Management staffing planning system

Abstract

To provide a management staff placement planning system capable of appropriately placing management staff.SOLUTION: A management staff placement planning system comprises: a measurement section 112 for identifying positions of participants in an event carrying communication devices within a facility; a head count calculation section 113 for, based on the positions of the participants within the facility, calculating a head count of the participants present at a first timing in each of a predetermined plurality of divisions within the facility; a head count estimation section 115 for using a neural network which has been trained to estimate the head count of the participants in each of the plurality of divisions, for estimating the head count of the participants present in each of the plurality of divisions at a timing later than the first timing from the head count of the participants present at the first timing, for each of the plurality of divisions calculated by the head count calculation section 113; and a staff placement determination section 116 for, based on the head count of people present in each of the plurality of divisions estimated by the head count estimation section 115, determining a head count for management staff to be placed in each of the plurality of divisions.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a management staffing planning system. [Background technology]

[0002] There has been proposed an area management system that manages people entering a specified monitored area, and that includes an RFID tag carried by each person entering the area, tag sensors that are placed at various locations within the monitored area and detect the position of the RFID tag, a management server that can communicate with each tag sensor, and a terminal device that can communicate with the management server (see, for example, Patent Document 1).Here, the management server counts the number of detected RFID tags present within the monitored area based on the position information of the RFID tags detected by each tag sensor, and generates information indicating the congestion status of the monitored area from the number of detections and distributes it to the terminal device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 603256 Summary of the Invention [Problem to be solved by the invention]

[0004] The area management system described in Patent Document 1 can generate information indicating the current congestion / free state within a monitored area, but cannot estimate the future congestion / free state within the monitored area. Therefore, the congestion / free state within the monitored area may differ from the estimated congestion / free state after a certain amount of time has passed. Therefore, even if the deployment of security personnel such as security guards within the monitored area is determined based on the congestion / free state within the monitored area estimated using the area management system described in Patent Document 1, it takes a considerable amount of time to actually deploy the security personnel within the monitored area, so there is a risk that the deployment of the security personnel will not be appropriate for the congestion / free state within the monitored area at that time.

[0005] The present invention has been made in view of the above-mentioned circumstances, and has an object to provide a management personnel allocation planning system that can appropriately allocate management personnel. [Means for solving the problem]

[0006] In order to achieve the above object, the management staffing planning system according to the present invention comprises: a positioning unit that uses a wireless signal transmitted from a communication device carried by a person present in the facility to measure the position of the person carrying the communication device within the facility; a number-of-people calculation unit that calculates the number of people present at a first time point in each of a plurality of pre-defined zones within the facility based on the positions of people carrying the communication devices within the facility measured by the positioning unit; At the first point in time The number of people present in each of the plurality of areas, the type of event being held in the facility, and the The time elapsed from the start to the first point in time and using a trained model for estimating the number of people who will be present in each of the plurality of areas in the future from the number of people who will be present in each of the plurality of areas at the first time point calculated by the number-of-people calculation unit, a second time point after the first time point is calculated. a number-of-people estimation unit that estimates the number of people present in each of the plurality of areas at a point; The number of people estimated by the number-of-people estimation unit and a personnel allocation determination unit that determines the number of management personnel to be allocated to each of the plurality of areas based on the number of people who will be assigned to each of the plurality of areas. [Effects of the Invention]

[0007] According to the present invention, the number of people estimation unit estimates the number of people who will be in each of the multiple areas at a second time point from the number of people who will be in each of the multiple areas at a first time point calculated by the number of people calculation unit, using a trained model for estimating the number of people who will be in each of the multiple areas in the future based on the number of people who will be in each of the multiple areas, the type of event being held in the facility, and the progress of the event.The personnel deployment determination unit then determines the number of supervision personnel to be deployed in each of the multiple areas based on the number of people who will be in each of the multiple areas at the second time point estimated by the number of people estimation unit.This makes it possible to appropriately estimate the number of people who will be in each of the multiple areas in the future, taking into account the time required for actually deploying supervision personnel in the monitored area, and therefore to appropriately deploy supervision personnel in each of the multiple areas. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a schematic configuration diagram of a management personnel deployment planning system according to an embodiment of the present invention; [Figure 2] FIG. 1 is a diagram illustrating a hardware configuration of a management staffing planning system according to an embodiment. [Figure 3] FIG. 1 is a diagram illustrating a functional configuration of a management personnel deployment planning system according to an embodiment. [Figure 4] FIG. 1A is a diagram showing the contents of information stored in a position storage unit according to the embodiment, and FIG. 1B is a diagram showing the contents of information stored in a number-of-persons storage unit according to the embodiment. [Figure 5]FIG. 1A is a diagram for explaining the structure of a neural network according to an embodiment, and FIG. 1B is a diagram showing the contents of information stored in a correlation storage unit according to an embodiment. [Figure 6] FIG. 2 is a sequence diagram illustrating the operation of the management staffing planning system according to the embodiment. [Figure 7] FIG. 2 is a sequence diagram illustrating the operation of the management staffing planning system according to the embodiment. [Figure 8] FIG. 10 is a diagram showing an example of an image displayed on the terminal device according to the embodiment. [Figure 9] 10 is a flowchart illustrating an example of the flow of a management staffing planning process according to an embodiment. [Figure 10] 10 is a flowchart illustrating an example of the flow of a model generation process according to the embodiment. [Figure 11] 10 is a flowchart illustrating an example of the flow of a management staffing planning process according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] A supervisory personnel deployment planning system according to an embodiment of the present invention will be described in detail below with reference to the drawings. The supervisory personnel deployment planning system according to this embodiment includes a positioning unit that measures the positions of people carrying communication devices within a facility using wireless signals transmitted from the communication devices carried by the people within the facility, a number of people calculation unit, a number of people estimation unit, and a personnel deployment determination unit. The number of people calculation unit calculates the number of people present in each of multiple pre-defined zones within the facility at a first time point based on the positions of people carrying the communication devices within the facility measured by the positioning unit. The number of people estimation unit estimates the number of people present in each of multiple zones at a second time point after the first time point from the number of people present in each of the multiple zones at the first time point calculated by the number of people calculation unit, using a trained model for estimating the number of people present in each of the multiple zones in the future based on the number of people present in each of the multiple zones, the type of event being held within the facility, and the progress of the event. The personnel deployment determination unit determines the number of supervisors to be deployed in each of the multiple zones based on the number of people present in each of the multiple zones at the second time point estimated by the number of people estimation unit.

[0010] As shown in FIG. 1 , a staffing planning system according to this embodiment includes a staffing planning device 1, a terminal device 2 connected to the staffing planning device 1 via a network NW, and an access point 3. The terminal device 2 is used by a supervisor who commands and supervises staffing personnel, such as facility security guards. The access points 3 are installed in each of multiple areas within the facility and communicate with communication devices (not shown), such as smartphones and wireless tags, carried by participants in an event held within the facility. When the access points 3 receive positioning information request information from the staffing planning device 1, the access points 3 receive wireless signals from communication devices carried by each participant that can communicate with the access point 3. The positioning information request information requests the transmission of positioning information to the staffing planning device 1, the positioning information including device identification information of the communication devices, reception strength information indicating the reception strength of the wireless signals received from the communication devices, and area identification information of the area in which the access point 3 is installed. When the access point 3 receives the wireless signal, it generates positioning information including device identification information extracted from the received wireless signal, reception strength information indicating the reception strength of the wireless signal, and area identification information of the area where the access point 3 is installed. Then, the access point 3 transmits the generated positioning information to the managerial staffing planning device 1.

[0011] As shown in FIG. 2, the terminal device 2 includes a CPU (Central Processing Unit) 21, a main memory 22, an auxiliary memory 23, an input unit 24, a display unit 25, a communication unit 26, and a bus 29 connecting the various units. The main memory 22 is composed of a volatile memory such as a RAM (Random Access Memory) and is used as a work area for the CPU 21. The auxiliary memory 23 is composed of a nonvolatile memory such as a magnetic disk or semiconductor memory and stores programs for implementing various functions of the terminal device 2. The input unit 24 is an input device such as a keyboard or touchpad, and receives various operation information input by a user and outputs the received operation information to the CPU 21. The display unit 25 is, for example, a liquid crystal display, and displays various information input from the CPU 21. The communication unit 26 includes a modem and a gateway, and communicates with the terminal device 2 via a network NW.

[0012] In the terminal device 2, the CPU 21 loads the program stored in the auxiliary storage unit 23 into the main storage unit 22 and executes it, thereby functioning as a reception unit 211, an event registration unit 212, an allocation plan request unit 213, an allocation plan acquisition unit 214, and a display control unit 215, as shown in Fig. 3. The auxiliary storage unit 23 shown in Fig. 2 also has a allocation plan storage unit 231, as shown in Fig. 3. The allocation plan storage unit 231 stores the allocation plan information acquired by the allocation plan acquisition unit 214.

[0013] When the user performs a staffing plan request operation on the input unit 24 to acquire staffing plan information indicating a staffing plan for staff from the staffing planning device 1, the reception unit 211 receives operation information corresponding to the operation. Furthermore, when the user inputs event information of an event for which the number of participants at multiple locations in the facility is to be recorded via the input unit 24, the reception unit 211 receives the input event information. When the reception unit 211 receives operation information corresponding to the staffing plan request operation, the staffing plan request unit 213 generates staffing plan request information and transmits it to the staffing planning device 1 via the communication unit 26 (see FIG. 2 ). When the reception unit 211 receives event information, the event registration unit 212 transmits the received event information to the staffing planning device 1.

[0014] When the deployment plan acquisition unit 214 receives the deployment plan information transmitted from the management personnel deployment planning device 1, it stores the received deployment plan information in the deployment plan storage unit 231. The display control unit 215 displays the deployment plan information stored in the deployment plan storage unit 231 on the display unit 25.

[0015] 2, the management staffing planning device 1 includes a CPU 11, a main memory unit 12, an auxiliary memory unit 13, a communication unit 16, and a bus 19 connecting the various units. The main memory unit 12 is composed of a volatile memory, and the auxiliary memory unit 13 is composed of a non-volatile memory, and they store programs for realizing various functions of the management staffing planning device 1. The communication unit 16 has a modem and a gateway, and communicates with the terminal device 2 via the network NW.

[0016] In the staffing planning device 1, the CPU 11 loads the program stored in the auxiliary storage unit 13 into the main storage unit 12 and executes it, thereby functioning as a request acquisition unit 111, a positioning unit 112, a headcount calculation unit 113, a model generation unit 114, a headcount estimation unit 115, a staffing determination unit 116, a staffing plan generation unit 117, and a staffing plan transmission unit 118, as shown in Fig. 3. The auxiliary storage unit 13 also has a position storage unit 131, a headcount storage unit 133, a model storage unit 134, an estimated headcount storage unit 135, and a correlation storage unit 136. As shown in Fig. 4(A), the position storage unit 131 stores coordinate information (X[k], Y[k]) indicating the position within the facility of the terminal device 2 carried by each event participant, in association with terminal identification information TeID[k] that identifies the terminal device 2. Then, the position storage unit 131 stores the coordinate information of each terminal device 2 at each time T[i] during the event in association with the time information.

[0017] 4(B), the number-of-people storage unit 133 stores number-of-people information indicating the number of participants present in each of multiple zones in the facility at each time point during the event, in association with the zone identification information AID[m] of each of the multiple zones. The number-of-people storage unit 133 also stores the number-of-people information for each event in association with event identification information that identifies the event.

[0018] Returning to FIG. 3 , the model storage unit 134 stores information indicating a trained model for estimating the number of people in each of multiple zones in the future based on the number of people in each of multiple zones within the facility, the type of event taking place within the facility, and the progress of the event, i.e., the elapsed time since the start of the event. Here, the trained model is, for example, a trained neural network having a predetermined number of nodes and layers. In this case, the model storage unit 134 stores information indicating the number of nodes and layers of the neural network, as well as the weight coefficients and activation functions corresponding to each node. As shown in FIG. 5(A), the neural network has an input layer LY1, a hidden layer LY2, and an output layer LY3. The input layer LY1 inputs information about the number of people in each of multiple zones within the facility, event identification information indicating the type of event taking place within the facility, and the elapsed time since the start of the event to the hidden layer LY2. Here, the event identification information is represented, for example, by an event identification number previously set for each type of event. The hidden layer LY2 is composed of N (N is a positive integer) layers containing a preset number M[j] of nodes x[j,i] (1≦i≦M[j], M[j] is a positive integer). The hidden layer LY2 has a structure in which each node column is connected to another. Here, the output y[j,i] of each node x[j,i] is expressed by the relational expression (1) below.

number

[0019] Returning to Fig. 3, the estimated number of participants storage unit 135 stores estimated number of participants information indicating the estimated number of participants present in multiple zones in each of multiple pre-set time periods from time 1 during the event to the end of the event, in association with zone identification information. The correlation storage unit 136 stores number of participants correlation information indicating the correlation between the number of participants present in each of the multiple zones and the number of management personnel to be assigned to each of the multiple zones. The number of participants correlation information indicates, for example, the correlation shown in Fig. 5(B).

[0020] Returning to FIG. 3 , upon receiving placement plan request information transmitted from a terminal device 2, the request acquisition unit 111 notifies the number of people estimation unit 115 that the placement plan request information has been received. The positioning unit 112 receives positioning information transmitted from access points 3 installed at multiple locations within the facility, and identifies the location within the facility of a communication device corresponding to the device identification information based on the device identification information, reception strength information, and area identification information included in the received positioning information. Specifically, the positioning unit 112 transmits positioning information request information to the access points 3 installed within the facility, requesting the access points 3 to transmit positioning information, thereby obtaining positioning information including the device identification information from the access points 3. The positioning unit 112 also identifies, from the received plurality of pieces of positioning information, the positioning information having the greatest reception strength indicated by the reception strength information. The positioning unit 112 then stores the area identification information included in the identified positioning information in the position storage unit 131 in association with the device identification information. For example, the positioning unit 112 receives positioning information including device identification information TeID[k] from multiple access points 3, and assumes that the positioning information identified from the received positioning information includes area identification information AID[m]. In this case, the positioning unit 112 stores the area identification information AID[m] in the position storage unit 131 in association with the device identification information TeID[k] and time information indicating the time zone in which the positioning information was received.

[0021] The number of people calculation unit 113 refers to the location storage unit 131, tallies the device identification information corresponding to each area identification information, and calculates the number of communication devices present in each of multiple areas within the facility as the number of participants present in that area. Then, the number of people calculation unit 113 stores the number of people information indicating the calculated number of participants in the number of people storage unit 133 in association with the area identification information and the above-mentioned time information.

[0022] The model generation unit 114 performs machine learning using training data including information indicating the number of people present in each of multiple zones at each time point during an event held at the facility in the past and information indicating the type of event held at the facility, to generate the trained model. Specifically, the model generation unit 114 determines the weighting coefficients of the neural network each time an event held at the facility ends and the positioning end time arrives. The model generation unit 114 first obtains initial weighting coefficient information indicating the initial weighting coefficients from the model storage unit 134, and then uses the neural network set to the obtained initial weighting coefficients to calculate an estimated number of people present in each of multiple zones at a second time point after the first time point during an event held at the facility in the past, based on the number of people present in each of multiple zones at that time point. Next, the model generation unit 114 calculates the error between the calculated estimated number of people present in each of multiple zones at the second time point and the actual number of participants at the second time point indicated by the number of people information stored in the number of people storage unit 133. Here, the model generation unit 114 calculates the error between the estimated number of people and the actual number of people for each of a plurality of preset time points between the start time of the event and the actual time point of the event, with that time point being defined as a first time point. Then, the coefficient determination unit 113 determines the weighting coefficients of the neural network described above by backpropagation based on the calculated error. Here, the model generation unit 114 determines the weighting coefficients using, for example, an autoencoder. Then, the model generation unit 114 stores weighting coefficient information indicating the determined weighting coefficients in the model storage unit 134.

[0023] The number of participants estimation unit 115 uses the trained model stored in the model storage unit 134, i.e., the trained neural network with the determined weighting coefficients, to estimate the number of participants present in each of the multiple zones at a second time point after the first time point, based on the number of participants present in each of the multiple zones at a first time point calculated by the number of participants calculation unit 113. Specifically, the number of participants estimation unit 115 uses the neural network set to the weighting coefficients determined by the model generation unit 114 to calculate the number of participants in each of the multiple zones for each preset time period from the current time point to the end of the event, based on the type of event being held in the facility, the elapsed time from the start of the event to the current time point, and the number of participants in each of the multiple zones at the current time point. The number of participants estimation unit 115 stores the calculated number of participants information in the estimated number of participants storage unit 135, in association with the zone identification information for each of the multiple zones.

[0024] The staffing determination unit 116 determines the number of supervision personnel to be allocated to each of the multiple areas at the second time point from the number of people present in each of the multiple areas at the second time point estimated by the number of people estimation unit 115, based on the number-of-people correlation information stored in the correlation storage unit 136. The allocation plan generation unit 117 generates allocation plan information indicating an allocation plan for supervision personnel based on the number of supervision personnel in each of the multiple areas determined by the staffing determination unit 116. The allocation plan transmission unit 118 transmits the allocation plan information generated by the allocation plan generation unit 117 to the terminal device 2.

[0025] Next, the operation of the staffing planning system according to this embodiment will be described with reference to FIGS. 6 to 8. First, as shown in FIG. 6, it is assumed that a user performs an event registration operation on the input unit 24 of the terminal device 2 to register an event for which training data on the number of people in multiple areas within a facility during the event is to be acquired. Here, the user performs the event registration operation, for example, when the event starts at the facility. In this case, the terminal device 2 accepts the event registration operation (step S1). Event information registered by the event registration operation is transmitted from the terminal device 2 to the staffing planning device 1 (step S2). Meanwhile, upon receiving the event information, the staffing planning device 1 stores the received event information in the number-of-people storage unit 133. After the event starts, when a preset positioning time arrives, the staffing planning device 1 broadcasts positioning information request information to each of the multiple access points 3 installed within the facility, requesting that each access point 3 transmit positioning information (step S3). Meanwhile, upon receiving the positioning information request information, the access point 3 generates positioning information (step S4). Here, the access point 3 receives wireless signals from communication devices that can communicate with the access point 3 among the communication devices carried by each of the event participants. The access point 3 then generates positioning information including device identification information extracted from the received wireless signals, reception strength information indicating the reception strength of the wireless signals, and area identification information of the area in which the access point 3 is installed. Next, the generated positioning information is transmitted from the access point 3 to the management personnel deployment planning device 1 (step S5).

[0026] Next, based on the device identification information, reception strength information, and area identification information included in the positioning information transmitted from the access point 3, the personnel deployment planning device 1 identifies the location within the facility of the communication device corresponding to the device identification information (step S6). At this time, the personnel deployment planning device 1 stores the location of the communication device as area identification information of the area in which the communication device is located in the location storage unit 131 in association with the device identification information. Thereafter, the personnel deployment planning device 1 generates headcount information indicating the number of participants in each area by referencing the location storage unit 131 and aggregating the device identification information corresponding to each area identification information for each area identification information. Then, the personnel deployment planning device 1 stores the generated headcount information in the headcount storage unit 133 in association with the area identification information and the time information (step S7). Thereafter, during the event, the series of processes from steps S3 to S7 is repeatedly executed each time the positioning period arrives.

[0027] Next, when the event ends and the preset positioning end time arrives, the management personnel deployment planning device 1 generates a trained model using the number of people information stored in the number of people memory unit 133 as training data, and stores it in the model memory unit 134 (step S8).

[0028] Thereafter, it is assumed that the user performs a plan request operation on the input unit 24 of the terminal device 2 to request staffing planning device 1 for staffing plan information for a new event. In this case, terminal device 2 accepts the plan request operation (step S9). Next, the plan request information is transmitted from terminal device 2 to staffing planning device 1 (step S10). Subsequently, after the new event has started, when a preset positioning time arrives, the positioning information request information is broadcast from staffing planning device 1 to each of the multiple access points 3 (step S11). Meanwhile, upon receiving the positioning information request information, access point 3 generates positioning information (step S12). Thereafter, the generated positioning information is transmitted from access point 3 to staffing planning device 1 (step S13).

[0029] Next, the management personnel deployment planning device 1 identifies the location of the communication device corresponding to the device identification information included in the positioning information at a first time point within the facility, based on the device identification information, reception strength information, and area identification information included in the positioning information transmitted from the access point 3 (step S14). Here, the first time point is set to, for example, the current time. Next, the management personnel deployment planning device 1 generates headcount information indicating the number of participants in each area, and stores the generated headcount information in the headcount storage unit 133 (step S15).

[0030] Then, the management personnel deployment planning device 1 uses the learned model stored in the model memory unit 134 to estimate the number of participants present in each of the multiple areas at a second time point after the first time point from the number of participants present in each of the multiple areas at the first time point calculated by the number calculation unit 113 (step S16).

[0031] Next, the supervisory staffing planning device 1 determines the number of supervisors to be allocated to each of the plurality of zones at the second time point from the number of people present in each of the plurality of zones at the second time point estimated by the number-of-people estimation unit 115, based on the number-of-people correlation information stored in the correlation storage unit 136 (step S17). Subsequently, the supervisory staffing planning device 1 generates allocation plan information indicating an allocation plan for supervisors based on the determined number of supervisors for each of the plurality of zones, as shown in Fig. 7 (step S18). Thereafter, the generated allocation plan information is transmitted from the supervisory staffing planning device 1 to the terminal device 2 (step S19).

[0032] On the other hand, when the terminal device 2 receives the allocation plan information, it displays the received allocation plan information on the display unit 25 (step S20). At this time, the terminal device 2 displays, for example, a display screen 25a as shown in Fig. 8 on the display unit 25. The display screen 25a shown in Fig. 8 displays the number of management personnel in each area at a first point in time T[0] and the number of management personnel in each area at second points in time T[1], . . ., T[i], T[i+1], . . . that are later than the first point in time T[0].

[0033] Next, the management staffing planning process executed by the management staffing planning device 1 according to this embodiment will be described with reference to Fig. 9 to Fig. 11. This management staffing planning process is started when an application for executing the management staffing planning process is launched after a user turns on the power to the management staffing planning device 1.

[0034] First, the event information receiving unit 119 determines whether or not it has received event information from the terminal device 2 (step S101). If the event information receiving unit 119 determines that it has not received event information (step S101: No), the process of step S109, which will be described later, is executed. On the other hand, if the event information receiving unit 119 determines that it has received event information (step S101: Yes), the positioning unit 112 determines whether or not a preset positioning time has arrived (step S102). If the positioning unit 112 determines that the positioning time has not arrived (step S102: No), the process of step S107, which will be described later, is executed. On the other hand, it is assumed that the positioning unit 112 determines that the positioning time has arrived (step S102: Yes). In this case, the positioning unit 112 transmits positioning information request information to the access point 3 installed in the facility, requesting the access point 3 to transmit positioning information (step S103). Then, the positioning unit 112 acquires the positioning information from the access point 3 that is the transmission destination of the positioning information request information (step S104).

[0035] Next, the positioning unit 112 identifies the location within the facility of the communication device corresponding to the device identification information based on the device identification information, reception strength information, and area identification information included in the received positioning information (step S105). At this time, the positioning unit 112 stores the area identification information of the area in which the identified communication device is located in the location storage unit 131 in association with the device identification information. Next, the number of people calculation unit 113 generates number of people information indicating the number of participants present in each of the multiple areas within the facility by referencing the location storage unit 131 and aggregating the device identification information corresponding to each area identification information for each area identification information. Then, the number of people calculation unit 113 stores the generated number of people information for each of the multiple areas in association with the area identification information and the above-mentioned time information in the number of people storage unit 133 (step S106). Thereafter, the positioning unit 112 determines whether a preset positioning end time has arrived (step S107). If the positioning unit 112 determines that the positioning end time has not yet arrived (step S107: No), the process of step S102 is executed again.

[0036] On the other hand, if the positioning unit 112 determines that the positioning end time has arrived (step S107: Yes), a model generation process is executed (step S108).

[0037] 10, in this model generation process, first, the model generation unit 114 acquires number of people information and event information from the number of people storage unit 133 (step S201). Next, the model generation unit 114 acquires initial weighting coefficient information of the neural network from the model storage unit 134, and sets the weighting coefficients indicated by the acquired initial weighting coefficient information as the weighting coefficients of the neural network (step S202).

[0038] Next, the model generation unit 114 calculates an estimated number of people in each of the multiple zones at a second time point after the first time point, based on the number of people information and event information in each of the multiple zones at the first time point, using a neural network set to the weight coefficients indicated by the initial weight coefficient information (step S203). The model generation unit 114 then calculates the error between the estimated number of people and the number of people at the second time point indicated by the number of people information acquired from the number of people storage unit 133 (step S204). Next, the model generation unit 114 determines new weight coefficients for the neural network using backpropagation based on the calculated error (step S205). The model generation unit 114 then stores weight coefficient information indicating the determined weight coefficients in the model storage unit 134 as weight coefficient information for the neural network constituting the trained model (step S206).

[0039] Returning to FIG. 9 , thereafter, the request acquisition unit 111 determines whether or not it has received the placement plan request information transmitted from the terminal device 2 (step S109). If the request acquisition unit 111 determines that it has not received the placement plan request information from the terminal device 2 (step S109: No), the process of step S101 is executed again. On the other hand, if the request acquisition unit 111 determines that it has received the placement plan request information from the terminal device 2 (step S109: Yes), the positioning unit 112 determines whether or not the positioning time has arrived (step S110). As long as the positioning unit 112 determines that the positioning time has not arrived (step S110: No), the positioning unit 112 repeatedly executes the process of step S110. On the other hand, if the positioning unit 112 determines that the positioning time has arrived (step S110: Yes), it transmits positioning information request information to the access point 3 (step S111) and acquires positioning information from the access point 3 (step S112).

[0040] Next, the positioning unit 112 identifies the location within the facility of the communication device corresponding to the device identification information based on the device identification information, reception strength information, and area identification information included in the received positioning information (step S113). At this time, the positioning unit 112 stores the area identification information of the area in which the identified communication device is located in the location storage unit 131 in association with the device identification information. Next, the number of people calculation unit 113 refers to the location storage unit 131 and counts the device identification information corresponding to each area identification information for each area identification information, thereby generating number of people information indicating the number of participants present in each of the multiple areas within the facility. Then, the number of people calculation unit 113 stores the generated number of people information for each of the multiple areas in association with the area identification information and the above-mentioned time information in the number of people storage unit 133 (step S114). Then, as shown in FIG. 11, the number of participants estimation unit 115 uses the trained model stored in the model memory unit 134, i.e., the neural network with determined weighting coefficients, to estimate the number of participants present in each of the multiple areas at a second time point after the first time point from the number of participants present in each of the multiple areas at the first time point calculated by the number of participants calculation unit 113 (step S115).

[0041] Next, the staffing determination unit 116 determines the number of supervisors to be allocated to each of the plurality of zones at the second time point from the number of people present in each of the plurality of zones at the second time point estimated by the number-of-people estimation unit 115, based on the number-of-people correlation information stored in the correlation storage unit 136 (step S116). Subsequently, the allocation plan generation unit 117 generates allocation plan information indicating an allocation plan for supervisors based on the number of supervisors in each of the plurality of zones determined by the staffing determination unit 116 (step S117). Thereafter, the allocation plan transmission unit 118 transmits the allocation plan information generated by the allocation plan generation unit 117 to the terminal device 2 (step S118). Next, the process of step S101 shown in FIG. 9 is executed again.

[0042] As described above, in the supervision personnel allocation system according to this embodiment, the number of participants estimation unit 115 uses a neural network to estimate the number of participants who will be present in each of the multiple zones at a second time point that is later than the first time point, based on the number of participants present in each of the multiple zones within the facility at a first time point calculated by the number of participants calculation unit 113. Then, the personnel allocation determination unit 116 determines the number of supervision personnel to be allocated to each of the multiple zones based on the number of participants present in each of the multiple zones at the second time point estimated by the number of participants estimation unit 115. This makes it possible to appropriately estimate the number of people who will be present in each of the multiple zones in the future, taking into account the time required to actually deploy supervision personnel in the monitored area, thereby making it possible to appropriately deploy supervision personnel in each of the multiple zones.

[0043] Although the embodiments of the present invention have been described above, the present invention is not limited to the configurations of the above-described embodiments. For example, the neural network may be a trained model for determining the number of people in each of a plurality of areas in a facility for each predetermined time period from the start of the event to the end of the event, based on the number of people in each of the areas in the facility at the start of the event for which a management staff deployment plan is being made and the event information. Alternatively, the neural network may be configured to determine the number of people in each of the plurality of areas at a second time point after a predetermined time has elapsed from the first time point, based on the number of people in each of the areas at a first time point during the event and the event information.

[0044] Furthermore, the various functions of the management personnel deployment planning device 1 according to the present invention can be realized using a normal computer system, rather than a dedicated system. For example, a program for executing the above operations may be stored on a non-transitory recording medium (such as a CD-ROM (Compact Disc Read Only Memory)) that can be read by a computer system and distributed to a computer connected to a network, and the program may be installed in the computer system to configure the management personnel deployment planning device 1 that executes the above processes.

[0045] The method of providing the program to the computer is arbitrary. For example, the program may be uploaded to a bulletin board system (BBS) on a communication line and distributed to the computer via the communication line. The computer then launches the program and executes it under the control of an operating system (OS) in the same way as other applications. In this way, the computer functions as a management personnel allocation planning device 1 that executes the above-mentioned processing.

[0046] Although the embodiments and modifications of the present invention have been described above, the present invention is not limited to these. The present invention includes any combination of the embodiments and modifications, and any combination to which appropriate modifications have been made. [Industrial Applicability]

[0047] The present invention is suitable for creating a deployment plan for security guards and other management personnel during an event held at a facility such as an arena. [Explanation of symbols]

[0048] 1: management personnel allocation determination device, 2: terminal device, 3: access point, 11, 21: CPU, 12, 22: main memory unit, 13, 23: auxiliary memory unit, 16, 26: communication unit, 19, 29: bus, 24: input unit, 25: display unit, 25a: display screen, 111: request acquisition unit, 112: positioning unit, 113: number of people calculation unit, 114: model generation unit, 115: number of people estimation unit, 116: personnel allocation determination unit, 117: Placement plan generation unit, 118: Placement plan transmission unit, 131: Position memory unit, 133: Number of people memory unit, 134: Model memory unit, 135: Estimated number of people memory unit, 136: Correlation memory unit, 211: Reception unit, 212: Event registration unit, 213: Placement plan request unit, 214: Placement plan acquisition unit, 215: Display control unit 215, LY1: Input layer, LY2: Hidden layer, LY3: Output layer, NW: Network

Claims

1. a positioning unit that uses a wireless signal transmitted from a communication device carried by a person present in the facility to measure the position of the person carrying the communication device within the facility; a number-of-people calculation unit that calculates the number of people present at a first time point in each of a plurality of pre-defined zones within the facility based on the positions of people carrying the communication devices within the facility measured by the positioning unit; a people count estimation unit that estimates the number of people that will be present in each of the plurality of areas at a second time point that is later than the first time point from the number of people that will be present in each of the plurality of areas at the first time point calculated by the people count calculation unit, using a trained model for estimating the number of people that will be present in each of the plurality of areas in the future based on the number of people that will be present in each of the plurality of areas at the first time point, the type of event being held in the facility, and the elapsed time from the start of the event to the first time point; a personnel allocation determination unit that determines the number of management personnel to be allocated to each of the plurality of areas based on the number of people present in each of the plurality of areas at the second time point estimated by the number-of-people estimation unit, Management staffing planning system.

2. The facility further includes a model generation unit that generates the trained model using, as training data, information indicating the number of people present in each of the plurality of zones at each time point in an event that was previously held in the facility, and information indicating the type of event that will be held in the facility. The management staffing planning system of claim 1 .

3. a correlation storage unit configured to store number-of-people correlation information indicating a correlation between the number of people present in each of the plurality of zones and the number of management personnel to be allocated to each of the plurality of zones; the personnel allocation determination unit determines the number of management personnel to be allocated to each of the plurality of areas at the second time point from the number of people present in each of the plurality of areas at the second time point estimated by the number of people estimation unit, based on the number of people correlation information stored in the correlation storage unit; 3. The management personnel allocation planning system according to claim 1 or 2.

Images