Title of the invention: Elevator analysis system and method for designing an elevator analysis system
Capture by reference
[0001]
　This application claims the priority of Japanese Patent Application No. 2019-156006, which is a Japanese application filed on August 28, 2019, and incorporates it into this application by reference to its contents.
Technical field
[0002]
　The present invention relates to an elevator analysis system.
Background technology
[0003]
　In buildings such as offices and various facilities, it is required to improve the convenience of elevator users. For example, by predicting the flow of people to an elevator, that is, predicting which floor the elevator user is on and which floor the elevator is going to go to, the elevator is advanced before the user presses the call button. It becomes possible to control such as waiting, which leads to reduction of waiting time.
[0004]
　As a method of realizing such a flow prediction, for example, there is a method of recording a past record of the flow of people and generating a prediction model by learning the results. In order to generate an accurate predictive model by this method, it is necessary to record the actual results of the flow of people over a certain length of time, and it is necessary to secure a storage area for that purpose.
[0005]
　On the other hand, a technique for lossless compression of data by utilizing sparsity is known (see, for example, Non-Patent Document 1).
Prior art literature
Non-patent literature
[0006]
　　Non-Patent Document 1: Gibbs, Norman E .; Poole, William G .; Stockmeyer, Paul K. (1976). "A comparison of several bandwidth and profile reduction algorithms". ACM Transactions on Mathematical Software. 2 (4): 322 -330. doi: 10.1145 / 355705.355707.
Outline of the invention
Problems to be solved by the invention
[0007]
　When the function of analyzing the boarding / alighting data and generating the flow prediction model is to be implemented in the control panel of the elevator, it is necessary to store the boarding / alighting data in the memory of the control panel. However, in general, the memory capacity of the control panel is limited. On the other hand, how much data can be compressed by lossless compression using sparsity depends on the number of occurrences of non-zero values ​​in the data. However, since the number of occurrences of non-zero values ​​in elevator boarding / alighting data is unknown, when implementing a function to analyze data and generate a predictive model on the control panel, the required memory capacity cannot be determined and analysis is performed. And it was difficult to guarantee the stability of model generation.
Means to solve problems
[0008]
　In order to solve at least one of the above problems, the present invention is an elevator analysis system including a processor and a storage device connected to the processor, wherein the storage device is a movement of a person between floors. The size of the storage area of ​​the Origin-Destination information is calculated based on the minimum time required to move between the floors of the elevator. It is characterized in that it is determined based on the maximum number of non-zero values.
The invention's effect
[0009]
　According to one embodiment of the present invention, the storage capacity required for recording the actual results of the flow of people can be calculated in advance based on the property information of the elevator to be delivered. Issues, configurations and effects other than those described above will be clarified by the description of the following embodiments.
A brief description of the drawing
[0010]
FIG. 1 is a functional block diagram showing a configuration of an elevator analysis system according to an embodiment of the present invention.
FIG. 2 is a block diagram showing a hardware configuration of a computer system that realizes an elevator analysis system according to an embodiment of the present invention.
FIG. 3 is an explanatory diagram of an OD table held by the elevator analysis system according to the embodiment of the present invention.
FIG. 4 is an explanatory diagram of time series data of an OD table used by the elevator analysis system of the embodiment of the present invention as an explanatory variable for destination floor prediction.
FIG. 5 is an explanatory diagram of a table that stores non-zero values ​​of explanatory variables for destination floor prediction, which is held by the elevator analysis system according to the embodiment of the present invention.
FIG. 6 is a flowchart showing a process in which the elevator analysis system according to the embodiment of the present invention stores an OD table as a sparse matrix.
Embodiment for carrying out the invention
[0011]
　Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[0012]
　FIG. 1 is a functional block diagram showing a configuration of an elevator analysis system 100 according to an embodiment of the present invention.
[0013]
　The elevator analysis system 100 has a number of occurrence prediction unit 110 and a destination floor prediction unit 130.
[0014]
　The number of occurrence prediction unit 110 predicts the number of occurrences on each floor. In this embodiment, "occurrence" means that a person who intends to use the elevator reaches the elevator hall (that is, the elevator platform), and "occurrence number" is the number of persons who have occurred. The number of occurrence prediction unit 110 may predict the number of occurrences by any method. Here, an example thereof will be described.
[0015]
　The number of occurrence prediction unit 110 of this embodiment is the number of boarding / alighting number calculation unit 111, the simulation data generation unit 112, the offline conversion model generation unit 113, the real-time conversion model generation unit 114, the prediction model learning unit 115, the prediction unit 116, and the conversion generation database. It has (DB) 117, a model database (DB) 118, a simulation database (DB) 119, and a local boarding / alighting database (DB) 120.
[0016]
　The boarding / alighting number calculation unit 111 acquires data on the state of the elevator 140 acquired during actual operation in the past from the elevator 140. The data acquired here may include, for example, the position of each car of the elevator 140 for each time (or a time zone of a predetermined length), the moving direction, the weight of the load of each car, and the like. Further, the boarding / alighting number calculation unit 111 may acquire data indicating the call state of each floor at each time (or a time zone of a predetermined length), that is, whether or not the call button of each floor has been pressed. .. These data are also referred to as local data.
[0017]
　Further, the boarding / alighting number calculation unit 111 generates local boarding / alighting data from the acquired data. For example, the boarding / alighting number calculation unit 111 may estimate the number of people in each car at each time based on the weight of each car at each time. Further, the boarding / alighting number calculation unit 111 may estimate the number of people who got into each car on each floor, the number of people who got off at each floor, etc. from the changes in the position, moving direction, and weight of each car at each time. Furthermore, the number of people who got on from one floor and went down to another floor may be estimated based on the operation records of the destination floor button of each car and the call button of each floor. Local boarding / alighting data includes at least one of such information. Since the above estimation can be performed by any method, detailed description thereof will be omitted here.
[0018]
　The boarding / alighting number calculation unit 111 stores the acquired data such as the state of the car and the local boarding / alighting data estimated based on the data in the local boarding / alighting database 120. The local boarding / alighting database 120 may include, for example, an OD (Origin-Destination) table described later and a table generated based on the OD table.
[0019]
　The simulation data generation unit 112 generates virtual traffic demand. For example, the simulation data generation unit 112 uses a random number to determine the time when a person occurs, the floor where the person occurs, and the floor (destination floor) where the person intends to go using the elevator 140. You may decide and assume that such a person has occurred.
[0020]
　Further, the simulation data generation unit 112 generates operation data of the elevator 140 from the virtual traffic demand. For example, the simulation data generation unit 112 may have an operation simulator of the elevator 140, and by inputting a virtual traffic demand into the operation simulator, the operation simulation may be executed to generate virtual operation data. The generated virtual traffic demand and operation data are stored in the simulation database 119.
[0021]
　The offline conversion model generation unit 113 generates a model for estimating the number of people generated before the time, based on the operation data such as the number of people getting on and off after the time. The real-time conversion model generation unit 114 generates a model for estimating the number of people generated after a certain time based on the operation data such as the number of people getting on and off before the time. These models are stored in the model database 118. The number of occurrences estimated by these models is stored in the conversion occurrence database 117.
[0022]
　The prediction model learning unit 115 learns a prediction model for predicting the number of occurrences after a certain time from the number of occurrences before a certain time based on the number of occurrences stored in the conversion occurrence database 117. The trained predictive model is stored in the model database 118.
[0023]
　The prediction unit 116 uses a prediction model to predict the number of people who will occur after a certain time from the on-site boarding / alighting data before a certain time. Here, the on-site boarding / alighting data before a certain time to be input may be estimated by the model generated by the real-time conversion model generation unit 114, or may be acquired by other means. May be good. The occurrence number prediction result by the prediction unit 116 is input to the destination floor prediction unit 130.
[0024]
　The destination floor prediction unit 130 predicts the destination floor of a person who has occurred on each floor. The destination floor prediction unit 130 of this embodiment has a prediction feature amount calculation unit 131, a destination floor prediction model generation unit 132, a destination floor probability generation unit 133, and a destination floor allocation unit 134.
[0025]
　The predicted feature amount calculation unit 131 calculates the feature amount of the departure floor, the destination floor, and the number of people for each time zone of a predetermined length included in the past local boarding / alighting data stored in the local boarding / alighting database 120. The destination floor prediction model generation unit 132 predicts the departure floor, destination floor, and number of people in the time zone after the time zone of the local boarding / alighting data that is the basis of the calculation of the feature quantity from the calculated feature quantity. Generate a predictive model.
[0026]
　The destination floor probability generation unit 133 generates a destination floor probability indicating what percentage of the persons generated on each floor go to which floor based on the generated destination floor prediction model. Then, the destination floor allocation unit 134 multiplies the occurrence number prediction result by the prediction unit 116 by the destination floor probability, so that the prediction result of the occurrence number for each destination floor, that is, how many of the number of people predicted to occur on each floor The result of predicting which floor to go to is output to the elevator 140 as the result of predicting the flow of people. The control panel of the elevator 140 (not shown) can control the elevator according to the demand based on the result of predicting the flow of people.
[0027]
　As described above, according to the embodiment of the present invention, it is possible to plan the operation of the elevator 140 that better meets the actual demand by predicting not only the number of people generated on each floor but also the number of people generated on each destination floor. It will be possible and the satisfaction of users will be improved.
[0028]
　FIG. 2 is a block diagram showing a hardware configuration of a computer system that realizes the elevator analysis system 100 according to the embodiment of the present invention.
[0029]
　The elevator analysis system 100 is realized by, for example, a computer system 200 having an interconnected interface (I / F) 201, an input device 202, an output device 203, a processor 204, a main storage device 205, and an auxiliary storage device 206. ..
[0030]
　The interface 201 is connected to a network (not shown) and communicates with the elevator 140 via the network. The input device 202 is a device used by the user of the elevator analysis system 100 to input information to the elevator analysis system 100, and may include at least one such as a keyboard, a mouse, and a touch sensor. The output device 203 is a device that outputs information to the user of the elevator analysis system 100, and may include, for example, a display device that displays characters, images, and the like.
[0031]
　The processor 204 executes various processes according to the program stored in the main storage device 205. The main storage device 205 is a semiconductor storage device such as a DRAM, and stores a program executed by the processor 204 and data necessary for processing of the processor. The auxiliary storage device 206 is a storage device having a relatively large capacity such as a hard disk drive or a flash memory, and stores data or the like referred to in a process executed by the processor 204.
[0032]
　In the main storage device 205 of this embodiment, the number of people getting on and off calculation unit 111 of the number of occurrence prediction unit 110, the simulation data generation unit 112, the offline conversion model generation unit 113, the real-time conversion model generation unit 114, the prediction model learning unit 115, and the prediction A program for realizing the prediction feature amount calculation unit 131 of the destination floor prediction unit 130, the destination floor prediction model generation unit 132, the destination floor probability generation unit 133, and the destination floor allocation unit 134 is stored. Therefore, in the following description, the process executed by each of the above parts is actually executed by the processor 204 according to the program corresponding to each part stored in the main storage device 205.
[0033]
　The auxiliary storage device 206 of this embodiment stores a simulation database 119, a conversion generation database 117, a model database 118, and a local boarding / alighting database 120. Further, a program corresponding to each unit included in the generation number prediction unit 110 and the destination floor prediction unit 130 may be stored in the auxiliary storage device 206 and copied to the main storage device 205 as needed. Further, at least a part of the above database may be copied to the main storage device 205 as needed.
[0034]
　The elevator analysis system 100 may be realized by, for example, a computer system 200 connected to the elevator 140 via a network, or may be realized by the hardware of the existing control panel of the elevator 140. In that case, the computer system 200 corresponds to the hardware of the control panel of the elevator 140. In that case, the computer system 200 does not have to have the interface 201. Further, the computer system 200 does not have a large-capacity auxiliary storage device 206, and all programs and data may be stored in a relatively small-capacity main storage device 205. By mounting the elevator analysis system 100 on the control panel, the present invention can be applied to the configuration of the current elevator product, and it is not necessary to connect the control panel to, for example, an external analysis server via a network.
[0035]
　FIG. 3 is an explanatory diagram of an OD table held by the elevator analysis system 100 according to the embodiment of the present invention.
[0036]
　FIG. 3 shows an example of the OD table 300 included in the local boarding / alighting database 120. The OD table 300 is information recording the movement of a person (that is, the flow of people) between floors during a predetermined length of time (for example, a certain 5 minutes). The horizontal axis of the OD table 300 shows the floor (departure floor, Origin) where a person was generated and got into the basket, and the vertical axis shows the floor (destination floor, Destination) where the person got off. The numbers indicate the number of people who boarded at the corresponding departure floor and got off at the corresponding destination floor. In the example of Fig. 3, in a certain 5 minutes, there are 3 people who got on the 1st floor and got off on the 2nd floor, and no one got on the 1st floor and got off on the 3rd floor, and got on the 1st floor. It shows that there were four people who got off on the 4th floor.
[0037]
　FIG. 3 shows an example of a 5-minute OD table 300, but in reality, for example, 5 minutes from 8:00 to 8:05, 5 minutes from 8:01 to 8:06, and so on. The OD table 300 is generated and stored every 5 minutes. Then, such data is used as training data for generating a destination floor prediction model.
[0038]
　FIG. 4 is an explanatory diagram of time series data of the OD table used by the elevator analysis system 100 of the embodiment of the present invention as an explanatory variable for destination floor prediction.
[0039]
　FIG. 4 shows, as an example, an explanatory variable in which the movement of a person between floors in a certain time zone is predicted based on the OD table in the time zone 5 minutes before and the OD table in the time zone 10 minutes before. The time series data 400 used as is shown.
[0040]
　For example, the numerical value "3" stored in the field corresponding to "1 → 2" at the time "8:00" and "5 minutes ago" is on the first floor for 5 minutes from 7:55 to 8:00. It shows that there were three people who got on the basket and got off on the second floor. That is, the one-row fields corresponding to the times "8:00" and "5 minutes ago" are arranged two-dimensionally as shown in FIG. 3 in the 5-minute OD table 300 from 7:55 to 8:00. The fields are rearranged into one line.
[0041]
　Similarly, the numerical value "2" stored in the field corresponding to "1 → 2" at the time "8:00" and "10 minutes ago" is on the first floor for 5 minutes from 7:50 to 7:55. It shows that there were two people who got on the basket and got off on the second floor. In this example, the movement of a person between floors for a certain 5 minutes (for example, from 8:00 to 8:00) is OD table 300 for 5 minutes (for example, from 7:55 to 8:00) 5 minutes before that. Then, a destination floor prediction model for prediction is generated based on the OD table 300 for 5 minutes (for example, from 7:50 to 7:55) 5 minutes before that.
[0042]
　In the example of FIG. 4, for example, the 5-minute OD table 300 from 8:00 to 8:05 is stored, and then the 5-minute OD table 300 from 8:01 to 8:06 is stored. As such, time-series data in 1-minute increments is stored. However, this step size is an example, and another step size such as a 5-minute step may be adopted.
[0043]
　In order to store the OD table 300, the elevator analysis system 100 needs to secure an area for storing the number of people corresponding to all combinations of the departure floor and the destination floor. In an elevator where the number of floors is N, the number of combinations of departure floors and destination floors is N × (N-1), and the storage area for storing the OD table 300 is proportional to the square of the number of floors. Will increase. For example, if the number of floors is 32, the number of combinations of departure floors and destination floors is 992. That is, in the time series data of FIG. 4, the number of columns corresponding to each of "5 minutes ago" and "10 minutes ago" is 992.
[0044]
　Since these data are used as training data for generating a destination floor prediction model, the OD table 300 for a sufficiently long period (for example, one month) is used to ensure its accuracy. Need to hold. However, especially when the elevator analysis system 100 is realized by the control panel of the elevator 140, the storage area of ​​the control panel will be compressed to store such a long-term OD table 300.
[0045]
　Therefore, in this embodiment, the data is compressed by utilizing the sparsity of the OD table 300. Specifically, in this embodiment, the movement of a person for 5 minutes is recorded in one OD table, but in reality, the values ​​of most of the fields in the OD table 300 are 0. This is because there is a limit to the number of combinations of the departure floor and the destination floor where the movement of the person actually occurs in 5 minutes. Therefore, the storage area used can be reduced by storing the non-zero values ​​in the OD table 300 and not storing the zero values.
[0046]
　However, especially when the elevator analysis system 100 is incorporated into the control panel of the elevator 140, the upper limit of the number of occurrences of the non-zero value is determined in order to determine the size of the array to be reserved in the storage area for storing the non-zero value. Need to know in advance. Here, since the non-zero values ​​in the OD table 300 correspond to the actual movement of the basket between the floors, the number of occurrences of the non-zero values ​​is the number of occurrences of the non-zero values ​​between the floors that can actually occur in 5 minutes. Do not exceed the maximum number of movements of the basket. In this embodiment, this is used to calculate the upper limit of the number of occurrences of non-zero values, that is, the size of the array to be secured.
[0047]
　Specifically, the number of occurrences of non-zero values ​​in the OD table 300 is calculated by the following equation (1).
[0048]
[Number 1]

[0049]
　Here, the observation unit time is 5 minutes in the above example. This length of 5 minutes can be said to be the window width for collecting statistics on the flow of people, and a time longer or shorter than 5 minutes may be adopted. In general, the demand pattern of elevators differs depending on the time zone. For example, in the case of an elevator in an office building, it is considered that the demand pattern differs greatly between the time zone immediately before the start time and the time zone immediately after the start time. In order to generate a destination floor prediction model that reflects such changes in demand patterns, it is desirable to set an observation unit time of an appropriate length. Generally, about 5 minutes is considered appropriate.
[0050]
　The minimum time required to move between floors is the minimum time required for the basket to move from the departure floor to the destination floor, and is usually the movement time when the departure floor and the destination floor are adjacent to each other. Since this includes the door opening / closing time, acceleration time, and deceleration time, it is generally about 10 seconds or more.
[0051]
　The number of elevators to be delivered is the number when a plurality of elevators are installed facing one elevator hall of one building.
[0052]
　For example, assuming that 10 elevators are delivered to the 32nd floor, the observation unit time is 5 minutes, and the minimum time required for movement between floors is 10 seconds, the observation unit time is divided by the minimum time required for movement between floors. The value is 30 times. This is the upper limit of the number of movements per elevator for 5 minutes. Multiplying this by the number of elevators delivered gives 300 times. That is, it can be seen that an array size of at most 300 is sufficient before the elevator is actually delivered.
[0053]
　The size of the array thus obtained, the number of bits required to record the number of people in each field, the step size of the time series data (for example, 1 minute), and the period required for training data (for example, 1 month). The size of the storage area to be secured in the local boarding / alighting database 120 is specified based on the above. Thereby, in particular, the capacity of the storage device to be secured when the elevator analysis system 100 is mounted on the control panel of the elevator 140 can be known in advance based on the property information of the elevator.
[0054]
　The calculation of the size of the array and the storage capacity to be secured may be performed, for example, by the processor 204 of the computer system having the configuration shown in FIG. 2 according to the program stored in the main storage device 205. This makes it possible to design an elevator analysis system 100 with a storage device of calculated capacity.
[0055]
　FIG. 5 is an explanatory diagram of a table that stores the non-zero values ​​of the explanatory variables of the destination floor prediction held by the elevator analysis system 100 of the embodiment of the present invention.
[0056]
　Table 500 shown in FIG. 5 is an example of a sparse matrix that stores only non-zero values ​​in the time series data 400 of FIG. Here, as an example, a table for storing the value of "5 minutes before" at the time "8:00" in the time series data 400 of FIG. 4 is shown. Assuming that the time series data 400 of FIG. 4 relates to an elevator on the 32nd floor, it includes 992 fields corresponding to the times "8:00" and "5 minutes ago". However, as mentioned above, the number of fields in which non-zeros are stored is at most 300.
[0057]
　For example, in the table 500 of FIG. 5, the array index 501 and the array index 503 identify the elements of the array stored in the table and correspond to each other. The explanatory variable value 502 is an explanatory variable value (that is, a non-zero value) extracted from the time series data 400. The index 504 corresponding to the explanatory variable is a value indicating from which field of the time series data 400 the non-zero explanatory variable is extracted. In the example of FIG. 5, the explanatory variable extracted from the field of “1 → 2” (that is, the departure floor is the first floor and the destination floor is the second floor) of the time series data 400 of FIG. 4 has an index corresponding to the explanatory variable. "0" is given as 504. The explanatory variable extracted from the field of "1 → 3" (that is, the departure floor is the first floor and the destination floor is the third floor) of the time series data 400 in FIG. 4 has "1" as the index 504 corresponding to the explanatory variable. Granted.
[0058]
　In the example of FIG. 5, "3" is stored as the value 502 of the explanatory variable corresponding to the value "0" of the index 501 of the array. This is an explanatory variable extracted from the “1 → 2” field of the time series data 400 in FIG. Then, "0" for identifying the field is stored as the index value 502 corresponding to the explanatory variable corresponding to the value "0" of the index 503 of the array.
[0059]
　Since the value of the explanatory variable in the field of "1 → 3" of the time series data 400 of FIG. 4 is "0", this is not stored in the table 500 of FIG. Therefore, "1" for identifying the field is not stored in the index 504 corresponding to the explanatory variable.
[0060]
　FIG. 6 is a flowchart showing a process in which the elevator analysis system 100 of the embodiment of the present invention stores an OD table as a sparse matrix.
[0061]
　This process is executed, for example, by the boarding / alighting number calculation unit 111.
[0062]
　In this example, the boarding / alighting number calculation unit 111 generates an OD table 300 based on the locally acquired local boarding / alighting data, temporarily stores it in the local boarding / alighting database 120, and once the daily OD table 300 is accumulated, they are stored. Is stored as a sparse matrix. However, one day is just an example, and the OD table 300 for a period other than one day (for example, one hour), which is sufficiently shorter than the training data accumulation period (for example, 30 days) for generating a destination floor prediction model. May be executed as a target.
[0063]
　When the process is started, the boarding / alighting number calculation unit 111 secures a storage area for the sparse matrix in the local boarding / alighting database 120 (step 601). At this time, the required storage area is calculated based on the size of the array calculated by the above equation (1).
[0064]
　Next, the boarding / alighting number calculation unit 111 reads the OD table 300 for one day into the memory (step 602).
[0065]
　Next, the boarding / alighting number calculation unit 111 records the read OD table 300 for one day as a sparse matrix (for example, table 500 in FIG. 5) in the storage area secured in step 601. This compresses the data stored in the storage device.
[0066]
　Next, the boarding / alighting number calculation unit 111 determines whether the sparse matrix for 30 days has been recorded (step 604). Here, 30 days (that is, one month) is an example of a learning data accumulation period for generating a destination floor prediction model. If 30 days' worth of sparse matrices have not been accumulated (step 604: No), steps 602 and subsequent steps are repeated. If 30 days' worth of sparse matrices have been accumulated (step 604: Yes), the process ends.
[0067]
　Then, for example, the destination floor prediction model generation unit 132 can generate a destination floor prediction model based on the OD table recorded as a sparse matrix. However, this is an example of a model for predicting the demand of the elevator 140, and the elevator analyzer may generate another model, for example, a model for predicting the number of occurrences, based on the recorded OD table.
[0068]
　The present invention is not limited to the above-described embodiment, and includes various modifications. For example, the above-mentioned examples have been described in detail for a better understanding of the present invention, and are not necessarily limited to those having all the configurations of the description. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.
[0069]
　Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in non-volatile semiconductor memories, hard disk drives, storage devices such as SSDs (Solid State Drives), or computer-readable non-readable devices such as IC cards, SD cards, and DVDs. It can be stored in a temporary data storage medium.
[0070]
　In addition, the control lines and information lines indicate what is considered necessary for explanation, and do not necessarily indicate all the control lines and information lines in the product. In practice, it can be considered that almost all configurations are interconnected.
The scope of the claims
[Claim 1]
　An elevator analysis system comprising a processor and a storage device connected to the processor, wherein the storage device has a storage area for 　Origin
　-Destination information for recording the movement of a person between floors.
-The size of the storage area of ​​the Destination information is determined based on the maximum number of non-zero values ​​of the Origin-Destination information calculated based on the minimum time required to move between the floors of the elevator. Elevator analysis system.
[Claim 2]
　In the elevator analysis system according to claim 1,
　the maximum number of non-zero values ​​of the Origin-Destination information is the length of unit time for observing the movement of a person between floors of one elevator. Calculated by multiplying the upper limit of the number of elevator movements per unit time obtained by dividing by the minimum time required for movement between floors by the number of installed elevators. Elevator analysis system characterized by that.
[Claim 3]
　The elevator analysis system according to claim 2,
　wherein the size of the storage area of ​​the Origin-Destination information is at least a period required as learning data for generating a model for predicting the demand of the elevator. -An elevator analysis system characterized in that the size is such that the maximum number of non-zero values ​​of the Destation information can be stored.
[Claim 4]
　The elevator analysis system according to claim 3,
　wherein the processor
　secures a storage area of ​​the Origin-Destination information of a determined size in the storage device and
　generates a model for predicting the demand of the elevator. A sparse matrix containing a non-zero value is generated from the Origin-Destination information containing a zero value for a period shorter than the period required as training data for the purpose, and stored in the storage area as data of the Origin-Destination information. After the
　sparse matrix for a period required as training data for generating a model for predicting the demand of the elevator is stored in the storage area, based on the data of the Origin-Destination information stored in the storage area. , An elevator analysis system characterized by generating a model that predicts the demand for the elevator.
[Claim 5]
　The elevator analysis system according to claim 4,
　wherein the model for predicting the demand for the elevator is a model for predicting the destination floor of a person who uses the elevator.
[Claim 6]
　A method of designing an elevator analysis system executed by a computer system having a processor and a storage device connected to the processor,
　wherein the elevator analysis system records Origin-Destination information for recording the movement of a person between floors. The
　design method comprises the Origin-Destination, wherein the processor calculates the size of the storage area of ​​the Origin-Destination information based on the minimum time required to move between the floors of the elevator. A design method comprising a procedure for determining based on the maximum number of non-zero values ​​of information.