JP5963634B2 - Elevator traffic demand forecasting device - Google Patents

Description

  The present invention relates to an elevator traffic demand prediction device that predicts traffic flow such as the generation time and number of passers-by who use an elevator.

  Conventional elevator traffic demand prediction devices include a device that performs traffic demand prediction considering long-term traffic demand changes and a device that performs traffic demand prediction considering short-term traffic demand changes.

  As an elevator traffic demand forecasting device that takes into account long-term changes in traffic demand, using simulation passenger data to which information such as transfer functions, attributes, and staircase usage is added from the learning results of traffic demand in a predetermined period, GA ( There is an apparatus that repeatedly executes a simulation applying a genetic algorithm (see, for example, Patent Document 1).

  In addition, it simulates the operation status of multiple means of transportation according to the arrangement of transportation means such as elevators and the operation plan, and designates based on the passer-by simulation information such as the rate of occurrence and number of passers by time zone There is a device that generates a specified number of passers-by at a designated place and simulates the flow of passers-by in a building (see, for example, Patent Document 2).

  As an elevator traffic demand prediction device considering short-term traffic demand changes, traffic information such as hall call information and car call information is classified and stored in a long-term storage unit and a primary information storage unit. There is a device that performs learning based on the stored contents of the information and changes the learning result according to the stored contents of the primary information storage unit to make a demand prediction (see, for example, Patent Document 3).

  In addition, personal authentication is performed to acquire personal attributes, and based on the detected personal attributes, personal boarding / exiting data relating to personal boarding / exiting is generated, and the staying time of each person on each floor is detected from the personal boarding / exiting data. There is a device that obtains the elevator usage rate of each individual from the personal boarding / exiting data and the stay time, and predicts the number of waiting customers on each floor from the elevator usage rates of all the elevator users according to the rise and fall of the elevator (for example, patents) Reference 4).

Japanese Patent Laid-Open No. 9-240931 JP 2000-44134 A JP-A-6-329352 JP 2010-6613 A

  Since the construction of the building has changed, the tenant's occupancy status and location change with the passage of time, and the traffic demand in the building changes daily. Therefore, it is necessary to correctly grasp the actual traffic demand in the facility operation and renewal plan for the building. Also, in elevator group management, it is necessary to predict traffic demand that changes from moment to moment depending on the time of day, the presence or absence of events in the building, and the like.

  Such a change in traffic demand can be grasped to some extent by the occurrence frequency of hall calls, the number of registered car calls, and the number of passengers getting on and off each floor, which are measured by analyzing elevator control signals.

  However, the actual passer-by is likely to be able to ride even if the car in the same direction at the time of arrival at the landing, immediately after the departure from the car, there is a car on the floor away from the current floor, the car is crowded In situations that are unlikely to occur, transportation means other than elevators, such as stairs, may be used, particularly when moving to a nearby floor or moving downward.

  Also, if the car that arrives is crowded, you may see off the ride. In the conventional traffic demand prediction apparatus, it is not possible to consider the ride behavior characteristics of passers-by that change in accordance with such elevator operation conditions, landing areas, and car congestion conditions. Therefore, there has been a problem that operation simulation and operation control considering the change in traffic demand in such a situation cannot be performed.

  SUMMARY OF THE INVENTION An object of the present invention is to provide an elevator traffic demand prediction device that takes into account the ride behavior characteristics of passers-by that change according to the operation status of the elevator, the hall, and the congestion status of the car.

The elevator traffic demand prediction device according to the present invention is an elevator traffic demand prediction device that predicts the number of passengers at an elevator hall, and stores and stores traffic flow data representing movement information of passers-by at the elevator hall. A flow data storage unit, a determination reference storage unit that accumulates and stores a determination criterion representing an elevator ride characteristic of a passerby at the elevator hall, the traffic flow data acquired from the traffic flow data storage unit, Based on the determination criterion acquired from the determination criterion storage unit, the passenger behavior determination unit that calculates the elevator use probability that is the probability that the passer- by moves using the elevator and the passenger behavior determination unit are calculated. The traffic flow data acquired from the traffic flow data storage unit is corrected based on the elevator use probability. And flowing the data correcting section, in which a correction traffic flow data storage unit that accumulates and stores the corrected the traffic flow data was by the traffic flow data correction unit.

According to the present invention , an elevator use probability that is a probability that a passerby moves using an elevator based on the traffic flow data acquired from the traffic flow data storage unit and the determination criterion acquired from the determination criterion storage unit. And a traffic flow data correction unit that corrects the traffic flow data acquired from the traffic flow data storage unit based on the elevator use probability calculated by the passenger behavior determination unit. Therefore, since it is possible to eliminate a hall call that is likely to be a useless call, it is possible to create traffic flow data that is close to an actual elevator usage situation. Thereby, the operation efficiency of an elevator can be improved and a highly accurate equipment plan can be realized.

It is a block diagram of the elevator traffic demand prediction apparatus which concerns on Embodiment 1. FIG. It is a figure which shows an example of the traffic flow data in the elevator traffic demand prediction apparatus which concerns on Embodiment 1. FIG. It is a figure which shows an example of the criterion data in the elevator traffic demand prediction apparatus which concerns on Embodiment 1. FIG. It is a flowchart which shows the correction process of the traffic flow data correction | amendment part in the elevator traffic demand prediction apparatus which concerns on Embodiment 1. FIG. It is a block diagram of the elevator traffic demand prediction apparatus which concerns on Embodiment 2. FIG. It is a figure which shows an example of the traffic flow data in the elevator traffic demand prediction apparatus which concerns on Embodiment 2. FIG. It is a figure which shows an example of the criterion data in the elevator traffic demand prediction apparatus which concerns on Embodiment 2. FIG. It is a block diagram of the elevator traffic demand prediction apparatus which concerns on Embodiment 3. FIG. It is a figure which shows an example of the traffic flow data in the elevator traffic demand prediction apparatus which concerns on Embodiment 3. FIG. It is a figure which shows an example of the criterion data in the elevator traffic demand prediction apparatus which concerns on Embodiment 3. FIG. It is a flowchart which shows the criterion correction process of the criterion correction | amendment part in the elevator traffic demand prediction apparatus which concerns on Embodiment 3. FIG. It is a figure which shows the other example of the criterion data in the elevator traffic demand prediction apparatus which concerns on Embodiment 3. FIG.

<Embodiment 1>
Embodiment 1 of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram of an elevator traffic demand prediction apparatus 1 according to Embodiment 1 of the present invention. The elevator traffic demand prediction device 1 is provided for each elevator group (bank) controlled by one group management device 15 and predicts the number of passengers at the landing of the bank. A traffic flow data generation device 14, a group management device 15, and an equipment planning device 16 are connected to the elevator traffic demand prediction device 1. Control devices 12 and 13 for controlling the operation of the elevators 10 and 11 are connected to the traffic flow data generation device 14 and the group management device 15.

  The traffic flow data generation device 14 creates traffic flow data based on the elevator control signals acquired from the control devices 12 and 13, and outputs the created traffic flow data to the elevator traffic demand prediction device 1. The traffic flow data correction process is performed in the elevator traffic demand prediction apparatus 1, and details of the correction process will be described later. The group management device 15 commands the operation of the elevators 10 and 11 using the traffic flow data corrected in the elevator traffic demand prediction device 1. The facility planning device 16 makes a facility plan using the corrected traffic flow data.

  Next, the elevator traffic demand prediction apparatus 1 will be described. The elevator traffic demand prediction device 1 includes a traffic flow data storage unit 2, a determination criterion storage unit 3, a passenger behavior determination unit 4, a traffic flow data correction unit 5, and a corrected traffic flow data storage unit 6. . The traffic flow data storage unit 2 accumulates and stores the traffic flow data output from the traffic flow data generation device 14. The determination reference storage unit 3 accumulates and stores determination reference data representing elevator ride characteristics of passers-by at the landings of the elevators 10 and 11.

  The passenger behavior determination unit 4 is based on the traffic flow data acquired from the traffic flow data storage unit 2 and the determination criterion data acquired from the determination criterion storage unit 3, and the boarding probability P that is the elevator use probability of the passerby. Is calculated.

  The traffic flow data correction unit 5 corrects the traffic flow data acquired from the traffic flow data storage unit 2 based on the use probability of the passer-by calculated by the passenger behavior determination unit 4. The corrected traffic flow data storage unit 6 accumulates and stores the traffic flow data corrected by the traffic flow data correction unit 5.

  In addition, the number of elevators 10 and 11 should just be one or more, and does not need to be the number shown by FIG. When there is one elevator, the group management device 15 is omitted. When there are a plurality of elevators, the bank is managed by one group management device 15.

  When performing long-term traffic demand prediction, the elevator traffic demand prediction apparatus 1 may correct and accumulate traffic flow data offline. In that case, the elevator traffic demand prediction device 1 does not output the corrected traffic flow data to the group management device 15. In addition, the determination criterion storage unit 3 does not need to be provided for each building, and the determination criterion data is accumulated in an elevator maintenance center or the like connected by a network, and the elevator traffic demand prediction device 1 determines via a communication device. Reference data may be obtained and used.

  When a call is generated at the landings of the elevators 10 and 11, the traffic flow data generation device 14 generates traffic flow data, and the generated traffic flow data is accumulated and stored in the traffic flow data storage unit 2. Also, at the time of equipment introduction planning or equipment renewal planning, not the actual elevator call information, but the number of people on each floor of the office building, the number of commuting hours, etc. Traffic flow data can also be created from the combination.

  The traffic flow data generation device 14 can be omitted, and when the traffic flow data generation device 14 is omitted, the control signals acquired from the control devices 12 and 13 and the group management device 15 are stored in the traffic flow data storage. Accumulated in part 2.

  Next, traffic flow data will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of traffic flow data accumulated in the traffic flow data storage unit 2, and is an example of a case where four records of data are accumulated. The traffic flow data is data related to the hall call registration at the halls of the elevators 10 and 11, that is, data representing passerby movement information. One record of traffic flow data represents one landing call, and when each passerby moves between floors, the movement start time is recorded in the time field, the movement source floor is recorded in the boarding floor field, and the movement direction is recorded in the destination direction field. ing.

  In the hall call registration method of registering the destination direction at the hall, the movement time is the time when the hall call button is pressed or the time when the call is registered, the source floor is the floor where the hall call button is pressed, and the movement direction is The pressed direction button type can be obtained from the elevator control signal.

  Moreover, in the hall call registration method in which the destination floor is registered at the hall, an exit floor field that represents the exit floor may be provided in the traffic flow data. Furthermore, in a hall call registration method in which an elevator call is registered for each individual using an ID card or the like, one passer may be recorded as one record.

  One record of traffic flow data as shown in FIG. 2 can be expressed as Psng (T, O, D) where T is the time of occurrence, O is the boarding floor, and D is the destination direction. When the elevators 10 and 11 arrive or respond, the traffic flow data generation device 14 deletes the traffic flow data in the direction on the floor from the traffic flow data storage unit 2.

  When a traffic flow data record is generated for each passerby, in the hall call registration method in which the passerby instructs an elevator to get on, the traffic flow data generation device 14 generates the traffic flow data of the passerby who is scheduled to board. delete. On the other hand, in the other hall call registration methods, the traffic flow data generation device 14 can board the passengers in that direction on the floor in the car capacity, the number of passengers that can be boarded with the car capacity or less, or less. Delete traffic flow data for all waiting customers.

  Next, the criterion data will be described with reference to FIG. FIG. 3 is an example of the determination reference data stored in the determination reference storage unit 3, and is an example of the case where four records of data are stored. The criterion data is data representing the elevator ride characteristics of the passerby at the halls of the elevators 10 and 11, more specifically, the probability representing the probability that the passer will move using the elevators 10 and 11 under certain conditions. It is a table. The judgment reference data is composed of a condition field group which is a predetermined condition that affects a passenger's ride on the elevators 10 and 11, and a boarding probability field. The determination reference data is set in advance and is accumulated and stored in the determination reference storage unit 3.

  The condition field group includes a time zone field, a boarding floor field, and a destination direction field. The condition field group may include data such as the number of accompanying persons, the position of the car, the traveling direction, and the getting-off floor. Furthermore, the condition field group may include personal attribute information such as weather conditions such as temperature and humidity, passer identification ID, and VIP driving target person information as well as passer's movement attribute information.

  Here, the criterion data shown in FIG. 3 is that 80% of the passers who move from the first floor to the upper floor in the time zone from 8 to 9 o'clock, 70% of the passers who move from the second floor to the upper floor, 3% This means that 50% of passers-by who move from the upper floor to the upper floor and 20% of passers-by who move from the fourth floor to the lower floor use the elevators 10 and 11 to move. This criterion data can be represented by C (T, O, D).

  The passenger behavior determination unit 4 reads (acquires) the traffic flow data from the traffic flow data storage unit 2 and the determination criterion data from the determination criterion storage unit 3, respectively. , O, D). For example, with respect to FIG. 2 and FIG. 3, P (8: 15: 10,4, DN) = 20% and P (8: 15: 15,1, UP) = 80% are calculated. This boarding probability P is used for the correction process of the traffic flow data correction | amendment part 5 demonstrated below.

  Next, the correction process of the traffic flow data correction unit 5 will be described with reference to FIG. FIG. 4 is a flowchart showing the correction process of the traffic flow data correction unit 5. First, the traffic flow data correction unit 5 acquires traffic flow data from the traffic flow data storage unit 2 (step S1). The traffic flow data correction unit 5 sets i to 1 (step S2), and the passenger behavior determination unit 4 outputs Psng (8:15:10, 4, DN) which is the i-th record of the traffic flow data. Boarding probability P (8:15:10, 4, DN) = 20% is acquired (step S3).

  Next, the traffic flow data correction unit 5 lowers the priority of Psng (8:15:10, 4, DN) when the boarding probability P is lower than the reference value. More specifically, the traffic flow data correction unit 5 generates a random number R of 0 to 99 that is a reference value (step S4), and determines whether or not the value is R <P × 100-1. (Step S5).

  When the random number R is 20 to 99 (No in step S5), the traffic flow data correction unit 5 determines Psng (8:15:10, 4, DN) that is the i-th record of the traffic flow data from the traffic flow data. ) Is lowered (step S6). Specifically, when the traffic flow data is used for operation control of the elevators 10 and 11, in step S6, the response rank of Psng (8:15:10, 4, DN) is lowered, and the boarding probability P is in descending order. The process of rearranging traffic flow data or confirming that Psng (8:15:10, 4, DN) passersby cancel the hall call and then deleting it so that it does not respond to the hall call Done.

  Then, the traffic flow data correction unit 5 stores the corrected traffic flow data in the corrected traffic flow data storage unit 6. On the other hand, when the random number R is 0 to 19 (Yes in step S5), the process proceeds to step S7.

  Next, in step S7, the traffic flow data correction unit 5 determines whether i is equal to or greater than n, that is, whether steps S3 to S6 have been performed on all records in the traffic flow data.

  In the case of No in step S7, that is, when steps S3 to S6 are not performed for all the records in the traffic flow data, the traffic flow data correction unit 5 increments i by 1 (step S8), the process proceeds to step S3. However, in the case of Yes in Step S7, that is, when Steps S3 to S6 are performed on all the records in the traffic flow data, the traffic flow data correction unit 5 ends the correction process.

  The elevator traffic demand prediction device 1 outputs the corrected traffic flow data to the group management device 15 for use in operation control of the elevators 10 and 11 and outputs it to the facility planning device 16 for use in facility planning. May be. In this case, the traffic flow data correction unit 5 does not delete the responding passenger Psng (8:15:10, 4, DN) from the traffic flow data in step S6.

  As described above, in the elevator traffic demand prediction apparatus 1 according to the first embodiment, the traffic travels based on the traffic flow data acquired from the traffic flow data storage unit 2 and the determination criterion acquired from the determination criterion storage unit 3. Passenger behavior determination unit 4 that calculates the elevator usage probability of the passenger, and traffic flow data that corrects the traffic flow data acquired from the traffic flow data storage unit 2 based on the elevator usage probability calculated by the passenger behavior determination unit 4 And a correction unit 5. Therefore, since it is possible to eliminate a hall call that has a low possibility of using the elevators 10 and 11, that is, a high possibility of being a useless call, it is possible to create traffic flow data that is close to an actual elevator usage situation. Thereby, the operation efficiency of the elevators 10 and 11 can be improved, and a highly accurate facility plan can be realized.

  When the boarding probability P calculated by the passenger behavior determination unit 4 is lower than the reference value, the traffic flow data correction unit 5 stores data related to the passer's landing call registration in the corrected traffic flow data storage unit 6. Since it is deleted from the traffic flow data, it is possible to eliminate landing calls that are likely to be useless calls.

  Since the traffic flow data correction unit 5 rearranges the traffic flow data stored in the corrected traffic flow data storage unit 6 in descending order of the boarding probability P calculated by the passenger behavior determination unit 4, the traffic flow data correction unit 5 is likely to be a useless call. It is possible to make it difficult to respond to the hall call.

<Embodiment 2>
Next, an elevator traffic demand prediction apparatus 1A according to Embodiment 2 will be described. FIG. 5 is a configuration diagram of an elevator traffic demand prediction apparatus 1A according to the second embodiment. In the second embodiment, the same components as those described in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.

  In the second embodiment, the operation condition data indicating the operation condition of the elevators 10 and 11 is added to the traffic flow data stored in the corrected traffic flow data storage unit 6, and the determination criterion data stored in the determination criterion storage unit 3. In addition, an index related to the operation status of the elevators 10 and 11 is added. The passenger behavior determination unit 4 calculates the boarding probability P based on traffic flow data including operation status data and determination reference data including an index related to the operation status.

  1 A of elevator traffic demand prediction apparatuses are the structures which added the operation simulation part 20 with respect to the elevator traffic demand prediction apparatus 1 which concerns on Embodiment 1. FIG. The operation simulation unit 20 calculates operation status data by simulating the operation of the elevators 10 and 11. The specific operation of the operation simulation unit 20 will be described later.

  Next, traffic flow data in the second embodiment will be described. FIG. 6 is an example of traffic flow data stored in the traffic flow data storage unit 2. The traffic flow data in the second embodiment is composed of a passenger field group and an operation status field group. The passenger field group includes a passenger number field, a time field, a boarding floor field, and a getting-off floor field. The operation status field group includes a waiting time field and a car congestion degree field. The operation status data is data stored in the operation status field group.

  The traffic flow data generation device 14 creates passenger field group data of the traffic flow data. One record of traffic flow data represents one passer, the identification number of the record or passer is the passenger number field, the movement start time is the time field, the source floor is the boarding floor field, and the destination floor is the exit floor Stored in the field. The passenger field group may include the presence / absence of a companion traveling together, the number of accompanying persons, a floor difference, and the like. Moreover, the destination direction may be included instead of the getting-off floor.

  The traffic flow data can be generated using the hall call information acquired from the group management device 15 or the control devices 12 and 13 in the hall call registration method in which the moving direction is registered at the hall. In addition, in the hall call registration method in the form of registering the destination direction at the hall, the number of people in each floor of the office building, the number of people entering and leaving the office, and the number of people in the combination of boarding floor-getting off floor for each time zone obtained statistically and Such traffic flow data can be created by calculating the number of people moving in each time zone from the number of people in each floor of the office building, the time of work, and statistically.

  One record of traffic flow data as shown in FIG. 6 is Psng (i), where passenger number is i, Psng (i), or generation time is T, boarding floor is O, destination direction is D, Psng (T, O, D) Can be represented. When the elevators 10 and 11 arrive or respond, the traffic flow data generation device 14 deletes the traffic flow data in the direction on the floor from the traffic flow data storage unit 2.

  When a traffic flow data record is generated for each passerby, in the hall call registration method in which the passerby instructs an elevator to get on, the traffic flow data generation device 14 generates the traffic flow data of the passerby who is scheduled to board. delete. On the other hand, in the other hall call registration methods, the traffic flow data generation device 14 can board the passengers in that direction on the floor in the car capacity, the number of passengers that can be boarded with the car capacity or less, or less. Delete traffic flow data for all waiting customers.

  The operation simulation unit 20 simulates the operation of the elevators 10 and 11 based on the traffic flow data acquired from the traffic flow data storage unit 2, calculates operation status data, and is stored in the traffic flow data storage unit 2. The traffic flow data is accumulated and stored in the operation status field group. In FIG. 6, the waiting time field and the car congestion level field are shown as the operation status field group. However, the waiting time field and the landing congestion level may be included.

  Next, the criterion data in the second embodiment will be described. FIG. 7 is an example of determination criterion data stored in the determination criterion storage unit 3. The criterion data is composed of a condition field group and a boarding probability field. The condition field group stores a time zone field, a boarding floor field, a getting-off floor field, a waiting time field, and a car congestion level field. Here, the waiting time field and the car congestion degree field correspond to the indicators relating to the operation status.

  The condition field group may include the number of people waiting for landing, the position of the car at the movement start time, the traveling direction of the car, and the like. The condition field group includes not only the movement attribute information of the passers and the operation status of the elevators 10 and 11, but also the weather status such as temperature and humidity, personal attribute information such as the passer identification ID and VIP driving target person information. May be included.

  Here, the criterion data shown in FIG. 7 shows that a passerby who moves from the first floor to the second floor has a waiting time of less than 30 seconds and a degree of congestion in the car of less than 50% in the time zone from 8 to 9 o'clock ( 60% in situations where the waiting time is 30 seconds or more and the degree of congestion in the car is 50% or more, passers who move from the 1st floor to the 3rd floor or higher are waiting time. Elevators 10 and 11 are used with a probability of 80% when the car is less than 30 seconds and the degree of congestion in the car is less than 50%, and 70% when the waiting time is more than 30 seconds and the degree of congestion in the car is 50% or more. It represents moving.

  The passenger behavior determination unit 4 reads the traffic flow data from the traffic flow data storage unit 2 and the determination criterion data from the determination criterion storage unit 3, and calculates a boarding probability P (i) for each passerby Psng (i). For example, with respect to FIGS. 6 and 7, the calculation is performed such that P (1) = 70%, P (2) = 80%, P (3) = 10%, and P (4) = 60%. The boarding probability P (i) calculated by the passenger behavior determination unit 4 is used for the correction process of the traffic flow data correction unit 5 as in the case of the first embodiment.

  As described above, the elevator traffic demand prediction device 1A according to the second embodiment further includes the operation simulation unit 20 that simulates the operation of the elevators 10 and 11 and calculates the operation status data representing the operation status of the elevators 10 and 11. The traffic flow data stored in the traffic flow data storage unit 2 includes operation status data. Therefore, the traffic demand which changes every moment according to the operation situation of the elevators 10 and 11 is predicted, and the hall calls that are unlikely to use the elevators 10 and 11, that is, are likely to be useless calls, are excluded. It is possible to create traffic flow data close to actual elevator usage. Thereby, the operation efficiency improvement of the elevators 10 and 11 and a highly accurate equipment plan drafting are realizable.

  Since the judgment reference data includes an index related to the operation status of the elevators 10 and 11, there is a possibility that the traffic demand that changes every moment according to the operation status of the elevators 10 and 11 is predicted and the elevators 10 and 11 are used. Passers who are low, that is, those who are likely to be useless calls can be excluded, and traffic flow data close to actual elevator usage can be created.

<Embodiment 3>
Next, an elevator traffic demand prediction apparatus 1B according to Embodiment 3 will be described. FIG. 8 is a configuration diagram of an elevator traffic demand prediction apparatus 1B according to the third embodiment. In the third embodiment, the same components as those described in the first and second embodiments are denoted by the same reference numerals, and the description thereof is omitted.

  In the first and second embodiments, the criterion data is a fixed value set in advance. In the third embodiment, the criterion is based on the traffic flow data newly created by the traffic flow data generation device 14. Data is updated. The elevator traffic demand prediction apparatus 1B has a configuration in which a determination criterion correction unit 21 is added to the elevator traffic demand prediction apparatus 1 according to the first embodiment. The determination criterion correction unit 21 corrects the determination criterion data accumulated in the determination criterion storage unit 3 based on the traffic flow data newly acquired from the traffic flow data storage unit 2.

  Next, traffic flow data in the third embodiment will be described. FIG. 9 is an example of traffic flow data stored in the traffic flow data storage unit 2. The traffic flow data includes a passenger number field, a movement start time field, a boarding floor field, a getting-off floor field, and a use flag field assigned to each passerby.

  In the landing call registration method in which the destination floor field registers the destination floor at the landing, data can be obtained from a call registration device (not shown), and the hall call registration in the form in which the destination direction is registered at the landing In the method, it is estimated from an elevator signal output from a scale device (not shown) of the elevators 10 and 11 or a door sensor (not shown) of the elevators 10 and 11, or each passer's residence using an ID card or the like. You can also guess from the floor.

  The use flag field is data indicating whether or not each passerby has moved using the elevators 10 and 11, and is “1” when moving by using the elevators 10 and 11. Then, “0” is input. The traffic flow data generation device 14 estimates whether or not it has moved using the elevators 10 and 11 and the number of people from the amount of change in the scale device of the elevators 10 and 11, the passage time of the door sensor, and the like. 11, 11, and the like, by combining tag readers installed near other moving means such as stairs and personal ID cards, etc., it is possible to acquire and input data by estimating the moving means of each passerby. In FIG. 9, one record is set for each passer, but one record may be set for each hall call.

  Next, the criterion data in the third embodiment will be described. FIG. 10 is an example of determination criterion data stored in the determination criterion storage unit 3. The judgment reference data includes a condition field group, a passer-by number field indicating the number of passers-by who meets the conditions of the condition field group for a certain period, and the number of users indicating the number of passers-by who use the elevators 10 and 11. It is comprised from the field and the boarding probability field showing the ratio of the user of the elevators 10 and 11 among passers-by.

  It should be noted that the condition field group may include a waiting time, a degree of car congestion, the number of people waiting for landing, a car position at the movement start time, a car traveling direction, and the like. The condition field group includes not only the movement attribute information of the passers and the operation status of the elevators 10 and 11, but also the weather status such as temperature and humidity, personal attribute information such as the passer identification ID and VIP driving target person information. May be included.

  Next, the determination reference correction process of the determination reference correction unit 21 will be described with reference to FIG. FIG. 11 is a flowchart showing the determination criterion correction process of the determination criterion correction unit 21. When new traffic flow data is created by the traffic flow data generation device 14, the corresponding criterion data is updated in the following procedure for the traffic flow data. First, criteria data is acquired from the criteria storage unit 3 (step S11). i is set to 1 and the i-th data of the determination reference data is acquired (step S12).

  The determination criterion correction unit 21 determines whether or not the traffic flow data matches the condition field group of the i-th determination criterion data (step S13). Specifically, it is determined whether the time field, boarding floor field, and getting-off floor field of the traffic flow data match the time zone field, boarding floor field, and getting-off floor field of the determination reference data, respectively.

  If the traffic flow data does not match the condition field group of the i-th criterion data (No in step S13), i is incremented by 1 to obtain (i + 1) -th criterion data (step S14). The process proceeds to step S13. On the other hand, if the traffic flow data matches the condition field group of the i-th criterion data (Yes in step S13), the traffic flow data is updated to a value obtained by adding 1 to the value of the number of passers-by field in the criterion data (step S13). S15).

  The determination criterion correction unit 21 determines whether or not the passerby recorded in the traffic flow data has used the elevators 10 and 11, that is, whether or not the user flag field of the traffic flow data is “1”. (Step S16). When the passerby uses the elevators 10 and 11 (Yes in step S16), the value is updated to a value obtained by adding 1 to the value of the number of users field (step S17).

  The criterion correction unit 21 recalculates and updates the value C of the boarding probability field by the following formula using the updated value A of the number of passersby field and the value B of the number of users field (step) S18).

C = B / A
Then, the determination criterion correction unit 21 ends this process. However, when other means are used (No in step S16), the determination criterion correction unit 21 recalculates and updates the value C in the boarding probability field (step S18), and then ends this process.

  Further, the condition field group of the criterion data may include a period field as shown in FIG. In this case, the passenger behavior determination unit 4 calculates the boarding probability P of the traffic flow data based on the weighted average of the determination criteria that match the condition field groups other than the period field. For example, if there are n judgment reference data for time zone T, boarding floor O, and getting-off floor D, and the respective probabilities are P1, P2,. The boarding probability P (T, O, D) of the user moving to is calculated by the following formula.

P (T, O, D) = k1 * P1 + k2 * P2 + ... + kn * Pn
However, k1 + k2 +... + Kn = 1.

  k1, k2,..., kn represent the weights for the periods 1, 2,..., n, respectively. For example, the weights for periods close to the present time are increased or the weights for the same season or the same month are increased. By doing so, it is possible to reflect the long-term change and seasonal variation of the elevator usage tendency. In addition, when the new traffic flow data is acquired, the determination criterion correction unit 21 can reflect the latest elevator usage tendency by deleting the determination criterion data of the old period.

  As described above, the elevator traffic demand prediction device 1B according to the third embodiment includes the determination criterion correction unit 21 that updates the determination criterion data based on the traffic flow data newly acquired from the traffic flow data storage unit 2. In addition, the determination criterion data includes a condition field group that is a predetermined condition that affects the passers-by on the elevators 10 and 11, and the determination criterion correction unit 21 includes the newly acquired traffic flow data and conditions Update the criteria data for which the field groups match. Therefore, it is possible to update the elevator use probability of the passerby reflecting the traffic demand that changes every moment according to the operation status of the elevators 10 and 11. Thereby, traffic flow data close to the latest elevator usage situation can be created, and operation efficiency of the elevators 10 and 11 and high-accuracy equipment planning can be realized.

  It should be noted that the present invention can be freely combined with each other within the scope of the invention, and each embodiment can be appropriately modified or omitted.

  1, 1A, 1B Elevator traffic demand prediction device, 2 traffic flow data storage unit, 3 judgment criterion storage unit, 4 passenger behavior determination unit, 5 traffic flow data correction unit, 6 corrected traffic flow data storage unit, 10, 11 elevator, 20 operation simulation part, 21 judgment standard correction part.

Claims (8)

In the elevator traffic demand prediction device that predicts the number of passengers at the elevator hall,
A traffic flow data storage unit for accumulating and storing traffic flow data representing movement information of passersby at the elevator hall;
A criterion storage unit that accumulates and stores criteria representing elevator ride characteristics of passers-by at the elevator hall;
Elevator use probability, which is a probability that the passer- by moves using an elevator based on the traffic flow data acquired from the traffic flow data storage unit and the determination criterion acquired from the determination criterion storage unit A passenger behavior determination unit for calculating
A traffic flow data correction unit that corrects the traffic flow data acquired from the traffic flow data storage unit based on the elevator use probability calculated by the passenger behavior determination unit;
A corrected traffic flow data storage unit for accumulating and storing the traffic flow data corrected by the traffic flow data correction unit;
Elevator traffic demand prediction device equipped with.   The traffic flow data correction unit stores data related to the hall call registration of the passer-by in the corrected traffic flow data storage unit when the elevator use probability calculated by the passenger behavior determination unit is lower than a reference value. The elevator traffic demand prediction apparatus according to claim 1, wherein the elevator traffic demand prediction device is deleted from the traffic flow data. The traffic flow data correction unit lowers the response rank of the traffic flow data stored in the corrected traffic flow data storage unit calculated by the passenger behavior determination unit and has a low elevator use probability, and The elevator traffic demand prediction apparatus according to claim 1, wherein the traffic flow data stored in the corrected traffic flow data storage unit is rearranged in descending order. An operation simulation unit that simulates the operation of the elevator and calculates operation status data representing the operation status of the elevator;
The elevator traffic demand prediction apparatus according to claim 1, wherein the traffic flow data stored in the traffic flow data storage unit includes the operation status data. The elevator traffic demand prediction device according to claim 4 , wherein the operation status data includes at least one of a waiting time, a degree of congestion of a car, a waiting number of passengers, a car position, and a running direction of the car . The elevator traffic demand prediction device according to claim 4 , wherein the determination criterion includes an index related to an operation status of the elevator. The elevator traffic demand prediction device according to claim 6, wherein the indicator related to the operation status includes at least one of waiting time, car congestion level, waiting-for-parking number, and landing congestion level. Based on the traffic flow data newly acquired from the traffic flow data storage unit, further comprises a determination criterion correction unit that corrects to update the determination criterion,
The determination criterion includes a predetermined condition that affects the rider's ride on the elevator, and represents the number of passers-by indicating the number of passers-by in the condition and the number of passers-by who use the elevator. Including the number of users,
2. The elevator traffic demand prediction according to claim 1, wherein the determination criterion correction unit updates a determination criterion including the number of passers and the number of users whose newly acquired traffic flow data matches the predetermined condition. apparatus.

Images