Elevator analysis system and elevator analysis method

Abstract

To achieve control that reduces dissatisfaction of elevator involved persons.SOLUTION: An elevator analysis system comprises: a prediction unit that predicts an expected number of passengers occurring during a time span from a given time at an elevator hall as an expected occurring number of passengers at the given time, based on historical information on number of passengers in an elevator car at each floor and their riding time; a destination floor estimation unit that calculates a probability of a destination floor to be selected by a user who appears at the elevator hall; and a destination floor prediction unit that predicts the destination floor based on the expected occurring number of passengers and the probability of the destination floor.SELECTED DRAWING: Figure 1A

Description

[Technical Field]

[0001] The present invention relates to a technique for analyzing group control elevators. [Background technology]

[0002] In relatively large buildings, multiple elevators are installed to improve elevator transport capacity, and a system is introduced that selects the most appropriate car for service when a call is registered at the hall. As the size of the building increases, the number of elevators installed also increases, and a group control device appropriately controls these multiple elevators to improve service, such as reducing waiting times for users. In such cases, the group control device attempts to achieve optimal control by predicting elevator usage status using operation data, etc.

[0003] In Patent Document 1, the demand for use is predicted and analyzed based on the number of passengers in the car, using the feature values ​​of the upward boarding ratio, the feature values ​​of the upward alighting ratio, the feature values ​​of the downward boarding ratio, and the feature values ​​of the downward alighting.

[0004] In Patent Document 2, a camera is installed in the elevator hall to count the number of people at the elevator hall. When predicting the number of people waiting at a certain time, the average waiting time at the same time over a certain period in the past is used as the predicted value.

[0005] In Patent Document 3, the number of passengers in the car is used. The congestion situation is predicted using the current congestion situation of the building and past usage history.

[0006] In Patent Document 4, a camera is installed in front of the elevator hall so as to take pictures toward the building entrance, and when it detects a person approaching the elevator hall, a car is dispatched. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-172718 [Patent Document 2] Japanese Patent Application Laid-Open No. 2015-9909 [Patent Document 3] International Publication No. 2017 / 006379 [Patent Document 4] Japanese Patent Application Laid-Open No. 2000-26034 Summary of the Invention [Problem to be solved by the invention]

[0008] Group elevator control is limited because the arrival time, boarding floor, disembarking floor, and number of people arriving at the landing who will use the elevator are unknown.

[0009] In Patent Documents 1 and 3, the number of passengers in the elevator car is used, so the status of the boarding floor and the disembarking floor can be determined, but the status of the landing cannot. Therefore, it is difficult to control in accordance with changes in the landing.

[0010] In addition, in Patent Documents 2 and 4, cameras are installed at the landing, so the situation at the landing can be seen, but the situation at the boarding floor and the disembarking floor cannot be seen. Therefore, it is difficult to control according to the situation at the boarding floor and the disembarking floor. In addition, the cost of installing the camera is incurred separately.

[0011] The object of the present invention is to obtain from data the visit time, boarding floor, disembarking floor, and number of people arriving at the elevator hall who will be using the elevator in the future, and to implement control that reduces user dissatisfaction, such as waiting times, when future congestion is predicted. [Means for solving the problem]

[0012] In order to solve at least one of the above problems, the present invention is characterized by comprising a prediction unit that predicts the number of users who will occur at a boarding area within a time range from a certain time based on information on the past number of passengers in cars at each floor and boarding time information on the number of passengers, as the predicted number of passengers who will occur at the certain time; a destination floor estimation unit that calculates the probability of a destination floor selected by a user who appears at the boarding area; and a destination floor prediction unit that predicts a destination floor based on the predicted number of passengers and the probability of the destination floor. [Effects of the Invention]

[0013] According to one aspect of the present invention, by realizing optimal elevator control, it is possible to reduce dissatisfaction among elevator personnel. Problems, configurations, and effects other than those described above will become clear from the following description of the embodiment. [Brief explanation of the drawings]

[0014] [Figure 1A] 1 is a block diagram showing the overall configuration of a group management elevator control system according to an embodiment of the present invention. [Figure 1B] FIG. 2 is a block diagram showing a hardware configuration of an analysis server according to the embodiment of the present invention. [Figure 2] FIG. 2 is an explanatory diagram showing the processing and data association of the group management elevator control system according to the embodiment of the present invention. [Figure 3] FIG. 2 is a sequence diagram showing an overview of the process of predicting the number of passengers and predicting the destination floor in the group management elevator control system according to the embodiment of the present invention. [Figure 4] FIG. 2 is a sequence diagram showing an outline of effective rule / parameter selection in the processing of the group management elevator control system according to the embodiment of the present invention. [Figure 5] 10 is a flowchart illustrating a process performed by a number-of-occurrence estimation model generation unit according to the embodiment of the present invention. [Figure 6] 10 is a flowchart illustrating a process performed by a number-of-occurrence estimation unit according to the embodiment of the present invention. [Figure 7] 10 is a flowchart illustrating a process performed by a number-of-events predicting unit according to the embodiment of the present invention. [Figure 8] 10 is a flowchart showing a process of a destination floor estimation unit according to the embodiment of the present invention. [Figure 9] 10 is a flowchart illustrating a process of a destination floor prediction unit according to the embodiment of the present invention. [Figure 10] 10 is a flowchart illustrating a process of a control selector unit according to the embodiment of the present invention. [Figure 11] 10 is a flowchart showing the processing of a rule / parameter evaluation unit according to the embodiment of the present invention. [Figure 12] FIG. 2 is an explanatory diagram of basic building information held by an analysis server according to an embodiment of the present invention. [Figure 13] FIG. 10 is an explanatory diagram of a random seed held by the analysis server according to the embodiment of the present invention. [Figure 14] FIG. 10 is an explanatory diagram of the number of passengers stored in the analysis server according to the embodiment of the present invention. [Figure 15] FIG. 2 is an explanatory diagram of an elevator operation log held by an analysis server according to an embodiment of the present invention. [Figure 16] FIG. 2 is an explanatory diagram of external information (weather) held by an analysis server according to an embodiment of the present invention. [Figure 17] FIG. 2 is an explanatory diagram of external information (camera) held by the analysis server according to the embodiment of the present invention. [Figure 18] FIG. 2 is an explanatory diagram of external information (building information) held by an analysis server according to an embodiment of the present invention. [Figure 19] FIG. 10 is an explanatory diagram of an input of an estimated number of occurrences held by the analysis server according to the embodiment of the present invention. [Figure 20] FIG. 10 is an explanatory diagram of a number-of-event occurrence estimation model held by the analysis server according to the embodiment of the present invention. [Figure 21] FIG. 10 is an explanatory diagram of an estimated result of the number of occurrences stored in the analysis server according to the embodiment of the present invention. [Figure 22] FIG. 10 is an explanatory diagram of a result of forecasting the number of occurrences held by the analysis server according to the embodiment of the present invention. [Figure 23] FIG. 10 is an explanatory diagram of a second predicted result of the number of occurrences held by the analysis server according to the embodiment of the present invention. [Figure 24]FIG. 10 is an explanatory diagram of time-zone-specific destination floor estimation stored in the analysis server according to the embodiment of the present invention. [Figure 25] FIG. 10 is an explanatory diagram of a time-zone-specific destination floor prediction result stored in the analysis server according to the embodiment of the present invention. [Figure 26] FIG. 3 is an explanatory diagram of a rule / control template held by an analysis server according to an embodiment of the present invention. [Figure 27] FIG. 10 is an explanatory diagram of a KPI list held by an analysis server according to the embodiment of the present invention. [Figure 28] 10 is an explanatory diagram of the input and results of a simulation held by the analysis server according to the embodiment of the present invention. FIG. [Figure 29] FIG. 10 is an explanatory diagram of valid rules / parameters held by an analysis server according to the embodiment of the present invention. [Figure 30] FIG. 10 is an explanatory diagram of a subdivision list of valid rules / parameters held by the analysis server according to the embodiment of the present invention. [Figure 31] FIG. 4 is an explanatory diagram of a rule / parameter list held by an analysis server according to the embodiment of the present invention. [Figure 32] FIG. 10 is an explanatory diagram of a building individualized report output by the analysis server according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] Next, an embodiment of the present invention will be described in detail with reference to the drawings, but the present invention is not limited to the following embodiment and includes various modifications and applications within the technical concept of the present invention. One embodiment of the present invention will be described below with reference to FIG.

[0016] FIG. 1A is a block diagram showing the overall configuration of a group management elevator control system according to an embodiment of the present invention.

[0017] The analysis server SA, client terminal CL, external information neighboring building information EXN, external information database EXD, external information camera EXC, control panel CA, car 1 CA1, car 2 CA2, and car 8 CA8 are connected to an open or closed network NW.

[0018] The analysis server SA constitutes an elevator analysis system that performs analysis related to the control of group-controlled elevators. The analysis server SA is composed of a database SA0, a display unit SA1, a request unit SA2, and an execution unit SA3.

[0019] The database SA0 handles input / output data used within the analysis server SA. Specifically, the database SA0 includes information previously set in the analysis server SA, information acquired via the network NW, and information generated by the processing of the execution unit SA3. Although not shown in FIG. 1A, the database SA0 includes, for example, building basic information SA00, a random seed SA01, the number of passengers boarding and alighting SA02, an elevator operation log SA03, external information (weather) SA04, external information (camera) SA05, external information (building information) SA06, an occurrence number estimation input SA07, an occurrence number estimation model SA08, an occurrence number estimation result SA09, an occurrence number prediction result SA10, an occurrence number prediction result SA11, a time-of-day destination floor estimation SA12, a time-of-day destination floor prediction result SA13, a rule / control template SA14, a KPI list SA15, a simulation input and result SA16, an effective rule / parameter SA17, and a rule / parameter list SA19 (see FIGS. 2 and 12 to 31).

[0020] The execution unit SA3 is the part that actually carries out the analysis, and is composed of a measurement processing unit SA31, a number of people estimation model generation unit SA32, a number of people estimation unit SA33, a number of people prediction unit SA34, a destination floor estimation unit SA35, a destination floor prediction unit SA36, a control selector unit SA37, and a rule / parameter evaluation unit SA38.

[0021] The client terminal CL is a terminal for the administrator to view the analysis status. External information neighboring building information EXN, external information database EXD, external information camera EXC, and control panel CA provide information that is not information related to elevator operation. These are referred to as external information. In addition to the above, external information may also include publicly available information such as rail traffic data and road condition data. Car 1 CA1, car 2 CA2, and car 8 CA8 are elevator cars, and the control panel CA is a control device that controls car 1 CA1 to car 8 CA8.

[0022] Although some illustrations are omitted, in the example of Fig. 1A, eight cars, car 1CA1 to car 8CA8, are controlled by control panel CA. Cars 1CA1 to 8CA8 are, for example, cars of a group of eight elevators that are the subject of group management and are installed facing the same elevator hall (elevator hall) in the same building. However, eight cars is just one example, and the present invention can be applied to an elevator group consisting of two or more cars.

[0023] In this embodiment, the number of people who appeared is the number of people who appeared in the elevator hall to get on the elevator.

[0024] FIG. 1B is a block diagram showing the hardware configuration of the analysis server SA according to the embodiment of the present invention.

[0025] The analysis server SA is, for example, a computer having an interface (I / F) 101, an input device 102, an output device 103, a processor 104, a main memory device 105, and an auxiliary memory device 106, all of which are interconnected.

[0026] The interface 101 is connected to the network NW and communicates with the client terminal CL, the external information database EXD, the external information camera EXC, and the control panel CA via the network NW, as well as acquiring the external information neighboring building information EXN. The input device 102 is a device used by a user of the analysis server SA to input information to the analysis server SA, and may include, for example, at least one of a keyboard, a mouse, a touch sensor, etc. The output device 103 is a device that outputs information to the user of the analysis server SA, and may include, for example, a display device that displays characters, images, etc.

[0027] The processor 104 executes various processes in accordance with programs stored in the main memory device 105. The main memory device 105 is a semiconductor memory device such as a DRAM, and stores the programs executed by the processor 104 and data necessary for the processor's processing. The auxiliary memory device 106 is a relatively large-capacity storage device such as a hard disk drive or flash memory, and stores data referenced in the processing executed by the processor.

[0028] In this embodiment, the main memory device 105 stores programs for realizing the measurement processing unit SA31, the number of people occurrence estimation model generation unit SA32, the number of people occurrence estimation unit SA33, the number of people occurrence prediction unit SA34, the destination floor estimation unit SA35, the destination floor prediction unit SA36, the control selector unit SA37, and the rule / parameter evaluation unit SA38, which are included in the execution unit SA3. Therefore, in the following description, the processes executed by the units included in the execution unit SA3 are actually executed by the processor 104 in accordance with the programs corresponding to the units stored in the main memory device 105.

[0029] Furthermore, the processing of request unit SA2 may be realized by processor 104 controlling interface 101 or input device 102 in accordance with a program corresponding to request unit SA2 stored in main memory device 105. The processing of display unit SA1 may be realized by processor 104 controlling output device 103 in accordance with a program corresponding to display unit SA1 stored in main memory device 105.

[0030] The auxiliary storage device 106 of this embodiment stores the database SA0. Furthermore, programs corresponding to the units included in the execution unit SA3 may be stored in the auxiliary storage device 106 and copied to the main storage device 105 as needed. Furthermore, at least a part of the database SA0 may be copied to the main storage device 105 as needed.

[0031] FIG. 2 is an explanatory diagram showing the processing and data relationships of the group management elevator control system according to the embodiment of the present invention.

[0032] By referring to this diagram, the input and output data for each process becomes clear. It also allows for an overview of the processes and data. Blocks framed in thick lines represent processes, and blocks framed in thin lines represent data. The areas framed in solid lines represent real-time processing, while the areas framed in dashed lines are preferably executed offline.

[0033] Specifically, the occurrence number of people estimation model generation unit SA32 executes occurrence number of people model processing SP01 (FIG. 5) based on the building basic information SA00 (FIG. 12) and the random seed SA01 (FIG. 13), and outputs the occurrence number of people estimation model SA08 (FIG. 20). In the example of FIG. 2, this occurrence number of people model processing SP01 is executed as offline processing SZ1.

[0034] The number of people estimation unit SA33 executes the number of people estimation process SP02 (FIG. 6) based on the number of people getting on and off SA02 (FIG. 14), elevator operation log SA03 (FIG. 15), external information (weather) SA04 (FIG. 16), external information (camera) SA05 (FIG. 17), external information (building information) SA06 (FIG. 18), building basic information SA00, and the number of people estimation model SA08, and inputs the results to the number of people prediction unit SA34. The number of people estimation unit SA33 may use external information other than the above, if available.

[0035] The passenger number prediction unit SA34 executes passenger number prediction process SP03 (FIG. 7) based on the result of the passenger number estimation process SP02, and inputs the result to the destination floor prediction unit SA36 and the control selector unit SA37. The result is also saved by save process SP07 (FIG. 9).

[0036] The destination floor estimation unit SA35 executes the destination floor estimation process SP04 (FIG. 8) based on the number of passengers SA02 getting on and off, and inputs the result to the destination floor prediction unit SA36.

[0037] The destination floor prediction unit SA36 executes a destination floor prediction process SP05 (FIG. 9) based on the results of the number of passengers prediction process SP03 and the destination floor estimation process SP04. The results are saved in a saving process SP07.

[0038] The control selector unit SA37 executes the control selector SP06 (Figure 10) based on the results of the destination floor prediction process SP05, the results of the number of passengers prediction process SP03, and the rule / parameter list SA19 generated by the display / control data generation process SP15 described below, and outputs the results to the control panel CA.

[0039] In the example of FIG. 2, the above-described number-of-events occurrence estimation process SP02 to the storage process SP07 are executed as real-time process SZ0.

[0040] The rule / parameter evaluation unit SA38 executes a KPI simulation process SP11, an effective rule / parameter selection SP12, an end determination process SP13, an effective rule / parameter subdivision process SP14, and a display / control data generation process SP15 (FIG. 11) based on the data saved by the save process SP07, the rule / control template SA14 (FIG. 26), and the KPI list SA15 (FIG. 27). In the process, the simulation input and results SA16 (FIG. 28) and effective rules / parameters SA17 (FIG. 29) are generated, and finally a rule / parameter list SA19 (FIG. 31) and a building individualization report SA20 (FIG. 32) are output.

[0041] In the example of FIG. 2, the above-mentioned KPI simulation process SP11 to display / control data generation process SP15 are executed as offline process SZ2.

[0042] FIG. 3 is a sequence diagram showing an overview of the process of predicting the number of passengers and the destination floor in the group management elevator control system according to the embodiment of the present invention.

[0043] The sequence diagram in Figure 3 is expressed using four axes corresponding to data-related information (number of passengers SA02, elevator operation log SA03, external information (weather) SA04, external information (camera) SA05, etc.), analysis server SA, control panel CA, and client terminal CL.

[0044] Data collection S01 is a process in which an external system, such as an external information database EXD, periodically transmits data to the analysis server SA. The measurement processing unit SA31 of the execution unit SA3 of the analysis server SA receives the data and performs database registration S02, storing the received data in the respective tables of the database SA0. The execution unit SA3's occurrence number estimation model generation unit SA32, occurrence number estimation unit SA33, occurrence number prediction unit SA34, destination floor estimation unit SA35, destination floor prediction unit SA36, and control selector unit SA37 periodically execute processing, and the resulting data is stored in the respective tables of the database SA0 by database registration S03. Finally, the analysis server SA transmits the control parameters selected by the control selector unit SA37 to the control panel CA as input commands CA0.

[0045] FIG. 4 is a sequence diagram showing an outline of effective rule / parameter selection in the processing of the group management elevator control system according to the embodiment of the present invention.

[0046] The sequence diagram in Figure 4 is expressed using the same four axes as in Figure 3.

[0047] In the client terminal CL, a manager information input step S04 is executed in which the manager inputs manager information such as KPIs and periods, etc. The client terminal CL sends a request command including the input information to the analysis server SA.

[0048] The analysis server SA executes data acquisition S05 to acquire data sent from the client terminal CL. Then, the analysis server SA executes the rule / parameter evaluation unit SA38 to select useful rules and control parameters while acquiring the relevant data from the database SA0, and generates content using the results. The analysis server SA transmits display data including the generated content to the client terminal CL.

[0049] The client terminal CL executes a display process S06 to display the content. An example of the content to be displayed will be described later with reference to Fig. 30. Furthermore, since the KPI, period, etc. are used during analysis, it is desirable to register them in advance.

[0050] FIG. 5 is a flowchart showing the processing of the number-of-events estimation model generation unit SA32 according to the embodiment of the present invention.

[0051] The passenger occurrence number model processing SP01 is composed of passenger occurrence number data generation SP010 and passenger occurrence number estimation model generation SP011. In passenger occurrence number data generation SP010, the passenger occurrence number estimation model generation unit SA32 determines the number of passengers getting on and off each car (i.e., the number of passengers getting on and off) and the car status by simulation (second simulation) from the building basic information SA00 and the random seed SA01.

[0052] For example, the number-of-people estimation model generation unit SA32 randomly generates, in the simulation, a plurality of people who are about to board an elevator in the elevator hall on each floor. Specifically, the number-of-people estimation model generation unit SA32 uses a random seed SA01 to randomly determine the floor in the elevator hall where each person will appear and the time of appearance. Furthermore, the number-of-people estimation model generation unit SA32 randomly determines the destination floor of each person from among floors that can be selected based on the building basic information SA00.

[0053] The number of passengers occurrence estimation model generation unit SA32 then simulates the operation of each car according to the determined time, appearance floor, and destination floor of each person, determines the number of passengers getting on and off each car at each time, and the car status, and generates these as the number of passengers occurrence estimation input SA07. The car status refers to, for example, the floor on which each car is located, the direction of travel of each car (upward or downward), the number of passengers in each car, etc., and in detail may be the same as the values ​​registered in the elevator operation log SA03 described below. However, while the elevator operation log SA03 registers actually measured values, the number of passengers occurrence estimation model generation unit SA32 generates values ​​through simulation.

[0054] At this time, the number-of-people estimation model generation unit SA32 may execute the simulation according to, for example, any of the operation rules / control parameters registered in a rule / control template SA14 (FIG. 26) described later.

[0055] In the passenger occurrence number estimation model generation SP011, the passenger occurrence number estimation model generation unit SA32 generates a passenger occurrence number estimation model SA08 by performing a two-stage process consisting of step 1 and step 2. In step 1, the passenger occurrence number estimation model generation unit SA32 identifies the passenger occurrence number for each time period and the corresponding passenger numbers getting on and off and car status from the simulation results. Then, in step 2, the passenger occurrence number estimation model generation unit SA32 determines a model for estimating the passenger occurrence number from the status of each car and the number of passengers getting on and off in each car at each floor, i.e., a function f such that the passenger occurrence number = f (number of passengers getting on and off, car status). For example, as will be described later with reference to FIG. 20, a multiple regression analysis may be performed using the passenger numbers getting on and off and car status as explanatory indicators and the passenger occurrence number as a response variable.

[0056] At this time, if at least one of the elevator operation log SA03, external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06 (or other external information) can be used, these values ​​may be used as external variables to determine a function f that satisfies the equation: number of passengers = f (number of passengers getting on and off, car status, external variables). When determining the function f, it is sufficient to determine the inverse conversion of the conversion from the number of passengers identified in step 1 to the number of passengers getting on and off, etc. Alternatively, other methods may be used as long as the function f can be determined.

[0057] FIG. 6 is a flowchart showing the process of the number-of-occurrence estimation unit SA33 according to the embodiment of the present invention.

[0058] In the occurrence number estimation process SP02, the occurrence number estimation unit SA33 calculates the current occurrence number estimation result SA09 by substituting the current number of people getting on and off SA02 and the actual number of people getting on and off, and the car status obtained from the elevator operation log SA03, into the occurrence number estimation model SA08 calculated in Fig. 5, and stores this in the main memory device 105 or the auxiliary memory device 106. This makes it possible to estimate the occurrence situation of people who are about to get on the elevator from the situation of people getting on and off each car, and the status of each car, such as its position and direction of travel.

[0059] The number of people getting on and off each car can be estimated, for example, from the change in the weight of each car measured by the control panel CA. Furthermore, the position, direction of travel, etc. of each car depend on the control by the control panel CA. Therefore, according to the above-mentioned number of people occurrence model processing SP01 and number of people occurrence estimation processing SP02, even if no external information is available, it is possible to estimate the situation of people about to get on the elevator based on information obtained from the elevator itself.

[0060] The current number of people getting on and off SA02 and the elevator operation log SA03 may also include information identifying the operation rules / control parameters that were applied to the elevator when the data included therein was acquired (i.e., the operation rules / control parameters based on which the control panel CA controlled each car, see, for example, FIG. 26). In this case, the number of people estimated by the number of people estimation unit SA33 obtains the current number of people estimated result SA09 by substituting the actual number of people getting on and off, the number of people getting off, and the car status obtained from the current number of people getting on and off SA02 and the elevator operation log SA03 into the number of people estimated model SA08 generated by the number of people estimation model generation unit SA32 based on a simulation following the operation rules / control parameters. This enables highly accurate estimation.

[0061] At this time, if at least one of the elevator operation log SA03, external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06 (or other external information) is available, it may be substituted.

[0062] FIG. 7 is a flowchart showing the process of the occurrence number prediction unit SA34 according to the embodiment of the present invention.

[0063] The process for predicting the number of occurrences SP03 is made up of a process for predicting the number of occurrences SP030 and a process for converting the format SP031.

[0064] In the number of people predicted SP030, the number of people predicted unit SA34 uses the number of people estimation result SA09 for each time point (e.g., for each time slot having a predetermined time width) obtained by the process of Figure 6 to predict the number of people to be generated at a time in the future from the time stored in the number of people estimation result SA09, and outputs the result as the number of people predicted result SA10. At this time, if at least one of the elevator operation log SA03, external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06 (or other external information) is available, it may be used. For example, if the external information (camera) SA05 is available, the number of people (SA057) included in the external information (camera) SA05 may be used instead of the number of people obtained from the number of people estimation result SA09, or if the number of people identified from other external information is available, it may be used.

[0065] In the format conversion SP031, the occurrence number prediction result SA10 obtained in the occurrence number prediction SP030 is converted into an occurrence probability for each number of people per unit time using the Poisson distribution, and the result is output as the occurrence number prediction result 2_SA11. This occurrence probability can be used to execute the KPI simulation described later.

[0066] FIG. 8 is a flowchart showing the processing of the destination floor estimation unit SA35 according to the embodiment of the present invention.

[0067] The destination floor estimation unit SA35 estimates the destination floor by determining the tendency of people getting off the car for each time period based on the number of people getting on and off SA02, and outputs the result as a destination floor estimation by time period SA12.

[0068] FIG. 9 is a flowchart showing the processing of the destination floor prediction unit SA36 according to the embodiment of the present invention.

[0069] The destination floor prediction unit SA36 executes the destination floor prediction process SP05 and the storage process SP07.

[0070] In destination floor prediction processing SP05, destination floor prediction unit SA36 predicts the destination floor of the people who have appeared, i.e., which floor the people who have appeared are going to. Specifically, destination floor prediction unit SA36 predicts the destination floor by multiplying the number of people who have appeared prediction result 2_SA11, which is the processing result of number of people prediction unit SA34 in Figure 7, by the time-of-day destination floor estimation SA12, which is the processing result of destination floor estimation unit SA35 in Figure 8, and outputs the result as time-of-day destination floor prediction result SA13.

[0071] The saving process SP07 is a process for saving the results of the number of passengers predicted SA10 and the time-zone-specific destination floor prediction SA13 that have been obtained so far in, for example, the database SA0. The reason for performing this is that a large amount of past data is required when performing offline processing.

[0072] FIG. 10 is a flowchart showing the processing of the control selector unit SA37 according to the embodiment of the present invention.

[0073] The control selector SP06 executed by the control selector unit SA37 is a process for selecting a rule / parameter list that satisfies the predicted number of passengers SA10 and the predicted destination floor by time period SA13. The selected parameters are sent to the control panel CA as an input command CA0.

[0074] FIG. 11 is a flowchart showing the processing of the rule / parameter evaluation unit SA38 according to the embodiment of the present invention.

[0075] The rule / parameter evaluation unit SA38 is made up of a KPI simulation process SP11, a valid rule / parameter selection SP12, a termination determination process SP13, a valid rule / parameter subdivision process SP14, and a display / control data generation process SP15.

[0076] In the KPI simulation process SP11, the rule / parameter evaluation unit SA38 uses the rule / control template SA14, KPI list SA15, time-zone-specific destination floor prediction result SA13, and occurrence number prediction result 2_SA11 to perform multiple simulations (first simulations) while changing the operation rules / control parameters, and outputs the KPI value.

[0077] Specifically, the rule / parameter evaluation unit SA38 generates people in the elevator hall of each floor according to the destination floor probability entered in the time-of-day destination floor estimation SA12 and the occurrence probability for each number of people entered in the number-of-people prediction result 2_SA11, and executes a simulation to control each car accordingly according to the operation rules / control parameters selected from the rule / control template SA14. As will be described later, this simulation is executed multiple times while changing the applied operation rules / control parameters.

[0078] In the effective rule / parameter selection SP12, the rule / parameter evaluation unit SA38 selects effective rules / parameters from the values ​​substituted into the KPI simulation process SP11 and the results thereof.

[0079] In the termination determination process SP13, the rule / parameter evaluation section SA38 determines whether or not an improvement effect is observed as a result of the effective rule / parameter selection SP12, and proceeds to Yes if an improvement effect is observed, and to No if not.

[0080] In the effective rule / parameter subdivision process SP14, the rule / parameter evaluation unit SA38 determines the range for subdivision for more effective feature amounts based on the results of the effective rule / parameter selection SP12.

[0081] The rule / parameter evaluation unit SA38 substitutes the result into the KPI simulation process SP11, and repeats the loop until an improvement in the result due to the termination determination process SP13 is observed.

[0082] In the display / control data generation process SP15, the rule / parameter evaluation section SA38 generates a rule / parameter list SA19 and a building individualized report SA20 based on the valid rules / parameters SA17.

[0083] FIG. 12 is an explanatory diagram of the building basic information SA00 held by the analysis server SA according to the embodiment of the present invention.

[0084] The building basic information SA00 is a table that lists basic information about a building. In each building, elevators are made up of multiple cars, which are called elevator banks. Since control is performed for each elevator bank, the table that manages them is the building basic information table (Figure 12). For example, cars 1CA1 to 8CA8 in Figure 1A belong to one elevator bank. One elevator bank corresponds to a group of elevators that are the subject of group management by control panel CA. If one building has multiple elevator banks, there will be multiple combinations of control panels and multiple cars.

[0085] The building ID (SA000) is the identification information (ID) of the building in which the elevator is installed. Each building is identified by a different ID. The elevator bank ID (SA001) is an ID used to distinguish between elevator banks in a building. The bank name (SA002) is the name of the elevator bank. The number of cars (SA003) is the number of cars that make up the elevator bank. The target floor (SA004) indicates the floor where the cars that make up the elevator bank stop. The latitude (SA005) and longitude (SA006) are the latitude and longitude, respectively, that indicate the location of the elevator bank. If the elevator bank has a large area, they may also be the latitude and longitude of its center of gravity. Additionally, any information that can indicate the location of the elevator bank in absolute coordinates that use the Earth as a whole is sufficient, and values ​​other than latitude and longitude are acceptable. The building name (SA007) is the official name of the building in which the elevator is located.

[0086] The information shown in FIG. 12 is just an example, and if there is data required as basic information about the building during analysis, the basic building information SA00 can be modified to add that data.

[0087] FIG. 13 is an explanatory diagram of the random seed SA01 held by the analysis server SA according to the embodiment of the present invention.

[0088] Random Seed SA01 is a table that lists the seeds used to generate random numbers. Random Seed No. (SA010) is the ID of the random seed. Each random seed is identified by a different ID.

[0089] Random seed (SA011) is the random seed value. By using this table, you can specify the random seed number and refer to the corresponding value.

[0090] The example shown in FIG. 13 is an example, and if there is necessary data when generating a random number, the random seed SA01 can be changed so that the necessary data is added.

[0091] FIG. 14 is an explanatory diagram of the number of passengers SA02 stored in the analysis server SA according to the embodiment of the present invention.

[0092] The number of passengers getting on and off SA02 is a table showing the number of passengers getting on and off in each car for each floor in an actual elevator.

[0093] The building ID (SA020) is an ID that identifies the building. The elevator bank ID (SA021) is an ID that identifies each of the multiple elevator banks in the building. The date (SA022) is the date that indicates the operation status of this elevator. The time (SA023) is the time that indicates the operation status of this elevator.

[0094] Day of the week (SA024) is the day of the week showing the operation status of this elevator. Time range (SA025) is the time range over which the operation status of this elevator is aggregated. Car 1 (SA026) indicates that one car belonging to the elevator bank identified by Elevator Bank ID (SA021) is identified. Floor (SA027) is the floor on which Car 1 (SA026) is located during the time period specified by Date (SA022), Time (SA023), Day of the week (SA024), and Time range (SA025). Number of people in car (SA028) is the number of people in the car (i.e., the number of people in the car) during the time period specified by Date (SA022), Time (SA023), Day of the week (SA024), and Time range (SA025).

[0095] The number of passengers (SA02A) in the upward direction (SA029) indicates the number of people who got into car 1 (SA026) when the car was facing upward during the time period specified by the date (SA022), time (SA023), day of the week (SA024), and time range (SA025) (i.e., the number of passengers). The number of passengers alighting in the upward direction (SA029) indicates the number of people who alighted from car 1 (SA026) when the car was facing upward during the time period specified by the date (SA022), time (SA023), day of the week (SA024), and time range (SA025) (i.e., the number of passengers alighting).

[0096] The number of passengers boarding in the downward direction (SA02C) (SA02D) indicates the number of passengers boarding when the car is facing downward during the time period specified by the date (SA022), time (SA023), day of the week (SA024), and time range (SA025). The number of passengers alighting in the downward direction (SA02C) (SA02E) indicates the number of passengers alighting when the car is facing downward during the time period specified by the date (SA022), time (SA023), day of the week (SA024), and time range (SA025).

[0097] The number of passengers SA02 includes information about all of the cars that make up the elevator bank. The information about car 1 (SA026) shown in Figure 14 is one of the cars. Although omitted from Figure 14, data about the other cars is also stored as the number of passengers SA02.

[0098] The timing at which data is entered in the number of passengers SA02 may be for each event (for example, when there is an actual change), or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry may be indicated by the date (SA022), time (SA023), and day of the week (SA024). When data is entered at predetermined intervals, the interval may be entered as the time range (SA025). Also, it is not necessary for all data specified in this table to be stored.

[0099] For example, the first row of the table in FIG. 14 indicates that during the five-minute period beginning at 10:00:01 AM on Tuesday, June 27, 2017, car 1 (SA026) belonging to the elevator bank identified by elevator bank ID "01" in the building identified by building ID "B001" stopped at the third floor at least once, with the number of people in the car at that time (SA028) being 10, the number of people boarding (SA02A) and the number of people alighting (SA02B) when the car stopped while traveling upward were 15 and 1, respectively, and the number of people boarding (SA02D) and the number of people alighting (SA02E) when the car stopped while traveling downward were 0 and 10, respectively. The number of people in the car (SA028) is the number of people after boarding and alighting at the stopped floor. If car 1 (SA026) stopped at the third floor multiple times during the five-minute period, these numbers may be the sum of the number of people at each of those stops, or the number of people for each stop at the third floor may be entered. Furthermore, if car 1 (SA026) stops at another floor at least once during the same five-minute period, the same information as above is entered for that floor in the table.

[0100] The example shown in FIG. 14 is an example, and if there is necessary data to express the number of passengers getting on and off by floor, the number of passengers SA02 can be changed to add that data.

[0101] FIG. 15 is an explanatory diagram of the elevator operation log SA03 held by the analysis server SA according to the embodiment of the present invention.

[0102] The elevator operation log SA03 is a table showing the actual elevator operation log. This table can store both data collected for each elevator bank and data for the cars belonging to the elevator bank.

[0103] The building ID (SA030) is an ID that identifies the building. The elevator bank ID (SA031) is an ID that identifies multiple elevator banks within the building. The date (SA032) is the date that indicates the operation status of this elevator. The time (SA033) is the time that indicates the operation status of this elevator.

[0104] The day of the week (SA034) is the day of the week showing the operation status of this elevator. The time range (SA035) is the time range over which the operation status of this elevator is aggregated. The long waiting rate (SA036) indicates the percentage of waiting times that are longer than a predetermined length (e.g., 60 seconds) among the waiting times that occurred in the elevator bank during the time period specified by the date (SA032), time (SA033), day of the week (SA034), and time range (SA035) (i.e., the time that the person who called the car waited for the car to arrive). The predetermined length can be changed by specifying it in advance.

[0105] The number of car calls (SA037) is the number of times the car call button is pressed within the elevator bank during a time period specified by the date (SA032), time (SA033), day of the week (SA034), and time span (SA035). The traffic flow mode (SA038) is the operation mode of the elevator bank.

[0106] The long waiting rate (SA036), number of car calls (SA037), and traffic flow mode (SA038) are values ​​that are aggregated for each elevator bank, but if necessary, the above information can be changed and other information can be added.

[0107] Car 1 (SA039) indicates that one car belonging to elevator bank ID (SA031) is being identified. Floor (SA0A) is the location (floor) where Car 1 (SA039) was at the time specified by date (SA032), time (SA033), and day of the week (SA034). Direction (SA03B) is the direction in which Car 1 (SA039) was moving at the time specified by date (SA032), time (SA033), and day of the week (SA034). For example, "up" indicates that Car 1 was moving upward, and "down" indicates that Car 1 was moving downward.

[0108] The status (SA03C) indicates the status of cage 1 (SA039) at a time specified by the date (SA032), time (SA033), and day of the week (SA034). For example, "moving" indicates that cage 1 (SA039) was actually moving, and "stopped" indicates that it was stopped. The number of passengers (SA03D) indicates the number of passengers in cage 1 (SA039) at a time specified by the date (SA032), time (SA033), and day of the week (SA034).

[0109] The elevator operation log SA03 includes information about all of the cars that make up the elevator bank. Car 1 (SA039) shown in Figure 15 is one of these cars. Although omitted from Figure 15, data about the other cars is also stored in the elevator operation log SA03.

[0110] The timing at which data is entered into the elevator operation log SA03 may be for each event (for example, when an actual change occurs), or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry may be indicated by the date (SA032), time (SA033), and day of the week (SA034). When data is entered at predetermined intervals, the interval may be entered as the time span (SA035). Also, it is not necessary for all data specified in this table to be stored.

[0111] The data shown in FIG. 15 is just an example, and if there is any necessary data when expressing an elevator operation log, the elevator operation log SA03 can be modified so that the necessary data is added.

[0112] FIG. 16 is an explanatory diagram of the external information (weather) SA04 held by the analysis server SA according to the embodiment of the present invention.

[0113] The external information (weather) SA04 is a table that compiles data relating to weather, which is one type of external information.

[0114] The external information ID (SA040) is the identification ID of the external information. The date (SA041) is the date when the external information was acquired. The time (SA042) is the time when the external information was acquired. The day of the week (SA043) is the day of the week when the external information was acquired. The location (SA044) is the location where the external information was acquired. The latitude (SA045) is the latitude where the external information was acquired. The longitude (SA046) is the longitude where the external information was acquired. The weather (SA047), temperature (SA048), and precipitation (SA049) are the weather, temperature, and precipitation, respectively, at the location specified by the location (SA044) at the time specified by the date (SA041) and time (SA042).

[0115] The timing at which data is entered into the external information (weather) SA04 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry and the location where the data was obtained may be indicated by the date and time (SA041), time (SA042), and location (SA044). Also, it is not necessary for all data specified in this table to be stored.

[0116] The example shown in Figure 16 is an example, and if there is necessary data to represent data related to weather, which is one type of external information, the external information (weather) SA04 can be modified to add that data.

[0117] FIG. 17 is an explanatory diagram of external information (camera) SA05 held by the analysis server SA according to the embodiment of the present invention.

[0118] External information (camera) SA05 is a table that compiles data on things recognized by measurements made by a camera, which is one type of external information.

[0119] The external information ID (SA050) is an identification ID for the external information. The date (SA051) is the date on which this information was acquired. The time (SA052) is the time on which this information was acquired. The day of the week (SA053) is the day on which this information was acquired. The building ID (SA054) is an ID that identifies the building on which this information was acquired. The floor (SA055) is the floor on which this information was acquired. The installation location (SA056) is the location on which the camera was installed to acquire this information.

[0120] Number of people (SA057) is the number of people detected by a camera installed at a location specified by installation location (SA056) at a time specified by date (SA051) and time (SA052). Children (SA058), adults (SA059), men (SA05A), women (SA05B), wheelchairs (SA05C), and trolleys (SA05D) are the numbers of children, adults, men, women, wheelchairs, and trolleys, respectively, detected by a camera installed at a location specified by installation location (SA056) at a time specified by date (SA051) and time (SA052). In this way, not only the total number of people can be detected, but also a breakdown of people by attributes (e.g., age group and gender) and objects other than people can be detected.

[0121] Anger (SA05E) is the number of people who were determined to be angry among those detected by a camera installed at a location specified by the installation location (SA056) at a point in time specified by the date (SA051) and time (SA052), based on the results of detection by the camera. In this way, it is possible to count not only the number of people, but also the number of people in whom a specific emotion was detected by detecting people's emotions from their faces and actions with the camera.

[0122] The timing at which data is entered into the external information (camera) SA05 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry and the installation location of the camera that acquired the data should be indicated by the date (SA051), time (SA052), and installation location (SA056). Also, it is not necessary for all data specified in this table to be stored.

[0123] The example shown in Figure 17 is an example, and when expressing data relating to something recognized by measurement by a camera, which is one type of external information, if there is necessary data, the external information (camera) SA05 can be modified to add that data.

[0124] FIG. 18 is an explanatory diagram of the external information (building information) SA06 held by the analysis server SA according to the embodiment of the present invention.

[0125] The external information (building information) SA06 is a table that compiles data related to buildings, which are one type of external information.

[0126] The external information ID (SA060) is an identification ID for the external information. The building ID (SA061) is an ID that identifies the building from which this information was obtained. The date (SA062) is the date on which this information was obtained. The time (SA063) is the time on which this information was obtained. The day of the week (SA064) is the day on which this information was obtained. The east side of the 3rd floor (SA065) indicates the floor (3rd floor) on which this information was obtained and the area (east side) from which this information was obtained among the areas divided on that floor. The aggregated values ​​for each floor and area are stored. Floors and areas can be added at will, and when added, the aggregated data for that floor and area can be stored in the same way as the east side of the 3rd floor (SA065).

[0127] Electricity usage (SA066) and water usage (SA067) are the amounts of electricity and water used, respectively, on the east side of the third floor (SA065) at the time specified by date (SA062) and time (SA063). Temperature (SA068) and humidity (SA069) are the temperature and humidity, respectively, on the east side of the third floor (SA065) at the time specified by date (SA062) and time (SA063). Number of people occupying the building (SA06A) is the number of people occupying the building on the east side of the third floor (SA065) at the time specified by date (SA062) and time (SA063).

[0128] The timing at which data is entered into the external information (building information) SA06 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry and the location where the data was obtained should be indicated by the date (SA062), time (SA062), and third floor east side (SA065). Also, it is not necessary for all data specified in this table to be stored.

[0129] The example shown in Figure 18 is an example, and if there is necessary data when expressing data related to a building, which is one piece of external information, the external information (building information) SA06 can be modified to add that data.

[0130] FIG. 19 is an explanatory diagram of the occurrence number estimation input SA07 held by the analysis server SA according to the embodiment of the present invention.

[0131] The passenger occurrence number estimation input SA07 is a table that stores data generated by the passenger occurrence number data generation SP010 in the passenger occurrence number model processing SP01. The generated data includes the passenger occurrence number for each floor, the number of passengers getting on and off by car, and the car status.

[0132] The occurrence number estimation input ID (SA070) is an ID for identifying the occurrence number estimation input value. The time (SA071), day of the week (SA072), and time range (SA073) are the time, day of the week, and time range, respectively, generated by the occurrence number data generation SP010. The occurrence number (SA074) is the occurrence number generated by the occurrence number data generation SP010. The occurrence number is calculated by floor. In Figure 19, the occurrence number on the third floor is shown as 3rd floor (SA075). Although omitted in Figure 19, the occurrence number on other floors is entered in the same way. The occurrence number can be generated for each floor, area, and elevator hall, in which case the generated occurrence number is stored in the occurrence number (SA074).

[0133] The number of passengers boarding and alighting by car (SA076) is the number of passengers boarding and alighting by car generated by the generated passenger number data generation SP010 during the time period specified by the time (SA071), day of the week (SA072), and time span (SA073). The number of passengers boarding and alighting by car (SA076) is calculated by car. In Figure 19, the number of passengers boarding and alighting by car 1 is shown as car 1 (SA077). Car 1 (SA077) stores information about the number of passengers boarding and alighting in car 1, floor (SA078) is the floor on which the car is located, upward (SA079) is the number of passengers boarding and alighting when a car moving upward stops at the floor, and downward (SA07A) is the number of passengers boarding and alighting when a car moving downward stops at the floor. In addition to the above, information about car 1 can also be stored in car 1 (SA077). The number of passengers per car (SA076) can store information about the car other than car 1.

[0134] The car status (SA07B) stores data about the car status, and data about car 1 (SA07C) is stored in car 1. The floor is the floor on which car 1 (SA07C) is located during the time period specified by the time (SA071), day of the week (SA072), and time span (SA073). The direction is the direction in which car 1 (SA07C) is moving during the time period specified by the time (SA071), day of the week (SA072), and time span (SA073). For example, "up" indicates moving upward, and "down" indicates moving downward.

[0135] The status indicates the status of cage 1 (SA07C) during the time period specified by the time (SA071), day of the week (SA072), and time range (SA073). For example, "moving" indicates that it is actually moving, and "stopped" indicates that it is stopped. The number of passengers indicates the number of people riding in cage 1 (SA07C) during the time period specified by the time (SA071), day of the week (SA072), and time range (SA073). In addition to the above, information regarding the status of cage 1 can also be stored in cage 1 (SA07C). ​​Cage status (SA07B) can also store information regarding the status of cages other than cage 1.

[0136] The timing at which data is entered into the occurrence number estimation input SA07 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry should be indicated by the time (SA071) and day of the week (SA072). Also, it is not necessary for all data specified in this table to be stored.

[0137] The example shown in FIG. 19 is an example, and if there is any data required to represent the data generated in the number of occurrence data generation SP010, the number of occurrence occurrence estimation input SA07 can be modified to add that data.

[0138] FIG. 20 is an explanatory diagram of the number-of-event occurrence estimation model SA08 held by the analysis server SA according to the embodiment of the present invention.

[0139] The passenger occurrence number estimation model SA08 is a table that stores data generated in the passenger occurrence number estimation model generation SP011 in the passenger occurrence number model processing SP01. The generated data is a function f when "passenger occurrence number = f (number of passengers getting on and off, car status, external information)". The passenger occurrence number, number of passengers getting on and off, and car status are acquired as passenger occurrence number estimation input SA07, and the external information is acquired from external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06.

[0140] The occurrence number estimation ID (SA080) is an ID for identifying the occurrence number estimation model. The floor (SA081) is the floor targeted by the generated estimation model. The direction (SA082) is the direction targeted by the generated estimation model. The time (SA083) is the time targeted by the generated estimation model. The day of the week (SA084) is the day of the week targeted by the generated estimation model. The time range (SA082) is the time range targeted by the generated estimation model.

[0141] The following columns store the coefficients of the function f. The feature quantities are the number of passengers getting on and off by car (SA076), car status (SA07B) of the passenger number estimation input SA07, or one or more items of data selected from external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06. The feature quantity coefficients can then be found by performing multiple regression analysis using these feature quantities as explanatory indicators and the number of passengers occurring (SA074) as the objective indicator. The coefficients of the feature quantities obtained by the analysis are the number of passengers getting on and off coefficient 1 (SA085), car status coefficient 1 (SA087), and external variable coefficient 1 (SA088). Since a coefficient is found for each feature quantity, it is desirable to store a coefficient for each feature quantity.

[0142] As a method for generating a model for estimating the number of occurrences, an analysis method other than multiple regression analysis may be used.

[0143] The timing at which data is entered into the occurrence number estimation model SA08 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry should be indicated by the time (SA083) and day of the week (SA084). Also, it is not necessary for all data specified in this table to be stored.

[0144] The figure in Figure 20 is just one example, and if there is any data required to represent the model generated in the number of occurrence estimation model generation SP011, the number of occurrence estimation model SA08 can be modified to add that data.

[0145] FIG. 21 is an explanatory diagram of the number-of-events estimation result SA09 held by the analysis server SA according to the embodiment of the present invention.

[0146] The occurrence number of passengers estimation result SA09 is a table that stores data generated in the occurrence number of passengers estimation SP020 in the occurrence number of passengers estimation process SP02. The occurrence number of passengers estimation SP020 uses the stored occurrence number of passengers estimation model (function f), the number of passengers getting on and off at the current time, the car status, and external variables as inputs to estimate the number of passengers that will occur on each floor. The occurrence number of passengers estimation result SA09 in Figure 21 stores the results.

[0147] The estimated number of occurrences ID (SA090) is an ID used to identify the estimated number of occurrences. The date (SA092) is the date the number of occurrences was estimated. The time (SA093) is the time the number of occurrences was estimated. The day of the week (SA094) is the day of the week the number of occurrences was estimated. The time range (SA092) is the time range the number of occurrences was estimated. The floor (SA093) is the floor the number of occurrences was estimated on. The location (SA094) is the location the number of occurrences was estimated on. The number of occurrences (SA095) is the estimated number of occurrences.

[0148] The timing at which data is entered into the occurrence number estimation result SA09 may be for each event (for example, when an actual change occurs) or at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry should be indicated by the date (SA092), time (SA093), and day of the week (SA094). Also, it is not necessary for all data specified in this table to be stored.

[0149] The figure in FIG. 21 is just one example, and if there is any data required to represent the number of occurrences generated in the number of occurrences estimation SP020, the number of occurrences estimation result SA09 can be modified to add that data.

[0150] FIG. 22 is an explanatory diagram of the number-of-events prediction result SA10 held by the analysis server SA according to the embodiment of the present invention.

[0151] The number of event occurrence prediction result SA10 is a table storing data generated in the number of event occurrence estimation SP020 in the number of event occurrence prediction process SP03. In the number of event occurrence prediction SP030, the number of event occurrence prediction unit SA34 performs a process to estimate the number of event occurrences in the future using the number of event occurrence estimation result SA09 obtained in the number of event occurrence estimation process SP02 and external information. The result is stored in the number of event occurrence prediction result SA10 in FIG. 22.

[0152] As explained with reference to Figure 7, the inputs for the occurrence number prediction SP030 are the time range to be used for analysis (e.g., the past 10 minutes), the occurrence number estimation result SA09, external information (weather) SA04, external information (camera) SA05, and external information (building information) SA06, and the output is the future occurrence number.

[0153] Methods for predicting the number of occurrences include, for example, an AR model (autoregression model), but analysis methods other than the AR model may also be used.

[0154] The occurrence number prediction ID (SA100) is an ID for identifying the occurrence number prediction that has been performed. The date (SA101), time (SA102), and day of the week (SA103) are the date, time, and day of the week of the analysis target (i.e., the time when the analysis was performed), respectively. The prediction time (SA104) is the time when the analysis target is predicted (i.e., the occurrence number at that time is predicted). The time span (SA105) is the time span of the analysis target. The floor (SA106) is the floor of the analysis target. The location (SA107) is the location of the analysis target. The occurrence number (SA108) is the occurrence number at the time when the analysis target is predicted.

[0155] For example, the first line of the occurrence number prediction result SA10 in Figure 22 shows that the process to predict the number of people who will occur on the third elevator floor in the five minutes from 10:06:01 on Tuesday, June 27, 2017, was executed at 10:01:01 a.m. on the same day, and as a result, the number of people who will occur was predicted to be 12.

[0156] The timing for substituting the number of occurrence prediction result SA10 may be for each event (for example, when there is an actual change), or may be at a predetermined interval (for example, every millisecond, every second, or every minute). The actual date and time of entry should be indicated by the date (SA101), time (SA102), and day of the week (SA103). Also, it is not necessary for all data specified in this table to be stored.

[0157] The example shown in FIG. 22 is an example, and if there is necessary data when expressing the predicted number of occurrences in the predicted number of occurrences SP030, the predicted number of occurrences result SA10 can be modified to add that data.

[0158] FIG. 23 is an explanatory diagram of the number-of-events prediction result 2_SA11 stored in the analysis server SA according to the embodiment of the present invention.

[0159] The event number prediction result 2_SA11 is a table that stores the format-converted version of the event number prediction generated in the format conversion SP031 in the event number prediction process SP03.

[0160] In the format conversion SP031, the number-of-events prediction unit SA34 uses the number-of-events prediction result SA10 to calculate the occurrence probability for each number of people per unit time using the Poisson distribution. The result is stored in the number-of-events prediction result 2_SA11 in FIG. 23.

[0161] The formula for the Poisson distribution is shown below in equation (1). The probability P(k) that k or more people will occur can be calculated by substituting the number of people occurring on each floor for λ in equation (1).

[0162]

number

[0163] The above example is a method for calculating the probability of occurrence for each number of people based on the assumption that the probability distribution of the number of people follows a Poisson distribution. However, analytical methods other than those using the Poisson distribution can also be used to calculate the probability of the number of people.

[0164] The occurrence number prediction ID (SA110) is an ID for identifying the occurrence number prediction that was performed. The date (SA111), time (SA112), and day of the week (SA113) are the date, time, and day of the week of the analysis target (i.e., the time when the analysis was performed), respectively. The prediction time (SA114) is the time when the analysis target is predicted (i.e., the occurrence probability at that time is predicted). The time span (SA115) is the time span of the analysis target. The floor (SA116) is the floor of the analysis target. The location (SA117) is the location of the analysis target. The probability of 1 or more occurrences (SA118) is the probability that 1 or more people will occur in a unit time. The probability of 2 or more occurrences (SA119) is the probability that 2 or more people will occur in a unit time. The time span (SA115) may be used as the unit time.

[0165] For example, the first row of occurrence number prediction result 2_SA11 in Fig. 23 shows an example corresponding to the prediction result entered in the first row of occurrence number prediction result SA10 in Fig. 22. That is, the first row of occurrence number prediction result 2_SA11 in Fig. 23 indicates that, based on the number of people predicted to appear on the third elevator floor ("12 people"), the probability that one or more people will appear on the third elevator floor per unit time is predicted to be 90%, and the probability that two or more people will appear is predicted to be 75%. Although omitted in Fig. 23, the probability of three or more people appearing, the probability of four or more people appearing, etc. are also calculated in a similar manner and entered in occurrence number prediction result 2_SA11.

[0166] The example shown in Figure 23 is an example, and if there is necessary data when expressing the predicted number of occurrences in the format conversion SP031, the predicted number of occurrences result 2_SA11 can be modified to add that data.

[0167] FIG. 24 is an explanatory diagram of the time-zone-based destination floor estimation SA12 held by the analysis server SA according to the embodiment of the present invention.

[0168] The time-zone-specific destination floor estimation SA12 is a table that stores data generated by the destination floor estimation process SP04. In the destination floor estimation process SP04, the destination floor estimation unit SA35 generates a model that estimates destinations by time zone using the number of passengers getting on and off by floor (SA02). Specifically, the destination floor estimation unit SA35 counts the number of passengers getting off by floor for each time zone, and determines the trend in the number of passengers getting off by floor. This is then converted into an estimated value with the total as 100%. The results are stored in the time-zone-specific destination floor estimation SA12 in Figure 24.

[0169] The destination floor estimation ID (SA120) is an ID for identifying the destination floor estimation that has been performed. The date (SA121), time (SA122), day of the week (SA123), and time range (SA124) are the date, time, day of the week, and time range to be analyzed, respectively. The boarding floor (SA125) is the floor where the passenger boarded. The direction (SA126) is the direction in which the car is moving. The destination floor (SA127) is the floor where the passenger disembarked. For floors where the elevator stops, an estimated value is entered, with the entire value assumed to be 100%.

[0170] For example, the first row in FIG. 24 indicates that, during the 60 minutes from 10:01:01 AM on Tuesday, June 27, 2017, it was estimated from the number of passengers SA02 that 10% of the people who boarded an upward-moving car from the third floor got off at the 26th floor, and another 10% got off at the 27th floor. While the percentage of people who got off at other floors is omitted in FIG. 24, the total percentage calculated for all floors that could be destinations for people who boarded from the third floor is 100%. Similar percentages are calculated for destination floors from other floors. In this embodiment, these percentages are used as destination floor probabilities, which are the probability that a person who appears at a boarding point on each floor will go to that floor.

[0171] If it is possible to determine, for example, based on external information (camera) SA05, whether the person who got on the car at each floor and the person who got off the car at each floor are the same person, it is possible to identify which floor each person who got on at each floor got off at based on the determination result, and based on that, it is possible to calculate the proportion of destination floors for people who got on at each floor, such as, for example, that 10% of people who got on at floor 3 got off at floor 26. However, if such external information as above is not available, and if it is not possible to identify each person who got on or off, for example, by estimating the number of people who got on or off at each floor from the weight of the car, the proportion of destination floors may be calculated approximately based on some assumption.

[0172] For example, the number of people getting off at each floor during a time period specified by the date (SA121), time (SA122), day of the week (SA123), and time range (SA124) may be tallied, and the ratio of the number of people getting off at the 26th floor to the total number of people getting off at floors other than the 3rd floor may be calculated as the ratio of people who got on at the 3rd floor and got off at the 26th floor (i.e., the probability that the destination floor of people who got on at the 3rd floor was the 26th floor). In this case, the ratio of people getting off at other floors and the ratio of people who got on at other floors and got off at each floor are also calculated in a similar manner.

[0173] The example shown in FIG. 24 is an example, and if there is necessary data when expressing a destination floor estimation in the destination floor estimation process SP04, the time-zone-specific destination floor estimation SA12 can be modified to add that data.

[0174] FIG. 25 is an explanatory diagram of the time-zone-specific destination floor prediction result SA13 held by the analysis server SA according to the embodiment of the present invention.

[0175] The time-slot-specific destination floor prediction result SA13 is a table that stores data generated in the time-slot-specific destination floor prediction SP051 in the destination floor prediction process SP05. In the time-slot-specific destination floor prediction SP051, the destination floor prediction unit SA36 uses the time-slot-specific destination floor estimation SA12 and the occurrence number prediction result 2_SA11 as input data, and by combining these, it is possible to predict which floors the people who have occurred will visit. Specifically, the occurrence probability for each predicted occurrence time for each floor is multiplied by the destination floor estimation for the same time.

[0176] The above-described time-zone-specific destination floor prediction method is an example, and other methods may be used. The time-zone-specific destination floor prediction result SA13 in Fig. 25 stores the result.

[0177] The destination floor prediction ID (SA130) is an ID for identifying the destination floor prediction that was made. The date (SA131), time (SA132), and day of the week (SA133) are the date, time, and day of the week of the analysis target (i.e., the time when the analysis was made), respectively. The predicted time (SA134) is the time when the analysis target was predicted (i.e., the occurrence probability at that time is predicted). The time span (SA135) is the time span of the analysis target. The boarding floor (SA136) is the boarding floor of the analysis target. The destination floor (SA137) is the destination floor of the analysis target. The direction (SA138) is the direction in which the car of the analysis target will travel. The probability of one or more people occurring (SA139) is the probability that one or more people will occur per unit time. The probability of two or more people occurring (SA13A) is the probability that two or more people will occur per unit time. The time span (SA135) may be used as the unit time.

[0178] For example, the first row of the time-zone-specific destination floor prediction result SA13 in Fig. 25 shows an example corresponding to the prediction result entered in the first row of the number of people predicted 2_SA11 in Fig. 23 and the estimation result entered in the first row of the time-zone-specific destination floor estimation SA12 in Fig. 24. That is, the first row of the time-zone-specific destination floor prediction result SA13 in Fig. 25 indicates that, per unit time, there is a 9% probability that one or more people will appear on the third floor elevator floor in an upward-going car trying to get off at the 26th floor, and a 7.5% probability that two or more people will appear.

[0179] In this example, "9%" is obtained by multiplying "90%", which is the probability of 1 or more occurring (SA118) in the first row of Figure 23, by "10%", which is the value corresponding to the 26th floor of the destination floor (SA127) in the first row of Figure 24. "7.5%" is obtained by multiplying "75%", which is the probability of 2 or more occurring (SA119) in the first row of Figure 23, by "10%", which is the value corresponding to the 26th floor of the destination floor (SA127) in the first row of Figure 24.

[0180] The example shown in Figure 25 is an example, and if there is necessary data when expressing the time-zone-specific destination floor prediction in the time-zone-specific destination floor prediction SP051, the time-zone-specific destination floor prediction result SA13 can be modified to add that data.

[0181] FIG. 26 is an explanatory diagram of the rule / control template SA14 held by the analysis server SA according to the embodiment of the present invention.

[0182] The rule / control template SA14 is a table that stores templates of elevator operation rules / control parameters. Here, operation rules are rules that are applied by the control panel CA to control the operation of multiple elevator cars that are the subject of group management, and control parameters are parameters that can be changed in each operation rule. In this embodiment, operation rules and the control parameters included therein are collectively referred to as operation rules / control parameters. Furthermore, operation rules may be simply referred to as rules, and control parameters may be simply referred to as parameters.

[0183] Using the rule / control template SA14, it is possible to search for optimal operation rules / control parameters. The search method consists of two steps. The first step is to search for the rule / control number (SA140). This is the step of selecting the control parameters that are suitable for improving the KPI from among the many operation rules / control parameters. The second step is to search for the parameter values ​​(initial values) (SA144). The search targets parameter values ​​that can be controlled within the control parameters. By searching for these, it is possible to find more optimal control parameters.

[0184] The rule / control number (SA140) is an ID for identifying the operation rule / control parameter. The rule name (SA141) is the name of the operation rule / control parameter. The condition (SA142) is the operating condition of the operation rule / control parameter. The parameter value (initial value) (SA143) is a controllable parameter within the operation rule / control parameter. For example, in the rule corresponding to rule / control number "Ru01," "Direct train from floor ○ in 5 minutes," the ○ part (in this example, the floor number) is a controllable parameter. The coefficient (initial coefficient) (SA145) is a coefficient used when calculating regression equations, etc. The stored values ​​of the parameter value (initial value) (SA143) and coefficient (initial coefficient) (SA145) can be changed by repeating the optimization process.

[0185] The example shown in FIG. 26 is an example, and if there is any data required to implement the elevator operation rules / control parameters, the rule / control template SA14 can be modified to add that data.

[0186] FIG. 27 is an explanatory diagram of the KPI list SA15 held by the analysis server SA according to the embodiment of the present invention.

[0187] The KPI list SA15 is a table that stores KPIs (key performance indicators), which are evaluation indices used when searching for optimal operation rules / control parameters. Because KPIs may differ from building to building, the KPIs for each building are set in advance using the usage flag (SA155). At that time, the target values ​​for the KPIs (SA154) are also set.

[0188] KPIID (SA150) is an ID for identifying a KPI. Classification (SA151) classifies the KPI. Specifically, Classification (SA151) indicates who will benefit from improving this KPI.

[0189] Name (SA152) is the name of the KPI. Condition (SA153) indicates the content of the KPI. Target value (SA154) indicates the target value for the changeable parameter value portion of condition (SA153) (the portion marked with a circle in the example in Figure 27). This differs for each building, so it is set before use. Usage flag (SA155) specifies the KPI to be used when performing this optimization from multiple KPIs. A usage flag (SA155) of 1 means that it is specified. Multiple KPIs may also be specified.

[0190] 27, the KPIs shown are the waiting time for a person who has arrived at the platform to get into a car, the platform congestion rate, and the electricity usage on the floor (i.e., the amount including the amount of power consumed to move the car). In these examples, operation rules / control parameters that shorten the maximum waiting time, reduce the platform congestion rate, and reduce electricity usage are evaluated as appropriate operation rules / control parameters.

[0191] However, the above is just an example, and other KPIs may be specified. For example, a KPI may be used that gives a higher evaluation the lower the rate at which multiple people boarding from different floors share the same car. This makes it possible to control the car in a way that is less likely to dissatisfy elevator personnel (e.g., users or managers) in accordance with their wishes.

[0192] The example shown in FIG. 27 is an example, and if there is any data required to implement the elevator operation rules / control parameters, the KPI list SA15 can be modified to add that data.

[0193] FIG. 28 is an explanatory diagram of the simulation input and results SA16 held by the analysis server SA according to the embodiment of the present invention.

[0194] The simulation input and results SA16 is a table that stores the results of processing by the KPI simulation process SP11. The KPI simulation process SP11 uses as input the number of people predicted 2_SA11, which indicates the situation that has occurred, the time-of-day destination floor predicted result SA13, the rule / control template SA14, which indicates the control parameters, and the KPI list SA15, which stores the KPIs that are the optimization targets. By using this data, it is possible to determine the operation rules / control parameters that will increase the KPIs when people are present.

[0195] In the KPI simulation process SP11, the process of outputting KPIs when certain operation rules / control parameters are used in a state where people are present is performed multiple times while changing the operation rules / control parameters. The results are the simulation input and result SA16.

[0196] The KPI simulation ID (SA160) is an ID that identifies the KPI simulation. The number of times (SA161) is the number of times when multiple KPI simulations have been performed. The rule control list 1 (SA162) indicates one set of operation rule / control parameters used in each simulation. The rule / control No. (SA163) is an ID that identifies the operation rule / control parameter. The parameter value (SA164) is the control parameter used for this control. The coefficient (SA165) is a coefficient used when calculating regression equations, etc. Multiple rule control lists can be stored for one simulation. The KPI ID (SA166) is an ID that identifies the KPI. The KPI simulation result (SA167) is the KPI value obtained as a result of a KPI simulation using the rule control list.

[0197] The example shown in FIG. 28 is an example, and if there is any data required to realize the elevator operation rules / control parameters, the simulation input and result SA16 can be modified to add that data.

[0198] FIG. 29 is an explanatory diagram of the valid rules / parameters SA17 held by the analysis server SA according to the embodiment of the present invention.

[0199] The effective rules / parameters SA17 is a table that stores the results of determining operation rules / control parameters that contribute to optimization (i.e., effective) from the simulation input and results SA16 shown in Fig. 28. The rule / parameter evaluation unit SA38 can perform multiple regression analysis using the simulation input and results SA16 shown in Fig. 28 as input, the KPI simulation results as the objective variables, and the rule control list as the explanatory variables, with the results of multiple runs. However, as long as it is possible to identify the rule control parameters that contribute to optimization, a method other than multiple regression analysis may be used for this purpose.

[0200] The effective rule / parameter ID (SA170) is an ID for identifying an effective operation rule / control parameter. The effective rule control list 1 (SA171) is the rule control parameter that contributed most when multiple regression analysis was performed. The rule / control No. (SA172) is an ID for identifying an operation rule / control parameter. The parameter value (SA173) is the control parameter value used in this process. The coefficient (SA174) is a coefficient obtained by multiple regression analysis, and is a value that indicates the degree of contribution to optimization. By referring to this, effective operation rules / control parameters (i.e., those that contribute to improving the KPI) can be identified. Multiple effective rule control lists can be stored. The KPI ID (SA175) is an ID for identifying the KPI. The predicted value (SA176) is the KPI value predicted using the regression formula obtained by multiple regression analysis.

[0201] The example shown in FIG. 29 is an example, and if there is any data required to implement the elevator operation rules / control parameters, the valid rules / parameters SA17 can be modified to add that data.

[0202] FIG. 30 is an explanatory diagram of the valid rule / parameter subdivision list SA18 held by the analysis server SA according to the embodiment of the present invention.

[0203] Further optimization can be achieved by subdividing the control parameter values ​​of operation rules / control parameters that have a high contribution to optimization and are identified from the active rules / parameters SA17 shown in Figure 29. Operation rules / control parameters with large coefficients (SA174) are selected from the active rule control list of the active rules / parameters SA17. The rule / parameter evaluation unit SA38 then executes the active rule / parameter subdivision process SP14 for the selected operation rules / control parameters. Specifically, the rule / parameter evaluation unit SA38 can search for more optimized operation rules / control parameters by increasing or decreasing the control parameter values ​​included in the selected operation rules / control parameters.

[0204] The valid rule / parameter refinement ID (SA180) is an ID for identifying the valid rule / parameter refinement. The valid rule / parameter ID (SA181) is an ID for identifying the valid operation rule / control parameter. The valid rule control list 1 (SA182) is the rule control parameter estimated to be the most contributing by multiple regression analysis. The rule / control No. (SA183) is an ID for identifying the operation rule / control parameter. The parameter value (SA184) is the control parameter value used in this process. The coefficient (SA185) is a coefficient obtained by multiple regression analysis and is a value contributing to optimization. The parameter value subdivision range (SA186) is a value obtained by the valid rule / parameter subdivision process SP14. Multiple valid rule control lists can be stored. The KPI ID (SA187) is an ID for identifying the KPI. The predicted value (SA188) is the KPI value predicted using the regression formula obtained by multiple regression analysis. The rule / parameter evaluation unit SA38 may also randomly select several operation rules / control parameters from the rule / control template SA14.

[0205] The example shown in Figure 30 is an example, and if there is any data required to implement the elevator operation rules / control parameters, the valid rule / parameter subdivision list SA18 can be modified to add that data.

[0206] FIG. 31 is an explanatory diagram of the rule / parameter list SA19 held by the analysis server SA according to the embodiment of the present invention.

[0207] The rule / parameter list SA19 is a table that stores operation rules / control parameters selected for use in actual operation from the valid rules / parameters SA17 in Fig. 29. Among the operation rules / control parameters in the valid rule control list, those with a large coefficient (SA174) are determined to be operation rules / control parameters with a high contribution rate.

[0208] The rule / parameter ID (SA190) is an ID that identifies the operation rule / control parameter. The effective rule control number 1 (SA191) is the rule control parameter that is estimated to have the greatest degree of contribution as a result of the multiple regression analysis. The rule / control No. (SA192) is an ID that identifies the operation rule / control parameter. The parameter value (SA193) is the control parameter value used in this processing. The coefficient (SA194) is a coefficient found by the multiple regression analysis, and is a value that contributes to optimization.

[0209] Effective Rule Control No. 2 (SA195) is the operation rule / control parameter estimated to have the second largest contribution as a result of multiple regression analysis. Rule / Control No. (SA196) is the control parameter value used in this process. Parameter Value (SA197) is the control parameter value used in this process. Coefficient (SA198) is a coefficient found by multiple regression analysis, and is the value that contributes to optimization.

[0210] KPIID (SA199) is an ID for identifying a KPI. Predicted value (SA19A) is a value predicted using a regression formula obtained by multiple regression analysis.

[0211] The rule / parameter list SA19 is sent to the control selector SP06. Based on the rule / parameter list SA19, the control selector SP06 generates an input command CA0 that specifies operation rules / control parameters for improving the KPI, and sends it to the control panel CA. Based on the input command CA0, the control panel CA changes the operation rules / control parameters that have already been set to the specified ones, and controls the car based on the changed operation rules / control parameters. This achieves elevator control that improves the KPI.

[0212] The example shown in FIG. 31 is an example, and if there is any data required to implement the elevator operation rules / control parameters, the rule / control parameter list SA19 can be modified to add that data.

[0213] The processing described in this embodiment is executed in the execution unit SA3 of the analysis server SA, but part or all of it may be executed by the control panel CA. For example, the control panel CA may have hardware similar to that of the analysis server SA shown in Figure 1B, and at least part of the functions of the analysis server SA may be realized by this hardware.

[0214] FIG. 32 is an explanatory diagram of a building individualized report SA20 output by the analysis server SA according to the embodiment of the present invention.

[0215] The building individualized report SA20 is generated by the rule / parameter evaluation unit SA38 in the display / control data generation process SP15 and transmitted to the display unit SA1. The display unit SA1 (for example, a display device implemented as the output device 103) displays the received building individualized report SA20.

[0216] The building individualized report SA20 includes, for example, a building name 3201, an elevator bank name 3202, a period 3203, a KPI 3204, and a result 3205, as shown in FIG.

[0217] Elevator bank name 3202 and building name 3201 are the names of the elevator bank and the building in which it is installed that were the subject of the execution of each process shown in FIG. 2, and correspond to the bank name (SA002) and building name (SA007) shown in FIG. 12. Period 3203 is the period that is the subject of the simulation. KPI 3204 is the evaluation index selected as the subject of evaluation in the processing of rule / parameter evaluation unit SA38, and corresponds to the KPI whose usage flag (SA155) shown in FIG. 27 is enabled. Result 3205 is the valid operation rule / control parameter selected as the result of the processing of rule / parameter evaluation unit SA38, and corresponds to the operation rule / control parameter registered in rule / parameter list SA19.

[0218] By referring to the building individualization report SA20, the elevator manager can understand the changes to the operation rules / control parameters that are required to improve the evaluation index displayed as KPI3204. The manager may manually set the changes to the operation rules / control parameters that he / she has identified in the control panel CA. This allows elevator control that improves the KPI to be realized.

[0219] As described above, according to this embodiment, the number of passengers in the elevator hall is predicted from the number of passengers getting on and off at each floor, a control method suited to the prediction result is generated, and the control method is evaluated using an index related to user dissatisfaction, thereby achieving optimal elevator control. For example, by smoothly dispatching cars to the hall around the time when future congestion is predicted, long waiting times for passengers at the hall can be reduced, improving user transportation capacity and thereby improving user satisfaction.

[0220] In addition to what is set forth in the claims, the following are representative aspects of the present invention. (1) An elevator analysis system having a processor and a storage device coupled to the processor, The storage device stores the number of people who have appeared at the landings of each floor of the elevator group to use the elevators, The processor: predicting the number of occurrences in the future from the number of occurrences stored in the storage device; determining, from the predicted future number of passengers, operation rules to be applied for controlling the operation of each of the cars belonging to the elevator group, and control parameters to be set in each operation rule; An elevator analysis system that outputs the determined operation rules and control parameters. (2) The elevator analysis system according to (1), the storage device further stores information on the number of passengers boarding and alighting, the information indicating the actual number of passengers boarding and alighting at each floor of each car belonging to the elevator group; The processor: calculate a destination floor probability, which is the probability that the destination floor of the person who appeared at the boarding / alighting platform at each floor will be that floor, for each floor that can be a destination floor of the person who appeared at the boarding / alighting platform at each floor based on the boarding / alighting number information; An elevator analysis system characterized by determining operation rules to be applied to control the operation of each of the cars belonging to the elevator group, and control parameters to be set in each operation rule, based on the future number of people and the destination floor probability. (3) The elevator analysis system according to (2), the storage device further stores information specifying an evaluation index for evaluating the operation of each of the cars of the elevator group; The processor: a first simulation in which people are generated at the landings of each floor based on the future number of people to be generated and the destination floor probability, and each of the cars of the elevator group is operated, the first simulation being executed a plurality of times while changing the operation rule and the control parameter to be applied; Calculating the specified evaluation index based on the result of the first simulation; and determining, based on the calculated evaluation index, the operation rules and the control parameters that contribute to improving the evaluation index as operation rules to be applied to control the operation of each car belonging to the elevator group and control parameters to be set in each operation rule. (4) The elevator analysis system according to (3), The processor: From the predicted future number of occurrences, calculate the occurrence probability, which is the probability that that number of people will appear, for each number of occurrences based on the assumption that the probability distribution of the number of occurrences follows a Poisson distribution; An elevator analysis system characterized by generating people according to the occurrence probability for each number of people to be generated and the destination floor probability for each destination floor, and executing the first simulation. (5) The elevator analysis system according to (3), a display device connected to the processor; the processor identifies the operation rule and the control parameter whose degree of contribution to improvement of the evaluation index satisfies a predetermined condition; The display device displays the identified operation rules and control parameters. (6) The elevator analysis system according to (3), further comprising an interface connected to the processor and to a network external to the elevator analysis system; a control device that controls each car belonging to the elevator group is connected to the network; The processor: Identifying the operation rules and the control parameters whose contribution to improving the evaluation index satisfies a predetermined condition; and transmitting the identified operation rules and control parameters to the control device via the interface. (7) The elevator analysis system according to (3), The evaluation index includes any one of the waiting time for the person to board one of the cars, the congestion rate of the hall, and the amount of power consumed to operate each car of the elevator group. (8) The elevator analysis system according to (1), The storage device information on the number of people getting on and off, which indicates the actual number of people getting on and off at each floor of each car belonging to the elevator group to be controlled; and further storing operation log information indicating the actual status of each car belonging to the elevator group; The processor: a second simulation is performed in which a plurality of people appear at the landings of the elevator group to use an elevator, the floor of the landing at which each person appears, the time at which each person appears, and the destination floor for each person are randomly determined, and each car belonging to the elevator group is operated according to the time at which each person appears, the floor at which each person appears, and the destination floor, thereby generating an occurrence number estimation model that estimates the occurrence number, which is the number of people appearing at the landings on each floor, from the state of each car, the number of people getting on in each car at each floor, and the number of people getting off in each car at each floor; The actual number of passengers getting on and off and the state of each car obtained from the boarding and alighting number information and the operation log information are applied to the passenger number estimation model to estimate the number of passengers that will occur on each floor; The estimated number of occurrences is stored in the storage device; An elevator analysis system characterized by predicting the number of people who will occur in the future from the estimated number of people who will occur stored in the storage device. (9) The elevator analysis system according to (8), The processor generates the number of passengers occurring estimation model by performing multiple regression analysis in the second simulation using the number of passengers occurring at each floor for each predetermined time interval as a target indicator, and using the state of each car for each predetermined time interval, the number of passengers getting on each car at each floor, and the number of passengers getting off each car at each floor as explanatory indicators. (10) The elevator analysis system according to (8), the information on the number of passengers getting on and off and the operation log information include information indicating operation rules that were applied to control the operation of each of the cars belonging to the elevator group and control parameters that were set in the operation rules when the number of passengers getting on and off, and the actual state of each of the cars were acquired, The processor executes the second simulation by operating each of the cars in accordance with the applied operation rules and the set control parameters. (11) A prediction unit that predicts the number of users who will occur at the boarding area within a time range from a certain time based on information on the past number of passengers in the car at each floor and information on the boarding time of the number of passengers, as the predicted number of passengers who will occur at the certain time; A control unit that controls a car based on the predicted number of passengers predicted by the prediction unit; An elevator car control system comprising: (12) The elevator car control system according to claim 1, The control unit controls the car based on a predicted occurrence time, which is a time when the prediction unit predicts that the predicted number of users will appear at the platform. An elevator car control system characterized by: (13) The elevator car control system according to claim 2 of (12), a storage unit that stores information on the number of passengers getting on and off, the information including the past number of passengers and the boarding time information, the information indicating the past number of passengers getting on and off at each floor of the car; an estimation unit that estimates an estimated value of the number of users who have occurred at the platform within a time range from a certain time based on the boarding and alighting number information as an estimated number of users who have occurred at the certain time, and sets the time at which it is estimated that the users of the estimated number of users have occurred at the platform as an estimated occurrence time, the prediction unit predicts the predicted number of occurrences and the predicted occurrence time based on the predicted number of occurrences and the predicted occurrence time; An elevator car control system characterized by: (14) The elevator car control system according to claim 2 of (12), a selection unit that selects one of a plurality of operation rules to be applied to control operation of the car based on the predicted number of people and the predicted occurrence time, The control unit controls the car based on the operation rule selected by the selection unit. An elevator car control system characterized by: (15) The elevator car control system according to claim 4 of (14), the selection unit determines a value of a control parameter to be set in the selected operation rule based on the predicted number of occurrences and the predicted occurrence time. An elevator car control system characterized by: (16) The elevator car control system according to claim 5 of (15), a destination floor estimation unit that calculates a destination floor probability, which is the probability of a destination floor selected by a user who has appeared at the boarding area; the selection unit selects the operation rule and determines the value of the control parameter based on the predicted number of passengers and the destination floor probability. An elevator car control system characterized by: (17) The elevator car control system according to claim 6, a storage unit for storing information specifying an evaluation index for evaluating the operation of the car; a simulation unit that executes a first simulation of operating the car by generating people at the boarding area of ​​each floor based on the predicted number of people and the destination floor probability a plurality of times while changing the value of the control parameter, and calculates an evaluation value of the evaluation index specified for each changed value of the control parameter, the selection unit determines the value of the control parameter to be the value of the control parameter that contributes to improving the evaluation value. An elevator car control system characterized by: (18) The elevator car control system according to claim 7, The control unit controls a plurality of cars, The evaluation index includes any one of the waiting time for the person to board the car, the congestion rate of the boarding area, and the amount of power consumed to operate each car. An elevator car control system characterized by: (19) The elevator car control system according to claim 3 of (13), a simulation unit that generates a plurality of people who will appear at the landing to use the elevator, determines the floor of the landing at which the plurality of people will appear, the time at which the plurality of people will appear, and the destination floor of the plurality of people for each of the plurality of people, and executes a second simulation in which the car operates in accordance with the time at which the plurality of people will appear, the floor of the landing at which they will appear, and the destination floor; an occurrence number estimation model generation unit that generates an occurrence number estimation model that estimates the estimated occurrence number and the estimated occurrence time from the number of people getting on the car at each floor and the number of people getting off the car at each floor based on the simulation result of the simulation unit, The estimation unit estimates the estimated number of passengers and the estimated occurrence time on each floor by applying the boarding and alighting number of passengers information to the occurrence number estimation model. An elevator car control system characterized by: (20) The elevator car control system according to claim 9, The storage unit stores information indicating control parameters applied to control the operation of the car, The elevator car control system is characterized in that the simulation unit executes the second simulation by operating each of the cars in accordance with the applied control parameters.

[0221] It should be noted that the present invention is not limited to the above-described embodiment, and includes various modifications. For example, the above-described embodiment has been described in detail to provide a better understanding of the present invention, and the present invention is not necessarily limited to an embodiment having all of the configurations described.

[0222] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations, functions, etc. may also be implemented in software, with a processor interpreting and executing a program that implements each function. Information such as the programs, tables, and files that implement each function can be stored in storage devices such as nonvolatile semiconductor memory, hard disk drives, and solid-state drives (SSDs), or in computer-readable, non-transitory data storage media such as IC cards, SD cards, and DVDs.

[0223] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0224] SA...analysis server, SA0...database, SA1...display unit, SA2...request unit, SA3...execution unit, SA31...measurement processing unit, SA32...occurrence number estimation model generation unit, SA33...occurrence number estimation unit, SA34...occurrence number prediction unit, SA35...destination floor estimation unit, SA36...destination floor prediction unit, SA37...control selector unit, SA38...rule / parameter evaluation unit, NW...network, CL...client terminal, EXN...external information neighboring building, EXD...external information database, EXC...external information camera, CA...control panel, CA1...car 1, CA2...car 2, CA8...car 8

Claims

1. a prediction unit that predicts the number of users who will occur at the boarding area within a time range from a certain time based on information on the past number of passengers in the car at each floor and boarding time information on the number of passengers, as the predicted number of passengers who will occur at the certain time; a destination floor estimation unit that calculates the probability of a destination floor being selected by a user who has appeared at the boarding area; A destination floor prediction unit that predicts a destination floor based on the predicted number of passengers and the probability of the destination floor, Elevator analysis system.

2. In claim 1, The prediction unit predicts the predicted number of passengers based on external information other than information related to elevator operation. Elevator analysis system.

3. In claim 2, When the external information is external information acquired by an imaging means, the prediction unit predicts the number of people included in the external information as the predicted number of people that will occur at the certain time. Elevator analysis system.

4. a prediction step of predicting the number of passengers who will occur at the boarding area within a time range from a certain time based on information on the past number of passengers in the car at each floor and boarding time information on the number of passengers; and a destination floor estimation step of calculating the probability of a destination floor selected by a user who appears at the platform; a destination floor prediction step of predicting a destination floor based on the predicted number of passengers and the probability of the destination floor, Elevator analysis methods.

5. In claim 4, the prediction step includes a step of predicting the predicted number of passengers based on external information other than information about elevator operation, Elevator analysis methods.

6. In claim 5, the prediction step includes a step of predicting, when the external information is external information acquired by an imaging means, the number of people included in the external information as the predicted number of people that will occur at the certain time; Elevator analysis method.

Images