Event time estimation device and event time estimation method

Abstract

This event time estimation device comprises: a determination unit that determines occupancy information pertaining to a temporal change in the number of occupants in an area in which an event is held; and an estimation unit that estimates, on the basis of the occupancy information, at least on of the start time of the event and the end time of the event.

Description

Event time estimation device and event time estimation method

[0001] The present invention relates to an event time estimation device and an event time estimation method.

[0002] Conventionally, there are systems that estimate the change over time in the number of visitors to a venue where various events are held, etc. For example, Patent Literature 1 discloses a system that estimates the type of a facility based on the name of the facility extracted from map information, and estimates the number of visitors to the facility for each time period based on the estimated type.

[0003] International Publication No. 2011 / 024379

[0004] In a typical event, at least one of the start time and the end time is planned in advance, but due to the progress of the event, at least one of the actual start time and the end time may not match the planned time. However, the system of Patent Document 1 cannot determine whether at least one of the actual start time and the end time of the event matches the planned time. As a result, there is a problem that, for example, the degree of congestion inside and outside the event venue may not match the advance security plan.

[0005] The present invention has been made to solve the above-mentioned problems, and has an object to estimate at least one of the substantial start time and end time of an event.

[0006] An event time estimation device according to a preferred aspect of the present invention includes a determination unit that determines stay information regarding changes over time in the number of visitors in an area where an event is held, and an estimation unit that estimates at least one of the start time and the end time of the event based on the stay information.

[0007] An event time estimation method according to a preferred aspect of the present invention determines stay information regarding changes over time in the number of visitors in an area where an event is being held, and estimates at least one of the start time and the end time of the event based on the stay information.

[0008] The event time estimation device according to the present invention can estimate the substantial start time or end time of an event.

[0009] 1 is an external view of an event time estimation device according to a first embodiment. FIG. 2 is a block diagram showing an example of the configuration of the terminal device of FIG. 1. FIG. 3 is a block diagram showing an example of the configuration of the server of FIG. 1. FIG. 4 is a diagram showing an example of a venue database according to the first embodiment. FIG. 5 is a diagram showing an overview of venue location information and user location information. FIG. 6 is a diagram showing an example of a location information database according to the first embodiment. FIG. 7 is a diagram showing an example of an event database according to the first embodiment. FIG. 8 is a diagram for explaining characteristics of a free entry / exit event type. FIG. 9 is a diagram for explaining characteristics of a fixed entry / exit event type. FIG. 10 is a diagram showing an example of changes over time in the number of visitors at a free entry / exit event. FIG. 11 is a diagram showing an example of changes over time in the number of visitors at a fixed entry / exit event. FIG. 12 is a diagram showing an example of changes over time in the number of visitors at a fixed entry / exit event. FIG. 13 is a diagram showing an example of changes over time in the number of visitors at a fixed entry / exit event. FIG. 14 is a diagram showing an example of changes over time in the number of visitors at other times. FIG. 15 is a diagram showing an example of changes over time in the number of visitors at other times. FIG. 16 is a schematic diagram showing an example of a neural network model applied to a learning model according to the first embodiment. FIG. 17 is an explanatory diagram relating to the cumulative number of visitors and the cumulative number of visitors. Fig. 12 is a diagram showing the cumulative number of visitors and the cumulative number of exits corresponding to the time changes in the number of visitors and the number of exits in Fig. 11. Fig. 13 is a diagram showing the cumulative number of visitors and the cumulative number of exits corresponding to the time changes in the number of visitors and the number of exits in Fig. 13. Fig. 14 is a diagram showing an example of the estimation results of the start time and end time for each event by the event time estimation device. Fig. 15 is a flowchart showing an example of the operation of a processing device.

[0010] 1. First Embodiment Hereinafter, the configuration of an event time estimation device according to a first embodiment of the present invention will be described with reference to FIGS.

[0011] 1.1. Configuration of the First Embodiment 1.1.1. Configuration of the Event Time Estimation Device Fig. 1 is a diagram showing the overall configuration of an information processing system 1 including an event time estimation device according to the first embodiment. The information processing system 1 includes a terminal device 10, a server 20, and a communication network NET.

[0012] The terminal devices 10 include n terminal devices 10[1], 10[2], ..., 10[k], ..., 10[n]. Here, n is any natural number, and k is any natural number smaller than n. In this embodiment, the configurations of the terminal devices 10[1] to 10[n] are identical to each other. Note that the terminal devices 10 may include terminal devices that do not have the same configuration.

[0013] A user who uses terminal device 10[1] is user U[1], a user who uses terminal device 10[2] is user U[2], a user who uses terminal device 10[k] is user U[k], and a user who uses terminal device 10[n] is user U[n]. When referring to an unspecified user or all users, the user is also written as user U. User U is an example of a person.

[0014] The terminal device 10 includes a personal computer, a tablet terminal, a smartphone, a smart watch, and the like.

[0015] In the information processing system 1, terminal devices 10[1] to 10[n] and a server 20 are connected to each other so as to be able to communicate with each other via a communication network NET.

[0016] 1.1.2. Configuration of the Terminal Device Fig. 2 is a block diagram showing an example of the configuration of the terminal device 10[1] in Fig. 1. As shown in Fig. 2, the terminal device 10[1] includes a processing device 11, a storage device 12, a communication device 13, a display device 14, an input device 15, and a positioning device 16. The elements included in the terminal device 10[1] are connected to each other by one or more buses for communicating information.

[0017] In the description of this embodiment, terminal device 10[1] is used as an example, but since terminal devices 10[2], ..., 10[k], ..., 10[n] also have the same configuration as terminal device 10[1], the description of terminal devices 10[2], ..., 10[k], ..., 10[n] will be omitted.

[0018] The processing device 11 is a processor that controls the entire terminal device 10 [1] and is configured, for example, using one or more chips. The processing device 11 is configured, for example, using a central processing unit (CPU) including an interface with peripheral devices, an arithmetic unit, a register, etc. Note that some or all of the functions of the processing device 11 may be realized by hardware such as a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA). The processing device 11 executes various processes in parallel or sequentially.

[0019] The storage device 12 is a recording medium that can be read and written by the processing device 11. The storage device 12 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), and an electrically erasable programmable read-only memory (EEPROM). The volatile memory is, for example, a random access memory (RAM).

[0020] The storage device 12 stores a plurality of programs including a control program PR1 to be executed by the processing device 11. The storage device 12 also functions as a work area for the processing device 11. The control program PR1 is a program that controls the entire processing device 11.

[0021] The communication device 13 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 13 is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 13 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 13 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0022] The display device 14 is a device that displays images and text information. The display device 14 displays various images under the control of the processing device 11. For example, various display panels such as a liquid crystal panel and an organic EL (Electro Luminescence) panel are suitably used as the display device 14.

[0023] The input device 15 accepts operations from the user U[1]. For example, the input device 15 includes a keyboard, a touchpad, a touch panel, and a pointing device such as a mouse. If the input device 15 includes a touch panel, it may also function as the display device 14.

[0024] The positioning device 16 acquires location information of the terminal device 10 [1]. The positioning device 16 may be, for example, a GNSS (Global Navigation Satellite System) receiver. The GNSS receiver receives radio signals transmitted from one or more GNSS satellites. GNSS is a positioning system using positioning satellites from countries around the world, including GPS (Global Positioning System) satellites. The radio signals include information such as the location information of the satellite that transmitted the radio signals and the transmission time of the radio signals. The GNSS receiver performs positioning based on the one or more received radio signals and outputs the location information of the GNSS receiver to the processing device 11. The location information indicates, for example, the latitude and longitude of the terminal device 10 [1].

[0025] The processing device 11 functions as an acquisition unit 111, an output unit 112, and a display control unit 113, for example, by reading and executing a control program PR1 from the storage device 12.

[0026] The acquisition unit 111 acquires various information transmitted from the server 20 and location information output from the positioning device 16 .

[0027] The output unit 112 outputs the position information to the server 20 via the communication device 13 .

[0028] The display control unit 113 causes the display device 14 to display various pieces of information based on the various pieces of information acquired by the acquisition unit 111 .

[0029] 1.1.3. Server Configuration Figure 3 is a block diagram showing an example configuration of the server 20 in Figure 1. As shown in Figure 3, the server 20 includes a processing device 21, a storage device 22, and a communication device 23. The elements included in the server 20 are connected to each other by one or more buses for communicating information. The server 20 is an example of an event time estimation device. Here, the event time means at least one of the start time and end time of an event to be held.

[0030] The processing device 21 is a processor that controls the entire server 20, and is configured using, for example, one or more chips. The processing device 21 is configured using, for example, a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and a register. Note that some or all of the functions of the processing device 21 may be realized by hardware such as a DSP, ASIC, PLD, or FPGA. The processing device 21 executes various processes in parallel or sequentially.

[0031] The storage device 22 is a recording medium that can be read and written by the processing device 21. The storage device 22 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, and an EEPROM. The volatile memory is, for example, a RAM.

[0032] The storage device 22 stores a plurality of programs including a control program PR2 to be executed by the processing device 21, a venue database DB1, a location information database DB2, an event database DB3, and a learning model LM1. The storage device 22 also functions as a work area for the processing device 21. The venue database DB1, the location information database DB2, the event database DB3, and the learning model LM1 will be described below.

[0033] FIG. 4 is a diagram showing an example of the venue database DB1 according to the first embodiment. Venue information is stored in the venue database DB1. As shown in FIG. 4, the venue database DB1 has the following fields: venue name and polygon coordinates. The "venue name" indicates the name of a facility or the like that will be the venue for an event. The "polygon coordinates" indicate the polygon coordinates of an area that includes the venue for the event. The venue information is information that links the venue name with the location and geographical extent of the venue.

[0034] FIG. 5 is a diagram illustrating an overview of venue location information and user location information. As shown in FIG. 5 , for example, the location of one venue, "Stadium A" ST, is indicated by a rectangular polygon POL surrounding Stadium A ST. The coordinates of each vertex of the polygon POL, i.e., the latitude and longitude of each vertex, are recorded in the venue database DB1 as venue location information. In this example, the area specified by the polygon coordinates, i.e., the area surrounded by the polygon POL, is an example of an area where an event will be held. Note that in this embodiment, the polygon POL is rectangular, but the polygon POL may have any polygonal shape. The venue location information may be obtained in advance from a map application or the like. Note that the polygon coordinates may be represented by a combination of the minimum latitude, minimum longitude, maximum latitude, and maximum longitude.

[0035] FIG. 6 is a diagram illustrating an example of a location information database DB2 according to the first embodiment. The location information database DB2 stores location information for user U[n]. As shown in FIG. 6, the location information database DB2 includes the following fields: user ID, latitude, longitude, and timestamp. The "user ID" indicates a unique number that identifies user U[n]. The "latitude" indicates the latitude of the terminal device 10 owned by user U[n]. The "longitude" indicates the longitude of the terminal device 10 owned by user U[n]. The "timestamp" indicates the time when the latitude and longitude of the terminal device 10 were acquired. In this way, the location information for user U[n] is stored in the location information database DB2 together with a timestamp, with the latitude and longitude of the user U[n]'s location linked to the user ID. The location information for user U[n] is acquired by the positioning device 16 of the terminal device 10[n].

[0036] 5, for example, the position of each user U[n] is indicated by a pin mark. Because the pin mark representing user U[k] is located within the range of the polygon POL, user U[k] is identified as a user who has entered Stadium A ST. Because the pin mark representing user U[j] is located outside the range of the polygon POL, user U[j] is identified as a user U[n] who has not entered Stadium A ST.

[0037] FIG. 7 is a diagram showing an example of the event database DB3 according to the first embodiment. Event holding information is stored in the event database DB3. As shown in FIG. 7, the event database DB3 has the following fields: event start date, venue, event name, and event type. "Event start date" indicates the date the event started. "Venue" indicates the name of the venue where the event is held. "Event name" indicates the name of the event. "Event type" indicates a type classified into multiple types depending on the manner in which user U[n] enters and exits the area where the event is held. The event type is an example of an event type. The event database DB3 also stores information regarding the scheduled start time and scheduled end time of the event.

[0038] In this embodiment, event types are classified into three types: (A) free entry / exit type, (B) uniform entry / exit type, and (C) other. Event types according to the first embodiment will be described below with reference to FIGS. 8 to 15. In the following description, users U who visit the area where the event is held will also be referred to as visitors. Visitors include those who enter the area where the event is held and those who leave the area where the event is held. Staying visitors are defined as visitors who remain in the area where the event is held.

[0039] FIG. 8 is a diagram illustrating the characteristics of a free entry / exit event type. FIG. 8 shows the entry and exit of four users U who visit an event venue between the start time and the end time of the event. In this example, the four users U enter the event venue at different times, and also exit the venue at different times. The stay time is the time from when one user U enters the venue to when they exit. The free entry / exit type is an example of the first type.

[0040] In this way, in the free entry / exit event type, the user U can freely enter and exit the event venue between the start time and the end time of the event. Typical examples of the free entry / exit event type include fireworks displays, special events, festivals, etc.

[0041] FIG. 9 is a diagram illustrating the characteristics of a uniform entry / exit type event type. FIG. 9 shows the entry and exit of a representative user U among users U who visit an event venue between the start time and the end time of the event. In this example, the time at which the representative user U enters the event venue coincides with the start time of the event, and the time at which the user U leaves the event venue coincides with the end time of the event. Although not shown, the time at which other users U who visited the event also enter the event venue coincides with the start time of the event, and the time at which the other users U leave the event venue coincides with the end time of the event, just like the representative user. The stay time is the time from when one user U enters the venue to when they leave. The uniform entry / exit type is an example of the second type.

[0042] In this way, in the second type of entry / exit, the user U enters and exits the event venue uniformly between the start time and the end time of the event. Typical examples of the uniform entry / exit type include live music concerts and the like.

[0043] Event types that do not fall under either the free entry / exit type or the fixed entry / exit type are classified as "other." Typical examples of "other" include when no event is being held at the venue, or when multiple events are being held simultaneously at the same venue.

[0044] In this way, the event types include at least a free entry / exit type and a uniform entry / exit type. When the event type is the free entry / exit type, the degree of variation in the times at which multiple users U enter and exit the event area is greater than the degree of variation in the times at which multiple users U enter and exit the event area when the event type is the uniform entry / exit type.

[0045] FIG. 10 is a diagram showing an example of the change over time in the number of visitors at a free entry / exit event. As shown in FIG. 10 , at a free entry / exit event, the number of visitors monotonically increases as time approaches the event start time Ts1, reaching its first peak at the event start time Ts1. After that, the number of visitors decreases and increases twice, and then monotonically decreases as the event end time Te1 approaches. The number of visitors also gradually decreases monotonically at the event end time Te1, and gradually approaches zero after the event end time Te1 has passed. The event period Tev1 is the period from the event start time Ts1 to the event end time Te1.

[0046] Figure 11 shows an example of the change over time in the number of visitors and the number of people leaving an event with free entry and exit. In Figure 11, the direction of increase in the number of visitors corresponds to the positive (+) direction on the vertical axis, and the direction of increase in the number of people leaving corresponds to the negative (-) direction on the vertical axis.

[0047] 11, in a free entry / exit event, the number of visitors Pen1 peaks before the event start time Ts1 and then monotonically decreases as the time approaches the event start time Ts1. At the event start time Ts1, the number of visitors Pen1 is nearly zero, and then repeatedly increases and decreases until the event end time Te1.

[0048] In a free entry / exit event, the number of exiting people Pex1 remains at zero until the event start time Ts1 has passed. The number of exiting people Pex1 increases gradually after the event start time Ts1, and then decreases and increases several times. As the event end time Te1 approaches, the number of exiting people Pex1 increases monotonically and then peaks, and then decreases monotonically toward zero as the event end time Te1 approaches.

[0049] FIG. 12 is a diagram showing an example of the change over time in the number of visitors at a uniform entry / exit event. As shown in FIG. 12, at a uniform entry / exit event, the number of visitors monotonically increases as time approaches the event start time Ts2, reaching a peak value at the event start time Ts2. Thereafter, the number of visitors remains approximately constant until the event end time Te2. As time passes the event end time Te2, the number of visitors begins to decrease and then decreases monotonically. The event period Tev2 is the period from the event start time Ts2 to the event end time Te2.

[0050] Figure 13 shows an example of the change over time in the number of visitors and the number of people leaving an event with a uniform entry and exit system. In Figure 13, as in Figure 11, the direction of increase in the number of visitors corresponds to the positive (+) direction on the vertical axis, and the direction of increase in the number of people leaving corresponds to the negative (-) direction on the vertical axis.

[0051] 13, in a uniform entry / exit event, the number of visitors Pen2 peaks before the event start time Ts2 and then monotonically decreases as the event start time Ts2 approaches. At the event start time Ts2, the number of visitors Pen2 is nearly zero and remains near zero thereafter. The number of exiting visitors Pex2 begins to increase after the event end time Te2, then peaks, and then monotonically decreases toward zero.

[0052] 14 is a diagram showing an example of the change in the number of visitors over time in other cases. As shown in FIG. 14, in other cases, a clear event start time and end time are not determined. The number of visitors has several peaks over time, but compared to the free entry / exit type or the uniform entry / exit type, the change in the number of visitors over time is gradual and no distinctive change is observed.

[0053] Figure 15 shows an example of the change over time in the number of visitors and the number of people leaving in other cases. In Figure 15, as in Figure 11, the direction of increase in the number of visitors corresponds to the positive (+) direction of the vertical axis, and the direction of increase in the number of people leaving corresponds to the negative (-) direction of the vertical axis.

[0054] As shown in Figure 15, there are several peaks in the number of entrants Pen3 and the number of exits Pex3 over time, but compared to the free entry / exit type or the uniform entry / exit type, the changes over time in the number of entrants Pen3 and the number of exits Pex3 are gradual and no distinctive changes are observed.

[0055] The learning model LM1 is a model that classifies an event type into one of the three event types based on input stay information. The stay information is information regarding changes over time in the number of visitors in the area where the event is held. For example, a machine learning model capable of multi-class classification is used for the learning model LM1. The machine learning model capable of multi-class classification is trained using techniques such as a neural network model, logistic regression, or support vector machine. Below, a machine learning method using a neural network model will be described as an example.

[0056] FIG. 16 is a schematic diagram showing an example of a neural network model 90 applied to the learning model LM1 according to the first embodiment.

[0057] The neural network model 90 receives the stay information as input data.

[0058] The neural network model 90 is configured by a convolutional neural network, a recurrent neural network, or the like.

[0059] The neural network model 90 outputs output data that includes the event type.

[0060] When the training data is input to the neural network model 90, the correlation between the stay information as input data and the event type as output data is machine-learned by the neural network model 90. The input data and output data that make up the training data are also referred to as explanatory variables and target variables, respectively.

[0061] More specifically, the stay information, which is an explanatory variable, is input to the neural network model 90 as input data.

[0062] Using an evaluation function that compares the output data output as an inference result from the neural network model 90, i.e., the event type, with the output data constituting the training data, i.e., the correct label for the event type, the weights associated with each synapse are repeatedly adjusted so as to reduce the value of the evaluation function. Adjusting the weights associated with each synapse is called backpropagation. In this way, a learning model LM1 is machine-learned to perform multi-class classification in which visit information is classified into one of three event types included in the correct label, i.e., free entry / exit type, uniform entry / exit type, and others.

[0063] When a predetermined learning termination condition is satisfied, the machine learning is terminated, and the neural network model 90 at that point is stored as a trained learning model LM1 in the storage device 22. The predetermined learning termination condition is, for example, that the number of iterations of the series of machine learning processes reaches a predetermined number, that the value of the evaluation function becomes smaller than an allowable value, etc.

[0064] Referring again to FIG. 3 , the communication device 23 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 23 may also be referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 23 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 23 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0065] The processing device 21 functions as an acquisition unit 211, a determination unit 212, and an estimation unit 213, for example, by reading and executing a control program PR2 from the storage device 22.

[0066] The acquisition unit 211 acquires location information of the area where the event will be held from the venue database DB1. The acquisition unit 211 acquires location information of the user U from the location information database DB2. The acquisition unit 211 acquires event information from the event database DB3.

[0067] The determination unit 212 determines the stay information based on the location information of the terminal device 10 possessed by each user U. Hereinafter, the determination of the stay information by the determination unit 212 will be described in detail.

[0068] The determination unit 212 identifies an event venue corresponding to the held event based on the event date and time and the event venue name included in the event information. The determination unit 212 acquires location information of the identified event venue based on the venue information. The event information is acquired from the event database DB3. The venue information is acquired from the venue database DB1.

[0069] When the event venue is identified, the determination unit 212 identifies users U[n] located within the area and users U[n] located outside the area based on the location information of the area including the event venue and the location information of users U[n]. The location information of users U[n] is obtained from the location information database DB2.

[0070] The determination unit 212 chronologically tally the number of visitors per unit time in the area, the number of entrants into the area per unit time, and the number of exits from the area per unit time. The number of visitors is the number of users U located within the area. The number of entrants is the number of users U who moved into the area from outside the area. The number of exits is the number of users U who moved from inside the area to outside the area.

[0071] In this way, the determination unit 212 determines the stay information corresponding to the event. In other words, determining the stay information involves identifying the event venue and chronologically aggregating the number of visitors, the number of entrants, and the number of exits per unit time within the area based on location information including the identified event venue and the location information of the identified terminal device 10.

[0072] FIG. 17 is an explanatory diagram regarding the cumulative number of visitors and the cumulative number of exits. The determination unit 212 determines, as stay information, the cumulative number of visitors and the cumulative number of exits for an event area during a target period Ta including a planned event period Tevp. The planned event period Tevp is the period from a planned event start time Tsp to a planned event end time Tep. The planned event start time Tsp is the time when the event is scheduled to start, and the planned event end time Tep is the time when the event is scheduled to end. The planned event start time Tsp and the planned event end time Tep are stored in the event database DB3. The cumulative number of visitors is the number of visitors per unit time accumulated over time. The cumulative number of exits is the number of exits per unit time accumulated over time. The cumulative number of visitors and the cumulative number of exits are included in the stay information.

[0073] The estimation unit 213 includes a first estimation unit 213a and a second estimation unit 213b. Based on the stay information determined by the determination unit 212, the first estimation unit 213a estimates one event type from multiple event types classified by the user U's entry and exit patterns for the area where the event is held. More specifically, the first estimation unit 213a estimates one event type by inputting the stay information into a learning model LM1 that has learned the relationship between the time change in the number of visitors in the area where the event is held and the multiple event types classified by the user U's entry and exit patterns. That is, the first estimation unit 213a inputs the stay information as an explanatory variable into the learning model LM1 and performs multi-class classification to classify the events into one of three event types: free entry and exit type, uniform entry and exit type, and others.

[0074] The second estimation unit 213b estimates the start time and end time of the event based on the event type estimated by the first estimation unit 213a and the stay information. More specifically, the estimation unit 214 estimates the start time of the event based on the change over time in the cumulative number of visitors. The estimation unit 214 estimates the end time of the event based on the change over time in the cumulative number of visitors leaving.

[0075] Figure 18 is a diagram showing the cumulative number of visitors Aen1 and the cumulative number of visitors Aex1, which respectively correspond to the time changes in the number of visitors and the number of visitors leaving in Figure 11. That is, Figure 18 shows the cumulative number of visitors and the cumulative number of visitors leaving when the event type is free entry and exit. In Figure 18, the direction of increase in the cumulative number of visitors Aen1 corresponds to the positive (+) direction on the vertical axis, and the direction of increase in the cumulative number of visitors Aex1 corresponds to the negative (-) direction on the vertical axis.

[0076] The estimation unit 214 estimates the time when the cumulative number of attendees Aen1 determined by the determination unit 212 exceeds a first threshold value Th1a as the start time TSes1 of the event. The first threshold value Th1a is defined as a first ratio of the cumulative number of attendees Aen1 to the maximum value Aen1max. Preferably, the first ratio is set to a ratio lower than 50%. More preferably, the first ratio is set to a ratio lower than 10%. In this embodiment, the first ratio is set to 5%.

[0077] In this way, when the event type is free entry / exit, the estimation unit 214 estimates the time when a certain number of users U begin to gather as the start time TSes1 of the event. Note that the first ratio may include 0%. In other words, the estimation unit 214 may estimate the time when the cumulative number of attendees Aen1 exceeds 0 as the start time TSes1 of the event.

[0078] The estimation unit 214 estimates the time when the cumulative number of exiting people Aex1 determined by the determination unit 212 exceeds a second threshold value Th2a as the end time TEes1 of the event. The second threshold value Th2a is defined as a second ratio of the cumulative number of exiting people Aex1 to the maximum value Aex1max. Preferably, the second ratio is set to a ratio higher than 50%. More preferably, the second ratio is set to a ratio higher than 90%. In this embodiment, the second ratio is set to 95%.

[0079] In this way, when the event type is a free entry / exit type, the estimation unit 214 estimates the time when the majority of users U who were staying in the area have left as the end time TEes1 of the event. Note that the second ratio may include 100%. That is, the estimation unit 214 may estimate the time when the cumulative number of exiting users Aex1 reaches the maximum value Aex1max as the end time TEes1 of the event.

[0080] Figure 19 is a diagram showing the cumulative number of visitors Aen2 and the cumulative number of exits Aex2, which respectively correspond to the time changes in the number of visitors and the number of exits in Figure 13. That is, Figure 19 shows the cumulative number of visitors and the cumulative number of exits when the event type is a uniform entry / exit type. In Figure 19, the direction of increase in the cumulative number of visitors Aen2 corresponds to the positive (+) direction on the vertical axis, and the direction of increase in the cumulative number of exits Aex2 corresponds to the negative (-) direction on the vertical axis.

[0081] The estimation unit 214 estimates the time when the cumulative number of attendees Aen2 determined by the determination unit 212 exceeds a first threshold value Th1b as the start time TSes2 of the event. The first threshold value Th1b is defined as a first ratio of the maximum value Aen2max of the cumulative number of attendees Aen2. Preferably, the first ratio is set to a ratio higher than 50%. More preferably, the first ratio is set to a ratio higher than 90%. In this embodiment, the first ratio is set to 95%.

[0082] In this way, when the event type is a uniform entry / exit type, the estimation unit 214 estimates the time when most of the users U who plan to participate in the event have entered the area as the start time TSes2 of the event. Note that the first ratio may include 100%. In other words, the estimation unit 214 may estimate the time when the cumulative number of attendees Aen2 reaches the maximum value Aen2max as the start time TSes2 of the event.

[0083] The estimation unit 214 estimates the time when the cumulative number of exiting people Aex2 determined by the determination unit 212 exceeds a second threshold value Th2b as the end time TEes2 of the event. The second threshold value Th2b is defined as a second ratio of the cumulative number of exiting people Aex2 to the maximum value Aex2max. Preferably, the second ratio is set to a ratio lower than 50%. More preferably, the second ratio is set to a ratio lower than 10%. In this embodiment, the second ratio is set to 5%.

[0084] In this way, when the event type is a uniform entry / exit type, the estimation unit 214 estimates the time when users U who had been staying in the area start to exit as the end time TEes2 of the event. Note that the second percentage may include 0%. That is, the estimation unit 214 may estimate the time when the cumulative number of exiting users Aex2 exceeds 0 as the end time TEes2 of the event.

[0085] In this way, when the event type is free entry / exit, the first ratio is set to a ratio lower than 50%, for example, 5%, and when the event type is uniform entry / exit, the first ratio is set to a ratio higher than 50%, for example, 95%. Also, when the event type is free entry / exit, the second ratio is set to a ratio higher than 50%, for example, 95%, and when the event type is uniform entry / exit, the second ratio is set to a ratio lower than 50%, for example, 5%.

[0086] If the event type is "Other," the estimation unit 214 does not estimate the start time and end time of the event. This is because, when the event type is "Other," it is possible that no event is being held, or multiple events are being held simultaneously at the same venue.

[0087] FIG. 20 is a diagram showing an example of the estimation results of the start time and end time for each event by the event time estimation device. As shown in FIG. 20 , the estimation result table has, for example, the event start date, venue, event type, start time, and end time as its fields. FIG. 20 shows that the event type of an event held on January 10, 2024, at Stadium A was determined to be free entry / exit, and the event start time was estimated to be 11:30 and the event end time was estimated to be 13:00. FIG. 20 also shows that the event type of an event held on the same day at Arena B was determined to be uniform entry / exit, and the event start time was estimated to be 18:00 and the event end time was estimated to be 20:30. FIG. 20 also shows that the event type of an event held on the same day at Stadium C was determined to be other, and therefore the start time and end time of the event were not estimated. Note that the results shown in FIG. 20 may be reflected in the event database DB3 of FIG. 7 .

[0088] 1.2. Operation of the event time estimation device according to the first embodiment 1.2.1. Operation of the processing device 21 Fig. 21 is a flowchart showing an example of the operation of the processing device 21. The operation of the processing device 21 will be described below with reference to Fig. 21. The routine in Fig. 21 is started, for example, when the processing device 21 is started, and is executed every time a certain period of time has elapsed.

[0089] In step S11, the processing device 21 functions as the acquisition unit 211 to acquire venue information, location information of user U[n], and event information from the venue database DB1, location information database DB2, and event database DB3, respectively.

[0090] In step S12, the processing device 21 functions as the determination unit 212 to identify the event venue based on the event information.

[0091] In step S13, the processing device 21 functions as the determination unit 212 to identify the user U[n] within the event venue based on the venue information and the position information of the user U[n].

[0092] In step S14, the processing device 21 functions as the determination unit 212 to chronologically tally the number of visitors, the number of people entering the event venue, and the number of people leaving the venue. As a result, the determination unit 212 determines the visit information.

[0093] In step S15, the processing device 21 functions as the first estimation unit 213a to determine whether the event type is free entry / exit from the aggregated stay information. That is, in step S15, the processing device 21 functions as the first estimation unit 213a to input the aggregated stay information into the learning model LM1 and determine whether the event type output from the learning model LM1 is free entry / exit.

[0094] If the event type is free entry / exit, i.e., if the judgment result in step S15 is positive, the processing device 21 functions as the second estimation unit 213b in step S16 to estimate the start time and end time of the event as follows.

[0095] The processing device 21 estimates the start time TSes1 as the time when the cumulative number of visitors Aen1 exceeds 5% of the maximum value Aen1max of the cumulative number of visitors Aen1. The processing device 21 estimates the end time TEes1 as the time when the cumulative number of exiting visitors Aex1 exceeds 95% of the maximum value Aex1max of the cumulative number of exiting visitors Aex1. After executing the process of step S16, the processing device 21 temporarily ends this routine.

[0096] On the other hand, if the event type is not the free entry / exit type, i.e., if the determination result in step S15 is negative, the processing device 21, functioning as the first estimation unit 213a, determines whether the event type is the uniform entry / exit type from the aggregated stay information in step S17. That is, the processing device 21, functioning as the first estimation unit 213a, determines whether the event type output from the learning model LM1 is the uniform entry / exit type in step S17.

[0097] If the event type is a uniform entry / exit type, i.e., if the judgment result in step S17 is positive, the processing device 21 functions as the second estimation unit 213b in step S18 to estimate the start time and end time of the event as follows.

[0098] The processing device 21 estimates the start time TSes2 as the time when the cumulative number of visitors Aen2 exceeds 95% of the maximum value Aen2max of the cumulative number of visitors Aen2. The processing device 21 estimates the end time TEes2 as the time when the cumulative number of exiting visitors Aex2 exceeds 5% of the maximum value Aex2max of the cumulative number of exiting visitors Aex2. After executing the process of step S18, the processing device 21 temporarily ends this routine.

[0099] On the other hand, if the event type is not a uniform entry / exit type, i.e., if the determination result in step S17 is negative, the processing device 21 temporarily ends this routine. That is, in this case, the processing device 21 does not estimate the start time and end time of the event.

[0100] 1.3. Effects of the First Embodiment As described above, the server 20 according to the first embodiment includes the determination unit 212 and the estimation unit 213. The determination unit 212 determines stay information. The stay information is information relating to changes over time in the number of visitors in an area where an event is held. The estimation unit 213 estimates the start time and end time of the event based on the stay information.

[0101] Attendees at an event act according to the scheduled start time and scheduled end time of the event, but the scheduled start time and actual start time of the event do not always coincide due to various factors. Similarly, the scheduled end time and actual end time of the event do not always coincide. According to this aspect, the actual start time or end time of the event can be estimated from the characteristics of time changes in the stay information. Therefore, more appropriate security plans can be made inside and outside the event venue based on the estimated start time or end time of the event.

[0102] Furthermore, the estimation unit 213 according to the first embodiment includes a first estimation unit 213a and a second estimation unit 213b. The first estimation unit 213a estimates one event type from multiple event types based on the stay information. The multiple event types are classified according to the manner in which the user U enters and exits the area where the event is held. The second estimation unit 213b estimates the start time and end time of the event based on the event type estimated by the first estimation unit 213a and the stay information.

[0103] The inventors have found that events can be classified into several types based on differences in the characteristics of time changes in stay information. According to this aspect, the actual start time and / or end time of an event can be estimated for each event type, thereby making it possible to more accurately estimate the start time or end time of an event.

[0104] Furthermore, in the server 20 according to the first embodiment, the determination unit 212 determines, as stay information, cumulative numbers of visitors Aen1 and Aen2 and cumulative numbers of exits Aex1 and Aex2 for an area of ​​an event during a target period Ta. The target period Ta is a period including a planned event period Tevp from a planned event start time Tsp to a planned event end time Tep. The second estimation unit 213b estimates the times at which the determined cumulative numbers of visitors Aen1 and Aen2 exceed first thresholds Th1a and Th1b as the event start times TSes1 and TSes2, and estimates the times at which the determined cumulative numbers of exits Aex1 and Aex2 exceed second thresholds Th2a and Th2b as the event end times TEes1 and TEes2. The first thresholds Th1a and Th1b are determined as first ratios of the maximum values ​​Aen1max and Aen2max of the cumulative numbers of visitors Aen1 and Aen2. The second thresholds Th2a and Th2b are defined as second ratios of the maximum values ​​Aex1max and Aex2max of the cumulative numbers of exiting persons Aex1 and Aex2.

[0105] According to this aspect, the actual start time is estimated from the admission rate relative to the final cumulative numbers of admissions Aen1 and Aen2, and the actual end time is estimated from the exit rate relative to the final cumulative numbers of exits Aex1 and Aex2, making it easier to estimate the start times TSes1 and TSes2 or the end times TEes1 and TEes2 of the event.

[0106] Furthermore, in the server 20 according to the first embodiment, the multiple event types include a free entry / exit type and a uniform entry / exit type. When the event type estimated by the first estimation unit 213a is the free entry / exit type, the degree of variation in the times at which multiple users U[n] enter and exit the event area is greater than the degree of variation in the times at which multiple users U[n] enter and exit the event area when the event type estimated by the first estimation unit 213a is the uniform entry / exit type.

[0107] Event types can be classified into at least two types. These two event types have different characteristics in terms of the degree of variability in the times at which multiple users enter and exit an area. According to this aspect, the actual start time or end time of an event can be estimated based on the characteristics of each of the two event types, thereby making it possible to more accurately estimate the start time or end time of the event.

[0108] Furthermore, in the server 20 according to the first embodiment, when the event type estimated by the first estimation unit 213a is a free entry / exit type, the first ratio is set to a ratio lower than 50%, and when the event type estimated by the first estimation unit 213a is a uniform entry / exit type, the first ratio is set to a ratio higher than 50%.

[0109] For the two types of events classified into two categories, the time change in the cumulative number of attendees during a verification period, which includes the event period from the start time of the event to the end time of the event, has different characteristics, and the time change in the cumulative number of exits during the verification period has different characteristics. According to this aspect, the start time or end time of an event can be more appropriately estimated for types of events having different characteristics.

[0110] Furthermore, in the server 20 according to the first embodiment, when the event type estimated by the first estimation unit 213a is a free entry / exit type, the second ratio is set to a ratio higher than 50%, and when the event type estimated by the first estimation unit 213a is a uniform entry / exit type, the second ratio is set to a ratio lower than 50%.

[0111] For the two types of events classified into two categories, the time change in the cumulative number of attendees during a verification period, which includes the event period from the start time of the event to the end time of the event, has different characteristics, and the time change in the cumulative number of exits during the verification period has different characteristics. According to this aspect, the start time or end time of an event can be more appropriately estimated for types of events having different characteristics.

[0112] Furthermore, in the server 20 according to the first embodiment, the first estimation unit 213a estimates the event type by inputting the visit information into a learning model LM1 that has learned the relationship between the change over time in the number of visitors in the area where the event is held and the event type, which is classified into multiple event types based on the manner in which people enter and exit.

[0113] The relationship between the stay information and the event type can be learned by the learning model LM1 using, for example, a multi-class classification technique. Therefore, according to this aspect, the event type can be easily determined.

[0114] Furthermore, in the server 20 according to the first embodiment, the determination unit 212 determines the stay information based on the location information of the terminal device 10[n] possessed by each of multiple users U[n], including user U[n] who is staying in the area where the event is being held.

[0115] According to this aspect, it is possible to easily obtain the location information of a plurality of users without requiring any special device or equipment.

[0116] In addition, the event time estimation method by the server 20 according to the first embodiment determines stay information regarding the change over time in the number of visitors in the area where the event is held, and estimates the start time and end time of the event based on the stay information.

[0117] Attendees at an event act according to the scheduled start time and scheduled end time of the event, but the scheduled start time and actual start time of the event do not always coincide due to various factors. Similarly, the scheduled end time and actual end time of the event do not always coincide. According to this aspect, the actual start time or end time of the event can be estimated from the characteristics of time changes in the stay information. Therefore, more appropriate security plans can be made inside and outside the event venue based on the estimated start time or end time of the event.

[0118] 2. Modifications The present disclosure is not limited to the above-described exemplary embodiments. Specific modifications are exemplified below. Two or more modifications selected from the following examples may be combined. Furthermore, the above-described embodiments and the following modifications may be combined in any manner as long as they are not mutually contradictory.

[0119] 2.1. Modification 1 In the above embodiment, an example was shown in which the estimation unit 214 estimated the start time and end time of an event. However, the estimation unit 214 may estimate only the start time of an event, or may estimate only the end time of an event.

[0120] 2.2. Modification 2 In the above embodiment, an example was given in which the location information of the venue was represented by polygon coordinates, but the location information of the venue may also be represented by the coordinates of the center of a circle and the radius of the circle.

[0121] 2.3. Modification 3 In the above embodiment, the location information of user U[n] is acquired by the positioning device 16 of terminal device 10[n]. However, the location information of user U[n] may be location information related to base stations or Wi-Fi location information. Location information related to base stations is location information of terminal device 10[n] located within a cell corresponding to each base station. Wi-Fi location information is location information of terminal device 10[n] located within an accessible range of each Wi-Fi access point.

[0122] 2.4. Modification 4 In the above embodiment, the processing device 21 determines whether the event type is a free entry / exit type in step S15, and if the determination result in step S15 is negative, determines whether the event type is a uniform entry / exit type in step S17. However, the order of the processes in steps S15 and S17 is not limited to this. For example, the processing device 21 may determine whether the event type is a uniform entry / exit type, and then determine whether the event type is a free entry / exit type. Alternatively, the processing device 21 may function as the first estimation unit 213a to first determine whether the event type is "other," and if the determination result is negative, determine whether the event type is a free entry / exit type or a uniform entry / exit type.

[0123] 3. Others (1) In the above-described embodiment, the storage device 12 and the storage device 22 are exemplified by ROM and RAM, but they may also be flexible disks, magneto-optical disks (e.g., compact disks, digital versatile disks, Blu-ray (registered trademark) disks), smart cards, flash memory devices (e.g., cards, sticks, key drives), CD-ROMs (Compact Disc-ROMs), registers, removable disks, hard disks, floppy (registered trademark) disks, magnetic strips, databases, servers, or other suitable storage media. The program may also be transmitted from a network via a telecommunications line. The program may also be transmitted from a communications network (NET) via a telecommunications line.

[0124] (2) In the above-described embodiments, the described information, signals, etc. may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0125] (3) In the above-described embodiment, input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0126] (4) In the above-described embodiment, the determination may be made based on a value (0 or 1) represented using one bit, a Boolean value (true or false), or a comparison of numerical values ​​(e.g., comparison with a predetermined value).

[0127] (5) The order of the exemplary procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be rearranged unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0128] (6) Each function illustrated in Figures 1 to 21 is realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (for example, by wire, wirelessly, etc.) and these multiple devices. A functional block may be realized by combining software with the single device or the multiple devices.

[0129] (7) The programs exemplified in the above-described embodiments should be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., regardless of whether they are called software, firmware, middleware, microcode, hardware description language, or by other names.

[0130] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0131] (8) In each of the foregoing embodiments, the terms "system" and "network" are used interchangeably.

[0132] (9) The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0133] (10) In the above-described embodiments, the server 20 may be a mobile station (MS). Those skilled in the art may refer to a mobile station as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term. In this disclosure, terms such as "mobile station," "user terminal," "event time estimation device (UE)," and "terminal" may be used interchangeably.

[0134] (11) In the above-described embodiments, the terms "connected," "coupled," or any variations thereof refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be a physical coupling or connection, a logical coupling or connection, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0135] (12) In the above embodiments, the phrase "based on" does not mean "based only on," unless otherwise specified. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0136] (13) As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), and ascertaining something that is considered to be a "determining." Also, "determining" and "determining" may include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and so on. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0137] (14) In the above embodiments, when the terms "include," "including," and variations thereof are used, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used in this disclosure, is not intended to be an exclusive or.

[0138] (15) In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are plural.

[0139] (16) In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

[0140] (17) Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0141] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0142] 10... terminal device, 20... server, 212... determination unit, 213... estimation unit, 213a... first estimation unit, 213b... second estimation unit, Aen1, Aen2... cumulative number of visitors, Aen1max, Aen2max, Aex1max, Aex2max... maximum value, Aex1, Aex2... cumulative number of exiting visitors, LM1... learning model, Pen1, Pen2, Pen3... number of visitors, Pex1 , Pex2, Pex3...number of people leaving, Ta...target period, Tep...scheduled end time of the event, Te1, Te2, TEes1, TEes2...end time, Tev1, Tev2...event period, Tsp...scheduled start time of the event, Ts1, Ts2, TSes1, TSes2...start time, Th1a, Th1b...first threshold, Th2a, Th2b...second threshold, U...user.

Claims

1. An event time estimation device comprising: a determination unit that determines stay information regarding changes over time in the number of visitors in an area where an event is held; and an estimation unit that estimates at least one of the start time and the end time of the event based on the stay information.

2. The event time estimation device of claim 1, wherein the estimation unit comprises: a first estimation unit that estimates one event type from a plurality of event types classified by the type of people entering and exiting the area based on the stay information; and a second estimation unit that estimates at least one of the start time and the end time based on the type estimated by the first estimation unit and the stay information.

3. The event time estimation device described in claim 2, wherein the determination unit determines, as the stay information, the cumulative number of visitors and the cumulative number of exits for the area during a target period including the planned event period from the planned start time of the event to the planned end time of the event; the second estimation unit estimates the time when the determined cumulative number of visitors exceeds a first threshold as the start time, and estimates the time when the determined cumulative number of exits exceeds a second threshold as the end time; the first threshold is defined as a first ratio to the maximum value of the cumulative number of visitors; and the second threshold is defined as a second ratio to the maximum value of the cumulative number of exits.

4. The event time estimation device described in claim 3, wherein the multiple event types include at least a first type and a second type, and the degree of variation in the times at which multiple users enter and exit the area when the event type estimated by the first estimation unit is the first type is greater than the degree of variation in the times at which multiple users enter and exit the area when the event type estimated by the first estimation unit is the second type.

5. An event time estimation device as described in claim 4, wherein the first ratio is set to a ratio lower than 1 / 2 when the event type estimated by the first estimation unit is the first type, and the first ratio is set to a ratio higher than 1 / 2 when the event type estimated by the first estimation unit is the second type.

6. An event time estimation device as described in claim 4, wherein the second ratio is set to a ratio higher than 1 / 2 when the event type estimated by the first estimation unit is the first type, and the second ratio is set to a ratio lower than 1 / 2 when the event type estimated by the first estimation unit is the second type.

7. The event time estimation device described in claim 2, wherein the first estimation unit estimates the event type by inputting the visit information into a learning model that has learned the relationship between the change over time in the number of visitors in the area where the event is held and the event type, which is classified into multiple event types based on the manner in which people enter and exit.

8. The event time estimation device according to claim 1, wherein the determination unit determines the stay information based on location information of terminal devices carried by a plurality of people, including people staying in the area.

9. An event time estimation method, comprising: determining stay information regarding changes over time in the number of visitors in an area where an event is held; and estimating at least one of a start time and an end time of the event based on the stay information.

Images