Device for predicting the number of people present, equipment management system and method for predicting the number of people present

Abstract

A schedule information acquisition unit (11) acquires schedule information of each user who intends to use a predetermined area in a building. A primary prediction unit (13) predicts whether each user is in the area at a prediction target time based on the schedule information, thereby calculating a primary prediction value of the number of people in the area at the prediction target time. A correction unit (19) corrects the primary prediction value using a correction parameter set according to the area and the prediction target time, thereby calculating a secondary prediction value of the number of people in the area.

Description

Technical Field

[0001] The invention relates to a device for predicting the number of people present, an equipment management system and a method for predicting the number of people present. Background Art

[0002] In terms of operating and managing equipment in buildings such as buildings, there is a case where it is desired to predict the number of people who will be in each floor after a specified time. For example, in order to suppress the power consumption of the entire building after one hour, an air conditioner with a reduced output is selected from the air conditioners installed on each floor. In this case, if the predicted value of the number of people in the room after one hour on each floor is obtained, for example, the output of the air conditioner on the floor where it is predicted that the number of people in the room after one hour will be small can be suppressed, and power consumption can be suppressed without reducing the comfort of the users of the building.

[0003] In the past, the following technology has been proposed: when predicting the number of people in the office, the company employees passing through the automatic ticket gate are detected to calculate the predicted arrival time at the office, and the number of people in the office at each time is calculated based on the predicted arrival time of each company employee (for example, Patent Document 1).

[0004] In addition, a technique has been proposed in which, when predicting the number of people present, the schedules of building users are referred to and the predicted number of people present in a specific time period in a specific area is increased or decreased according to the schedules of the users (for example, Patent Document 2).

[0005] In addition, a technology has been proposed in which the number of people on each floor is obtained based on the elevator boarding and alighting history information, and the number of people on each floor is corrected using a correction parameter obtained based on the action history data (for example, Patent Document 3).

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Application Publication No. 2012-109680

[0009] Patent Document 2: Japanese Patent Application Publication No. 2011-180974

[0010] Patent Document 3: Japanese Patent Application Publication No. 2016-74525 Summary of the invention

[0011] Problems to be solved by the invention

[0012] However, when using schedule information to predict the number of people present in the future, the schedule information of each user is created by each user registering a schedule. That is, there is a possibility that a prediction error will occur in the number of people present due to omission or erroneous registration of schedule information.

[0013] Therefore, an object of the present invention is to suppress prediction errors caused by schedule information determined by users in schedule registration, as compared with the related art.

[0014] Means for solving problems

[0015] The present invention provides a device for predicting the number of people in a building, comprising a schedule information acquisition unit, a primary prediction unit, and a correction unit. The schedule information acquisition unit acquires schedule information of each user who intends to use a predetermined area in a building. The primary prediction unit predicts whether each user is in the area at the prediction target time based on the schedule information, and calculates a primary prediction value of the number of people in the area at the prediction target time. The correction unit calculates a secondary prediction value of the number of people in the area by correcting the primary prediction value using a correction parameter set according to the area and the prediction target time.

[0016] According to the above invention, a secondary prediction value is calculated by correcting a primary prediction value using a correction parameter. By correcting a prediction error included in the primary prediction value using the correction parameter, the prediction error can be suppressed.

[0017] In the above invention, the number of people prediction device may also include a number of people acquisition unit and a correction parameter setting unit. The number of people acquisition unit acquires the actual value of the number of people in the area. The correction parameter setting unit sets the correction parameter according to the difference between the primary prediction value at the same time and the actual value of the number of people in the area.

[0018] According to the above invention, the correction parameter is set based on the difference between the primary predicted value and the actual value of the number of people present. By setting the correction parameter so as to reduce the difference, the predicted value with suppressed prediction error can be calculated.

[0019] In addition, in the above invention, the location number prediction device may also include a commuting information acquisition unit, which acquires the commuting information of each user in the area. In this case, the primary prediction unit uses the historical records of the commuting information of each user to predict the number of office workers in the area at the prediction target time, and calculates the primary prediction value based on the number of office workers and schedule information.

[0020] According to the above invention, since people who are not at work and people who are leaving get off work are excluded from the rated number of people in the area, it is possible to calculate a predicted value with a further suppressed error.

[0021] In the above invention, the primary prediction unit may calculate the primary prediction value at the prediction target time by subtracting the number of people absent at the prediction target time predicted based on the schedule information from the number of people working at the prediction target time.

[0022] According to the above invention, the number of people working in the area is obtained by excluding those who are absent and those who are leaving work from the rated number of people in the area, and the number of people absent predicted based on schedule information is subtracted from the total number of people to obtain a primary predicted value, thereby calculating a predicted value with further suppressed errors.

[0023] The present invention also relates to a facility management system comprising: the occupancy prediction device of the above invention; and a facility management device for managing facilities installed in a building based on the number of people in an area predicted by the occupancy prediction device.

[0024] The present invention also relates to a method for predicting the number of people in a building. The method includes the following steps: obtaining schedule information of each user who wants to use a specified area in a building; predicting whether each user is in the area at a prediction target time based on the schedule information, and calculating a primary prediction value of the number of people in the area at the prediction target time; and calculating a secondary prediction value of the number of people in the area by correcting the primary prediction value using a correction parameter set according to the area and the prediction target time.

[0025] Effects of the Invention

[0026] According to the present invention, it is possible to suppress the prediction error caused by the schedule information that is determined by the user in the schedule registration, as compared with the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is an overall configuration diagram showing one embodiment of the equipment management system of the present invention.

[0028] Figure 2 This is a hardware configuration diagram of a computer that forms the presence number prediction device of implementation mode 1.

[0029] Figure 3 This is a block diagram illustrating the structure of the presence number prediction device according to the first exemplary embodiment.

[0030] Figure 4 This is a diagram showing an example of the data structure of schedule information stored in the schedule information storage unit according to the first embodiment.

[0031] Figure 5 This is a diagram illustrating correction parameters in the first embodiment.

[0032] Figure 6 It is a diagram for explaining the correction process (1 / 2) of the primary prediction value.

[0033] Figure 7 It is a diagram for explaining the correction process (2 / 2) of the primary prediction value.

[0034] Figure 8 This is a flowchart illustrating the presence number prediction process according to the first embodiment.

[0035] Fig. 9 This is a block diagram illustrating the structure of a device for predicting the number of people present according to the second exemplary embodiment.

[0036] Fig.10 This is a flowchart showing the presence number prediction processing of the second implementation mode. DETAILED DESCRIPTION

[0037] Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

[0038] <Implementation Method 1>

[0039] Figure 1 1 is an overall configuration diagram showing an embodiment of the equipment management system of the present invention. The equipment management system of the present embodiment is constructed in a building 1. In the present embodiment, a multi-story building 1 is assumed as a building.

[0040] In this embodiment, each floor of the building 1 corresponds to the area of ​​the present invention. In addition, when each floor (level) is divided into a plurality of areas (rooms) by partition walls, each area (room) may be the area of ​​the present invention.

[0041] Furthermore, in the following description, for convenience of explanation, it is assumed that the building 1 is exclusively used by one company. Employees and visitors working for the company enter and exit the building 1. In this embodiment, the number of people on each floor is referred to as the "number of people on that floor".

[0042] The building 1 is provided with a structure in which the number of people present in the area predicted by the number of people present in the area prediction device 10, the equipment management device 2, the schedule management server 3, and the commuting management device 5 are connected to the network 4. The equipment management device 2 manages the equipment installed in the building based on the number of people present in the area predicted by the number of people present in the area prediction device 10.

[0043] The schedule management server 3 manages the schedule information of each employee working in the building 1. The schedule information can be obtained by using a general schedule management application. However, the application needs to have a function of determining the start and end time of an event such as a meeting to be managed, and the floor (area) where the meeting is held.

[0044] The commuting management device 5 manages the commuting information of employees who work in the building 1. For example, the commuting management device 5 includes an attendance system, which is installed on each floor of the building 1 and can be accessed from a terminal assigned to each employee. Employees access the attendance system from the terminal and punch in and out of get off work, so that the commuting information of each employee in the building 1 is recorded in the commuting management device 5. For example, information such as the employee's ID (name, identification number, etc.), office floor (office area), and affiliation is associated with the time of coming on and time of leaving get off work and stored in the storage unit of the commuting management device 5.

[0045] Figure 2 1 is a diagram showing the hardware configuration of a computer forming the presence prediction device 10 of the present embodiment. In the present embodiment, the computer forming the presence prediction device 10 can be realized by a conventional general-purpose hardware configuration such as a personal computer (PC).

[0046] That is, Figure 2 As shown, the presence prediction device 10 has a CPU (central processing unit) 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23 and a hard disk drive (HDD) 24, which are connected to an internal bus 30. In addition, the presence prediction device 10 has a mouse 25 and a keyboard 26 provided as input units, and a display 27 provided as a display unit, which are connected to an input-output controller 28. In addition, the presence prediction device 10 has the input-output controller 28 and a network controller 29 provided as a communication unit, which are also connected to the internal bus 30. The equipment management device 2 is also implemented by a computer, so its hardware structure can be the same as Figure 2 The same diagram is shown.

[0047] Figure 3 1 is a block diagram of the structure of the number of people in the present embodiment. Figure 3 The components not used in the description of this embodiment are omitted. The number of people prediction device 10 of this embodiment is composed of a schedule information acquisition unit 11, a schedule information storage unit 12, a primary prediction unit 13, a primary prediction value information storage unit 14, a number of people acquisition unit 15, a number of people information storage unit 16, a correction parameter setting unit 17, a correction parameter information storage unit 18 and a correction unit 19.

[0048] Each component of the number of people present prediction device 10, namely, the schedule information acquisition unit 11 to the correction unit 19, is implemented by a computer forming the number of people present prediction device 10 and a CPU 21 (see Figure 2 ) is realized by the cooperative action of the program running in. In addition, each storage unit 12, 14, 16, 18 is realized by the HDD 24 installed in the number of people prediction device 10. Alternatively, RAM 23 or an external storage unit can be used via a network.

[0049] In addition, the program used in this embodiment can be provided through a communication unit, and can also be provided by being stored in a computer-readable recording medium such as a CD-ROM (Compact Disc Read-Only Memory) or a USB (Universal Serial Bus) memory. The program provided from the communication unit or the recording medium is installed in the computer, and the CPU of the computer executes the program in sequence, thereby forming a device for realizing various processing.

[0050] The schedule information acquisition unit 11 obtains the schedule information from the schedule management server 3 (see Figure 1 ) obtains the schedule information of the users (e.g., employees) of each floor (i.e., each area) of the building 1, and stores it in the schedule information storage unit 12. For example, the schedule information acquisition unit 11 obtains the estimated schedule information of the day at 0:00 every day. In addition, since the schedule information of the day may be changed after 0:00, the schedule information may also be updated periodically.

[0051] exist Figure 4 , the data structure of the schedule information stored in the schedule information storage unit 12 of the present embodiment is illustrated in a table format. The schedule information is generated for each user (employee) and for each event (schedule), and each record represents one schedule (plan) of one user.

[0052] exist Figure 4 In the above, user ID is the identification information of the user, i.e. the employee (company employee number). Start date and start time are information indicating the start period of the schedule (scheduled plan). End date and end time are information indicating the end period of the schedule (scheduled plan). Scheduled category is information indicating the type of scheduled plan, which is set by the user selecting from pre-specified items when registering the schedule. Scheduled content is information indicating the specific content in the scheduled category. Location is information indicating the place where the scheduled plan is to be implemented.

[0053] In this embodiment, since the number of people present is predicted for each floor (area), it is necessary to include information that can identify the floor. Figure 4The example of information setting shown shows that users u001, u002, and u003 are all scheduled to attend a "department meeting" to be held at the same date and time (2017 / 2 / 1) and location (4th floor, 1st meeting room). In addition, even for the same meeting, the schedule information is set and registered as a different schedule for each user.

[0054] Since the schedule information acquisition unit 11 has already acquired the schedule information before (in the past) the forecast day and stored it in the schedule information storage unit 12, the schedule information to be acquired here may be only the schedule information related to the forecast day. The schedule information related to the forecast day refers to the schedule information including the schedule information of the forecast day. For example, the schedule information is not limited to the schedule information set only on the forecast day, and a long-term business trip including the forecast day and the dates before and after the forecast day is also included in the schedule information.

[0055] In addition, strictly speaking, there are cases where the schedule after the prediction time is changed by the user on the prediction day (for example, a 16:00 schedule is added to 10:00 on the prediction day). Therefore, the schedule information for the prediction day can also be obtained every time the number of people prediction processing is executed. However, events that may cause a large error in the prediction of the number of people (special events estimated to have a large change in the number of people) are usually planned in advance. Therefore, considering the processing load when a large number of employees are involved, the schedule information can also be obtained only for the first time on the prediction day.

[0056] In addition, in this embodiment, from the schedule management server 3 (refer to Figure 1 ) to obtain the schedule information, but an alternative means may be used. For example, in the absence of the schedule management server 3, the schedule information may be directly obtained from groupware or a schedule manager commonly used by users in the building 1 or on each floor, or from a schedule manager installed in a portable terminal used by each user.

[0057] return Figure 3 The primary prediction unit 13 predicts whether each user is present on each floor (each area) at the prediction target time based on the schedule information, thereby calculating a primary prediction value of the number of people present on each floor (each area) at the prediction target time.

[0058] That is, the primary prediction unit 13 calculates a predicted value (primary prediction value) of the number of people in the specified area in the future based on the schedule information stored in the schedule information storage unit 12 and the schedule information input by each user who uses the specified area, for example, an employee of a specified floor (specified area). The specific calculation process will be described later.

[0059] The primary prediction value is calculated for each time point. That is, the primary prediction unit 13 calculates the primary prediction value Y(i) at time i from the prediction start time i=1 to the prediction end time i=k.

[0060] The primary prediction value Y(i) predicted by the primary prediction unit 13 is stored in the primary prediction value information storage unit 14. For example, the primary prediction value Y(i) is stored in the primary prediction value information storage unit 14 by floor (by area) and by time.

[0061] The number of people obtaining unit 15 periodically (for example, every 1 minute) obtains the number of people at the current moment, that is, the actual value of the number of people, for each floor (each area) in the building 1, and stores it in the number of people information storage unit 16. For example, the number of people obtaining unit 15 may include a number counting sensor provided on each floor (each area). In addition, the number of people obtaining unit 15 may include a counter for measuring the number of people getting on and off the elevator.

[0062] For example, the presence number information stored in the presence number information storage unit 16 is formed by associating at least the number of persons on each floor acquired from the presence number acquisition unit 15 , the floor (area) on which the number of persons was acquired, and the acquisition date and time for each floor.

[0063] The correction parameter setting unit 17 calculates the correction parameter A(i) based on the history of the number of people information stored in the number of people information storage unit 16, in other words, based on the difference between the actual value Y*(i) and the primary prediction value Y(i) stored in the primary prediction value information storage unit 14. The detailed calculation process will be described later.

[0064] The correction parameter A(i) is a parameter set according to each floor (area) and the predicted time to compensate for the imperfection of the schedule manager operation. When the input (registration) of schedule information to the schedule manager is determined by the user (employee) of each floor, schedule information may not be registered by the schedule manager due to a short absence. In addition, incorrect schedule information such as wrong date, time, and location may be registered by the schedule manager.

[0065] Due to such unregistered schedule information and incorrect schedule information, the number of people absent from a predetermined floor (predetermined area) may be estimated to be smaller than the actual number. As a result, a positive error may occur in the primary prediction value Y(i) calculated based on the schedule information.

[0066] Therefore, in the presence prediction process of the present embodiment, the correction parameter A(i) is used as a ratio for removing the above-mentioned error from the primary prediction value Y(i).

[0067] Considering that the imperfection of the schedule manager operation is caused by the habits of users on each floor, in other words, the habits of employees in each area, it can be considered that the imperfection rate is stable over multiple dates and times, and the imperfection rate is unique to each floor (each area). Therefore, as described later, the correction parameter setting unit 17 calculates the correction parameter A(i) at a predetermined time interval (for example, 30-minute intervals) for each floor (each area).

[0068] exist Figure 5 In the figure, the correction parameter A(i) for each area and each time is illustrated. For example, the correction parameter setting unit 17 calculates the correction parameter A(i) according to the difference between the actual value Y*(i) of the number of people and the one-time predicted value Y(i) at a specified time interval (for example, 30-minute intervals). The calculation process will be described later. Regarding the correction parameter A(i), for example, a value greater than 0 and less than 1 can be taken, in other words, a value greater than 0% and less than 100%. In addition, the correction parameter A(i) can also be set to have a negative value.

[0069] The correction parameter A(i) calculated by the correction parameter setting unit 17 is stored in the correction parameter information storage unit 18. The correction parameter A(i) is stored in the correction parameter information storage unit 18 by floor (by area) and by time.

[0070] The correction unit 19 corrects the primary prediction value Y(i) calculated by the primary prediction unit 13 using the correction parameter A(i) calculated by the correction parameter setting unit 17, thereby calculating the secondary prediction value X(i) of the number of people on each floor (each area). The secondary prediction value X(i) becomes the final number of people predicted at time i. The detailed calculation process of the secondary prediction value X(i) will be described later.

[0071] exist Figure 6 In the example, the characteristic line of the primary prediction value Y(i) is shown when the prediction start time (i=1) is 10:00 and the prediction end time (i=k) is 22:00. In addition, the time period before 10:00 shows the actual performance value of the number of people. Figure 6 A curve chart with the horizontal axis representing time and the vertical axis representing the number of people.

[0072] For example, suppose that the predicted value Y(i) contains a positive error. Figure 7 As shown in the example, the positive error is corrected using the correction parameter A(i) and plotted as a secondary prediction value X(i).

[0073] <Prediction of the number of people present>

[0074] Next, refer to Figure 8The present embodiment describes the number of people prediction processing. As described above, in the present embodiment, the first prediction value Y(i) and the correction parameter A(i) are respectively calculated, and the second prediction value X(i) is calculated using the first prediction value Y(i) and the correction parameter A(i).

[0075] As described above, the schedule information stored in the schedule information storage unit 12 is updated periodically (for example, every 30 minutes). Figure 8 The primary prediction unit 13 sets the count i of the prediction target time time_i to an initial value 1 (S101).

[0076] The prediction target time time_1 when the initial value i=1 can be, for example, the start time of the number of people prediction processing flow ( Figure 6 In addition, the prediction target time time_k when the final value i=k may be, for example, the final time of the target time period for number of people prediction, for example, 22:00.

[0077] First, the primary prediction unit 13 calculates a primary prediction value Y(i) by subtracting the number of people estimated to be absent from the floor at the prediction target time (absent number) based on schedule information from the number of users (employees) on the prediction target floor (prediction target area), that is, the rated number of people.

[0078] For example, the primary prediction unit 13 uses the number of users (employees) registered (with seats) on a specified floor (specified area) as the rated number of people, increases or decreases the rated number of people according to the number of absent people predicted from the schedule information, and uses the value as the primary prediction value Y(i). For example, the value obtained by subtracting the number of schedule items n_skd_i at the prediction object time time_i from the rated number of people is used as the primary prediction value Y(i) (S102). In addition, it is also possible that, in the case where the number of schedule items n_skd_i is not directly used as the number of absent people, the number of schedule items n_skd_i is corrected and subtracted from the rated number of people, and the value obtained by the subtraction operation is used as the primary prediction value Y(i). For example, it is also possible that, in the case where the implementation area of ​​the input schedule is an office area (without leaving the specified area), the number of schedule items n_skd_i in the number of schedule items n_skd_i that has an implementation area different from the office area (specified floor, specified area) is subtracted from the rated number of people, and the obtained value is used as the primary prediction value Y(i).

[0079] For example, suppose the number of employees on the fourth floor is 100, and the predicted schedule for the day is only Figure 47 cases are shown as examples. When predicting the number of people at 15:00, user u001 is scheduled to attend a meeting on the 6th floor, user u002 is scheduled to go out, and user u003 is scheduled to attend a meeting on the 5th floor. Therefore, it can be estimated that these three people are not on the 4th floor at 15:00 (they have moved to another area or outside the building 1). Therefore, 100-3=97 people are calculated as the primary prediction value Y (i=15:00) of the number of people at 15:00. The calculated primary prediction value Y (i) is stored in the primary prediction value information storage unit 14.

[0080] Next, the correction parameter setting unit 17 obtains the correction parameter A(i) based on the past one-time prediction value Y(i) and the actual value Y*(i) of the number of people at the same time on the same day (S103). The correction parameter setting unit 17 obtains the history of the one-time prediction value Y(i) during the past specified period (excluding holidays) stored in the one-time prediction value information storage unit 14. Furthermore, the correction parameter setting unit 17 obtains the history of the corresponding number of people (actual value) Y*(i) stored in the number of people information storage unit 16.

[0081] Furthermore, the correction parameter setting unit 17 calculates the correction parameter A(i) for each floor / each time. For example, the correction parameter setting unit 17 calculates the average value of "(first predicted value-actual value)÷first predicted value" at each time of each floor (each area) as the correction parameter A(i).

[0082] That is, when Y(d, i) represents a past prediction value at time i on a specified date d (d=1~n), and Y*(d, i) represents the actual value of the number of people at the same date and time, the correction parameter A(i) at time i on the specified floor (area) can be recorded as shown in the following formula (1).

[0083] [Formula 1]

[0084]

[0085] In addition, the calibration parameter setting process in step S103 may not be performed in all Figure 8 For example, the correction parameter setting process may be executed when the location number prediction process is first executed, and then executed at any time (for example, every month) to update the correction parameter A(i).

[0086] In addition, the correction parameter setting unit 17 may not be provided in the presence prediction device 10 of the present embodiment, but the correction parameter A(i) may be calculated by another computing device and provided to the presence prediction device 10. In short, the calculated correction parameter A(i) is stored in the correction parameter information storage unit 18.

[0087] When the correction parameter A(i) is calculated, the correction unit 19 calculates the secondary prediction value X(i) at the time point time(i) (S104). Specifically, the secondary prediction value X(i) is calculated according to the following equation (2).

[0088] [Formula 2]

[0089] X(i)=Y(i)×(1-A(i))…(2)

[0090] Furthermore, the calculated secondary prediction value X(i) is output to the display 27 (refer to Figure 2 )(S105). In addition to displaying the secondary prediction value X(i) on the display 27, the secondary prediction value X(i) may also be stored in the HDD 24. In addition, the output information may not be the predicted value of the number of people present, but may be output in a range of a few percent before and after the predicted value.

[0091] After the secondary prediction value X(i) is output, the primary prediction unit 13 determines whether the count i reaches the final value k (S106). Figure 8 On the other hand, when the count i has not reached the final value k, the primary prediction unit 13 increments the count i (S107) and returns to step S102.

[0092] As described above, according to this embodiment, the primary prediction value of the number of people predicted based on the schedule information is corrected according to the predicted floor and predicted time, and the predicted value (secondary prediction value) is calculated. This can suppress the prediction error caused by actions not registered as schedule information, and the omission or erroneous registration of schedule information.

[0093] Furthermore, since the correction parameter for each floor and each time is calculated and set based on the difference between the primary predicted value and the actual value of the number of people present, it is possible to set the correction parameter reflecting the user characteristics of each floor.

[0094] <Implementation Method 2>

[0095] In the first embodiment described above, when calculating the primary prediction value Y(i), the number of absent persons predicted based on schedule information is subtracted from the rated number of persons on each floor (area), but the number of persons working may be used instead of the rated number of persons.

[0096] For example, due to working outside the prescribed working hours (overtime) and the use of flexible working hours, there are many cases where users do not necessarily come to work at the prescribed start time and leave work at the prescribed end time. In addition, it is generally believed that the schedule is not registered for the start time and the end time. That is, the users (employees) who constitute the rated personnel of each floor (area) outside the working hours can be divided into the following three categories:

[0097] (1) Users who have registered their schedule;

[0098] (2) Users who are currently working (overtime) even though they have not registered their schedule;

[0099] (3) The user does not have a schedule registration and is not at work (before or after get off work).

[0100] In this embodiment, when calculating the primary prediction value Y(i), the number of people working is obtained by subtracting the number of people (3) from the rated number of people.

[0101] exist Fig. 9 In FIG. 1 , a block diagram of the structure of the number of people predicted by the present embodiment is illustrated. Figure 3 The difference between the present invention and the present invention is that the commuting information acquisition unit 40 and the commuting information storage unit 41 are added to the present number of people prediction device 10. Figure 3 The description of the structures with the same reference numerals will be appropriately omitted.

[0102] The commuting information storage unit 41 is connected to the upper layer of the primary prediction unit 13. In addition, the commuting information acquisition unit 40 is connected to the upper layer of the commuting information storage unit 41. The commuting information acquisition unit 40 obtains the commuting information from the building 1 (refer to Figure 1 )'s commuting management device 5 obtains the commuting information of users (employees) who use building 1 as their workplace.

[0103] As described above, for example, the commuting management device 5 includes an attendance system installed on each floor of the building 1 and accessible from a terminal assigned to each employee.

[0104] In the case of the attendance system, employees access the attendance system from a terminal and clock in and out of get off work, thereby recording the on-duty and off-duty information of each employee in the building 1 in the on-duty and off-duty management device 5. For example, information such as the employee's ID (name, company employee number, etc.), office floor (office area), and affiliation is associated with the on-duty and off-duty times and stored in the storage unit of the on-duty and off-duty management device 5.

[0105] In the case of an entry and exit management system, based on the building entry and exit information of the building 1, or the room entry and exit information of each floor, each time each user (employee) goes to work or leaves work, the user's identification information and the time of going to work or leaving get off work are grouped together and stored in the storage unit of the get off work and leave management device 5.

[0106] The commuting information acquisition unit 40 accesses the storage unit of the commuting management device 5 to acquire the commuting information of each user (employee) on each floor (each area). The acquired commuting information is stored in the commuting information storage unit 41. For example, information such as the employee's ID (name, company employee number, etc.), office floor (office area), and affiliation are associated with the start time and the end time and stored in the commuting information storage unit 41.

[0107] In the number of people prediction processing, the primary prediction unit 13 refers to the history of commuting information in addition to the schedule information to predict whether each user is on the prediction target floor at the prediction target time, and calculates the primary prediction value of the number of people on the prediction target floor at the prediction target time.

[0108] exist Fig.10 The present embodiment illustrates the number of people prediction processing. Figure 8 The difference between the steps S101 and S102 is that step S201 is inserted between step S101 and step S102. Figure 8 The description of the steps with the same number will be omitted as appropriate.

[0109] In step S201, the primary prediction unit 13 obtains the number of commuters on each floor at the prediction target time time_i from the commuting information storage unit 41. For example, users (employees) who have a work record before the prediction target time time_i and no leave record thereafter are added to the number of commuters S(i) at the prediction target time time_i.

[0110] In addition, for users whose predicted start time is in the morning but who have no work record (and of course no leave record), the predicted values ​​of the work start time and leave time can be calculated based on the historical records of the work start time and leave time, and used to calculate the number of office workers S(i). For example, it is also possible to distinguish each user, and calculate the work start time and leave time based on the historical records. For example, after calculating the average value and the mode, the predicted values ​​of the work start time and leave time are calculated to estimate whether the user specified at the predicted target time is working. In addition, this estimation is not limited to the morning, and can also be applied to such a situation: the predicted target time is at night, there is only a work start record but no leave record at the predicted start time, but it is possible that the user has left work at the predicted target time.

[0111] The primary prediction unit 13 calculates the primary prediction value Y(i) of the prediction object time time_i based on the estimation result of whether or not the office is working, that is, the number of office workers S(i) and the schedule information. For example, the value obtained by subtracting the number of schedule items n_skd_i of the prediction object time time_i from the number of office workers S(i) is used as the primary prediction value Y(i). In addition, as described above, the value obtained by subtracting the number of schedule items n_skd_i in which the implementation area is different from the office area (specified floor, specified area) from the number of office workers S(i) is used as the primary prediction value Y(i).

[0112] According to this embodiment, whether each user is working at the prediction target time is estimated based on the history of commuting information, and the number of people present is predicted based on the result and schedule information. Therefore, time periods outside working hours are included, and prediction errors can be suppressed.

[0113] Description of symbols

[0114] 1: Building; 2: Equipment management device; 3: Schedule management server; 4: Network; 5: Commute management device; 10: Number of people present device; 11: Schedule information acquisition unit; 12: Schedule information storage unit; 13: Primary prediction unit; 14: Primary prediction value information storage unit; 15: Number of people present acquisition unit; 16: Number of people present information storage unit; 17: Correction parameter setting unit; 18: Correction parameter information storage unit; 19: Correction unit; 40: Commute information acquisition unit; 41: Commute information storage unit.

Claims

1. A device for predicting the number of people in a location, wherein: The device for predicting the number of people present has: a schedule information acquisition unit that acquires schedule information of each user who intends to use a predetermined area in the building; a primary prediction unit that predicts whether each user is in the prescribed area at a prediction target time based on the schedule information, thereby calculating a primary prediction value of the number of people in the prescribed area at the prediction target time; a correction unit that corrects the primary prediction value using a correction parameter set for each area of ​​the building and at each time to calculate a secondary prediction value of the number of people in the specified area at the prediction target time; a person-occupied number obtaining unit configured to obtain an actual value of the number of people in the specified area; and A correction parameter setting unit calculates the correction parameter to be set for the prediction target time in the predetermined area based on a difference between the past one-time prediction value at the same time as the prediction target time in the predetermined area and an actual value of the number of people present.

2. The device for predicting the number of people present according to claim 1, wherein: The user population prediction device further includes a commuting information acquisition unit that acquires commuting information of each user in the area. The primary prediction unit predicts the number of people working at the prediction target time, that is, the number of office workers, among the users using the history of the commuting information of each user, and calculates the primary prediction value based on the number of office workers and the schedule information.

3. The device for predicting the number of people present according to claim 2, wherein: The primary prediction unit calculates the primary prediction value at the prediction target time by subtracting the number of absent persons at the prediction target time predicted based on the schedule information from the number of persons working at the prediction target time.

4. A device management system, wherein: The equipment management system has: The device for predicting the number of people present according to any one of claims 1 to 3; as well as A device management device manages the devices installed in the building based on the secondary predicted value of the number of people in the area predicted by the number of people predicting device.

5. A method for predicting the number of people in a location, wherein: The computer performs the following steps: Acquiring schedule information of each user who intends to use a specified area in a building; predicting whether each user is in the prescribed area at a prediction target time based on the schedule information, and calculating a primary prediction value of the number of people in the prescribed area at the prediction target time; The primary prediction value is corrected by using a correction parameter set for each area of ​​the building and at each time to calculate a secondary prediction value of the number of people in the specified area at the prediction target time; Obtaining the actual number of people in the specified area; as well as The correction parameter to be set for the prediction target time in the predetermined area is obtained based on the difference between the past one-time prediction value at the same time as the prediction target time in the predetermined area and the actual value of the number of people present.

Images