JP7685769B2 - Behavioral attribute analysis system and information processing device - Google Patents

Description

The present invention relates to a behavioral attribute analysis system and information processing device that analyzes people flow.

Conventionally, technologies for analyzing human movement routes have been proposed. For example, Patent Document 1 discloses a data analysis device that analyzes sensor data from sensors installed at multiple points. This data analysis device includes a data receiving unit that receives sensor data via a wireless network, and a data analysis unit that calculates the amount of movement between two points based on the sensor data received by the data receiving unit, and analyzes a series of movement routes by tracing routes with large amounts of movement between two points.

JP 2019-175240 A

The data analysis device described in Patent Document 1 makes it possible to display analysis results such as the amount of movement between two points, the total number of detections, and the number of detections by spot. However, the technology described in Patent Document 1 has the problem that it cannot analyze people flow by patterns of people's behavior.

The present invention has been made to solve the above-mentioned problems, and aims to provide a behavior attribute analysis system and information processing device that can analyze people flow according to people's behavior patterns.

The behavioral attribute analysis system of the present invention includes a detection device that is installed at a plurality of locations and acquires user identification information from communication devices carried by people within a predetermined range, a collection device that collects, as collected information, the user identification information acquired by the detection device, detection identification information that identifies the detection device, and information on the date and time when the user identification information was acquired, and an information processing device that acquires the collected information, wherein the information processing device has a memory unit that stores correspondence information between the detection identification information and the location types, and a behavioral attribute assignment unit that assigns, to each of the user identification information, a behavioral attribute that is a combination of a type of behavior of the person at the plurality of locations and a type of the plurality of locations based on the collected information and the correspondence information, and the location types include types corresponding to demographic attributes of the person .

The present invention can analyze people flow according to patterns of human behavior by assigning behavior attributes, which are a combination of the type of human behavior at a location and the type of location, to each user identification information based on collected information and corresponding information.

1 is a schematic configuration diagram of a behavior attribute analysis system according to a first embodiment. 1 is a schematic layout diagram showing an example of installation of a detection device of a behavior attribute analysis system according to a first embodiment. FIG. 2 is a control block diagram of an information processing device of the behavior attribute analysis system according to the first embodiment. FIG. 4 is a diagram showing a data structure of correspondence information in the behavior attribute analysis system according to the first embodiment; FIG. 2 is a diagram showing a data structure of collected information of the behavior attribute analysis system according to the first embodiment; FIG. 4 is a diagram showing an example of assigning a behavior type in the behavior attribute analysis system according to the first embodiment; FIG. 4 is a diagram showing an example of behavior attribute assignment in the behavior attribute analysis system according to the first embodiment; FIG. FIG. 2 is a diagram showing an input screen of the behavior attribute analysis system according to the first embodiment. FIG. 2 is a diagram showing an input screen of the behavior attribute analysis system according to the first embodiment. FIG. 2 is a diagram showing an output screen of the behavior attribute analysis system according to the first embodiment. FIG. 11 is a control block diagram of an information processing device of a behavior attribute analysis system according to embodiment 3. FIG. 13 is a diagram showing an output screen of the behavior attribute analysis system according to the third embodiment. FIG. 13 is an explanatory diagram of positioning of a behavior attribute analysis system according to embodiment 4. FIG. 13 is a schematic configuration diagram of a behavior attribute analysis system according to a fifth embodiment. FIG. 13 is an explanatory diagram of face authentication in the behavior attribute analysis system according to the fifth embodiment. FIG. 13 is an explanatory diagram of the assignment of user identification information in the behavior attribute analysis system 1 according to embodiment 5.

Embodiment 1.
The behavior attribute analysis system 1 of the first embodiment analyzes the flow of people in a specific area, such as a commercial facility or an airport. The area in which the behavior attribute analysis system 1 analyzes the flow of people can be any area, whether indoors or outdoors. For example, the system may be applied to an outdoor area such as a shopping mall or a theme park.

(System Configuration)
1 is a schematic configuration diagram of a behavior attribute analysis system 1 according to embodiment 1. As shown in FIG. 1, the behavior attribute analysis system 1 includes a plurality of detection devices 10, a collection device 20, and an information processing device 100.

The detection devices 10 are installed at multiple locations within the area to be analyzed for people flow, and communicate with communication devices 2 carried by people P located within a specified range. The communication devices 2 are, for example, information processing terminals such as mobile phones including smartphones, tablet terminals, watch-type information terminals, and notebook PCs (Personal Computers).

The detection device 10 acquires user identification information contained in a communication signal between the detection device 10 and the communication device 2. The communication between the detection device 10 and the communication device 2 is, for example, a beacon signal, and the user identification information is information contained in the beacon signal. Specifically, the detection device 10 is, for example, configured as a Wi-Fi packet sensor, a Wi-Fi access point, or a PC capable of Wi-Fi communication. The detection device 10 receives a Probe Request packet sent from the communication device 2, and acquires unique information for identifying the communication device 2, such as a MAC address (Media Access Control address) or SSID (Service Set Identifier) contained in the Probe Request packet, as user identification information. Note that Wi-Fi is a registered trademark.

The collection device 20 is configured as a PC or a server, and is connected to a plurality of detection devices 10 via a network so as to be able to communicate with each other via wired or wireless communication. The collection device 20 collects, as collected information, the user identification information acquired by the detection device 10, the detection identification information that identifies the detection device 10, and information on the date and time when the user identification information was acquired. The collection device 20 is also connected to the information processing device 100 via a network so as to be able to communicate with each other via wired or wireless communication, and transmits the collected information to the information processing device 100 periodically or on an as-needed basis.

The information processing device 100 is configured as a PC or a server, and performs analysis of people flow. Details will be described later.

Figure 2 is a schematic layout diagram showing an example of installation of the detection device 10 of the behavior attribute analysis system 1 according to the first embodiment. In the first embodiment, an example is described in which the behavior attribute analysis system 1 is applied to the analysis of people flow inside a complex commercial facility that has multiple retail stores, restaurants, entertainment facilities, etc.

As shown in FIG. 2, the detection devices 10 are installed at multiple points within the commercial facility. The detection devices 10 are capable of communicating with communication devices 2 located within a specified range from the installation points. In FIG. 2, the specified range within which the detection devices 10 can communicate with the communication devices 2 is indicated by a dotted circle. This specified range includes, for example, the range of the store floor area of each retail store and restaurant. The specified range also includes, for example, the range of facilities such as the entrances and exits of the commercial facility, men's restrooms, women's restrooms, baby rooms, kids' spaces, escalators, and elevators.

In this way, the detection device 10 is installed at multiple locations within the commercial facility with different uses and purposes of use. Hereinafter, the type or category of the use and purpose of use of the location where the detection device 10 is installed will be referred to as the "location type." Hereinafter, the type of location where the detection device 10 is installed includes a type corresponding to the demographic attributes of person P. Demographic attributes are attributes based on demographic attributes such as a person's gender, age, occupation, family structure, etc. For example, the type of location where the gender corresponds to male is a men's restroom. As another example, the type of location where the age corresponds to children is a cram school. As another example, the type of location where the occupation corresponds to an employee of the commercial facility is an employee entrance. As another example, the type of location where the family structure corresponds to a family with children is a kids' space.

Figure 3 is a control block diagram of the information processing device 100 of the behavior attribute analysis system 1 according to embodiment 1. As shown in Figure 3, the information processing device 100 has an acquisition unit 110, a behavior attribute assignment unit 120, a storage unit 130, an extraction processing unit 140, an input unit 150, and an output unit 160. The acquisition unit 110, the behavior attribute assignment unit 120, and the extraction processing unit 140 are functional units that are realized by the CPU executing a program. The input unit 150 is an interface with an input device, and accepts a selection operation of a behavior attribute, which will be described later. The output unit 160 is an interface with an output device, and outputs the extraction result of the user identification information, which will be described later, to the output device.

The storage unit 130 is made up of non-volatile memory such as RAM, ROM, flash memory, and HDD. The storage unit 130 stores correspondence information between the detection identification information and the type of location. This correspondence information will be explained using FIG. 4.

FIG. 4 is a diagram showing the data structure of the correspondence information of the behavior attribute analysis system 1 according to the first embodiment. As shown in FIG. 4, the correspondence information has detection identification information (Sensor ID) and a location type. The detection identification information is information for identifying the detection device 10. The location type is the name of the type or category of the use and purpose of use of the location where the detection device 10 is installed. Note that the location type may be a general name indicating the use and purpose of use of the location, or may be a specific store or facility name.

(operation)
The operation of the information processing device 100 will be described.
The acquiring unit 110 periodically or at any time acquires collected information from the collecting device 20, and stores the acquired collected information in the storage unit 130. The acquiring unit 110 may perform data cleansing, such as deleting duplicate data, on the information acquired from the collecting device 20. The collected information is stored in the storage unit 130 every time the acquiring unit 110 acquires collected information. This collected information will be described with reference to FIG. 5.

FIG. 5 is a diagram showing the data structure of collected information of the behavior attribute analysis system 1 according to the first embodiment. As shown in FIG. 5, the collected information has user identification information (User ID), detection identification information (Sensor ID), and date and time information (Date Time). The user identification information is information acquired by the detection device 10 from the communication device 2. The detection identification information is information for identifying the detection device 10 that acquired the user identification information. The date and time information is information on the date and time when the detection device 10 acquired the user identification information. In the following description, the location of the detection device 10 whose detection identification information is "S01" may be referred to as "location 1," and the location of the detection device 10 whose detection identification information is "S02" may be referred to as "location 2," etc.

The behavior attribute assigning unit 120 assigns a type of human behavior at the location where the detection device 10 is installed for each user identification information based on the collected information. Here, the type of human behavior is a type or category of a person's characteristic behavior pattern, such as the following:

[stay]
The behavior type "stay" refers to a state in which person P remains at a certain point (location) for a predetermined period of time or more. When user identification information is acquired continuously at one location for a predetermined period of time or more, the behavior attribute assignment unit 120 assigns the behavior type "stay." For example, the predetermined period of time is five minutes. When the behavior type is "stay," it can be distinguished that person P is someone who has used a store or facility at that location.

[passing]
The behavior type "passing" refers to a state in which person P does not stay at a certain point (location) for a predetermined period of time or more. When user identification information is acquired without remaining at one location for a predetermined period of time or more continuously, the behavior attribute assigning unit 120 assigns the behavior type "passing." For example, the predetermined period of time is five minutes. When the behavior type is "passing," it can be distinguished that person P passed through an entrance or passage at the location, or used a means of transportation such as an elevator or escalator.

[First place passed]
The type of behavior "first passed place" refers to the location (place) that the person P passed through first on a specific day. The behavior attribute assigning unit 120 sets the location from which the user identification information was acquired first among multiple locations on a day as the "first passed place" as the type of behavior. When the type of behavior is "first passed place", it is possible to distinguish the entrance/exit through which the person P entered the facility on a specific day.

[Last place passed]
The type of behavior "last passed place" refers to the location (place) that the person P last passed through on a specific day. The behavior attribute assigning unit 120 sets the location from which user identification information was last acquired among multiple locations on a day as the "last passed place" as the type of behavior. When the type of behavior is the "last passed place", it is possible to distinguish the entrance/exit through which the person P left the facility on a specific day.

[Total stay time]
The behavior type "total stay time" refers to the time from the first time that person P enters the facility to the last time that person P leaves the facility on a specific day. The behavior attribute assignment unit 120 calculates the time from the first time that user identification information is acquired to the last time that user identification information is acquired on a single day, and sets this time as the "total stay time" as the behavior type. This total stay time can be used to distinguish whether person P is a long-term visitor or a short-term visitor on a specific day.

[Number of visits]
The number of visits as the type of behavior refers to the number of days on which the person P entered the facility during a specific period or a specified period in the past from a specific day. The behavior attribute assigning unit 120 extracts the number of days on which the user identification information was acquired within the specified period, and sets this as the "number of visits" as a behavior attribute. This number of visits can distinguish whether the person P is a first-time visitor to the facility or a frequent visitor (regular customer).

The behavior attribute assigning unit 120 assigns at least one of the multiple "behavior types" described above to each piece of user identification information. A specific example is shown in FIG. 6.

Figure 6 is a diagram showing an example of behavior classification in the behavior attribute analysis system 1 according to the first embodiment. Note that the example shown in Figure 6 describes a portion of the behavior classification. Also, the example shown in Figure 6 is not consistent with the information exemplified in other figures.

The example shown in FIG. 6 shows a case where "stay" and "pass" are assigned as the behavior types. Based on the collected information, the behavior attribute assigning unit 120 calculates the time during which user identification information is continuously acquired for each combination of user identification information and detection identification information as the stay time.

The behavior attribute assigning unit 120 determines whether the calculated stay time is equal to or longer than a predetermined time, and assigns the behavior type "stay" if it is equal to or longer than the predetermined time, and assigns "passage" if it is shorter than the predetermined time. In the example shown in FIG. 6, a person P carrying a communication device 2 with a User ID of "jSIK" moves to Sensor IDs in the order of "S01", "S02", "S01", "S02", ... [S04], that is, from point 1 to point 2 to point 1 to point 2 ... point 4, and the behavior type at each point is assigned as either "stay" or "passage".

Next, the behavior attribute assigning unit 120 assigns a behavior attribute, which is a combination of the type of human behavior at the location where the detection device 10 is installed and the type of location, to each piece of user identification information based on the collected information and the corresponding information. Specifically, the behavior attribute assigning unit 120 assigns a "type of location" corresponding to the detection identification information and at least one of the multiple "types of behavior" described above to each piece of user identification information included in the collected information. A specific example is shown in FIG. 7.

Figure 7 is a diagram showing an example of behavioral attribute assignment in the behavioral attribute analysis system 1 according to embodiment 1. Note that the example shown in Figure 7 shows a portion of the behavioral attributes. Also, the example shown in Figure 7 is not consistent with the information exemplified in other figures.

In the example shown in FIG. 7, for each User ID, if the type of behavior at each location corresponds to "passing" and "staying", "TRUE" is assigned. In addition, for each User ID, the numbers (detection identification information) of the locations corresponding to the types of behavior "first passed" and "last passed" are assigned. In addition, for each User ID, the calculated value of the behavior type "total stay time" and the calculated value of "number of visits" are assigned. As a specific example, referring to the record in the first row of FIG. 7, a person P carrying a communication device 2 with a User ID of "HhpD" is assigned the behavior attribute that he/she first passed through the north entrance/exit and entered the facility, stayed in the cafe, the 100 yen shop, and the kids' space, and then passed through the south entrance/exit and left the facility last, and that the total stay time on the detection date 2022-10-1 was 125 minutes and that he/she has visited the facility 7 times.

Next, when the extraction processing unit 140 receives a selection operation of a behavior attribute from the input unit 150, it extracts user identification information whose behavior attribute matches the selection operation of the input unit 150 from among the multiple user identification information. Specific examples are described using Figs. 8 to 10.

Figures 8 and 9 are diagrams showing an input screen 200 of the behavior attribute analysis system 1 according to embodiment 1. Figure 10 is a diagram showing an output screen 300 of the behavior attribute analysis system 1 according to embodiment 1. Note that the examples shown in Figures 8 to 10 show a portion of the various information. Also, they are not consistent with the information exemplified in other figures.

As shown in FIG. 8, the input screen 200 has a date input section 201 for inputting a specific day or period, or day of the week to be analyzed for people flow, and a behavior type input section 202 for inputting a type of behavior. The selection operation input from the date input section 201 corresponds to a specific day or a predetermined period in the above-mentioned behavior type. Also, the selection operation input from the behavior type input section 202 corresponds to the above-mentioned type of behavior.

Figure 9 shows the state in which "Places stayed" and "Number of visits" are selected in the behavior type input section 202 of the input screen 200. For example, when "Places stayed" is selected in the behavior type input section 202, the location input section 203 for selecting the type of location of the corresponding information is displayed as a selection option. Also, for example, when "Number of visits" is selected in the behavior type input section 202, selection options for each number of visits are displayed.

A user of the behavior attribute analysis system 1 selects the condition of the behavior attribute that he or she wishes to extract from the options displayed on the input screen 200. For example, if he or she wishes to extract male regular customers who visited a ramen restaurant during a certain period, he or she inputs the corresponding period into the date input section 201, and selects "ramen" and "men's restroom" in the "location input section 203" and the number of visits "10 or more times" in the "behavior type input section 202" as shown in FIG. 9.

The extraction processing unit 140 extracts user identification information whose behavioral attributes match the selection operation of the input unit 150 from among the multiple user identification information, and outputs the extraction result to an output device via the output unit 160. The output device may be any device, such as display on an output screen or data output to another information processing device.

As shown in FIG. 10, the extraction results are displayed on an output screen 300 of an output device such as a monitor. The output screen 300 has a behavior attribute display 301 that displays the results of a behavior attribute selection operation, and an extraction result display 302. The extraction result display 302 displays, for example, the number of user identification information extracted by the extraction processing unit 140 for each date in a specified period in a bar graph. Note that the display method is not limited to this, and can be set appropriately depending on the display item. In addition to bar graphs, other display methods include, for example, pie charts, heat maps, OD tables (Origin-Destination Tables), and information lists. Furthermore, the number of user identification information extracted by the extraction processing unit 140 is not limited to the absolute number, and may be a percentage of all users, or a rate of increase or decrease compared to a specific day.

(effect)
As described above, in the first embodiment, the behavior attribute assigning unit 120 assigns a behavior attribute to each user identification information based on the collected information and the corresponding information. Therefore, it is possible to analyze the flow of people based on the behavior attributes resulting from people's behavior patterns.

In addition, the location type of the corresponding information includes a type that corresponds to the demographic attributes of a person. Therefore, even if the information acquired from the communication device 2 does not include information regarding the demographic attributes of person P, the demographic attributes of person P can be estimated. In other words, even if the communication between the detection device 10 and the communication device 2 is a beacon signal, the demographic attributes of person P can be estimated.

The behavior attribute assigning unit 120 also assigns a type of human behavior at the location where the detection device 10 is installed for each user identification information based on the collected information. This makes it possible to distinguish the personal preferences and characteristic behavior patterns of person P.

The extraction processing unit 140 also extracts user identification information whose behavioral attributes match the selection operation of the input unit 150 from among the multiple user identification information. This allows a user of the behavior attribute analysis system 1 to analyze people flow for the behavioral attributes desired.

(Modification)
In the above description, the detection device 10 receives a beacon signal transmitted by the communication device 2 to acquire user identification information, but the first embodiment is not limited to this. Each of the multiple detection devices 10 may be configured to transmit a beacon signal including detection identification information. In this case, the communication device 2 receives a beacon signal from a detection device 10 within a predetermined range and acquires the detection identification information. Then, the communication device 2 transmits the detection identification information, the user identification information of the communication device 2, and information on the date and time when the beacon signal was received to the collection device 20.

The communication method between the communication device 2 and the detection device 10 may be any communication method. For example, BLE (Bluetooth Low Energy) communication may be used to transmit and receive beacon signals between the communication device 2 and the detection device 10. Note that Bluetooth is a registered trademark.

Embodiment 2.
In the second embodiment, a form in which "type of action" is further added will be described. Hereinafter, the second embodiment will be described, focusing on the differences from the first embodiment.

The behavior attribute assigner 120 in this embodiment 2 assigns at least one of the "behavior type" in embodiment 1 and the following "behavior type".

[Visiting time period]
The visiting time period as the type of behavior refers to the time period in a particular day when the person P first entered the facility. The behavior attribute assigning unit 120 sets the time period in a day when the user identification information was first acquired as the "visiting time period" as the type of behavior. This visiting time period can distinguish the behavior patterns of the person P by time period. The time period may be divided into morning, daytime, afternoon, etc., or may be divided into specific times such as 9:00 to 12:00, 12:00 to 16:00, etc.

[Route of travel]
The type of behavior is the behavior route, which refers to the order in which the person P moves between multiple points (locations). The behavior attribute assigning unit 120 sets the order of multiple points for which the same user identification information is acquired as the "movement route" as the type of behavior. This movement route can be used to extract the order in which the person P moves between each point in the facility. In addition, for example, it is possible to distinguish between those who use a dedicated passage for specific users provided in the facility and others.

[Visit Interval]
The type of behavior "visit interval" refers to the interval between days when person P visited the facility. The behavior attribute assignment unit 120 sets the interval between days when user identification information was acquired as the "visit interval" as the type of behavior. For example, by determining whether or not a person visits at a specific cycle during a specified period, it is possible to distinguish whether or not a person visits at a specific cycle for a specific purpose. For example, it is possible to distinguish between users who attend events or lessons that are regularly held within the facility.

[Event Sensitivity]
The event sensitivity of the behavior type refers to the ratio of visits by a person P on a specific day when an event or discount campaign is held at the facility. The behavior attribute assignment unit 120 sets the ratio of days on which user identification information is acquired to a specific day as the "event sensitivity" as the behavior type. For example, it is possible to tally up the visit rate limited to days when an event is held or days when a discount campaign is implemented.

[amount of movement]
The type of behavior is the amount of movement, which refers to the amount of movement between the multiple areas by the person P in a specific day, by dividing multiple points (locations) into two or more areas. The behavior attribute assigning unit 120 divides multiple points into two or more areas, counts the number of areas to which the multiple points for which the same user identification information is acquired belong, and regards the number as the "amount of movement" as the type of behavior. For example, it is possible to distinguish whether the person P is a person who moves a lot or not.

[Movement Speed]
The behavior type "movement speed" refers to the speed at which a person P moves between multiple points (locations). The behavior attribute assigning unit 120 calculates the movement speed from the distance between the multiple points at which user identification information is acquired and the time difference between the times at which the same user identification information is acquired at the multiple points, and sets this as the "movement speed" as the behavior type. For example, depending on whether the movement speed is equal to or higher than a predetermined speed, it is possible to distinguish between a person who passed between the points without moving and a person who passed slowly.

[People who tolerate crowds]
The behavior type of "crowding tolerant" refers to a classification of whether or not person P is a person who uses facilities in a crowded area (place). The behavior attribute assigning unit 120 assigns the behavior type of "crowding tolerant" to user identification information when user identification information is continuously acquired for a predetermined time or more in a crowded area where the number of different user identification information acquired exceeds a threshold value.

[Total time spent during the period]
The type of behavior "total stay time within a period" refers to the total time that the person P stayed in the facility during a specified period. The behavior attribute assigning unit 120 sets the total time of the above-mentioned overall stay time during a specified period as the type of behavior "total stay time within a period."

(effect)
As described above, in the second embodiment, the above-mentioned behavior types are further added to the behavior types in the first embodiment. Therefore, the personal preferences and characteristic behavior patterns of the person P can be further distinguished.

Embodiment 3.
In the third embodiment, an operation of clustering a plurality of behavioral attributes into a plurality of clusters based on similarity will be described. Hereinafter, the third embodiment will be described, focusing on the differences from the first and second embodiments.

FIG. 11 is a control block diagram of the information processing device 100 of the behavior attribute analysis system 1 according to embodiment 3. As shown in FIG. 11, the information processing device 100 has a clustering unit 170. The clustering unit 170 is a functional unit that is realized by the CPU executing a program. Note that the information processing device 100 may omit the input unit 150.

(operation)
The operation of the information processing device 100 will be described.
By performing operations similar to those in the first or second embodiment, the behavior attribute assigning unit 120 assigns a behavior attribute, which is a combination of a behavior type and a location type, to each piece of user identification information, based on the collected information and the corresponding information.

Next, the clustering unit 170 clusters the multiple behavioral attributes assigned by the behavioral attribute assigning unit 120 into multiple clusters based on the similarity. Specifically, the clustering unit 170 maps the behavioral attributes into a multidimensional space using the behavior type and location type in each user identification information as parameters, and clusters the mapped behavioral attributes according to the closeness of distance, for example, using the k-means method. Note that the clustering method is not limited to non-hierarchical clustering such as the k-means method, and any method can be used, such as hierarchical clustering such as the shortest distance method.

The extraction processing unit 140 extracts user identification information whose behavioral attributes are included in each cluster generated by the clustering unit 170. The extraction processing unit 140 also outputs the extraction result to an output device via the output unit 160. A specific example will be described with reference to FIG. 12.

Figure 12 is a diagram showing an output screen 400 of the behavior attribute analysis system 1 according to the third embodiment. As shown in Figure 12, each cluster is displayed as a circle on the output screen 400. The size of the circle is displayed according to the absolute number of user identification information whose behavior attribute is included in the cluster or the ratio to the total number of users. Inside the circle, the type of behavior and the type of location of the clustered behavior attribute are described. For example, if the behavior attributes of a certain cluster are the place of stay "kids space", the stay time "1 to 2 hours", the visit date "weekday", the visit time period "daytime", and the number of visits "10 times or more", this information is displayed inside the circle, and the ratio of the number of user identification information belonging to this cluster to the total number of users is displayed below the circle.

For example, as shown in FIG. 12, the type of behavior may be displayed by converting it into another term or name, such as displaying a stay time of "1 to 2 hours" as "long time" and displaying a visit count of "10 or more times" as "regular." Also, for example, multiple types of behavior may be displayed together as one term or name. For example, stay times of "30 minutes to 1 hour" and "1 to 2 hours" may be displayed together as "long time."

(effect)
As described above, in the third embodiment, the clustering unit 170 clusters a plurality of behavioral attributes into a plurality of clusters based on the similarity, and the extraction processing unit 140 extracts, for each cluster, user identification information whose behavioral attribute is included in the cluster. This allows the user of the behavior attribute analysis system 1 to know characteristic behavioral attributes that the user does not know.

The behavioral attributes classified into each cluster can be understood as a persona that represents a person with a typical behavioral pattern. In other words, a user of the behavioral attribute analysis system 1 can easily understand what kind of behavior a visitor to the facility being analyzed exhibits.

Embodiment 4.
In the fourth embodiment, an operation will be described in which the location of the person P is identified by obtaining the position coordinates of the communication device 2. Hereinafter, the fourth embodiment will be described, focusing on the differences from the first to third embodiments.

The collection device 20 of the fourth embodiment determines the position coordinates of the communication device 2 based on radio waves transmitted or received between the communication device 2 and the detection device 10. Specifically, the collection device 20 performs positioning using UWB (Ultra Wide Band).

In positioning using UWB, the communication device 2 acts as a transmitter and the detection device 10 acts as a receiver, with the transmitter transmitting a positioning signal of a specific pattern. In positioning, the position of the transmitter is calculated using the distance of the transmitter to the receiver, or the angle (direction) of the transmitter to the receiver. Distance can be measured using the reception strength of the positioning signal received by the receiver, the time it takes for the positioning signal from the transmitter to reach the receiver, or the time difference between receiving a positioning signal from one transmitter with multiple receivers. Angle can also be measured using the directivity of each antenna that makes up the receiver's antenna array to calculate the angle at which the transmitter is located.

Fig. 13 is an explanatory diagram of positioning of a behavior attribute analysis system 1 according to embodiment 4. Fig. 13 shows a schematic diagram of the positions of three detection devices 10-1 to 10-3 functioning as receivers and a communication device 2 functioning as a transmitter.

The communication device 2 to be positioned transmits a positioning signal. The detection devices 10-1 to 10-3 each receive the positioning signal and acquire its radio wave intensity. The collection device 20 collects the radio wave intensity acquired by each detection device 10. The collection device 20 pre-stores information on the position coordinates of each of the multiple detection devices 10. The collection device 20 then calculates the distance (R1 to R3) between each detection device 10 and the communication device 2 from the radio wave intensity acquired by each detection device 10. This allows the collection device 20 to calculate the position coordinates of the communication device 2.

Then, the collection device 20 determines that the detection device 10 whose position coordinates of the communication device 2 are within a predetermined range of position coordinates is the detection device 10 that has acquired the user identification information of the communication device 2. For example, the collection device 20 stores in advance position coordinate information indicating the predetermined range of each of multiple detection devices 10, and by comparing this position coordinate information with the position coordinates of the communication device 2, it is possible to determine at what point (location) the communication device 2 is located. The subsequent operations are the same as in any of the above embodiments 1 to 3.

The method of positioning to obtain the position coordinates of the communication device 2 is not limited to UWB positioning. For example, any positioning method may be used, such as positioning using BLE-AOA (Bluetooth Low Energy Angle of Arrival).

(effect)
As described above, in the fourth embodiment, the position coordinates of the communication device 2 are obtained based on radio waves transmitted or received between the communication device 2 and the detection device 10. Therefore, the location where the communication device 2 is located can be detected with high accuracy.

Embodiment 5.
In the present embodiment 5, an operation of acquiring facial features of a person P from an image of the person P and assigning user identification information will be described. Hereinafter, the present embodiment 5 will be described, focusing on the differences from the above embodiments 1 to 4.

FIG. 14 is a schematic configuration diagram of a behavior attribute analysis system 1 according to embodiment 5. As shown in FIG. 14, the behavior attribute analysis system 1 according to embodiment 5 includes a plurality of detection devices 11.

Multiple detection devices 11 are installed at points within the area to be analyzed for people flow. The detection device 11 is composed of a camera, and acquires facial features of person P from an image captured of a person within a specified range. Specifically, the detection device 11 extracts a multidimensional vector (e.g., a vector of about 128 dimensions) from the facial image, and uses this as the facial features of person P. The detection device 11 then transmits information on the facial features, detection identification information of the detection device 11, and information on the date and time when the facial features were acquired to the collection device 20.

The collection device 20 collects facial features, detection identification information that identifies the detection device 10, and information on the date and time when the detection device 10 acquired the features from multiple detection devices 11, and transmits the collected information to the information processing device 100.

The acquisition unit 110 of the information processing device 100 performs face authentication based on the facial features, and assigns the same user identification information to the facial features determined to be those of the same person. A specific example will be described with reference to Figures 15 and 16.

Figure 15 is an explanatory diagram of face recognition in a behavior attribute analysis system 1 according to embodiment 5. Figure 15 shows a schematic diagram of a case in which detection devices 11-A to 11-C capture images of the faces of people X, Y, and Z. Note that the dotted oval lines in Figure 15 indicate the predetermined range captured by each detection device 11.

As shown in FIG. 15, as person X moves through the facility, he is photographed by detection devices 11-A and 11-B, and the facial features (Fx-A, Fx-B) are calculated by each detection device 11. Similarly, as person Y and person Z move through the facility, the facial features are calculated by multiple detection devices 11. Note that the facial images photographed by each detection device 11 differ depending on the facial expression or angle, etc., and therefore the facial features do not match completely even for the same person.

Figure 16 is an explanatory diagram of the assignment of user identification information in the behavior attribute analysis system 1 according to embodiment 5. The acquisition unit 110 maps the collected facial features into a multidimensional space, clusters them using a method such as the k-means method, and determines that the features in each cluster are facial features of the same person. The acquisition unit 110 then assigns the same user identification information (e.g., U-ID01 to U-ID04) to the facial features determined to be from the same person.

Next, the acquisition unit 110 stores the multiple pieces of user identification information, the detection identification information that identifies the detection device 10, and information on the date and time when the detection device 10 acquired the feature amount in the storage unit 130 as collected information. The subsequent operations are the same as those in any of the above-mentioned embodiments 1 to 4.

The face recognition method is not limited to the above, and any method can be used. For example, if the difference between each feature amount is equal to or less than a predetermined value, it may be determined that the two people are the same person.

(effect)
As described above, in the fifth embodiment, face authentication is performed based on the facial features, and the same user identification information is assigned to the facial features determined to be of the same person. Therefore, even if the person P does not carry the communication device 2, the behavioral attribute of the person P can be assigned.

(Modification)
In the above description, the operation of performing face authentication based on the facial feature of the person P has been described, but the fifth embodiment is not limited thereto. The feature of the person P may be, for example, the feature of the whole body or any part of the person P, such as the whole body appearance or clothes of the person P. In this case, the detection device 11 acquires the feature of the whole body or any part of the person P from an image of the person. Then, the detection device 11 transmits information on the feature of the person, the detection identification information of the detection device 11, and information on the date and time when the feature of the person was acquired to the collection device 20. The collection device 20 collects, from the multiple detection devices 11, the feature of the person, the detection identification information for identifying the detection device 10, and information on the date and time when the detection device 10 acquired the feature, and transmits the collected information to the information processing device 100. The acquisition unit 110 of the information processing device 100 performs authentication based on the feature of the person, and assigns the same user identification information to the feature of the person determined to be the same person.

1 Behavioral attribute analysis system, 2 Communication device, 10 Detection device, 11 Detection device, 20 Collection device, 100 Information processing device, 110 Acquisition unit, 120 Behavioral attribute assignment unit, 130 Storage unit, 140 Extraction processing unit, 150 Input unit, 160 Output unit, 170 Clustering unit, 200 Input screen, 201 Date input unit, 202 Behavior type input unit, 203 Location input unit, 300 Output screen, 301 Behavioral attribute display, 302 Extraction result display, 400 Output screen.

Claims (9)

A detection device that is installed at a plurality of locations and acquires user identification information from communication devices carried by people within a predetermined range;
a collection device that collects, as collected information, the user identification information acquired by the detection device, detection identification information for identifying the detection device, and information on a date and time when the user identification information was acquired;
an information processing device that acquires the collected information;
Equipped with
The information processing device includes:
A storage unit that stores correspondence information between the detection identification information and the type of the location;
a behavior attribute assigning unit that assigns, to each of the user identification information, a behavior attribute that is a combination of a type of the person's behavior at the plurality of locations and a type of the plurality of locations based on the collected information and the corresponding information;
having
The types of locations include types corresponding to demographic attributes of the people.
Behavioral attribute analysis system. The information processing device includes:
an input unit that accepts a selection operation of the behavior attribute;
an extraction processing unit that extracts, from the plurality of pieces of user identification information, the user identification information whose behavior attribute matches a selection operation of the input unit;
The behavior attribute analysis system according to claim 1 . The information processing device includes:
A clustering unit that clusters the plurality of behavioral attributes into a plurality of clusters based on a similarity between the plurality of behavioral attributes;
an extraction processing unit that extracts, for each cluster obtained by the clustering unit, the user identification information whose behavior attribute is included in the cluster;
The behavior attribute analysis system according to claim 1 . The type of the person's behavior is
A stay in a state in which the user identification information is continuously acquired at one of the locations for a predetermined period of time or more;
Passing, in which the user identification information is not continuously acquired for a predetermined period of time or more at one of the points;
a first passed point in a day, which is a point among the plurality of points from which the user identification information was first acquired;
A last passed point in a day, which is the point from which the user identification information was last acquired among the plurality of points;
A total stay time in a day, which is the time from the time when the user identification information is first acquired to the time when the user identification information is last acquired;
A total stay time within a given period, which is the sum of all stay times within the given period;
A visit count, which is the number of days during which the user identification information was acquired within a predetermined period of time;
A visiting time period, which is a time period during which the user identification information was first acquired;
A visit interval, which is the interval between days when the user identification information is acquired;
an event sensitivity that is a percentage of a given day on which the user identification information was acquired;
a moving speed calculated from a distance between the plurality of points at which the user identification information is acquired and a time difference between the times at which the user identification information is acquired at the plurality of points;
And,
A congestion-tolerant user is a user who has been continuously acquired for a predetermined period of time or more in the area where the plurality of points are divided into two or more areas and where the number of different pieces of user identification information acquired exceeds a threshold value.
The behavior attribute analysis system according to any one of claims 1 to 3, wherein the behavior attribute analysis system is at least one of the above. The user identification information is
The behavior attribute analysis system according to claim 1 , wherein the information is included in a beacon signal transmitted or received between the communication device and the detection device. The collecting device comprises:
information on position coordinates indicating the predetermined range for each of the plurality of detection devices is stored in advance;
determining a position coordinate of the communication device based on radio waves transmitted or received between the communication device and the detection device;
The behavioral attribute analysis system according to any one of claims 1 to 3, wherein the detection device whose position coordinates of the communication device are included in the predetermined range of position coordinates is the detection device that has acquired user identification information of the communication device. A detection device that is installed at a plurality of locations and acquires feature amounts of people from images of people within a predetermined range;
a collection device that collects the feature amount of the person, detection identification information that identifies the detection device, and information on the date and time when the detection device acquired the feature amount;
an information processing device that acquires information from the collection device;
Equipped with
The information processing device includes:
an acquisition unit that performs authentication based on the feature amounts of the person, assigns the same user identification information to the feature amounts of the person determined to be the same person, and acquires, as collected information, the plurality of pieces of user identification information, detection identification information for identifying the detection device, and information on the date and time when the detection device acquired the feature amounts;
A storage unit that stores correspondence information between the detection identification information and the type of the location;
a behavior attribute assigning unit that assigns, to each of the user identification information, a behavior attribute that is a combination of a type of the person's behavior at the plurality of locations and a type of the plurality of locations based on the collected information and the corresponding information;
having
The types of locations include types corresponding to demographic attributes of the people.
Behavioral attribute analysis system. An information processing device that acquires, as collected information, user identification information of communication devices carried by people within a predetermined range acquired by detection devices installed at multiple locations, detection identification information that identifies the detection devices, and information on a date and time when the detection devices acquired the user identification information,
A storage unit that stores correspondence information between the detection identification information and the type of the location;
a behavior attribute assigning unit that assigns, to each of the user identification information, a behavior attribute that is a combination of a type of the person's behavior at the plurality of locations and a type of the plurality of locations based on the collected information and the corresponding information;
having
The types of locations include types corresponding to demographic attributes of the people.
Information processing device. An information processing device that acquires feature amounts of people within a predetermined range acquired by detection devices installed at multiple locations, detection identification information that identifies the detection devices, and information on dates and times when the detection devices acquired the feature amounts,
an acquisition unit that performs authentication based on the feature amounts of the person, assigns the same user identification information to the feature amounts of the person determined to be the same person, and acquires, as collected information, the plurality of pieces of user identification information, detection identification information for identifying the detection device, and information on the date and time when the detection device acquired the feature amounts;
A storage unit that stores correspondence information between the detection identification information and the type of the location;
a behavior attribute assigning unit that assigns, to each of the user identification information, a behavior attribute that is a combination of a type of the person's behavior at the plurality of locations and a type of the plurality of locations based on the collected information and the corresponding information;
having
The types of locations include types corresponding to demographic attributes of the people.
Information processing device.

Images