Elevator information providing device, elevator information providing method, and learning device

Abstract

The objective of the present invention is to obtain an elevator information providing device enabling a user of the elevator information providing device to consider elevator specifications on the basis of a standard model.　This elevator information providing device comprises: a building data acquisition unit (10) that acquires data relating to a building; and an inference unit (11) that uses a learned model for inferring, from data relating to a building, a standard model of an elevator suitable for installation in the building to infer a standard model of an elevator from the building data input from the building data acquisition unit (10) and outputs data relating to the inferred standard model of the elevator.

Description

Elevator information providing device, elevator information providing method, and learning device

[0001] The present invention relates to an elevator information providing device, an elevator information providing method, and a learning device.

[0002] An architectural designer who is ordering an elevator uses the elevator information providing device to order an elevator that meets his or her requirements.

[0003] An architectural designer inputs the building's purpose, the number of floors, the estimated resident population per floor, and the required specifications for the elevator into the elevator information providing device, and then orders an elevator (see, for example, Patent Document 1).

[0004] Japanese Patent Application Laid-Open No. 2002-230253

[0005] Such elevator information devices do not allow users to consider elevator specifications based on standard models. It is desirable for elevator manufacturers to guide users to consider elevator specifications based on standard models, taking into account factors such as the workload during the manufacturing process.

[0006] The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide an elevator information providing device that allows users of the elevator information providing device to consider elevator specifications based on standard models.

[0007] The elevator information providing device of the present invention includes a building data acquisition unit that acquires building data, and an inference unit that infers a standard elevator model from the building data input from the building data acquisition unit using a trained model for inferring a standard elevator model suitable for installation in the building from the building data, and outputs data on the inferred standard elevator model.

[0008] According to the elevator information providing device of the present invention, users of the elevator information providing device can consider elevator specifications based on standard models, because the inference unit infers the standard elevator model from building data and outputs data on the inferred standard elevator model.

[0009] FIG. 1 is a diagram illustrating an application example of an elevator information providing device according to a first embodiment of the present invention. FIG. 2 is a configuration diagram of an elevator information providing device according to a first embodiment of the present invention. FIG. 3 is an example of a cross-sectional view of an elevator seen from above. FIG. 4 is a flowchart illustrating an elevator information providing method using the elevator information providing device according to the first embodiment of the present invention. FIG. 4 is a configuration diagram of a learning device that generates a trained model used by the elevator information providing device according to the first embodiment of the present invention. FIG. 5 is a flowchart related to learning processing of a learning device that generates a trained model used by the elevator information providing device according to the first embodiment of the present invention. FIG. 5 is a diagram illustrating an example of a learning method performed by a learning device that generates a trained model used by the elevator information providing device according to the first embodiment of the present invention. FIG. 6 is a configuration diagram of an elevator information providing device according to a second embodiment of the present invention. FIG. 7 is a configuration diagram of a learning device that generates a trained model used by the elevator information providing device according to the second embodiment of the present invention. FIG. 8 is a configuration diagram of an elevator information providing device according to a third embodiment of the present invention. FIG. 9 is a configuration diagram of an elevator information providing device according to a fourth embodiment of the present invention.

[0010] First Embodiment First, an application example of the elevator information device 100 according to the first embodiment of the present invention will be described. The elevator information device 100 according to this embodiment assumes that the user is an architectural designer, but the user is not limited to this and may be anyone who is considering purchasing or ordering an elevator. Note that, hereinafter, when simply referred to as a user, it refers to a user of the elevator information device 100 who is considering purchasing or ordering an elevator, and elevator users will be referred to as passengers.

[0011] The elevator information device 100 according to this embodiment constitutes a part of a website that provides elevator information. That is, users of the elevator information device 100 are users of the website created by the elevator information device 100. The website created by the elevator information device 100 provides elevator information when a user inputs data on the building in which the elevator is to be installed and data on required specifications for the elevator.

[0012] FIG. 1 is a diagram illustrating an application example of an elevator information device 100 according to a first embodiment of the present invention. The elevator information device 100 according to this embodiment provides elevator information to a user via a server 102 and an internet line 103. FIG. 1 will be described along with the flow of data. As shown in FIG. 1, a user's personal computer 104 is connected to the server 102 via the internet line 103. Building data entered by the user into the personal computer 104 is input to the elevator information device 100 via the server 102. The elevator information device 100 uses a trained model stored in a trained model storage device 101 to infer a standard elevator model from the building data input via the server 102 and outputs the data of the inferred standard elevator model.

[0013] The data output from elevator information device 100 is input to the user's personal computer 104 via server 102, and the standard elevator model is displayed on personal computer 104. In other words, the website created by elevator information device 100 is a website that displays standard elevator models when a user inputs building data, and recommends standard elevator models suitable for installation in a building when a user inputs building data.

[0014] As described above, when a user of the elevator information providing device 100 inputs building data into the personal computer 104, the standard elevator models are displayed on the personal computer 104, and the user can begin to consider the elevator specifications based on the displayed standard elevator models.

[0015] Next, the configuration of the elevator information providing device 100 according to the first embodiment of the present invention will be described. FIG. 2 is a configuration diagram of the elevator information providing device 100 according to the first embodiment of the present invention. As shown in FIG. 2, the elevator information providing device 100 according to the present embodiment includes a building data acquiring unit 10 that acquires building data, and an inference unit 11 that infers a standard elevator model from the building data input from the building data acquiring unit 10 using a trained model for inferring a standard elevator model suitable for installation in the building from the building data, and outputs data of the inferred standard elevator model. The trained model is stored in a trained model storage device 101.

[0016] The building data acquiring unit 10 acquires, via the server 102, building data that a user of the elevator information providing device 100 has input into the user's personal computer 104. For example, if the user is an architectural designer who is about to build a building, the user inputs data of the building to be built into the personal computer 104. The data of the building to be built that has been input into the personal computer 104 is acquired by the building data acquiring unit 10 of the elevator information providing device 100 via the server 102.

[0017] The building data includes, for example, data on the area where the building will be constructed, data on the type of building, data on the number of floors in the building, data on the number of people who will use the elevator, data on the size of the building, data on whether the building needs welfare support, etc. The website created by the elevator information providing device 100 has fields for inputting the area where the building will be constructed, data on the type of building, data on the number of floors in the building, data on the number of people who will use the elevator, data on the size of the building, data on whether the building needs welfare support, etc., and the building data acquiring unit 10 acquires the data entered in these fields.

[0018] The inference unit 11 uses the trained model stored in the trained model storage device 101 to infer a standard elevator model from the building data input from the building data acquisition unit 10, and outputs the data of the inferred standard elevator model. The data of the standard elevator model output by the inference unit 11 is input to the user's personal computer 104, and the standard elevator model is displayed on the personal computer 104.

[0019] The elevator information providing device 100 is realized by, for example, but not limited to, a CPU (Central Processing Unit). The trained model storage device 101 is realized by, for example, but not limited to, a semiconductor memory such as a ROM (Read Only Memory), a RAM (Random Access Memory), a HDD (Hard Disk Drive), or a flash memory.

[0020] Next, a standard elevator model inferred by the inference unit 11 of the elevator information providing device 100 according to this embodiment will be described with reference to FIG. 3 . FIG. 3 is an example of a cross-sectional view of an elevator viewed from above, generally referred to as a hoistway plan view. The elevator has a car and moves up and down the hoistway. The hoistway member 1 forms the hoistway and a doorway opening. The hoistway member 1 is made separately from the building structure and has a height corresponding to the number of floors of the building. The hoistway is a space formed by the hoistway member 1 and is the space surrounded by a dotted line in FIG. 3 . The doorway opening is an opening formed by the hoistway member 1, and a part of the landing is formed in the doorway opening. Elevator users get on and off the elevator from a landing formed by the landing member 3.

[0021] The elevator car has an inner wall 2a and an outer wall 2b. The elevator shown in Figure 3 has two car doors 4, two hall doors 5, and two hall door pockets 6. The hall doors 5 open and close by sliding inside the hall door pockets 6. The car doors 4 open and close by sliding between the inner wall 2a and the outer wall 2b. The inner wall 2a of the car forms a car space and a car opening. The car space is the space where passengers stay when they board the elevator, and is the space surrounded by a dashed line in Figure 3. The car doors 4 are installed at the ends of the car opening.

[0022] Although the elevator shown in FIG. 3 has two entrances, some elevators have one entrance. In this embodiment, the elevator is not limited to one having two entrances, and may have one entrance. An elevator with one entrance includes one car door 4, one hall door 5, and one hall door pocket 6. In the hoistway plan, when an elevator has two entrances, the car's inner wall 2a is divided into two parts. However, when an elevator has one entrance, the car's inner wall 2a is formed integrally, resulting in a single wall. Furthermore, in the hoistway plan, when an elevator has two entrances, the hoistway member 1 is divided into two parts. However, when an elevator has one entrance, the hoistway member 1 is formed integrally, resulting in a single wall. The design of other components can be appropriately modified depending on the number of entrances the elevator has.

[0023] As shown in FIG. 3 , the interior dimensions of the hoistway are represented by X×Y, and the interior dimensions of the car are represented by A×B. The width through which elevator passengers can pass is represented by the width J of the car entrance. X is the distance within the hoistway among the distances between the inner walls of the hoistway member 1 in the hoistway plane, which is the distance parallel to the width J of the car entrance. Y is the distance within the hoistway among the distances between the inner walls of the hoistway member 1 in the hoistway plane, which is the distance perpendicular to the width J of the car entrance. In other words, X and Y are orthogonal. A is the distance within the car space among the distances between the inner walls 2a of the car in the hoistway plane, which is the distance parallel to the width J of the car entrance. B is the distance within the car space among the distances between the inner walls 2a of the car in the hoistway plane, which is the distance perpendicular to the width J of the car entrance. In other words, A and B are orthogonal.

[0024] In this embodiment, a standard model of elevator refers to a model that has the same car inside dimensions A x B, car entrance width J, and load capacity, but has a lineup with different specifications. In other words, if the elevator shown in Figure 3 is a standard model, there is a model that has the same car inside dimensions A x B, car entrance width J, and load capacity, but has different specifications from the elevator shown in Figure 3. For example, if there is an elevator that has the same car inside dimensions A x B, car entrance width J, and load capacity as the elevator shown in Figure 3, but has a different conveying speed, it would be a standard model of elevator.

[0025] Next, an elevator information providing method using the elevator information providing device 100 according to the present embodiment will be described. Fig. 4 is a flowchart showing the elevator information providing method using the elevator information providing device 100 according to the first embodiment of the present invention. As shown in Fig. 4, the elevator information providing method using the elevator information providing device 100 includes an acquisition step S1 of acquiring building data, an inference step S2 of inferring a standard elevator model from the building data acquired in the acquisition step S1 and outputting the data, a provision step S3 of providing the outputted standard elevator model data to a user, and a display step S4 of displaying the provided standard elevator model data on the user's personal computer 104.

[0026] Acquisition step S1 is a step of acquiring building data. In acquisition step S1, building data acquisition unit 10 acquires, via server 102, building data entered into personal computer 104 by a user of elevator information providing device 100. Then, building data acquisition unit 10 outputs the acquired building data to inference unit 11. After completion of acquisition step S1, the elevator information providing method using elevator information providing device 100 in this embodiment proceeds to inference step S2.

[0027] Inference step S2 is a step of inferring a standard elevator model from the building data acquired in acquisition step S1 using a trained model for inferring a standard elevator model suitable for installation in a building from the building data, and outputting data on the inferred standard elevator model. In inference step S2, first, the inference unit 11 acquires the trained model from the trained model storage device 101. Then, the building data output from the building data acquisition unit 10 is input into the trained model acquired by the inference unit 11, and the inference unit 11 infers a standard elevator model suitable for installation in the building. After inferring the standard elevator model, the inference unit 11 outputs the data to the server 102. After completing inference step S2, the elevator information provision method using the elevator information provision device 100 in this embodiment proceeds to provision step S3.

[0028] The provision step S3 is a step of providing the data on the standard elevator model output from the inference unit 11 to the user. In the provision step S3, the server 102 provides the data on the standard elevator model output by the inference unit 11 to the user via the Internet line 103. That is, in the provision step S3, the data on the standard elevator model output from the elevator information providing device 100 is provided to the user via the server 102 and the Internet line 103. After the provision step S3 is completed, the elevator information providing method using the elevator information providing device 100 in this embodiment proceeds to the display step S4.

[0029] Display step S4 is a step of displaying the provided data on the standard elevator model on the user's personal computer 104. In display step S4, the user's personal computer 104 displays the data on the standard elevator model provided from the server 102 via the Internet line 103. In this embodiment, the method of displaying the data on the standard elevator model is not particularly limited. For example, an external view of the standard elevator model may be displayed, or the product number of the standard elevator model may be displayed. It is sufficient if the display allows the user to determine which elevator to select for installation.

[0030] The standard elevator models are displayed on the personal computer 104, and the user can begin to consider the specifications of the elevator to be installed in the building based on the displayed standard elevator models. In the display step S4 of the elevator information providing method using the elevator information providing device 100 in this embodiment, the processing described below continues, but is not limited to this, and the display step S4 may be completed here.

[0031] In display step S4, when personal computer 104 displays the data of the standard elevator model, the user selects it on personal computer 104. When the user selects a standard elevator model displayed on personal computer 104, the specification data of that standard elevator model is displayed on personal computer 104. In other words, when the user selects a standard elevator model displayed on the website, the specification data of that standard elevator model is reflected in the contents of the elevator specification items on the website. This makes it easy for the user to customize elevator specifications based on the standard elevator model, and allows the user to easily start considering elevator specifications based on the standard elevator model. The elevator information providing method using elevator information providing device 100 in this embodiment ends when display step S4 is completed.

[0032] In this embodiment, the inference unit 11 may infer one type of standard elevator model in inference step S2, or two or more types. When the inference unit 11 infers one type of standard elevator model in inference step S2, the inference unit 11 infers the standard elevator model that is most suitable for installation in a building. When the inference unit 11 infers two or more types of standard elevator models in inference step S2, the inference unit 11 may infer the standard elevator models that are suitable for installation in a building by assigning a recommendation order to them, or may infer them without assigning a recommendation order to them. When the inference unit 11 infers the standard elevator models that are suitable for installation in a building by assigning a recommendation order to them, the inference unit 11 outputs data on the standard elevator models together with the recommendation order. When the inference unit 11 infers the standard elevator models that are suitable for installation in a building without assigning a recommendation order to them, only data on two or more types of standard elevator models is output.

[0033] In this embodiment, the method of displaying the data on standard elevator models displayed on the personal computer 104 is not particularly limited, and so, for example, if the inference unit 11 has inferred that two or more types of standard elevator models suitable for installation in a building have been ranked in order of recommendation, the model with the higher recommendation order may be displayed larger than the model with the lower recommendation order, or the model with the higher recommendation order may be displayed as an external view and the model with the lower recommendation order may be displayed as a product number.In addition, if the inference unit 11 has inferred two or more types of standard elevator models suitable for installation in a building without ranking them in order of recommendation, the external views may be displayed side by side in the same size to make it easier for the user to select an elevator to use as the basis for their consideration.

[0034] Next, a learning device 600 that generates a trained model used by the elevator information providing device 100 according to the present embodiment will be described. FIG. 5 is a configuration diagram of the learning device 600 that generates a trained model used by the elevator information providing device 100 according to the first embodiment of the present invention. As shown in FIG. 5, the learning device 600 includes a training data acquiring unit 60 and a model generating unit 61. The training data acquiring unit 60 acquires training data including building data and elevator specification data suitable for installation in the building. The model generating unit 61 uses the training data to generate a trained model for inferring a standard elevator model from the building data.

[0035] The learning device 600 is realized by, for example, a CPU, but is not limited to this.

[0036] The learning data acquisition unit 60 acquires building data and elevator specification data suitable for installation in the building as learning data. The learning data is input to the learning data acquisition unit 60 by elevator manufacturers, elevator distributors, etc. The learning data is data in which building data and elevator specification data suitable for installation in the building are associated with each other.

[0037] The model generation unit 61 learns the standard elevator model in accordance with the learning data created based on a combination of the building data and elevator specification data suitable for installation in the building output from the learning data acquisition unit 60. In other words, it generates a learned model that infers the optimal standard elevator model from the building data and the elevator specification data suitable for installation in the building.

[0038] Next, a learning procedure performed by the learning device 600 for generating a trained model used by the elevator information providing device 100 according to the present embodiment will be described. Fig. 6 is a flowchart showing the learning procedure performed by the learning device 600 for generating a trained model used by the elevator information providing device 100 according to the first embodiment of the present invention. As shown in Fig. 6, the learning device 600 includes a first learning step T1 for acquiring data, a second learning step T2 for performing a learning process, and a third learning step T3 for storing the trained model.

[0039] The first learning step T1 is a step of acquiring building data and elevator specification data suitable for installation in the building. In the first learning step T1, the learning data acquisition unit 60 acquires the building data and elevator specification data suitable for installation in the building. The learning data acquisition unit 60 may acquire the building data and elevator specification data suitable for installation in the building simultaneously, or may acquire the building data and elevator specification data suitable for installation in the building at different times. It is sufficient that the learning data acquisition unit 60 acquires the building data and elevator specification data suitable for installation in the building in association with each other. In this embodiment, the learning procedure performed by the learning device 600 that generates a trained model used by the elevator information provision device 100 proceeds to the second learning step T2 after completing the first learning step T1.

[0040] The second learning step T2 is a step of generating a trained model according to training data created based on a combination of the building data acquired in the second learning step T2 and elevator specification data suitable for installation in the building. In the second learning step T2, the model generation unit 61 first learns standard elevator models according to training data created based on a combination of the building data and elevator specification data suitable for installation in the building output from the training data acquisition unit 60. The model generation unit 61 then generates a trained model. In other words, the model generation unit 61 learns standard elevator models through so-called supervised learning to generate a trained model. After completing the second learning step T2, the learning procedure performed by the learning device 600 for generating a trained model used by the elevator information provision device 100 in this embodiment proceeds to a third learning step T3.

[0041] The third learning step T3 is a step of storing the trained model generated in the third learning step T3. In the third learning step T3, the trained model storage device 101 stores the trained model generated by the model generation unit 61 in the second learning step T2. The learning procedure performed by the learning device 600 that generates the trained model used by the elevator information provision device 100 in this embodiment ends when the third learning step T3 is completed.

[0042] 7 is a diagram illustrating an example of a learning method performed by the learning device 600 that generates a trained model used by the elevator information providing device 100 according to the first embodiment of the present invention. The learning algorithm used by the model generating unit 61 can be a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where a neural network is applied will be described.

[0043] The model generation unit 61 learns standard elevator models, for example, using so-called supervised learning in accordance with a neural network model. Here, supervised learning refers to a technique in which a learning device is provided with pairs of input and result (label) data, and the learning device learns the features of the learning data and infers the result from the input. The neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0044] In a three-layer neural network as shown in Figure 7, when multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result changes depending on the values ​​of weight W1 and weight W2.

[0045] In this embodiment, the neural network learns standard elevator models by so-called supervised learning in accordance with learning data created based on a combination of building data and elevator specification data suitable for installation in the building, acquired by the learning data acquisition unit 60. That is, the neural network learns by inputting building data into the input layer and adjusting the weights W1 and W2 so that the results output from the output layer approach the elevator specification data suitable for installation in the building.

[0046] The model generation unit 61 generates and outputs a trained model by performing the above-described learning. The output trained model is stored in the trained model storage device 101.

[0047] Next, a specific example of training data necessary for training by the model generation unit 61 that generates a trained model used by the elevator information providing device 100 according to this embodiment will be described. In this embodiment, multiple pieces of training data are acquired by the training data acquisition unit 60. The training data are pairs of input data and result (label) data, and each pair will be described below.

[0048] As one specific example, the learning data acquisition unit 60 acquires data on the area where a building is to be constructed and data on elevator specifications that comply with the laws of that area. The data on the area where a building is to be constructed is acquired as building data, and the data on elevator specifications that comply with the laws of that area is acquired as data on elevator specifications that are suitable for installation in the building. The data on the area where a building is to be constructed and the data on elevator specifications that comply with the laws of that area are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models.

[0049] There are multiple pieces of data on the area where the building will be constructed, and the learning data acquisition unit 60 acquires elevator specification data that conforms to the laws of each area. The data on the area where the building will be constructed is, for example, the name of a prefecture or a city, ward, town, or village, but is not limited to this in the present embodiment. When the elevator information providing device 100 according to the present embodiment is used outside Japan, the way the areas are divided is appropriately changed to the way local governments are divided in that country. Furthermore, the laws of that area are, for example, local ordinances.

[0050] As another example, the learning data acquiring unit 60 acquires data on the area where a building is to be constructed and data on the specifications of elevators previously used in that area. The data on the area where a building is to be constructed is acquired as building data, and the data on the specifications of elevators previously used in that area is acquired as data on elevator specifications suitable for installation in the building. The data on the area where a building is to be constructed and the data on the specifications of elevators previously used in that area are acquired in association with each other, and are used by the model generating unit 61 to learn standard elevator models. Note that there are multiple pieces of data on the area where a building is to be constructed, and the learning data acquiring unit 60 acquires data on the specifications of elevators previously used in each area. The data on the area where a building is to be constructed is, for example, the name of a prefecture or a city, ward, town, or village, but as described above, the present embodiment is not limited to this.

[0051] As another example, the learning data acquisition unit 60 acquires data on building types and elevator specification data suitable for the building type. The building type data is acquired as building data, and the elevator specification data suitable for the building type is acquired as elevator specification data suitable for installation in the building. The building type data and the elevator specification data suitable for the building type are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models. The building type data is the name of the building's purpose, such as office, residence, hospital, school, etc.

[0052] As another example, the learning data acquisition unit 60 acquires data on building types and data on elevator specifications previously used in that type. The building type data is acquired as building data, and the elevator specification data previously used in that type is acquired as elevator specification data suitable for installation in the building. The building type data and the elevator specification data previously used in that type are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models.

[0053] As another example, the learning data acquisition unit 60 acquires data on the number of floors of a building and data on elevator specifications that meet the speed required for that building. The data on the number of floors of a building is acquired as building data, and the data on elevator specifications that meet the speed required for that building is acquired as data on elevator specifications that are suitable for installation in the building. The data on the number of floors of a building and the data on elevator specifications that meet the speed required for that building are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models. Note that, in general, buildings with more floors require faster elevator speeds than buildings with fewer floors.

[0054] As another example, the learning data acquisition unit 60 acquires data on the number of people using an elevator and data on elevator specifications that satisfy a required capacity. The data on the number of people using an elevator is acquired as building data, and the data on elevator specifications that satisfy a required capacity is acquired as data on elevator specifications that are suitable for installation in a building. The data on the number of people using an elevator and the data on elevator specifications that satisfy a required capacity are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models.

[0055] The data on the number of people using an elevator may be a single piece of numerical data, such as data on the estimated resident population of the entire building, or may be composed of two or more pieces of numerical data. For example, the data on the number of people using an elevator may be composed of data on the population of the building's non-reference floor and data on the population of the building's reference floor. In this embodiment, the reference floor is the floor where the building's main entrance is located, or the floor where the entrance is located. The input fields of the website created by the elevator information providing device 100 include fields for inputting the population of the building's non-reference floor and the population of the building's reference floor so that the building data acquisition unit 10 can acquire data on the number of people using an elevator. The model generation unit 61 is trained to generate a trained model that can infer a standard elevator model from the data entered by a user in the fields for inputting the population of the building's non-reference floor and the population of the building's reference floor.

[0056] In the above example, when the data on the number of people using an elevator is composed of two or more pieces of numerical data, it is composed of, for example, data on the population of a building other than the base floor and data on the population of the base floor of the building, but this is not limited to this. For example, the data on the number of people using an elevator may be composed of data on the estimated resident population per floor and data on the number of floors of the building.

[0057] Alternatively, the data on the number of people using the elevator may be associated with data on the number of elevators and the desired size of the elevators desired by the user of the elevator information device 100. This is because the input fields of the website created by the elevator information device 100 include fields for inputting the desired number of elevators and the desired size of the elevators. When the learning data acquisition unit 60 associates and acquires the data on the number of people using the elevator with data on elevator specifications that satisfy the required capacity, the learning data acquisition unit 60 associates and acquires data that combines the data on the number of elevators and the desired size of the elevators desired by the user of the elevator information device 100 with the data on the number of people using the elevator. In other words, the model generation unit 61 may perform learning using learning data that is associated with the data that combines the data on the number of elevators and the desired size of the elevators desired by the user of the elevator information device 100, and that is a set of data on the number of people using the elevator and data on elevator specifications that satisfy the required capacity.

[0058] As another example, the learning data acquisition unit 60 acquires data on whether a building requires welfare facilities, elevator specification data for which the width of the car's entrance is wide enough for a wheelchair to pass through, and elevator specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair. The data on whether a building requires welfare facilities is acquired as building data, and the specification data for which the width of the car's entrance is wide enough for a wheelchair to pass through and the specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair are acquired as specification data for elevators suitable for installation in the building. The data on whether a building requires welfare facilities, the specification data for which the width of the car's entrance is wide enough for a wheelchair to pass through and the specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models. At this time, if the building requires welfare facilities, the model generation unit 61 learns to output a standard elevator model in which the width of the car's entrance is wide enough for a wheelchair to pass through and the car's interior dimensions are large enough to accommodate a wheelchair.

[0059] The input fields of the website created by the elevator information providing device 100 include a field for inputting whether or not a building requires welfare facilities, so that the building data acquisition unit 10 can acquire data on whether or not the building requires welfare facilities. The model generation unit 61 performs learning to generate a trained model that can infer a standard elevator model from data input by a user into the field for inputting whether or not the building requires welfare facilities. The field for inputting whether or not the building requires welfare facilities may be a field that directly asks whether or not welfare facilities are required, or may be a field that indirectly asks whether or not welfare facilities are required, such as whether or not the building is subject to the Barrier-Free Act.

[0060] As another example, the learning data acquisition unit 60 acquires data on the type of building, elevator specification data for which the width of the car entrance is wide enough for a wheelchair to pass through, and elevator specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair. The data on the type of building is acquired as building data, and the specification data for which the width of the car entrance is wide enough for a wheelchair to pass through and the specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair are acquired as specification data for elevators suitable for installation in a building. The data on the type of building, the specification data for which the width of the car entrance is wide enough for a wheelchair to pass through, and the specification data for which the interior dimensions of the car are large enough to accommodate a wheelchair are acquired in association with each other, and are used by the model generation unit 61 to learn standard elevator models. This learning is performed because some types of buildings require welfare facilities. For example, if the type of building is a hospital, the building requires welfare facilities.

[0061] In the above example, the model generation unit 61 learned using learning data that is a set of data on the building type, elevator specification data in which the width of the car entrance is wide enough for a wheelchair to pass through, and elevator specification data in which the interior dimensions of the car are large enough to fit a wheelchair, but this is not limited to this. For example, the model generation unit 61 may associate data on the building type with data on whether or not the building requires welfare assistance, and learn using learning data in which the data on whether or not the building requires welfare assistance is associated with the data on the building type, and elevator specification data in which the width of the car entrance is wide enough for a wheelchair to pass through and elevator specification data in which the interior dimensions of the car are large enough to fit a wheelchair.

[0062] As another example, the learning data acquisition unit 60 acquires building size data, elevator specification data indicating that the width of the car's entrance is wide enough for a wheelchair to pass through, and elevator specification data indicating that the car's interior dimensions are large enough to accommodate a wheelchair. The building size data is acquired as building data, and the elevator specification data indicating that the width of the car's entrance is wide enough for a wheelchair to pass through and the elevator specification data indicating that the car's interior dimensions are large enough to accommodate a wheelchair are acquired as elevator specification data suitable for installation in a building. The building size data, the elevator specification data indicating that the width of the car's entrance is wide enough for a wheelchair to pass through, and the elevator specification data indicating that the car's interior dimensions are large enough to accommodate a wheelchair are acquired in association with each other, and the model generation unit 61 uses these data to learn standard elevator models. This learning is performed because larger buildings require welfare facilities. The building size is, for example, the total floor area, but may also be a combination of the number of floors in the building and the area of ​​each floor.

[0063] In the above example, the model generation unit 61 learned using learning data that is a set of building scale data, elevator specification data in which the width of the car entrance is wide enough for a wheelchair to pass through, and elevator specification data in which the interior dimensions of the car are large enough to fit a wheelchair, but this is not limited to this. For example, the model generation unit 61 may associate building scale data with data on whether or not a building requires welfare facilities, and learn using learning data in which the data on whether or not a building requires welfare facilities, associated with the building scale data, is paired with elevator specification data in which the width of the car entrance is wide enough for a wheelchair to pass through, and elevator specification data in which the interior dimensions of the car are large enough to fit a wheelchair.

[0064] As another example, the learning data acquisition unit 60 acquires data on whether a building is a rental building and data on elevator specifications that meet the required capacity. The data on whether a building is a rental building is acquired as building data, and the data on elevator specifications that meet the required capacity is acquired as data on elevator specifications suitable for installation in the building. The data on whether a building is a rental building and the data on elevator specifications that meet the required capacity are acquired in association with each other and used by the model generation unit 61 to learn a standard elevator model. In this case, if the building is a rental building, the model generation unit 61 learns to output a standard elevator model with a larger capacity than if the building is not a rental building. In other words, if the building is a rental building, the model generation unit 61 generates a trained model so that the inference unit 11 infers a standard elevator model with a larger capacity than if the building is not a rental building.

[0065] The data on whether a building is a rental building is associated with the data on the type of building. That is, the learning data acquisition unit 60 acquires learning data that is a set of data associated with the data on the type of building, data on whether a building is a rental building, and data on elevator specifications that meet the required capacity. Note that a rental building is a building that is rented out as an office or store for a usage fee, and in this embodiment, it is considered a rental building whether the object being rented is the entire building or just one floor.

[0066] In this embodiment, when the model generation unit 61 learns a standard model of elevator using data on elevator specifications used in the past, the model generation unit 61 may learn to give a higher recommendation rank to that standard model of elevator.

[0067] As described above, according to the elevator information providing device 100 of this embodiment, a user of the elevator information providing device 100 can consider elevator specifications based on a standard model, because the inference unit 11 infers a standard elevator model from building data and outputs data of the inferred standard elevator model.

[0068] If a user of the elevator information device 100 according to this embodiment can consider elevator specifications based on a standard model, the elevator manufacturer can reduce the burden on the manufacturing process. This is because the manufacturing process for a standard model is already determined, so the occurrence of new work can be reduced. The burden on the manufacturing process can be reduced even when a user of the elevator information device 100 considers a special model. This is because, for a manufacturer, the burden on the elevator manufacturing process is lower when a special model is considered as a design change based on a standard model, rather than when a special model is considered from the beginning.

[0069] Furthermore, the elevator information device 100 according to the present embodiment uses a trained model for inferring a standard elevator model suitable for installation in a building from building data, a task that was previously performed by a sales representative of an elevator manufacturer or elevator seller. Conventionally, it has sometimes been difficult for a manufacturer's sales representative to guide a person considering purchasing or ordering an elevator to consider elevator specifications based on a standard model, depending on the manufacturer's sales representative. On the other hand, the elevator information device 100 according to the present embodiment uses a trained model for inferring a standard elevator model suitable for installation in a building from building data, making this task possible at any time. In other words, the elevator information device 100 according to the present embodiment can prevent inconsistencies in elevator information provided to a person considering purchasing or ordering an elevator from depending on a sales representative of an elevator manufacturer or elevator seller.

[0070] Furthermore, users of the elevator information device 100 according to this embodiment can easily select an elevator because they do not need to check the laws of the area where the building is being constructed before selecting an elevator. This is because the trained model used by the elevator information device 100 according to this embodiment is generated by acquiring and associating data on the area where the building is being constructed with data on elevator specifications that comply with the laws of that area, and the elevator information device 100 according to this embodiment outputs data on standard elevator models that comply with the laws of the area where the building is being constructed.

[0071] Furthermore, a user of the elevator information device 100 according to the present embodiment can select an elevator that is popular in the area where the building is being constructed. This is because the trained model used by the elevator information device 100 according to the present embodiment is generated by acquiring and associating data on the area where the building is being constructed with data on the specifications of elevators that have been used in the area in the past, and the elevator information device 100 according to the present embodiment outputs data on standard elevator models that have been used in the area where the building is being constructed.

[0072] Furthermore, a user of the elevator information device 100 according to the present embodiment does not need to consider the type of building when selecting an elevator. Depending on the type of building, the user must check various laws when selecting an elevator, which can be a burden for the user. On the other hand, since a user of the elevator information device 100 according to the present embodiment does not need to consider the type of building when selecting an elevator, the elevator selection process can be performed easily. This is because the trained model used by the elevator information device 100 according to the present embodiment is generated by acquiring data on the type of building and associating it with data on elevator specifications suitable for that type, and the elevator information device 100 according to the present embodiment outputs data on standard elevator models suitable for that type.

[0073] Furthermore, a user of the elevator information device 100 according to the present embodiment can select a preferred elevator for each type of building. This is because the trained model used by the elevator information device 100 according to the present embodiment is generated by acquiring and associating data on the type of building with data on the specifications of elevators previously used in that type, and the elevator information device 100 according to the present embodiment outputs data on the standard model of an elevator previously used in that type.

[0074] In this embodiment, the case where supervised learning is applied to the learning algorithm used by the model generation unit 61 has been described, but this is not limiting. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0075] In this embodiment, the elevator information providing device 100 and the learning device 600 may be incorporated into the server 102. Also, the elevator information providing device 100 may be made available to users directly, without going through the server 102 and the internet line 103. Also, the elevator information providing device 100 may be connected to the server 102 via an internet line. The application of the elevator information providing device 100 according to this embodiment may be changed as appropriate within the scope of the present invention.

[0076] In this embodiment, any type of internet line 103 is applicable. The server 102 may be a physical server or a cloud server.

[0077] Second Embodiment The configuration of an elevator information providing device 200 according to a second embodiment of the present invention will be described. The elevator information providing device 200 according to the second embodiment of the present invention has the same application example as the elevator information providing device 100 according to the first embodiment of the present invention, but includes an inference unit 22 instead of the inference unit 11 of the elevator information providing device 100 according to the first embodiment of the present invention. In the second embodiment of the present invention, only the differences from the first embodiment of the present invention will be described, and descriptions of the parts that are the same as those in the first embodiment of the present invention will be omitted.

[0078] 8 is a configuration diagram of an elevator information providing device 200 according to a second embodiment of the present invention. As shown in FIG. 8, the elevator information providing device 200 according to the present embodiment includes a building data acquiring unit 10 that acquires building data, and an inference unit 21 that infers a standard model of elevators and the number of elevators from the building data input from the building data acquiring unit using a trained model for inferring a standard model of elevators suitable for installation in the building from the building data, and outputs data on the inferred standard model of elevators and the number of elevators. The trained model is stored in a trained model storage device 201.

[0079] The inference unit 21 uses the trained model stored in the trained model storage device 201 to infer the standard model and number of elevators suitable for installation in a building from the building data input from the building data acquisition unit 10, and outputs the data on the inferred standard model and number of elevators. The data on the standard model and number of elevators output by the inference unit 21 is input to the user's personal computer 104 and displayed on the personal computer 104.

[0080] Unlike the first embodiment of the present invention, the inference unit 21 of the elevator information providing device 200 according to the present embodiment uses the trained model stored in the trained model storage device 201 to infer not only the standard model of elevator suitable for installation in a building but also the number of elevators from the building data input from the building data acquisition unit 10. Therefore, the trained model stored in the trained model storage device 201 differs between the present embodiment and the first embodiment of the present invention.

[0081] Next, a learning device 700 that generates a trained model used by the elevator information providing device 200 according to the present embodiment will be described. Fig. 9 is a configuration diagram of the learning device 700 that generates a trained model used by the elevator information providing device 200 according to the second embodiment of the present invention. As shown in Fig. 9, the learning device 700 includes a training data acquiring unit 70 that acquires training data, and a model generating unit 71 that uses the training data to generate a trained model for inferring a standard elevator model from building data.

[0082] Next, a specific example of training data necessary for training by the model generation unit 71 that generates a trained model used by the elevator information providing device 200 according to the present embodiment will be described. In the present embodiment, a plurality of pieces of training data are acquired by the training data acquisition unit 70. The training data acquisition unit 70 acquires the data described below in addition to the data acquired by the training data acquisition unit 60 of the training device 600 that generates the trained model used by the elevator information providing device 100 according to the first embodiment of the present invention. The training data is a set of input data and result (label) data, and specific examples of the data acquired by the training data acquisition unit 70 in addition to the training data acquisition unit 60 will be described one by one below.

[0083] As one specific example, the learning data acquisition unit 70 acquires data on the number of floors of a building, data on the number of people using an elevator, and data on the elevator's transportation capacity. Elevator transportation capacity is determined by a combination of the elevator's capacity and the number of elevators. The data on the number of floors of a building and the data on the number of people using an elevator are acquired as building data. The data on the number of floors of a building and the data on the number of people using an elevator are acquired in association with the data on the elevator's transportation capacity, and are used by the model generation unit 72 to learn standard elevator models and their number.

[0084] As another example, the learning data acquisition unit 70 acquires data on whether a building is a rental building and data on the elevator's transportation capacity. The data on whether a building is a rental building is acquired as building data. The data on whether a building is a rental building and the data on the elevator's transportation capacity are acquired in association with each other and used by the model generation unit 72 to learn the standard model of elevators and the number of elevators. In this case, the model generation unit 72 learns to output the standard model of elevators and the number of elevators so that the elevator transportation capacity is higher when the building is a rental building than when the building is not a rental building. In other words, when the building is a rental building, the model generation unit 72 generates a learned model so that the inference unit 21 infers the standard model of elevators and the number of elevators that have a higher elevator transportation capacity than when the building is not a rental building.

[0085] As described above, according to the elevator information device 200 of this embodiment, a user of the elevator information device 200 can consider elevator specifications based on standard models while taking into account the number of elevators to be installed in a building. This is because the inference unit 21 infers the standard model and number of elevators from building data and outputs data on the inferred standard model and number of elevators.

[0086] Third Embodiment The configuration of an elevator information providing device 300 according to a third embodiment of the present invention will be described. The elevator information providing device 300 according to the third embodiment of the present invention has the same application examples as the elevator information providing devices according to the first embodiment and the second embodiment of the present invention. In the third embodiment of the present invention, only the differences from the first embodiment and the second embodiment of the present invention will be described, and descriptions of the parts that are the same as the first embodiment and the second embodiment of the present invention will be omitted.

[0087] 10 is a configuration diagram of an elevator information providing device 300 according to a third embodiment of the present invention. As shown in FIG. 10, the elevator information providing device 300 according to the present embodiment includes a building data acquiring unit 10 that acquires building data, and an inference unit 11 that infers a standard elevator model from the building data input from the building data acquiring unit 10 using a trained model for inferring a standard elevator model suitable for installation in the building from the building data, and outputs data of the inferred standard elevator model. The trained model is stored in a trained model storage device 101.

[0088] The elevator information providing device 300 according to this embodiment further includes a regulation acquisition unit 13 that acquires data on regulations related to the installation of standard elevator models from multiple regulations related to building construction using the building data input from the building data acquisition unit 10 and the data on standard elevator models input from the inference unit 11, and outputs the acquired data on the regulations. Multiple regulations related to building construction are stored in a regulation storage device 301. The data on the regulations output from the regulation acquisition unit 13 is provided to the user via the server 102 and the Internet line 103. The data on the regulations acquired by the regulation acquisition unit 13 is then displayed on the user's personal computer 104.

[0089] The elevator information device 300 according to this embodiment allows a user to consider elevator specifications based on a standard model, and since the inference unit 11 infers the standard model of the elevator, the elevator information provided by the elevator information device 300 according to this embodiment relates to the standard model. For elevator manufacturers and sales representatives of elevator manufacturers, showing users the clauses of laws and regulations related to elevator installation is possible without requiring the laws and regulations acquisition unit 13 to perform complex processing, as long as the elevator is a standard model, and the elevator information device 300 according to this embodiment makes this possible.

[0090] The multiple laws and regulations related to the construction of buildings include, for example, various local government ordinances, the Building Standards Act, the Building Standards Act Enforcement Order, the Building Standards Act Enforcement Regulations, the City Planning Act, the Construction Business Act, the Architects Act, the Fire Service Act, the Act on Improvement of Energy Consumption Performance of Buildings, and the Act on Promotion of Smooth Mobility for the Elderly, Persons with Disabilities, etc. The Act on Improvement of Energy Consumption Performance of Buildings is commonly known as the Building Energy Conservation Act. The Act on Promotion of Smooth Mobility for the Elderly, Persons with Disabilities, etc. is commonly known as the Barrier-Free Act. In this embodiment, the article of the law related to the installation of a standard model of elevator acquired by the law acquisition unit 13 is, for example, an item of the law, such as Article 0 of the Building Standards Act. Note that when the elevator information providing device 300 according to this embodiment is used outside Japan, the multiple laws and regulations related to the construction of buildings may be appropriately changed to the relevant laws and regulations of that country.

[0091] In this embodiment, the display method and timing of the legal article data displayed on the personal computer 104 are not particularly limited. The display method may be, for example, to directly display the wording of the legal article on the personal computer 104, or to display a document containing the legal article so that it can be downloaded, or to display a link leading to a website containing the legal article. The display timing may be, for example, to display the data on the personal computer 104 simultaneously with the data on the standard elevator model, or to display the data on the standard elevator model first and then display it on the personal computer 104 after the user has finished considering all of the elevator specifications based on the standard model.

[0092] As described above, according to the elevator information device 300 of this embodiment, a user of the elevator information device 300 can consider elevator specifications based on a standard model and can also check data on the provisions of laws and regulations related to the installation of that standard model of elevator. This is because the laws and regulations acquisition unit 13 acquires data on the provisions of laws and regulations related to the installation of the standard model of elevator from multiple laws and regulations related to the construction of buildings using the building data input from the building data acquisition unit 10 and the data on the standard model of elevator input from the inference unit 11, and outputs the acquired data on the provisions of laws and regulations.

[0093] Fourth Embodiment The configuration of an elevator information providing device 400 according to a fourth embodiment of the present invention will be described. The elevator information providing device 400 according to the fourth embodiment of the present invention has the same application examples as the elevator information providing devices according to the first to third embodiments of the present invention. In the fourth embodiment of the present invention, only the differences from the first to third embodiments of the present invention will be described, and descriptions of the parts that are the same as the first to third embodiments of the present invention will be omitted.

[0094] 11 is a configuration diagram of an elevator information providing device 400 according to a fourth embodiment of the present invention. As shown in FIG. 11 , the elevator information providing device 400 according to the present embodiment includes a building data acquiring unit 10 that acquires building data, and an inference unit 11 that infers a standard elevator model from the building data input from the building data acquiring unit 10 using a trained model for inferring a standard elevator model suitable for installation in the building from the building data, and outputs data of the inferred standard elevator model. The trained model is stored in a trained model storage device 101.

[0095] The elevator information providing device 400 according to this embodiment further includes a drawing acquisition unit 14 that acquires a drawing relating to the installation of a standard elevator model from a plurality of drawings relating to elevator installation, using the building data input from the building data acquisition unit 10 and the data of the standard elevator model input from the inference unit 11, and outputs the acquired drawing. The plurality of drawings relating to elevator installation are stored in a drawing storage device 401. The drawing data output from the drawing acquisition unit 14 is provided to the user via the server 102 and the Internet line 103. The drawing data acquired by the drawing acquisition unit 14 is then displayed on the user's personal computer 104.

[0096] The elevator information device 400 according to this embodiment allows a user to consider elevator specifications based on a standard model, and since the inference unit 11 infers the standard model of the elevator, the elevator information provided by the elevator information device 400 according to this embodiment relates to the standard model. For elevator manufacturers and sales representatives of elevator manufacturers, showing drawings related to elevator installation to users is possible without requiring the drawing acquisition unit 14 to perform complex processing, as long as the elevator is a standard model, and the elevator information device 400 according to this embodiment makes this possible.

[0097] The multiple drawings related to elevator installation include, for example, drawings showing elevator shaft plan views, drawings showing elevator shaft cross-section views, and drawings showing installation diagrams, and include not only drawings created as 2D CAD data but also drawings created as 3D CAD data, and not only static drawings but also dynamic drawings.

[0098] In this embodiment, the display method and timing of the drawing data displayed on the personal computer 104 are not particularly limited. For example, the display method may involve displaying the drawing data directly on the personal computer 104, or displaying the drawing data so that the document can be downloaded. For example, the display timing may involve displaying the data on the personal computer 104 simultaneously with the data on the standard elevator model, or displaying the data on the standard elevator model first and then displaying it on the personal computer 104 after the user has finished considering all of the elevator specifications based on the standard model.

[0099] As described above, according to the elevator information device 400 of this embodiment, a user of the elevator information device 400 can consider elevator specifications based on a standard model and can also check drawing data related to the installation of the standard model of elevator. This is because the drawing acquisition unit 14 acquires drawing data related to the installation of the standard model of elevator from multiple drawings related to elevator installation using the building data input from the building data acquisition unit 10 and the data of the standard model of elevator input from the inference unit 11, and outputs the acquired drawing data.

[0100] It should be noted that, within the scope of the present invention, the embodiments and modifications can be freely combined, and the embodiments can be modified or omitted as appropriate.

[0101] 1 elevator shaft member, 2a cage inner wall, 2b cage outer wall, 3 landing member, 4 cage door, 5 landing door, 6 landing door door pocket, 10 building data acquisition unit, 11, 21 inference unit, 13 regulations acquisition unit, 14 drawing acquisition unit, 60, 70 learning data acquisition unit, 61, 71 model generation unit, 100, 200, 300, 400 elevator information providing device, 101, 201 learned model storage device, 102 server, 103 internet line, 104 personal computer, 301 regulations storage device, 401 drawing storage device, 600, 700 learning device.

Claims

1. A building data acquisition unit that acquires building data; an inference unit that infers a standard model of the elevator from the building data input from the building data acquisition unit using a trained model for inferring a standard model of the elevator suitable for installation in the building from the building data, and outputs data of the inferred standard model of the elevator; Equipped with The building data includes data on whether the building is a rental building, When the building is a rental building, the inference unit infers a standard model of the elevator having a larger capacity than when the building is not a rental building. Elevator information device.

2. The inference unit infers the number of standard models of the elevators from the building data input from the building data acquisition unit, and outputs data on the inferred number of standard models of the elevators. The elevator information providing device according to claim 1.

3. a regulation acquisition unit that acquires data on provisions of regulations related to the installation of the standard model of elevator from a plurality of regulations related to the construction of the building, using the building data input from the building data acquisition unit and the data on the standard model of elevator input from the inference unit, and outputs the acquired data on the provisions of regulations; 3. The elevator information providing device according to claim 1 or 2, further comprising:

4. a drawing acquisition unit that acquires drawing data relating to installation of the standard model of the elevator from a plurality of drawings relating to installation of the elevator using the building data input from the building data acquisition unit and the data of the standard model of the elevator input from the inference unit, and outputs the acquired drawing data; 3. The elevator information providing device according to claim 1 or 2, further comprising:

5. The data of the building includes data of an area in which the building is to be constructed; The inference unit infers a standard model of the elevator from elevator specification data conforming to the laws of the region.

3. The elevator information providing device according to claim 1 or 2.

6. The data of the building includes data of an area in which the building is to be constructed; The inference unit infers a standard model of the elevator from data on specifications of elevators used in the past in the area.

3. The elevator information providing device according to claim 1 or 2.

7. The building data includes data on the type of the building, The inference unit infers a standard model of the elevator from data of elevator specifications suitable for the type.

3. The elevator information providing device according to claim 1 or 2.

8. The building data includes data on the type of the building, The inference unit infers a standard model of the elevator from data of elevator specifications used in the past for the type.

3. The elevator information providing device according to claim 1 or 2.

9. The building data includes data on whether the building requires welfare support; If the building requires welfare support, the inference unit infers a standard model of the elevator in which the width of the elevator car entrance is set to a width that allows a wheelchair to pass through and the inside dimensions of the elevator car are set to an inside dimension that allows a wheelchair to fit therein.

3. The elevator information providing device according to claim 1 or 2.

10. An acquisition step of acquiring building data; an inference step of inferring a standard model of the elevator from the data of the building acquired in the acquisition step by using a trained model for inferring a standard model of the elevator suitable for installation in the building from the data of the building, and outputting data of the inferred standard model of the elevator; Equipped with The building data includes data on whether the building is a rental building, If the building is a rental building, in the inference step, a standard model of the elevator having a larger capacity than a case where the building is not a rental building is inferred. How to provide elevator information.

11. a learning data acquisition unit that acquires learning data including building data and elevator specification data suitable for installation in the building; A model generation unit that generates a trained model for inferring a standard model of the elevator from data of the building using the training data; Equipped with The building data includes data on whether the building is a rental building, The model generation unit generates the trained model that infers a standard model of the elevator having a larger capacity when the building is a rental building than when the building is not a rental building. Learning device.