, for the sake of brevity, the description of the same configuration as in the first embodiment will be omitted as appropriate.

[0139] The information processing system according to this embodiment includes a video analysis device 203 instead of the video analysis device 103 according to embodiment 1. Except for this point, the information processing system according to this embodiment may be configured similarly to the information processing system 100 according to embodiment 1.

[0140] 10 is a diagram showing an example of the functional configuration of a video analysis device 203 according to embodiment 2. The video analysis device 203 functionally includes, for example, an analysis unit 232 that replaces the analysis unit 132 according to embodiment 1. Except for this point, the video analysis device 203 may be configured similarly to the video analysis device 103 according to embodiment 1.

[0141] When the video acquisition unit 131 acquires a video, the analysis unit 232 processes the acquired video using an analysis function similar to that of the analysis unit 132 according to embodiment 1. Then, the analysis unit 232 detects an object included in the video and identifies the attributes of the detected object.

[0142] The analysis unit 232 includes an object detection unit 133 similar to that of the first embodiment, and an attribute identification unit 234 instead of the attribute identification unit 134 according to the first embodiment. Like the attribute identification unit 134 according to the first embodiment, the attribute identification unit 234 processes a video related to the facility and identifies a plurality of attributes for each of a plurality of customers included in the video. Then, like the attribute identification unit 134 according to the first embodiment, the attribute identification unit 234 generates attribute information including a plurality of attributes for each of the plurality of customers.

[0143] The attributes according to this embodiment include (1) a solo / group behavior attribute, and further include at least one of (2) a purchasing / non-purchasing attribute, (3) a facility usage attribute, (4) an age group, (5) a distance attribute, (6) a store visit time attribute, (7) a store visit means attribute, and (8) a clothing attribute.

[0144] (1) Example of Solo / Group Behavior Attribute According to Second Embodiment As in the first embodiment, the solo / group behavior attribute includes a group behavior attribute, and group identification information is used for the group behavior attribute.

[0145] The solo / group behavior attribute according to this embodiment further includes, for a group customer, the attribute of the group to which the group customer belongs (group attribute).

[0146] The group attribute may include, for example, the type of group (group type). The group attribute may be represented by a predetermined code associated with the group type. For example, the group types may be family, coworkers, sports buddies, and friends, and the codes "1," "2," "3," and "4" may be associated with each of the group types in advance.

[0147] Note that the group attribute is not limited to this and may be, for example, the number of people constituting the group, i.e., the number of customers associated with the same group identification information, etc. The group type is not limited to these and may include at least one of family, coworkers, sports buddies, friends, etc.

[0148] The (2) purchase / non-purchase attribute and (3) facility-usage attribute according to this embodiment may be the same as those in the first embodiment.

[0149] (4) Examples of Age Groups It is preferable that a plurality of age groups be defined in advance, such as age 12 and under, ages 13 to 19, ages 20 to 29, ages 30 to 49, and ages 50 and over. The plurality of age groups may be represented by corresponding predetermined codes. For example, the age groups may be age 12 and under, ages 13 to 19, ages 20 to 29, ages 30 to 49, and ages 50 and over, and the codes "1," "2," "3," "4," and "5" may be correspondingly defined in advance. However, the age groups are not limited to these.

[0150] (5) Examples of Distance Attributes The distance attribute is an attribute related to the distance between a customer and another customer. The distance attribute may be expressed, for example, as the distance between the customer and one or more customers located within a predetermined range.

[0151] (6) Examples of Visit Time Attributes The visit time attribute is an attribute related to the time when a customer visits a store. The time when a customer visits a store may be, for example, the time when the customer enters the facility through an entrance or the time when the customer enters the facility grounds. The visit time attribute may be expressed, for example, as the time when the customer visits the store.

[0152] The time when a customer arrived at a store is not limited to a time. The multiple attributes may include an attribute related to the time when a customer left the store (exit time attribute) together with or in addition to the arrival time attribute.

[0153] (7) Examples of Visit Means Attributes The visit means attribute is an attribute related to the means by which a customer visits a store. For example, the visit means may be walking, bicycle, or automobile, and may be represented by the codes "1" and "2" associated with each, and automobile identification information. An automobile is an example of a visit means that can be used by several people at the same time. The automobile identification information is identification information for identifying an automobile, and is an example of visit means identification information.

[0154] (8) Examples of Clothing Attributes Clothing attributes are attributes related to clothing. Clothing attributes include, for example, a first clothing attribute related to the type of clothing. Clothing attributes may further include at least one of a second clothing attribute related to the color of the clothing, a third clothing attribute related to the pattern of the clothing, etc.

[0155] The first clothing attribute may be represented by a predetermined code associated with the type of clothing. For example, the clothing types may be work clothes, uniforms, and suits, and the codes "1," "2," and "3" may be associated with each of these types in advance. Note that the clothing types are not limited to these and may include at least one of work clothes, uniforms, suits, etc.

[0156] The first clothing attribute may also include clothing type identification information for identifying clothing belonging to a predetermined clothing type. The clothing type identification information may be used together with or instead of the code associated with the clothing type.

[0157] The predetermined type of clothing includes, for example, at least one of work clothes and uniforms. Workers working in the same workplace often wear the same type of work clothes. Also, players on the same team often wear the same type of uniforms. By using the clothing type identification information, it is possible to identify the type of work clothes, uniforms, etc.

[0158] The second clothing attribute may be represented by at least one of a predetermined code associated with the color of the clothing, a numerical value representing the color of the clothing, etc. The third clothing attribute may be represented by a predetermined code associated with the design (e.g., pattern) of the clothing. The clothing design pattern may be a solid color, various checks, stripes, etc. Note that the methods of representing the second clothing attribute and the third clothing attribute are not limited to these.

[0159] In this embodiment as well, the attribute specifying unit 234 includes a specifying unit for specifying each of the multiple attributes.

[0160] 11 is a diagram illustrating an example of the functional configuration of the attribute identification unit 234 according to embodiment 2. Functionally, the attribute identification unit 234 includes, for example, a group identification unit 234a that replaces the group identification unit 134a according to embodiment 1, and a non-purchase identification unit 134b and a utilization facility identification unit 134c similar to those in embodiment 1.

[0161] The attribute specifying unit 234 functionally further includes, for example, a group attribute specifying unit 234d including a group type specifying unit 234d1, an age group specifying unit 234e, and a distance attribute specifying unit 234f. The attribute specifying unit 234 functionally further includes, for example, a store visit time attribute specifying unit 234g, a store visit means attribute specifying unit 234h, a first outfit specifying unit 234i, a second outfit specifying unit 234j, a third outfit specifying unit 234k, and an outfit type identifying unit 234l.

[0162] The group identification unit 234a processes a video related to the facility and identifies a group behavior attribute for each of the multiple customers included in the video, similar to the group identification unit 134a according to embodiment 1. Based on the identification result, the group identification unit 234a associates, for example, a solo / group behavior attribute with each of the multiple customers included in the attribute information.

[0163] Specifically, the group identification unit 234a identifies a group behavior attribute for each of the multiple customers using a first attribute group of each of the multiple customers and one or more first discrimination conditions.

[0164] The first attribute group includes at least one attribute pre-selected from the plurality of attributes as an attribute to be used to distinguish group customers, such as an age group, a distance attribute, a store visit time attribute, a store visit means attribute, and a clothing attribute.

[0165] The first determination condition is a condition for determining whether a customer is a group of customers. The first determination condition may be defined in advance using a first attribute group.

[0166] Each of the first determination conditions includes at least one of the following condition elements. Note that the first determination conditions and the condition elements are not limited to the following examples. Furthermore, the method of identifying the group type using the condition elements is not limited to the following example.

[0167] Condition element 1 (condition related to age group) is that the age groups are the same or different within a predetermined range. The group type of a group that satisfies condition element 1 can be identified as friends, for example. Condition element 1 may further include, for example, that the age group is equal to or less than a predetermined value.

[0168] Condition element 2 (condition related to distance at time of visit) is that the distance between customers at the time of visit must be within a predetermined first distance. Condition element 3 (condition 1 related to time of visit) is that the time difference between when customers entered the facility must be within a predetermined second hour. Multiple customers who satisfy at least one of condition elements 2 and 3 can be identified as, for example, a group of customers belonging to the same group.

[0169] Condition element 4 (condition 1 related to families) is that the distance between customers when visiting the store with their children whose ages are below a predetermined age threshold is within a predetermined second distance. Condition element 5 (condition 2 related to families) is that the time difference between when customers visit the store with their children is within a predetermined fourth hour. Multiple customers who satisfy at least one of condition elements 4 and 5 are, for example, a group of customers belonging to the same group, and the group type of the group can be identified as a family.

[0170] Condition element 6 (condition related to proximity behavior within a facility) is that the proximity behavior time is equal to or longer than a predetermined fifth time. The proximity behavior time is the total time during which customers are within a predetermined third distance from each other over the period of their stay at the facility. Multiple customers who satisfy condition element 6 can be identified as, for example, a group of customers belonging to the same group.

[0171] Condition element 7 (condition 2 related to the time of visit) requires that the time difference between the times when vehicles with different vehicle identification information for identifying the vehicle used as the means of visit to the facility enter the facility premises must be within a predetermined third time period. The facility premises may be, for example, the facility's parking lot or a road within the facility premises leading to the parking lot. Multiple customers who satisfy condition element 7 can be identified as, for example, a group of customers belonging to the same group.

[0172] Condition element 8 (condition related to the means of arrival) is that when customers arrive by car, which is a means of arrival that can be used by multiple people at the same time, they arrive by car with the same car identification information. Multiple customers who satisfy condition element 8 are, for example, customers who arrived by riding in the same car, and therefore can be identified as a group of customers belonging to the same group.

[0173] Condition element 9 (condition 1 related to clothing) is that the clothing type is the same. Multiple customers who satisfy condition element 9 can be identified as a group of customers belonging to the same group. For example, if all customers in the group wear suits, the group type of the group can be identified as coworkers.

[0174] Condition element 10 (condition 2 related to clothing) is that the clothing type identification information is common. Multiple customers who satisfy condition element 10 can be identified as, for example, a group of customers belonging to the same group. For example, multiple customers who satisfy condition element 10 can be identified as coworkers if they share the clothing type identification information for work clothes, or as sports buddies if they share the clothing type identification information for uniforms.

[0175] The group identification unit 234a identifies a first attribute group for each of a plurality of customers by using, for example, attribute information, and then identifies a group behavior attribute for the identified customer depending on whether the first attribute group of the identified customer satisfies one or more first determination conditions.

[0176] For example, if the first attribute group of the identified customer satisfies one or more first discrimination conditions, the group identification unit 234a sets the code "1" corresponding to a group customer to the individual / group behavior attribute associated with the identified customer in the attribute information. If the first attribute group of the identified customer does not satisfy one or more first discrimination conditions, the group identification unit 234a does not change the initial value of the individual / group behavior attribute associated with the identified customer in the attribute information.

[0177] In this way, the first discrimination condition is identified using an attribute other than the group behavior attribute. Therefore, after each of the identification units 234e to 234l described below has performed identification, the group identification unit 234a may identify the group behavior attribute for each of the multiple customers using the identification results. Note that the method by which the group identification unit 234a identifies the group behavior attribute is not limited to the example described here.

[0178] The group attribute specification unit 234d specifies the group attributes of the group customers. The group attribute specification unit 234d includes, for example, a group type specification unit 234d1.

[0179] The group type specifying unit 234d1 uses the group type specifying information to specify a group type associated with at least one first determination condition satisfied by the group customer. The group type specifying unit 234d1 sets the specified group type as the group type to which the group customer belongs.

[0180] The group type defining information is information that associates the group type with at least one first determination condition and is preferably determined in advance.

[0181] Using the example of the first discrimination condition described above, the group type specifying information associates, for example, a first discrimination condition including condition element 1 with the group type "friends." Also, for example, the group type specifying information associates a first discrimination condition including at least one of condition elements 4 and 5 with the group type "family." Furthermore, for example, the group type specifying information associates a first discrimination condition including condition element 9 and the type of clothing being "suit" (condition element 11) with the group type "workmates."

[0182] For example, the group type specifying information associates the first discrimination condition including the condition element 10 and the type of clothing being work clothes (condition element 12) with the group type "workplace colleagues." For example, the group type specifying information associates the first discrimination condition including the condition element 10 and the type of clothing being uniforms (condition element 13) with the group type "sports colleagues."

[0183] In this way, the group type is identified for the group customer using attributes other than the group behavior attribute. Therefore, after the group identification unit 234a and each of the identification units 234e to 234l described below have performed identification, the group attribute identification unit 234d may identify the group attributes of the group customer using the identification results. Then, based on the identification results, the group attribute identification unit 234d may associate, for example, a group attribute with each of the multiple group customers included in the attribute information.

[0184] The group attribute specifying unit 234d may include another specifying unit for specifying a group attribute, together with the group type specifying unit 234d1, or instead of the group type specifying unit 234d1. For example, the group attribute specifying unit 234d may include a group number specifying unit for specifying the number of customers constituting a group as a group attribute.

[0185] The age group identification unit 234e processes, for example, a video related to a facility to identify the age group of each of the multiple customers included in the video. Based on the identification result, the age group identification unit 234e associates an age group with each of the multiple customers included in the attribute information.

[0186] The distance attribute specification unit 234f processes, for example, a video related to a facility and determines the distance from each of a plurality of customers included in the video to one or more customers located within a predetermined range. The distance may be expressed, for example, as a distance within the image, but is not limited to this. Based on the determined distance, the distance attribute specification unit 234f associates a customer-to-customer distance with each of a plurality of customers included in the attribute information.

[0187] The store visit time attribute specifying unit 234g processes, for example, a video related to a facility to specify the times when multiple customers included in the video visited the store. Based on the result of the specification, the store visit time attribute specifying unit 234g associates the store visit time with each of the multiple customers included in the attribute information.

[0188] The store arrival means attribute identification unit 234h processes, for example, a video related to a facility to identify the means by which multiple customers included in the video arrived at the store. The store arrival means may be identified, for example, by processing video of the facility's entrance / exit, parking lot, etc. Based on the identification result, the store arrival means attribute identification unit 234h associates the store arrival means with each of the multiple customers included in the attribute information.

[0189] Each of the first to third clothing identification units 234i to 234k is an example of a clothing attribute identification unit that processes a video related to a facility and identifies clothing attributes of each of a plurality of customers included in the video. Based on the identification results, the clothing attribute identification unit associates a clothing attribute with each of the plurality of customers included in the attribute information.

[0190] For example, the first clothing identification unit 234i processes a video related to a facility to identify the type of clothing (first clothing attribute) of each of the multiple customers included in the video. Based on the identification result, the first clothing identification unit 234i associates the first clothing attribute with each of the multiple customers included in the attribute information.

[0191] The second clothing identification unit 234j processes, for example, a video related to a facility to identify the color of clothing (second clothing attribute) of each of the multiple customers included in the video. Based on the identification result, the second clothing identification unit 234j associates the second clothing attribute with each of the multiple customers included in the attribute information.

[0192] The third clothing identification unit 234k processes, for example, a video related to the facility to identify the pattern (third clothing attribute) of clothing of each of the multiple customers included in the video. Based on the identification result, the third clothing identification unit 234k associates the third clothing attribute with each of the multiple customers included in the attribute information.

[0193] The clothing type identification unit 234l identifies clothing type identification information using, for example, one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and the clothing type identification condition.

[0194] The clothing type identification condition is a condition for identifying clothing belonging to a predetermined clothing type (e.g., work clothes, uniforms, etc.). The clothing type identification condition is defined, for example, using clothing similarity, which indicates the degree to which clothing is similar, and a predetermined identification threshold. In more detail, for example, if the clothing is more similar, the clothing similarity becomes larger, the clothing type identification condition includes that the clothing similarity is equal to or greater than the identification threshold.

[0195] The clothing similarity is calculated using, for example, the similarity of one or more of the second clothing attribute and the third clothing attribute. For example, the similarity related to the second clothing attribute is color similarity, which indicates the degree to which the colors of the clothing are similar. For example, the similarity related to the third clothing attribute is pattern similarity, which indicates the degree to which the patterns of the clothing are similar. The clothing type identification unit 234l calculates the clothing similarity by, for example, adding the color similarity based on the second clothing attribute and the pattern similarity based on the third clothing attribute, each with a predetermined weight. Note that the method of calculating the clothing similarity is not limited to this.

[0196] Up to this point, an example of the functional configuration of the information processing system according to the second embodiment has been mainly described. The information processing system according to the second embodiment may be physically configured in the same manner as the information processing system 100 according to the first embodiment. For example, the video analysis device 203 may be physically configured in the same manner as the video analysis device 103 according to the first embodiment. From here, an example of the operation of the information processing system according to the second embodiment will be described.

[0197] (Example of Operation of Information Processing System According to Embodiment 2) The information processing system according to this embodiment executes information processing including, for example, a video analysis process different from that of Embodiment 1 and a statistical process similar to that of Embodiment 1. The video analysis process according to this embodiment will be described with reference to the drawings.

[0198] 12 is a flowchart showing an example of video analysis processing according to embodiment 2. The video analysis processing according to this embodiment includes an attribute identification processing (step S203) instead of the attribute identification processing (step S103) according to embodiment 1. Except for this, the video analysis processing according to this embodiment may be similar to the video analysis processing according to embodiment 1.

[0199] As in the first embodiment, when steps S101 and S102 are executed, the attribute identification unit 234 processes the video acquired in step S101 to identify a plurality of attributes for each of a plurality of customers included in the video (step S203). The details of the attribute identification process (step S203) differ from the attribute identification process (step S103) according to the first embodiment.

[0200] As shown in FIG. 12, for example, the group identification unit 234a processes video related to the facility and identifies group behavior attributes for each of multiple customers included in the video using a first attribute group and one or more first discrimination conditions (step S203a).

[0201] For example, the non-purchase identifying unit 134b and the facility-to-be-used identifying unit 134c identify the non-purchase attribute and the facility-to-be-used attribute in the same manner as in the first embodiment (steps S103b and S103c).

[0202] For example, the group attribute specifying unit 234d specifies the group attribute of each of the plurality of group customers specified in step S203a (step S203d). In step S203d, for example, the group type specifying unit 234d1 specifies the group type, which is an example of the group attribute, for each of the plurality of group customers.

[0203] Here, the group behavior attribute and the group attribute in steps S203a and S203d are identified using other attributes other than the respective attributes, and therefore steps S203a and S203d may be executed using the other attributes after the other attributes are identified by executing other processes (steps S103b, S103c, and S203e to S203l).

[0204] For example, the age group identification unit 234e processes a video related to a facility to identify the age group of each of multiple customers included in the video (step S203e). The distance attribute identification unit 234f processes a video related to a facility to identify the distance attribute by calculating the customer-to-customer distance (step S203f). The customer-to-customer distance is the distance between each of multiple customers included in the processed video and one or more other customers located within a predetermined range.

[0205] For example, the visit time attribute specifying unit 234g processes a video related to a facility and specifies the visit time attribute of each of the multiple customers included in the video (step S203g).The visit means attribute specifying unit 234h processes a video related to a facility and specifies the visit means attribute of each of the multiple customers included in the video (step S203h).

[0206] For example, the first clothing identifier 234i processes a video related to a facility to identify the type of clothing (first clothing attribute) of each of the multiple customers included in the video (step S203i). The second clothing identifier 234j processes a video related to a facility to identify the color of clothing (second clothing attribute) of each of the multiple customers included in the video (step S203j). The third clothing identifier 234k processes a video related to a facility to identify the pattern of clothing (third clothing attribute) of each of the multiple customers included in the video (step S203k).

[0207] For example, the clothing type identification unit 234l identifies clothing type identification information using one or more of the first clothing attribute, second clothing attribute, and third clothing attribute identified in steps S202i to S202k and clothing type identification conditions (step S202l).

[0208] Here, the clothing type identification information in step S203l is determined using the first to third clothing attributes. Therefore, step S203l may be performed using the determined first to third clothing attributes after steps S203i to S203k have been performed to determine the first to third clothing attributes.

[0209] The attribute identification unit 234 generates attribute information that associates the multiple attributes identified in steps S203a, S103b to S103c, and S203d to S203l with each of the multiple customers detected in step S102. As in the first embodiment, the attribute identification unit 134 stores the attribute information generated in the attribute identification process (step S203) in the attribute information storage unit 135 (step S104), and ends the video analysis process.

[0210] The order of steps S203a, S103b to S103c, and S203d to S203l may be changed as appropriate. However, when identifying an attribute using the results of identifying other attributes, the identification of the attribute may be performed after the other attributes necessary for identifying the attribute have been identified.

[0211] By executing such video analysis processing, it is possible to identify group behavior attributes and group attributes. Furthermore, it is possible to identify more attributes than in embodiment 1. Therefore, in customer statistical processing, it is possible to perform statistical processing using more attributes than in embodiment 1.

[0212] (Actions and Effects) As described above, according to this embodiment, the multiple attributes further include at least one of the following: a customer's age group, a distance attribute related to the customer distance, which is the distance between the customer and other customers, a store visit time attribute related to the time when the customer visits the store, a store visit means attribute related to the means by which the customer visits the store, and a clothing attribute related to the customer's clothing. In addition, the attribute identification unit 234 includes a group identification unit 234a that identifies a group behavior attribute for each of the multiple customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for distinguishing customers who act in groups of multiple people.

[0213] This allows the group behavior attribute to be identified using the first attribute group, making it possible to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0214] According to this embodiment, the plurality of attributes includes a group attribute related to a group. The attribute specifying unit 234 further includes a group attribute specifying unit 234d that specifies the group attribute of a customer who acts in a group of multiple people.

[0215] This makes it possible to identify the group attributes of customers who travel in groups of multiple people, and therefore to understand customer behavior in a facility depending on whether the customer travels in a group or alone.

[0216] According to this embodiment, the group attribute includes a group type. The group attribute identification unit 234d includes a group type identification unit 234d1. The group type definition information associates the group type with the at least one first discrimination condition. The group type identification unit 234d1 uses the group type definition information to identify the group type associated with the at least one first discrimination condition satisfied by a customer who acts in a group of multiple people as the group type of the customer who acts in the group of multiple people.

[0217] This makes it possible to identify the group type of customers who act in groups of multiple people, and therefore, by further using the group type, it becomes possible to understand customer behavior in a facility depending on whether the customer acts in a group or alone.

[0218] According to this embodiment, each of the one or more first determination conditions includes at least one of the following first to sixth conditions.

[0219] The first requirement is that the age groups of the customers are the same or different within a predetermined range. The second requirement is that the distance between the customers when they visit the store is within a predetermined first distance. The third requirement is that the time difference between the customers when they enter the facility is within a predetermined second hour.

[0220] The fourth requirement is that the distance between customers and their children who are below a predetermined age threshold is within a predetermined second distance. The fifth requirement is that the time difference between the customers' visits to the store and their children is within a predetermined fourth hour. The sixth requirement is that the total time spent in close proximity, calculated by adding up the time during which customers are within a predetermined third distance from each other over the period of their stay at the facility, is equal to or longer than a predetermined fifth hour.

[0221] This allows the group behavior attribute to be identified using the one or more first discrimination conditions and the first attribute group, thereby making it possible to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0222] According to this embodiment, the store arrival means attribute includes store arrival means identification information for store arrival means that can be used by multiple people at the same time. Each of the one or more first determination conditions includes at least one of the following seventh to eighth conditions.

[0223] The seventh condition is that the time difference between the times when people entered the facility premises using means of arrival that have different means of arrival identification information for identifying the means of arrival is within a predetermined third hour. The eighth condition is that when multiple people arrived at the facility using means of arrival that can be used simultaneously, they arrived at the facility using means of arrival that have the same means of arrival identification information.

[0224] This allows group behavior attributes to be identified using the store visit method, making it possible to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0225] According to this embodiment, the clothing attributes include a first clothing attribute relating to a clothing type. The first clothing attribute includes clothing type identification information for identifying clothing belonging to a predetermined clothing type. Each of the one or more first discrimination conditions includes at least one of the following ninth to tenth conditions.

[0226] The ninth condition is that the clothing type is common. The tenth condition is that the clothing type identification information is common.

[0227] This allows at least group behavior attributes to be identified using clothing attributes, making it possible to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0228] According to the present embodiment, the clothing attributes further include one or more of a second clothing attribute related to the color of the clothing and a third clothing attribute related to the pattern of the clothing. The attribute specifying unit 234 includes one or more of a first clothing specifying unit 234i, a second clothing specifying unit 234j, and a third clothing specifying unit 234k, and a clothing type identifying unit 234l.

[0229] The first clothing identification unit 234i identifies the type of clothing of each of the multiple customers, the second clothing identification unit 234j identifies the color of the clothing of each of the multiple customers, and the third clothing identification unit 234k identifies the pattern of the clothing of each of the multiple customers.

[0230] The clothing type identification unit 234l identifies clothing type identification information using one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and clothing type identification conditions. The clothing type identification conditions are conditions for identifying clothing that belongs to a predetermined clothing type.

[0231] This allows at least group behavior attributes to be identified using clothing attributes, making it possible to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0232] The clothing type identification information can also be used to identify the group type, which makes it possible to understand customer behavior in a facility depending on whether the customer is acting in a group or alone.

[0233] According to this embodiment, the clothing type identification condition is defined using a clothing similarity indicating the degree of similarity between clothing items and a predetermined identification threshold, and is calculated using the similarity of one or more of the second clothing attribute and the third clothing attribute.

[0234] This allows for identifying clothing type identification information using clothing similarity according to the degree of similarity of one or more of the second clothing attribute and the third clothing attribute. At least group behavior attributes can be identified using clothing attributes including clothing type identification information. Therefore, it becomes possible to understand customer behavior in a facility depending on whether the customer is in a group or alone.

[0235] The clothing type identification information can also be used to identify the group type, which makes it possible to understand customer behavior in a facility depending on whether the customer is acting in a group or alone.

[0236] Third Embodiment In this embodiment, an example of a method for identifying the non-purchasing attributes listed in the first embodiment will be described.

[0237] In this embodiment, for the sake of brevity, the description of the same configuration as in the first embodiment will be omitted as appropriate.

[0238] The information processing system according to this embodiment includes a video analysis device 303 instead of the video analysis device 103 according to embodiment 1. Except for this point, the information processing system according to this embodiment may be configured similarly to the information processing system 100 according to embodiment 1.

[0239] 13 is a diagram showing an example of the functional configuration of a video analysis device 303 according to embodiment 3. The video analysis device 203 functionally includes, for example, an analysis unit 332 that replaces the analysis unit 132 according to embodiment 1. Except for this point, the video analysis device 303 may be configured similarly to the video analysis device 103 according to embodiment 1.

[0240] When the video acquisition unit 131 acquires a video, the analysis unit 332 processes the acquired video using the same analysis function as the analysis unit 132 according to embodiment 1. Then, the analysis unit 332 detects an object included in the video and identifies the attributes of the detected object.

[0241] The analysis unit 332 includes an object detection unit 133 similar to that of the first embodiment, and an attribute identification unit 334 that replaces the attribute identification unit 134 according to the first embodiment. Like the attribute identification unit 134 according to the first embodiment, the attribute identification unit 334 processes a video related to the facility, identifies a plurality of attributes related to each of a plurality of customers included in the video, and generates attribute information including the plurality of attributes for each of the plurality of customers.

[0242] The multiple attributes according to this embodiment include (1) a solo / group behavior attribute. The multiple attributes according to this embodiment further include at least one of (2) a purchase / non-purchase attribute, (3) a facility used attribute, (9) a payment / non-payment attribute, and (10) a baggage attribute. The (1) solo / group behavior attribute, (2) a purchase / non-purchase attribute, and (3) a facility used attribute according to this embodiment may be the same as those in the first embodiment.

[0243] (9) Examples of Checkout / Non-Checkout Attributes The checkout / non-checkout attribute is an attribute that indicates whether a customer is a checkout customer or a non-checkout customer. A checkout customer is a customer who has checked out for merchandise at the facility. A non-checkout customer is a customer who has not checked out for merchandise at the facility.

[0244] The settlement / non-settlement attribute includes at least one of a settlement attribute and a non-settlement attribute. The settlement attribute is an attribute that indicates a settlement customer. The non-settlement attribute is an attribute that indicates a non-settlement customer.

[0245] In this embodiment, the settlement / non-settlement attribute is represented by two codes "0" and "1" that are predetermined to correspond to settlement customers and non-settlement customers, respectively. In this case, the settlement / non-settlement attribute "0" is an example of the settlement attribute. The settlement / non-settlement attribute "1" is an example of the non-settlement attribute.

[0246] (10) Examples of Baggage Attributes The baggage attributes are attributes related to the baggage carried by the customer. The baggage attributes include, for example, at least one of a first baggage attribute related to the color of the baggage, a second baggage attribute related to the pattern of the baggage, and a third baggage attribute related to the shape of the baggage.

[0247] The first package attribute may be represented by at least one of, for example, a code that is predetermined in association with the package color, a numerical value that indicates the package color, and the like.

[0248] The second baggage attribute may be represented by a predetermined code associated with, for example, a clothing pattern (pattern). The baggage pattern may be a pattern on a shopping bag, or a pattern on the packaging or other product packaging of products sold at the facility. The shopping bag may include a bag provided by the facility (e.g., a plastic shopping bag), a bag owned by the customer for carrying purchased products, etc.

[0249] The third baggage attribute may be represented by a predetermined code associated with, for example, the shape (shape pattern) of clothing. The baggage shape pattern may be the shape of a shopping bag, the shape of a product sold at a facility, etc.

[0250] The details of the package attributes are not limited to the color, pattern, and shape of the package, but may also include, for example, size.

[0251] In this embodiment as well, the attribute specifying unit 334 includes a specifying unit for specifying each of the multiple attributes.

[0252] 14 is a diagram illustrating an example of the functional configuration of the attribute identification unit 334 according to embodiment 3. Functionally, the attribute identification unit 334 includes, for example, a group identification unit 134a and a facility-of-use identification unit 134c similar to those in embodiment 1, and a non-purchase identification unit 334b ​​that replaces the non-purchase identification unit 134b according to embodiment 1.

[0253] The attribute identification unit 334 functionally includes, for example, an accounting identification unit 334m, a first package identification unit 334n, a second package identification unit 334o, and a third package identification unit 334p.

[0254] The non-purchasing identification unit 334b ​​processes a video related to the facility and identifies non-purchasing attributes for each of the multiple customers included in the video, similar to the group identification unit 134a according to embodiment 1. Based on the identification results, the non-purchasing identification unit 334b ​​associates, for example, purchasing / non-purchasing attributes with each of the multiple customers included in the attribute information.

[0255] Specifically, the non-purchasing identification unit 334b ​​identifies non-purchasing attributes for each of the multiple customers using the second attribute group of each of the multiple customers and one or more second discrimination conditions.

[0256] The second attribute group includes at least one attribute preselected from the plurality of attributes as an attribute to be used to identify non-purchasing customers, such as a payment attribute, a parcel attribute, etc.

[0257] The second determination condition is a condition for determining whether a customer is a non-purchasing customer, and may be defined in advance using a second attribute group.

[0258] The one or more second determination conditions include, for example, at least one of the following second determination conditions 1 and 2.

[0259] The second discrimination condition 1 is that the facility's payment device is not being used.

[0260] The second determination condition 2 is that the baggage attribute of the customer exiting the facility is not a purchased baggage that is predetermined using one or more of the first baggage attribute, the second baggage attribute, and the third baggage attribute. The purchased baggage is a baggage that the customer has purchased at the facility. For example, the purchased baggage is a baggage that the customer is carrying when leaving the facility, such as a predetermined shopping bag or a product sold at the facility.

[0261] The second determination condition is not limited to the example given here.

[0262] The non-purchasing identification unit 334b ​​identifies a second attribute group for each of the multiple customers, for example, by using attribute information. Then, the non-purchasing identification unit 334b ​​identifies a non-purchasing attribute for the identified customer depending on whether the second attribute group of the identified customer satisfies a second determination condition.

[0263] For example, if the second attribute group of the identified customer does not satisfy one or more second discrimination conditions, the non-purchasing identification unit 334b ​​sets the code "0" corresponding to a purchasing customer to the purchasing / non-purchasing attribute associated with the identified customer in the attribute information. If the first attribute group of the identified customer satisfies one or more first discrimination conditions, the non-purchasing identification unit 334b ​​does not change the initial value "1" of the purchasing / non-purchasing attribute associated with the identified customer in the attribute information.

[0264] In this way, the second discrimination condition is determined using an attribute other than the non-purchasing attribute. Therefore, after each of the determination units 334m to 334p described below has determined the non-purchasing attribute, the non-purchasing determination unit 334b ​​may determine the non-purchasing attribute for each of the multiple customers using the determination results. Note that the method by which the non-purchasing determination unit 334b ​​determines the non-purchasing attribute is not limited to the example described here.

[0265] The settlement identification unit 334m processes, for example, a video related to the facility and identifies the settlement attributes of each of the multiple customers included in the video using a third determination condition for determining whether the customer used a settlement device. The third determination condition may include, for example, whether each of the multiple customers stayed within a predetermined range of the settlement device at the facility for a predetermined length of time equal to or longer than a first hour. However, the third determination condition is not limited to this.

[0266] Based on the identification result, the settlement identification unit 334m associates a settlement attribute with each of the multiple customers included in the attribute information.

[0267] Each of the first to third luggage identification units 334n to 334p is an example of a luggage attribute identification unit that processes a video related to a facility and identifies luggage attributes of each of multiple customers included in the video. Based on the identification results, the luggage attribute identification unit associates luggage attributes with each of multiple customers included in the attribute information.

[0268] The first package identifier 334n processes, for example, a video related to a facility and identifies an attribute (first package attribute) related to the color of the package carried by each of the multiple customers included in the video. Based on the identification result, the first package identifier 334n associates the first package attribute with each of the multiple customers included in the attribute information.

[0269] The second package identifier 334o processes, for example, a video related to the facility and identifies attributes (second package attributes) related to the patterns of packages carried by each of the multiple customers included in the video. Based on the identification results, the second package identifier 334o associates the second package attributes with each of the multiple customers included in the attribute information.

[0270] The third package identifier 334p processes, for example, a video related to the facility and identifies attributes (third package attributes) related to the shape of packages carried by each of the multiple customers included in the video. Based on the identification result, the third package identifier 334p associates the third package attribute with each of the multiple customers included in the attribute information.

[0271] Up to this point, an example of the functional configuration of the information processing system according to the third embodiment has been mainly described. The information processing system according to the third embodiment may be physically configured in the same manner as the information processing system 100 according to the first embodiment. For example, the video analysis device 303 may be physically configured in the same manner as the video analysis device 103 according to the first embodiment. From here, an example of the operation of the information processing system according to the third embodiment will be described. (Example of the Operation of the Information Processing System According to the Third Embodiment) The information processing system according to this embodiment executes information processing including, for example, a video analysis process different from that of the first embodiment and a statistical process similar to that of the first embodiment. The video analysis process according to this embodiment will be described with reference to the drawings.

[0272] 15 is a flowchart showing an example of video analysis processing according to embodiment 3. The video analysis processing according to this embodiment includes an attribute identification process (step S303) instead of the attribute identification process (step S103) according to embodiment 1. Except for this, the video analysis processing according to this embodiment may be similar to the video analysis processing according to embodiment 1.

[0273] As in the first embodiment, when steps S101 and S102 are executed, the attribute identification unit 334 processes the video acquired in step S101 to identify a plurality of attributes for each of a plurality of customers included in the video (step S303). The details of the attribute identification process (step S303) differ from the attribute identification process (step S103) according to the first embodiment.

[0274] As shown in FIG. 15, for example, the group identifying unit 134a identifies a group behavior attribute in the same manner as in the first embodiment (step S103a).

[0275] For example, the non-purchasing identification unit 334b ​​processes video related to the facility and identifies non-purchasing attributes for each of the multiple customers included in the video using a second attribute group for each of the multiple customers and one or more second discrimination conditions (step S303b).

[0276] For example, the facility-to-be-used identifying unit 134c identifies the facility-to-be-used attribute in the same manner as in the first embodiment (step S103c).

[0277] For example, the settlement specification unit 334m processes the video related to the facility and specifies the settlement attribute of each of the multiple customers included in the video using a predetermined third determination condition (step S303m).

[0278] In step S303m, the settlement attribute is identified using the first to third package attributes. Therefore, step S303m may be executed using the identified first to third package attributes after steps S303n to S303p (described later) are executed to identify the first to third package attributes.

[0279] For example, the first package identifier 334n processes a video related to a facility to identify a first package attribute for each of a plurality of customers included in the video (step S303n), the second package identifier 334o processes a video related to the facility to identify a second package attribute for each of a plurality of customers included in the video (step S303o), and the third package identifier 334p processes a video related to the facility to identify a third package attribute for each of a plurality of customers included in the video (step S303p).

[0280] The attribute identification unit 334 generates attribute information that associates the multiple attributes identified in steps S103a, S303b, S103c, and S203m to S203p with each of the multiple customers detected in step S102. As in the first embodiment, the attribute identification unit 334 stores the attribute information generated in the attribute identification process (step S303) in the attribute information storage unit 135 (step S104), and ends the video analysis process.

[0281] The order of steps S103a, S303b, S103c, and S203m to S203p may be changed as appropriate. However, when identifying an attribute using the results of identifying other attributes, the identification of the attribute may be performed after the other attributes necessary for identifying the attribute have been identified.

[0282] By executing such video analysis processing, it is possible to identify non-purchasing attributes. Furthermore, it is possible to identify more attributes than in embodiment 1. Therefore, in the customer statistical processing, it is possible to perform statistical processing using more attributes than in embodiment 1.

[0283] (Operations and Effects) As described above, according to this embodiment, the multiple attributes further include at least one of a payment attribute indicating that payment for merchandise has been made at the facility and a baggage attribute relating to baggage carried by the customer.

[0284] The attribute identification unit 334 includes a non-purchasing identification unit 334b ​​that identifies, among the multiple customers, the non-purchasing attributes of customers who have not purchased any products at the facility, using a second attribute group and one or more second discrimination conditions for identifying customers who have not purchased any products at the facility. The second attribute group includes at least one of a payment attribute and a baggage attribute.

[0285] This allows the second attribute group to be used to identify non-purchasing attributes, which in turn allows the behavior of customers in a facility to be understood depending on whether they are in a group or alone.

[0286] According to this embodiment, the luggage attributes include one or more of a first luggage attribute, a second luggage attribute, and a third luggage attribute, which are respectively related to the color, pattern, size, and shape of the luggage. The second determination condition includes at least one of the following: the facility's checkout device is not being used; and the luggage attribute of the customer exiting the facility is not purchased luggage. Purchased luggage is luggage that is predetermined using one or more of the first luggage attribute, the second luggage attribute, and the third luggage attribute.

[0287] This allows the baggage attribute to be used to identify non-purchase attributes, which in turn allows the behavior of customers in a facility to be understood depending on whether they are in a group or traveling alone.

[0288] According to this embodiment, the attribute identification unit 334 further includes a settlement identification unit 334m that identifies a settlement attribute using a third determination condition for determining whether or not the customer has used a settlement device.

[0289] This allows the identification of payment attributes, and the identification of non-purchase attributes using the payment attributes, thereby making it possible to further use the non-purchase attributes to understand customer behavior in a facility depending on whether the customer acts in a group or acts alone.

[0290] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations can also be adopted.

[0291] In addition, although the flowcharts used in the above description show multiple steps (processes) in a sequential order, the order of steps executed in each embodiment is not limited to the order shown. In each embodiment, the order of the steps shown in the drawings can be changed as long as it does not cause any problems in terms of content. Furthermore, the above-described embodiments can be combined as long as the content is not contradictory.

[0292] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0293] 1. An information processing system comprising: attribute identification means for processing video related to a facility and identifying a plurality of attributes for each of a plurality of customers; and statistical processing means for performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes, wherein the at least one attribute includes a group behavior attribute for customers who act in groups of a plurality of people. 2. The information processing system described in 1., wherein the attributes further include a non-purchasing attribute for customers who do not purchase any products at the facility. 3. The plurality of attributes further include at least one of an age group of the customer, a distance attribute related to a customer-to-customer distance that is the distance between the customer and other customers, a store visit time attribute related to a time when the customer visits the store, a store visit means attribute related to a means by which the customer visits the store, and a clothing attribute related to the clothing of the customer, wherein the attribute identification means includes group identification means for identifying the group behavior attribute for each of the plurality of customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for discriminating between customers who act in groups of a plurality of people. or 2. The information processing system described in 3. 4. The information processing system described in 3., wherein the plurality of attributes include a group attribute related to the group, and the attribute identification means further includes a group attribute identification means for identifying the group attribute of the customer acting in the group of multiple people. 5. The information processing system described in 4., wherein the group attribute includes the group type, and the group attribute identification means includes a group type identification means for using group type definition information that associates the group type with the at least one first discrimination condition to identify the group type associated with the at least one first discrimination condition satisfied by the customer acting in the group of multiple people as the group type of the customer acting in the group of multiple people.6. The information processing system described in any one of 3. to 5., wherein each of the one or more first discrimination conditions includes at least one of: the age groups are the same or different within a predetermined range; the distance between the customers when they visit the store is within a predetermined first distance; the time difference between when they entered the facility is within a predetermined second hour; the distance between the customers when they visit with children whose age group is equal to or below a predetermined age threshold is within a predetermined second distance; the time difference between when they visit with the children is within a predetermined fourth hour; and the proximity behavior time obtained by adding up the length of time during which the distance between the customers is within a predetermined third distance from each other over the period of their stay at the facility is equal to or greater than a predetermined fifth hour. 10. The information processing system of any one of 3. to 6., wherein the store arrival means attribute includes store arrival means identification information for the store arrival means that can be used by multiple people simultaneously, and each of the one or more first discrimination conditions includes at least one of: a time difference between times when the multiple people entered the premises of the facility using store arrival means that have different store arrival means identification information for identifying the store arrival means is within a predetermined third hour, and, when the multiple people arrived using store arrival means that can be used by multiple people simultaneously, they arrived using store arrival means that have the same store arrival means identification information. 11. The information processing system of any one of 3. to 7., wherein the clothing attribute includes a first clothing attribute related to the type of clothing, and the first clothing attribute includes clothing type identification information for identifying clothing that belongs to a predetermined type of clothing, and each of the one or more first discrimination conditions includes at least one of: the clothing type being common, and the clothing type identification information being common.9. The information processing system described in 8., wherein the clothing attributes further include one or more of a second clothing attribute related to the color of the clothing and a third clothing attribute related to the pattern of the clothing, and the attribute identification means includes one or more of: a first clothing identification means for identifying the type of clothing of each of the plurality of customers, a second clothing identification means for identifying the color of the clothing of each of the plurality of customers, and a third clothing identification means for identifying the pattern of the clothing of each of the plurality of customers, and clothing type identification means for identifying the clothing type identification information using one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and clothing type identification conditions for identifying clothing belonging to a predetermined type of clothing. 10. The information processing system described in 9., wherein the clothing type identification conditions are defined using clothing similarity indicating the degree to which the clothing is similar and a predetermined identification threshold, and are determined using the respective similarities of one or more of the second clothing attribute and the third clothing attribute. 12. The information processing system described in any one of 2. to 10., wherein the plurality of attributes further include at least one of a settlement attribute indicating that a payment for merchandise has been made at the facility and a baggage attribute related to baggage carried by the customer, and the attribute identification means includes non-purchasing identification means for identifying the non-purchasing attribute of a customer among the plurality of customers who has not purchased merchandise at the facility using a second attribute group including at least one of the settlement attribute and the baggage attribute and one or more second discrimination conditions for identifying customers who have not purchased merchandise at the facility. 13. The information processing system described in 11., wherein the baggage attribute includes one or more of a first baggage attribute, a second baggage attribute, and a third baggage attribute respectively related to the color, pattern, size, and shape of the baggage, and the second discrimination condition includes at least one of: not using a payment device at the facility, and the baggage attribute of the customer leaving the facility is not purchased baggage predetermined using one or more of the first baggage attribute, the second baggage attribute, and the third baggage attribute. 13. The information processing system according to Item 12, wherein the attribute specifying means further includes a settlement specifying means for specifying the settlement attribute using a third determination condition for determining whether or not the customer has used a settlement device.14. The information processing system described in any one of 1. to 13., wherein the plurality of attributes further includes a facility usage attribute related to the facility facilities used by the customer. 15. An information processing method including one or more computers processing facility-related video to identify a plurality of attributes related to each of a plurality of customers, and performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes, wherein the at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people. 16. The information processing method described in 15., wherein the attributes further include a non-purchasing attribute related to customers who do not purchase any products at the facility. 17. The information processing method described in 15. or 16., wherein the multiple attributes further include at least one of an age group of the customer, a distance attribute related to a customer-to-customer distance that is the distance between the customer and other customers, a store visit time attribute related to a store visit time of the customer, a store visit means attribute related to a store visit means of the customer, and a clothing attribute related to the customer's clothing, and specifying the multiple attributes includes specifying the group behavior attribute for each of the multiple customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for discriminating customers who act in groups of multiple people. 18. The information processing method described in 17., wherein the multiple attributes include a group attribute related to the group, and specifying the multiple attributes further includes specifying the group attribute of customers who act in groups of multiple people. 19. The information processing method according to Item 18, wherein the group attribute includes the group type, and specifying the group attribute includes using group type definition information that associates the group type with the at least one first discrimination condition to specify the group type associated with the at least one first discrimination condition satisfied by the customer acting in a group of multiple people as the group type of the customer acting in a group of multiple people.20. The information processing method described in any one of 17. to 19., wherein each of the one or more first discrimination conditions includes at least one of: the age groups are the same or different within a predetermined range; the distance between the customers when they visit the store is within a predetermined first distance; the time difference between when they entered the facility is within a predetermined second hour; the distance between the customers when they visit with children whose age group is equal to or below a predetermined age threshold is within a predetermined second distance; the time difference between when they visit with the children is within a predetermined fourth hour; and the proximity behavior time obtained by adding up the length of time during which the distance between the customers is within a predetermined third distance from each other over the period of their stay at the facility is equal to or greater than a predetermined fifth hour. The information processing method described in any one of 17. to 20., wherein the store arrival means attribute includes the store arrival means identification information for the store arrival means that can be used by multiple people simultaneously, and each of the one or more first discrimination conditions includes at least one of: a time difference between times when the people entered the premises of the facility using store arrival means that have different store arrival means identification information for identifying the store arrival means is within a predetermined third hour, and, if the multiple people arrived using store arrival means that can be used by multiple people simultaneously, they arrived using store arrival means that have the same store arrival means identification information. 22. The information processing method described in any one of 17. to 21., wherein the clothing attribute includes a first clothing attribute related to the type of clothing, and the first clothing attribute includes clothing type identification information for identifying clothing that belongs to a predetermined type of clothing, and each of the one or more first discrimination conditions includes at least one of: the clothing type being common, and the clothing type identification information being common.23. The information processing method described in 22., wherein the clothing attributes further include one or more of a second clothing attribute related to the color of the clothing and a third clothing attribute related to the pattern of the clothing, and specifying the multiple attributes includes one or more of: specifying the type of clothing for each of the multiple customers; specifying the color of the clothing for each of the multiple customers; and specifying the pattern of the clothing for each of the multiple customers; and specifying the clothing type identification information using one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and clothing type identification conditions for identifying clothing belonging to a predetermined type of clothing. 24. The information processing method described in 23., wherein the clothing type identification conditions are defined using clothing similarity indicating the degree to which the clothing is similar and a predetermined identification threshold, and are determined using the respective similarities of one or more of the second clothing attribute and the third clothing attribute. 25. The information processing method described in any one of 16. to 24., wherein the multiple attributes further include at least one of a settlement attribute indicating that a payment for merchandise has been made at the facility and a baggage attribute related to baggage carried by the customer, and identifying the multiple attributes includes identifying the non-purchasing attribute of customers among the multiple customers who have not purchased merchandise at the facility using a second attribute group including at least one of the settlement attribute and the baggage attribute and one or more second discrimination conditions for discriminating customers who have not purchased merchandise at the facility. 26. The information processing method described in 25., wherein the baggage attribute includes one or more of a first baggage attribute, a second baggage attribute, and a third baggage attribute respectively related to the color, pattern, size, and shape of the baggage, and the second discrimination condition includes at least one of: not using a payment device at the facility, and the baggage attribute of the customer leaving the facility is not purchased baggage predetermined using one or more of the first baggage attribute, the second baggage attribute, and the third baggage attribute. 27. 26. The information processing method according to 25., wherein identifying the plurality of attributes further includes identifying the payment attributes using a third determination condition for determining whether the customer has used the payment device.28. The information processing method described in any one of 15. to 27., wherein the plurality of attributes further includes facility usage attributes related to the facility facilities used by the customer. 29. A program for causing one or more computers to process facility-related video to identify a plurality of attributes related to each of a plurality of customers, and perform statistical processing related to the plurality of customers using at least one attribute included in the identified plurality of attributes, and for causing the at least one attribute to include a group behavior attribute related to customers who act in groups of multiple people. 30. The program described in 29., wherein the attributes further include non-purchasing attributes related to customers who do not purchase any products at the facility. 31. The program described in 29. or 30., wherein the multiple attributes further include at least one of an age group of the customer, a distance attribute related to a customer-to-customer distance that is the distance between the customer and other customers, a store visit time attribute related to a store visit time of the customer, a store visit means attribute related to a store visit means of the customer, and a clothing attribute related to the customer's clothing, and specifying the multiple attributes includes specifying the group behavior attribute for each of the multiple customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for discriminating customers who act in groups of multiple people. 32. The program described in 31., wherein the multiple attributes include a group attribute related to the group, and specifying the multiple attributes further includes specifying the group attribute of customers who act in groups of multiple people. 32. The program according to Item 32, wherein the group attribute includes the group type, and identifying the group attribute includes using group type definition information that associates the group type with the at least one first discrimination condition to identify the group type associated with the at least one first discrimination condition satisfied by the customer acting in a group of multiple people as the group type of the customer acting in a group of multiple people.34. The program described in any one of 31. to 33., wherein each of the one or more first discrimination conditions includes at least one of: the age groups are the same or different within a predetermined range; the distance between the customers at the time of their visit is within a predetermined first distance; the time difference between the times when they entered the facility is within a predetermined second hour; the distance between the customers at the time of their visit with a child whose age group is equal to or below a predetermined age threshold is within a predetermined second distance; the time difference between the times when the customers visited with the child is within a predetermined fourth hour; and the proximity behavior time obtained by adding up the length of time during which the distance between the customers is within a predetermined third distance from each other over the period of their stay at the facility is equal to or greater than a predetermined fifth hour. 35. The program described in any one of 31. to 34., wherein the means of arrival attribute includes the means of arrival identification information for the means of arrival that can be used by multiple people simultaneously, and each of the one or more first discrimination conditions includes at least one of: a time difference between times when the multiple people entered the premises of the facility using means of arrival that have different means of arrival identification information for identifying the means of arrival is within a predetermined third hour, and, when the multiple people arrived using means of arrival that can be used by multiple people simultaneously, they arrived using means of arrival that have the same means of arrival identification information. 36. The program described in any one of 31. to 35., wherein the clothing attribute includes a first clothing attribute related to the type of clothing, and the first clothing attribute includes clothing type identification information for identifying clothing that belongs to a predetermined type of clothing, and each of the one or more first discrimination conditions includes at least one of: the clothing type is common, and the clothing type identification information is common.37. The program described in 36., wherein the clothing attributes further include one or more of a second clothing attribute related to the color of the clothing and a third clothing attribute related to the pattern of the clothing, and identifying the multiple attributes includes one or more of: identifying the type of clothing for each of the multiple customers; identifying the color of the clothing for each of the multiple customers; and identifying the pattern of the clothing for each of the multiple customers; and identifying the clothing type identification information using one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and clothing type identification conditions for identifying clothing belonging to a predetermined type of clothing. 38. The program described in 37., wherein the clothing type identification conditions are defined using clothing similarity indicating the degree to which the clothing is similar and a predetermined identification threshold, and are determined using the respective similarities of one or more of the second clothing attribute and the third clothing attribute. 39. The program described in any one of items 30 to 38, wherein the multiple attributes further include at least one of a settlement attribute indicating that a payment for merchandise has been made at the facility and a baggage attribute related to baggage carried by the customer, and identifying the multiple attributes includes identifying the non-purchasing attribute of customers among the multiple customers who have not purchased merchandise at the facility using a second attribute group including at least one of the settlement attribute and the baggage attribute and one or more second discrimination conditions for distinguishing customers who have not purchased merchandise at the facility. 40. The program described in item 39, wherein the baggage attribute includes one or more of a first baggage attribute, a second baggage attribute, and a third baggage attribute respectively related to the color, pattern, size, and shape of the baggage, and the second discrimination condition includes at least one of: not using a payment device at the facility, and the baggage attribute of the customer leaving the facility is not purchased baggage predetermined using one or more of the first baggage attribute, the second baggage attribute, and the third baggage attribute. 40. The program according to claim 40, wherein identifying the plurality of attributes further includes identifying the payment attributes using a third determination condition for determining whether the customer has used the payment device.42. The program described in any one of 29. to 41., wherein the plurality of attributes further includes facility usage attributes related to the facility facilities used by the customer. 43. A recording medium having recorded thereon a program that causes one or more computers to process facility-related video to identify a plurality of attributes related to each of a plurality of customers, and perform statistical processing related to the plurality of customers using at least one attribute included in the identified plurality of attributes, and to include in the at least one attribute a group behavior attribute related to customers who act in groups of multiple people. 44. A recording medium having recorded thereon the program described in 43., wherein the attributes further include non-purchasing attributes related to customers who do not purchase products at the facility. 45. 43. A recording medium having recorded thereon the program described in 43. or 44., wherein the multiple attributes further include at least one of an age group of the customer, a distance attribute related to a customer-to-customer distance which is the distance between the customer and other customers, a store visit time attribute related to a store visit time of the customer, a store visit means attribute related to a store visit means of the customer, and a clothing attribute related to the customer's clothing, and specifying the multiple attributes includes specifying the group behavior attribute for each of the multiple customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for discriminating customers who act in groups of multiple people. 46. A recording medium having recorded thereon the program described in 45., wherein the multiple attributes include a group attribute related to the group, and specifying the multiple attributes further includes specifying the group attribute of customers who act in groups of multiple people. 46. ​​A recording medium on which the program described in 46. is recorded, wherein the group attribute includes the group type, and specifying the group attribute includes using group type definition information that associates the group type with the at least one first discrimination condition to specify the group type associated with the at least one first discrimination condition satisfied by the customer acting in a group of multiple people as the group type of the customer acting in a group of multiple people.48. A recording medium having recorded thereon the program described in any one of 45. to 47., wherein each of the one or more first discrimination conditions includes at least one of: the age groups are the same or different within a predetermined range; the distance between the customers at the time of visiting the store is within a predetermined first distance; the time difference between the times when the customers entered the facility is within a predetermined second hour; the distance between the customers at the time of visiting with a child whose age group is equal to or below a predetermined age threshold is within a predetermined second distance; the time difference between the times when the customers visited with the child is within a predetermined fourth hour; and the proximity behavior time obtained by adding up the length of time during which the distance between the customers is within a predetermined third distance from each other over the period of stay at the facility is equal to or longer than a predetermined fifth hour. 48. A recording medium having recorded thereon the program described in any one of 45. to 48., wherein the store arrival means attribute includes the store arrival means identification information for the store arrival means that can be used by multiple people simultaneously, and each of the one or more first discrimination conditions includes at least one of: a time difference between times when the users entered the facility premises using store arrival means that have different store arrival means identification information for identifying the store arrival means is within a predetermined third hour period, and, when the multiple users arrived using store arrival means that can be used by multiple people simultaneously, they arrived using store arrival means that have the same store arrival means identification information. 50. A recording medium having recorded thereon the program described in any one of 45. to 49., wherein the clothing attribute includes a first clothing attribute related to the type of clothing, and the first clothing attribute includes clothing type identification information for identifying clothing that belongs to a predetermined type of clothing, and each of the one or more first discrimination conditions includes at least one of: the clothing type being common, and the clothing type identification information being common.51. A recording medium having recorded thereon the program described in 50., wherein the clothing attributes further include one or more of a second clothing attribute related to the color of the clothing and a third clothing attribute related to the pattern of the clothing, and specifying the plurality of attributes includes one or more of: specifying the type of clothing for each of the plurality of customers; specifying the color of the clothing for each of the plurality of customers; and specifying the pattern of the clothing for each of the plurality of customers; and specifying the clothing type identification information using one or more of the first clothing attribute, the second clothing attribute, and the third clothing attribute and clothing type identification conditions for identifying clothing belonging to a predetermined type of clothing. 52. A recording medium having recorded thereon the program described in 51., wherein the clothing type identification conditions are defined using clothing similarity indicating the degree to which the clothing is similar and a predetermined identification threshold, and are determined using the respective similarities of one or more of the second clothing attribute and the third clothing attribute. 53. 44. A recording medium having a program described in any one of items 44 to 52 recorded thereon, wherein the plurality of attributes further include at least one of a settlement attribute indicating that payment for merchandise has been made at the facility and a baggage attribute related to baggage carried by the customer, and identifying the plurality of attributes includes identifying the non-purchasing attribute of a customer among the plurality of customers who has not purchased merchandise at the facility using a second attribute group including at least one of the settlement attribute and the baggage attribute and one or more second discrimination conditions for discriminating customers who have not purchased merchandise at the facility. 54. A recording medium having a program described in item 53 recorded thereon, wherein the plurality of attributes further include at least one of a settlement attribute indicating that payment for merchandise has been made at the facility and a baggage attribute related to baggage carried by the customer, and identifying the non-purchasing attribute of a customer among the plurality of customers who has not purchased merchandise at the facility using a second attribute group including at least one of the settlement attribute and the baggage attribute and one or more second discrimination conditions for discriminating customers who have not purchased merchandise at the facility.55. A recording medium having recorded thereon the program described in 54., wherein identifying the plurality of attributes further includes identifying the payment attribute using a third determination condition for determining whether the customer has used a payment device. 56. A recording medium having recorded thereon the program described in any one of 43. to 55., wherein the plurality of attributes further include a facility use attribute related to the facility equipment used by the customer.

[0294] This application claims priority based on Japanese Patent Application No. 2023-022231, filed February 16, 2023, the disclosure of which is incorporated herein by reference in its entirety.

[0295] 100 Information processing system 101_1 to 101_M Imaging device 102 Video storage device 103, 203, 303 Video analysis device 104 Statistical processing device 111 Analysis unit 131 Video acquisition unit 132, 232, 332 Analysis unit 133 Object detection unit 134, 234, 334 Attribute identification unit 134a, 234a Group identification unit 134b, 334b ​​Non-purchase identification unit 134c Usage facility identification unit 135 Attribute information storage unit 136 Attribute transmission unit 141 Selection reception unit 142 Attribute information acquisition unit 143 Statistical processing unit 144 Output unit 145 Output control unit 234d Group attribute identification unit 234d1 Group type identification unit 234e Age group identification unit 234f Distance attribute identification unit 234h Visit means attribute identification unit 234i First clothing identification unit 234j Second clothing identification unit 234k Third clothing identification unit 234l Clothing type identification unit 334m Payment identification unit 334n First luggage identification unit 334o Second luggage identification unit 334p Third luggage identification unit

Claims

1. attribute identification means for processing video associated with the facility to identify a plurality of attributes associated with each of a plurality of customers; a statistical processing means for performing statistical processing on the plurality of customers using at least one attribute included in the specified plurality of attributes, The at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people. Information processing system.

2. The attributes further include non-purchasing attributes for customers who do not purchase merchandise at the facility. The information processing system according to claim 1 .

3. The plurality of attributes further include at least one of an age group of the customer, a distance attribute relating to a customer distance that is a distance between the customer and other customers, a store visit time attribute relating to a store visit time of the customer, a store visit means attribute relating to a store visit means of the customer, and a clothing attribute relating to clothing of the customer; The attribute identification means includes group identification means for identifying the group behavior attribute for each of the plurality of customers using a first attribute group including at least one of the age group, the distance attribute, the store visit time attribute, the store visit means attribute, and the clothing attribute, and one or more first discrimination conditions for discriminating customers who act in groups of the plurality of customers.

3. The information processing system according to claim 1 or 2.

4. the plurality of attributes includes a group attribute related to the group; The attribute specifying means further includes a group attribute specifying means for specifying the group attribute of the customers who act in a group of multiple people, the group attribute includes the group type, The group attribute specifying means includes a group type specifying means for specifying, by using group type defining information associating the group type with the at least one first discrimination condition, the group type associated with the at least one first discrimination condition satisfied by the customer acting in a group of a plurality of people, as the group type of the customer acting in the group of a plurality of people. The information processing system according to claim 3 .

5. Each of the one or more first determination conditions is The age groups are the same or different within a predetermined range; The distance between the customers when they visit the store is within a predetermined first distance. the time difference between the times when the users entered the facility is within a predetermined second time; the distance between the customer and a child who is below a predetermined age threshold and who visits the store together with the customer is within a predetermined second distance; The time difference between the visits of the customer and the child is within a predetermined fourth hour period; and a proximity behavior time, which is the sum of the length of time during which the distance between the customers is within a predetermined third distance from each other over the period of time during which the customers stay at the facility, is equal to or longer than a predetermined fifth time. The information processing system according to claim 3 .

6. The store visit means attribute includes the store visit means identification information for the store visit means that can be used by multiple people at the same time, Each of the one or more first determination conditions is The time difference between the times when the customer entered the facility premises using the different store-visiting means with different store-visiting means identification information is within a predetermined third hour; and When the plurality of people visit the store using the store visit means that can be used at the same time, the plurality of people visit the store using the store visit means that has the same store visit means identification information, the clothing attributes include a first clothing attribute related to a type of the clothing; the first clothing attribute includes clothing type identification information for identifying clothing belonging to a predetermined type of clothing, Each of the one or more first determination conditions is The type of clothing is common; and The clothing type identification information is common. The information processing system according to claim 3 .

7. The plurality of attributes further includes at least one of a checkout attribute indicating that a checkout for merchandise has been completed at the facility and a baggage attribute relating to a baggage carried by the customer; The attribute specifying means includes a non-purchasing specifying means for specifying the non-purchasing attribute of a customer who has not purchased a commodity at the facility among the plurality of customers, using a second attribute group including at least one of the payment attribute and the baggage attribute, and one or more second determination conditions for determining a customer who has not purchased a commodity at the facility. The information processing system according to claim 2 .

8. the luggage attributes include one or more of a first luggage attribute, a second luggage attribute, and a third luggage attribute, each of which is associated with a color, a pattern, a size, and a shape of the luggage; The second discrimination condition is Not using the payment device at the facility; and The luggage attribute of the customer exiting the facility is not a purchased luggage that has been predetermined using one or more of the first luggage attribute, the second luggage attribute, and the third luggage attribute. The information processing system according to claim 7 .

9. One or more computers processing the video associated with the facility to identify a plurality of attributes associated with each of a plurality of customers; performing statistical processing on the plurality of customers using at least one attribute included in the identified plurality of attributes; The at least one attribute includes a group behavior attribute related to customers who act in groups of multiple people. Information processing methods.

10. On one or more computers, processing the video associated with the facility to identify a plurality of attributes associated with each of a plurality of customers; performing statistical processing on the plurality of customers using at least one attribute included in the specified plurality of attributes; A program for including in the at least one attribute a group behavior attribute relating to customers who act in groups of multiple people.