Derivation system, derivation device, and derivation program

Abstract

A derivation system, a derivation device, and a derivation program are provided that can expect improved prediction accuracy regarding the use of transportation means when deriving a transportation plan for transportation means that transports materials necessary for the construction of a building. [Solution] The derivation system includes a trained model that stores the relationship between actual property information, which is property information on constructed buildings, and transportation records by transportation means, and the trained model is generated by machine learning using training data in which selected elements selected in advance from multiple elements included in the actual property information based on their relevance to transportation records are used as input data and the corresponding transportation records are used as labels.The derivation system refers to the trained model based on the acquired target property information and derives a transportation plan for transportation means that transports materials necessary for the construction of the building indicated in the target property information (S201 to S217).

Description

[Technical Field]

[0001] The present application discloses a deriving system that derives a transportation plan for a transportation means that transports materials required for the construction of a building, a deriving device used in such a deriving system, and a deriving program for realizing such a deriving device. [Background technology]

[0002] Many trucks are used nationwide every day to transport housing materials from factories to construction sites. When creating a transportation plan for truck operations, for example, after a transportation instruction is received at a factory, the person in charge uses a prediction formula that uses coefficients that each factory has learned through experience to predict the number of trucks required one month in advance based on property information and material information after the materials have been unpacked.

[0003] For example, Patent Document 1 proposes a method for creating a delivery plan for construction materials, which analyzes construction process from architectural design data and formulates a delivery schedule for delivering materials to a material storage area. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-312426 Summary of the Invention [Problem to be solved by the invention]

[0005] However, factories are required to accurately forecast demand further into the future, taking into consideration various issues such as the difficulty of securing trucks and the 2024 problem. Forecasts based on prediction formulas that meet these requirements have problems, such as the fact that they can only be predicted for a period of about one month, making long-term forecasts difficult. Furthermore, predictions using AI (Artificial Intelligence) technology, such as that described in Patent Document 1, face the challenge of improving the accuracy of predictions.

[0006] The derivation system disclosed in this application has been made in consideration of such circumstances, and aims to provide a derivation system that is likely to be able to handle long-term predictions and that can be expected to improve prediction accuracy.

[0007] Another object of the present application is to provide a derivation device used in the above-mentioned derivation system and a derivation program for realizing such a derivation device. [Means for solving the problem]

[0008] In order to solve the above problem, the derivation system disclosed in the present application is a derivation system that uses a derivation device that derives a transportation plan for a transportation means that transports materials necessary for the construction of a building, and is equipped with an acquisition means that acquires target property information, which is property information related to the building that is the target of deriving the transportation plan, and a trained model that stores the relationship between actual property information, which is property information for buildings that have already been constructed, and transportation records by the transportation means, wherein the trained model is generated by machine learning using training data in which selected elements selected in advance from multiple elements included in the actual property information based on their relevance to transportation records are used as input data and the corresponding transportation records are used as labels, and the derivation device is characterized by comprising a plan derivation means that refers to the trained model based on the target property information acquired by the acquisition means, and derives a transportation plan for a transportation means that transports materials necessary for the construction of the building indicated in the target property information.

[0009] Furthermore, in the derivation system, the trained model is characterized in that it uses multiple elements contained in the actual property information as explanatory variables and selects elements as selected elements whose contribution rate in multiple regression analysis using transportation history as the objective variable is higher than a predetermined value.

[0010] In addition, in the derivation system, the trained model is generated using the number of transports, transport intervals, and transport capacity of the transport performance as training data, and the plan derivation means derives a transport plan based on the derivation results of the number of transports, transport intervals, and transport capacity.

[0011] Further, in the derivation system, the trained model includes a transport count model generated using the number of transports from the transport record as training data, a transport interval model generated using the transport interval from the transport record as training data, and a transport capacity model generated using the transport capacity from the transport record as training data, and the plan derivation means derives the number of transports based on the target property information acquired by the acquisition means by referring to the transport count model, derives the transport interval based on the target property information acquired by the acquisition means and the derived number of transports by referring to the transport interval model, derives the transport capacity based on the target property information acquired by the acquisition means and the derived number of transports by referring to the transport capacity model, and derives a transport plan based on the derived transport interval and transport capacity.

[0012] In addition, in the derivation system, the property information includes information on the structure of the building, as well as identification information on the components used, materials, specifications, locations of use, methods of use, manufacturing locations, or accessories.

[0013] In addition, in the derivation system, the specifications relating to the components to be used include information indicating the slope of the roof, the roofing materials, or the shape of a composite roof.

[0014] Furthermore, the derivation device disclosed in the present application is a derivation device that derives a transportation plan for a transportation means that transports materials necessary for the construction of a building, and is equipped with an acquisition means for acquiring target property information, which is property information related to the building that is the target of deriving the transportation plan, and a means for accessing a trained model that stores the relationship between actual property information, which is property information for buildings that have already been constructed, and transportation records by the transportation means, wherein the trained model is generated by machine learning using training data in which selected elements selected in advance from multiple elements included in the actual property information based on their relevance to transportation records are used as input data and the corresponding transportation records are used as labels, and is characterized by being equipped with a plan derivation means that refers to the trained model based on the target property information acquired by the acquisition means and derives a transportation plan for a transportation means that transports materials necessary for the construction of the building indicated in the target property information.

[0015] Furthermore, the derivation program disclosed in the present application is a derivation program that causes a computer to derive a transportation plan for a transportation means that transports materials necessary for the construction of a building, and is configured to execute an acquisition step of acquiring target property information, which is property information related to the building that is the target of deriving the transportation plan, and a step of accessing a trained model that stores the relationship between actual property information, which is property information for buildings that have already been constructed, and transportation records by the transportation means, wherein the trained model is generated by machine learning using training data in which selected elements selected in advance from multiple elements included in the actual property information based on their relevance to transportation records are used as input data and the corresponding transportation records are used as labels, and is characterized in that, based on the target property information acquired in the acquisition step, the trained model is referenced and a transportation plan for a transportation means that transports materials necessary for the construction of the building indicated in the target property information is derived. [Effects of the Invention]

[0016] The derivation system disclosed herein derives a transportation plan for a transportation means for transporting materials based on property information, by referencing a trained model generated by machine learning using selection factors that have been selected in advance based on their relevance to transportation records. As a result, the derivation system disclosed herein is expected to be able to handle long-term predictions and has excellent effects, such as the possibility of improving the prediction accuracy regarding the use of transportation means. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is an explanatory diagram conceptually illustrating an example of an embodiment of a derivation system disclosed in the present application. [Figure 2] FIG. 2 is a block diagram conceptually illustrating an example configuration of various devices used in the derivation system disclosed in the present application. [Figure 3] FIG. 2 is a block diagram conceptually illustrating an example configuration of various devices used in the derivation system disclosed in the present application. [Figure 4] 10 is a flowchart illustrating an example of a learning process of a derivation device used in the derivation system disclosed in the present application. [Figure 5]10 is a flowchart illustrating an example of a plan derivation process used in the derivation system disclosed in the present application. [Figure 6] FIG. 10 is an explanatory diagram showing an example of an output result of a transportation plan in the derivation system disclosed in the present application. DETAILED DESCRIPTION OF THE INVENTION

[0018] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail preferred embodiments of the present invention. Note that the following preferred embodiments are merely examples of the present invention and are not intended to limit the technical scope of the present invention.

[0019] <Application example> The deriving system disclosed herein derives a transportation plan for a transportation means for transporting necessary materials from a factory when constructing a building, for example. Hereinafter, with reference to the drawings, an embodiment in which the deriving system disclosed herein is applied to the creation of a transportation plan for a truck will be described.

[0020] <System configuration> 1 is an explanatory diagram conceptually illustrating an example of an embodiment of a derivation system disclosed in the present application. The derivation system includes a derivation device 1 that executes main processing in the system. The derivation device 1 is connected to a communication network NW such as an in-house local area network (LAN), a wide area network (WAN), a dedicated communication network, or the Internet. A management device 2 used by a data manager and an ordering device 3 used by an ordering person are connected to the communication network NW.

[0021] Furthermore, various computers such as a database server computer 4 (hereinafter referred to as the database server 4) and an inference server computer 5 (hereinafter referred to as the inference server 5) are connected to the communication network NW. The derivation device 1 can access these database servers 4 and inference servers 5 and use the stored information. Although FIG. 1 shows an example of a system in which the derivation device 1 accesses devices such as the database server 4 and the inference server 5 via the communication network NW, the database server 4 and the inference server 5 may be directly connected to the derivation device 1 without going through the communication network NW. Furthermore, it is also possible to store some or all of the database server 4, the inference server 5, etc. within the derivation device 1 and configure it so that they can be accessed as needed.

[0022] <Hardware configuration of each device> Next, an example of the configuration of various devices used in the derivation system will be described. Figures 2 and 3 are block diagrams conceptually showing an example of the configuration of various devices used in the derivation system disclosed in the present application. The derivation device 1 is configured using a computer such as a server computer that is capable of communication. The derivation device 1 has various components such as a control unit 10, a storage unit 11, and a communication unit 12.

[0023] The control unit 10 includes various circuits such as an information processing circuit, a clock circuit, and a register circuit, and is a processor such as a CPU (Central Processing Unit) that controls the entire device.

[0024] The storage unit 11 is a storage unit configured using nonvolatile memories such as a hard disk, a solid state drive (SSD), a redundant array of inexpensive disks (RAID), and a flash memory, and volatile memories such as various random access memories (RAM). The storage unit 11 stores computer programs (hereinafter referred to as programs) such as a basic program (OS: Operating System) and application programs that run on the basic program. As the application programs, various programs such as a derivation program 110 for realizing the derivation device 1 disclosed in the present application are stored. The derivation program 110 includes programs for executing various processes such as a learning process and a plan derivation process.

[0025] The communication unit 12 is a communication device such as a LAN adapter, and connects to the communication network NW to access various devices and computers such as the database server 4 and the inference server 5.

[0026] A computer having the various configurations exemplified above operates as a derivation device 1 by reading various programs, such as the derivation program 110, stored in the storage unit 11 under the control of the control unit 10 and executing various procedures included in the read programs. Note that, although the following description will be given using an example in which the derivation device 1 is configured as a single device, the derivation device 1 disclosed herein can also be configured as a collection of multiple devices. For example, the derivation device 1 can be configured such that the derivation device 1 that executes the learning process and the derivation device 1 that executes the plan derivation process are separate devices. Furthermore, the derivation device 1 disclosed herein can also be used in conjunction with other devices, such as a management device 2 and an ordering device 3.

[0027] The management device 2 is a device using a computer such as a client computer used by a data management officer, etc. The management device 2 is used for tasks and / or processes such as inputting various data into various databases such as the residence information database 40 and the transportation record database 41 provided in the database server 4, and constructing a trained model 50. The management device 2 has various components such as a control unit 20, a memory unit 21, an input unit 22, a display unit 23, and a communication unit 24.

[0028] The input unit 22 is a device used for inputting operations such as a keyboard, a mouse, etc. The display unit 23 is a display device such as a liquid crystal display.

[0029] The ordering device 3 is a device using a computer such as a client computer used by an ordering person, etc. The ordering device 3 is used for work related to planning transportation plans for transportation means such as trucks that transport components, using the house information database 40 and the trained model 50. The ordering device 3 has various components such as a control unit 30, a memory unit 31, an input unit 32, a display unit 33, and a communication unit 34.

[0030] Next, we will explain the various databases provided in the database server 4. The residence information database 40 stores various pieces of property information in association with a property ID that identifies the property. The property information includes various pieces of information on various elements related to the structure of the building, the construction method of the building, the components used in the building and identification information related to the components used, materials, specifications, locations of use, methods of use, manufacturing locations, and accessories. The property information is stored as text information stored in a database stored in tabular format, drawing information showing the building drawings and information that can be read from the drawing information, and also as information that aggregates these pieces of information.

[0031] Building structure refers to information about the building's structure, such as the number of units, number of floors, style, and whether it is steel-framed or wooden. Building construction method refers to information about construction methods, such as construction classification and construction method. Regarding information about the components and materials used in a building, identification information refers to information about items such as product codes that identify the components used, such as information that identifies individual products. Even for the same type of components, identification information is assigned unique codes such as numbers, symbols, or signs for each element, such as specifications, construction direction, and structure. Materials refer to the materials used, such as concrete, plaster, or wood. Specifications refer to the specifications of the components used, such as roof slope, roof covering material, and composite roof shape. Location of use refers to information about items such as the roof, second floor, and entrance. Usage method refers to information about items in special cases. Manufacturing location refers to information about items such as the factory, workshop, or subcontractor where the item was manufactured. Accessories refer to items such as solar panels and distribution boards.

[0032] The transport record database 41 is a database that stores transport records. The transport record database 41 stores various transport record information in association with the property ID. The transport record information includes information on various items such as the number of transports, transport intervals, and transport capacity. The number of transports is the number of times that components have been transported to the property, for example, by truck. The transport interval is information indicating the number of days between each transport. The transport capacity is the capacity required for transport, and in the case of transport by truck, it indicates the number of trucks and the load capacity.

[0033] Next, the trained model 50 provided in the inference server 5 will be described. The trained model 50 has constructed multiple models, such as a transport count model 50a, a transport interval model 50b, and a transport capacity model 50c. The transport count model 50a is a model generated by machine learning using the transport count as training data. The transport interval model 50b is a model generated by machine learning using the transport interval as training data. The transport capacity model 50c is a model generated by machine learning using the transport capacity as training data.

[0034] <Device software processing> Next, the processing of various devices used in the derivation system disclosed herein will be described. First, the learning processing will be described. The learning processing is processing for generating a trained model 50 based on the contents stored in various databases stored in the database server 4. In the derivation system disclosed herein, the learning processing is executed by the derivation device 1 when a command is received from the management device 2 operated by a data manager, when a predetermined time is reached, or when a start condition is satisfied.

[0035] FIG. 4 is a flowchart showing an example of a learning process of the derivation device 1 used in the derivation system disclosed herein. The derivation device 1 executes the learning process under the control of the control unit 10 that executes the derivation program 110. The control unit 10 of the derivation device 1 acquires property information (achieved property information) related to buildings stored in the residence information database 40 (S101). In step S101, for example, property information of buildings whose construction has already been completed and whose transport records are stored in the transport record database 41 is extracted as accomplished property information, which is property information of completed buildings. The extracted accomplished property information includes information in text format. Furthermore, the control unit 10 acquires accomplished transport information stored in the transport record database 41 (S102). In step S102, accomplished transport information indicating the number of transports, transport intervals, and transport capacity is extracted.

[0036] The control unit 10 associates the acquired actual property information and actual transport information based on the property ID, and derives the contribution rate of each element of the actual property information to the actual transport information (S103). The derivation of the contribution rate in step S103 is performed, for example, by regression analysis such as multiple regression analysis, in which the actual property information is an explanatory variable and the actual transport information is a target variable.

[0037] Furthermore, the control unit 10 selects as selection elements those elements of the performance document information with the highest derived contribution rates, e.g., elements of the performance property information included in the top 60%, as selection elements (S104), and stores the selection elements in the residence information database 40 (S105). The processes of steps S103 to S105 are executed for each of the number of transfers, transfer intervals, and transfer capacity of the performance transfer information, and selection elements serving as explanatory variables for each of the number of transfers, transfer intervals, and transfer capacity are selected. For example, as performance property information related to the number of transfers, approximately 50 to 100 items such as product code, roof slope, number of units, number of floors, total floor area, B-type foundation specifications, B-type structural beam XX factory, sanitary ware, and distribution board are selected as selection elements. Also, as performance property information related to the transfer interval, approximately 50 to 100 items such as product code, construction classification, roof slope, roofing material, number of units, number of floors, bearing wall, B-type foundation specifications, B-type structural beam XX factory, and Japanese-style ceiling are selected as selection elements. Furthermore, for example, actual property information relating to transport capacity includes approximately 50 to 100 items such as product code, roofing material, roof composite, number of units, total floor area, underfloor inspection hatch, B-type foundation specifications, B-type structural beam △△ factory, unit bath, wall and ceiling-mounted ventilation fan, etc., which are selected as selection elements.

[0038] The control unit 10 acquires selection elements from the residence information database 40 (S106), and acquires actual transport information from the transport record database 41 (S107). Furthermore, the control unit 10 associates the acquired selection elements and actual transport information based on the property ID (S108), and generates training data using the selection elements of the actual property information as input data and the corresponding actual transport information as labels (S109). Then, the control unit 10 generates a trained model 50 by machine learning using the training data (S110), and stores the generated trained model 50 in the inference server 5 (S111). The processing of steps S106 to S111 generates trained models 50 related to the selection elements of the number of transports, the transport interval, and the transport capacity, as a transport number model 50a, a transport interval model 50b, and a transport capacity model 50c.

[0039] In this way, the derivation system disclosed in the present application performs a learning process to generate trained models 50, such as a transport count model 50a used for AI prediction of transport counts, a transport interval model 50b used for AI prediction of transport intervals, and a transport capacity model 50c used for AI prediction of transport capacity.

[0040] Next, the transportation prediction process will be described. The plan derivation process is a process for deriving a transportation plan using the trained model 50 stored in the inference server 5. In the derivation system disclosed in the present application, the plan derivation process is executed by the derivation device 1 when a command is received from the ordering device 3 operated by an ordering person, when a predetermined time is reached, or when a start condition is satisfied.

[0041] FIG. 5 is a flowchart showing an example of a plan derivation process used in the derivation system disclosed herein. The derivation device 1 executes the plan derivation process under the control of the control unit 10 that executes the derivation program 110. The control unit 10 of the derivation device 1 acquires, from the residence information database 40, target property information to be used for inferring the number of transports from among property information (target property information) related to a building that is a target for deriving a transport plan (S201). In step S201, property information related to the building that is a target for deriving a transport plan is extracted as the target property information. The target property information extracted for inferring the number of transports is, for example, target property information corresponding to an item of actual property information selected as a selection element related to the number of transports in the learning process. The extracted target property information includes information such as text information.

[0042] The control unit 10 standardizes the acquired target property information for inference using the trained model 50 (S202). The control unit 10 performs a first inference process to derive a predicted number of transports based on the acquired target property information, with reference to the transport count model 50a of the trained model 50 (S203). The control unit 10 standardizes the derivation result of the predicted number of transports obtained in the first inference process (S204), and stores the information after standardization in the memory unit 11 as the derivation result of the number of transports (S205). In this way, the number of transports for the building that is the target of deriving a transportation plan is derived.

[0043] The control unit 10 acquires the target property information to be used for estimating the transport interval from the residence information database 40 (S206), and further acquires the derived result of the transport count stored in step S205 from the memory unit 11 (S207). In step S206, the target property information extracted for estimating the transport count is, for example, target property information corresponding to the item of the actual property information selected as the selection element for the transport interval in the learning process. The extracted target property information includes information such as text information.

[0044] The control unit 10 standardizes the acquired target property information for inference using the trained model 50 (S208). The control unit 10 performs a second inference process to derive a predicted transport interval based on the acquired target property information and the derived result of the acquired number of transports, with reference to the transport interval model 50b of the trained model 50 (S209). The control unit 10 standardizes back the derived result of the predicted transport interval obtained in the second inference process (S210), and stores the information after standardization back in the memory unit 11 as the derived result of the transport interval (S211). In this way, the transport interval for the building that is the target of deriving a transport plan is derived.

[0045] The control unit 10 acquires from the residence information database 40 the target property information to be used for estimating the transport capacity from the acquired target property information (S212), and further acquires from the memory unit 11 the derived results of the number of transports stored in step S205 (S213). In step S212, the target property information extracted for estimating the transport capacity is, for example, target property information corresponding to the item of the actual property information selected as a selection element related to the transport capacity in the learning process. The extracted target property information includes information such as text format information.

[0046] The control unit 10 standardizes the acquired target property information for inference using the trained model 50 (S214). The control unit 10 performs a third inference process to derive a predicted transportation capacity based on the acquired target property information and the derived result of the acquired number of transportation trips, with reference to the transportation capacity model 50c of the trained model 50 (S215). The control unit 10 standardizes back the derived result of the predicted transportation capacity obtained in the third inference process (S216), and stores the information after standardization in the memory unit 11 as the derived result of the transportation capacity (S217). In this manner, the derived capacity for the building that is the target of deriving a transportation plan is derived.

[0047] The control unit 10 derives a transportation plan by processing such as BI tool (business intelligence tools) processing based on the number of transportation trips, transportation intervals, and transportation capacity stored in the storage unit 11 (S218). The derivation of the transportation plan in step S218 is a process of deriving, for example, the transportation date, loading capacity, and number of trucks to be used for transportation based on the number of transportation trips, transportation intervals, and transportation capacity. In particular, by deriving the transportation plan using BI tools, the plan is easy for the ordering person to understand, and the transportation plan is derived as information in a format that is easy to edit, analyze, and otherwise reuse.

[0048] Then, the control unit 10 outputs the derived transportation plan (S219). The output of the transportation plan in step S219 is executed as processing such as transmission to the ordering device 3, uploading to a communication network NW such as an in-house LAN, and storage in the storage unit 11 and a predetermined database.

[0049] Fig. 6 is an explanatory diagram showing an example of the output result of a transportation plan in the derivation system disclosed in the present application. As an example of the output result of a transportation plan, Fig. 6 shows an example of the output plan displayed on the display unit of the ordering device 3. Fig. 6 shows a graph by day showing the number of trucks used for transportation and the types of parts to be transported.

[0050] In this way, the derivation system disclosed herein performs a plan derivation process that, based on the target property information, refers to the trained model 50 and derives a transportation plan for the transportation means that will transport the materials necessary for the construction of the building indicated in the target property information.

[0051] As described above in detail, the derivation system disclosed herein derives a transportation plan by referring to a trained model 50 generated by machine learning using selection elements that have been selected in advance based on their relevance to transportation records. As a result, the derivation system disclosed herein can handle long-term predictions and has excellent effects, such as being able to expect improved prediction accuracy regarding predictions of transportation means usage.

[0052] The present invention is not limited to the above-described embodiments, but can be embodied in various other forms. Therefore, these embodiments are merely illustrative in all respects and should not be interpreted as limiting. The scope of the present invention is defined by the claims and is not limited in any way by the text of the specification. Furthermore, all modifications and variations that fall within the equivalent range of the claims are within the scope of the present invention.

[0053] The following supplementary notes are further disclosed regarding the technical contents described in the above-mentioned embodiments.

[0054] (Appendix 1) A deriving system using a deriving device that derives a transportation plan for a transportation means that transports materials necessary for building construction, an acquisition means for acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A trained model that stores the relationship between actual property information, which is property information on buildings that have already been constructed, and transportation records by transportation means. Equipped with The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; The delivery device is and a plan deriving means for deriving a transportation plan for a transportation means for transporting materials required for constructing a building indicated by the target property information, based on the target property information acquired by the acquisition means, by referring to the trained model. A derivation system characterized by:

[0055] (Appendix 2) 10. The derivation system of claim 1, further comprising: The trained model uses a plurality of elements included in the past property information as explanatory variables and selects elements as selected elements whose contribution rate is higher than a predetermined value in a multiple regression analysis using the transportation record as a target variable. A derivation system characterized by:

[0056] (Appendix 3) 10. The derivation system of claim 1 or 2, The trained model is The number of transports, transport intervals, and transport capacity of the transport record are each generated as training data, The plan derivation means A transportation plan is derived based on the results of deriving the number of transportations, transportation intervals, and transportation capacity. A derivation system characterized by:

[0057] (Appendix 4) 10. The derivation system of claim 1 or 2, The trained model is A transfer count model generated using the transfer count of the transfer record as training data; a transfer interval model generated using transfer intervals of transfer records as training data; The transport capacity model was generated using the transport capacity of the transport record as training data. Including, The plan derivation means The number of transports is derived based on the target property information acquired by the acquisition means by referring to the transport number model, The transport interval model is referenced to derive the transport interval based on the target property information acquired by the acquisition means and the derived number of transports, The transportation capacity is derived based on the target property information acquired by the acquisition means and the derived number of transportations by referring to the transportation capacity model, A transportation plan is derived based on the derived transportation intervals and transportation capacity. A derivation system characterized by:

[0058] (Appendix 5) 4. The derivation system according to claim 1, further comprising: The property information includes information on the structure of the building, identification information on the components used, materials, specifications, locations of use, methods of use, manufacturing locations, or accessories. A derivation system characterized by:

[0059] (Appendix 6) 6. The derivation system of claim 5, further comprising: The specifications for the components to be used include information indicating the slope of the roof, the roofing material, or the shape of the composite roof. A derivation system characterized by:

[0060] (Appendix 7) A deriving device that derives a transportation plan for a transportation means that transports materials necessary for building construction, an acquisition means for acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A means for accessing a trained model that stores the relationship between actual property information, which is property information on buildings that have already been constructed, and transportation records by transportation means; Equipped with The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; and a plan deriving means for deriving a transportation plan for a transportation means for transporting materials required for constructing a building indicated by the target property information, based on the target property information acquired by the acquisition means, by referring to the trained model. A derivation device characterized by:

[0061] (Appendix 8) A derivation program for deriving a transportation plan for transportation means for transporting materials required for the construction of a building in a computer, On the computer, an acquisition step of acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A step of accessing a trained model that stores the relationship between actual property information, which is property information of a constructed building, and transportation records by transportation means; It is designed to execute The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; Based on the target property information acquired in the acquisition step, a transportation plan for a transportation means for transporting materials required for constructing the building indicated by the target property information is derived by referring to the trained model. A derivation program characterized by: [Explanation of symbols]

[0062] 1 Derivation device 10 Control Unit 11 Storage section 110 Derivation Program 12 Communications Department 2 Management device 20 Control Unit 21 Memory section 22 Input section 23 Display section 24 Communications Department 3. Ordering equipment 30 Control Unit 31 Storage section 32 Input section 33 Display section 34 Communications Department 4. Database Server Computer 40 Residence Information Database 41 Transport performance database 5. Inference Server Computer 50 pre-trained models 50a Transport Count Model 50b Transport Interval Model 50c carrying capacity model NW communication network

Claims

1. A deriving system using a deriving device that derives a transportation plan for a transportation means that transports materials necessary for building construction, an acquisition means for acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A trained model that stores the relationship between actual property information, which is property information on buildings that have already been constructed, and transportation records by transportation means. Equipped with The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; The delivery device is and a plan deriving means for deriving a transportation plan for a transportation means for transporting materials required for constructing a building indicated by the target property information, based on the target property information acquired by the acquisition means, by referring to the trained model. A derivation system characterized by:

2. 2. The derivation system of claim 1, The trained model uses a plurality of elements included in the past property information as explanatory variables and selects elements as selected elements whose contribution rate is higher than a predetermined value in a multiple regression analysis using the transportation record as a target variable. A derivation system characterized by:

3. The derivation system according to claim 1 or claim 2, The trained model is The number of transports, transport intervals, and transport capacity of the transport record are each generated as training data, The plan derivation means A transportation plan is derived based on the results of deriving the number of transportations, transportation intervals, and transportation capacity. A derivation system characterized by:

4. The derivation system according to claim 1 or claim 2, The trained model is A transfer count model generated using the transfer count of the transfer record as training data; a transfer interval model generated using transfer intervals of transfer records as training data; The transport capacity model was generated using the transport capacity of the transport record as training data. Including, The plan derivation means The number of transports is derived based on the target property information acquired by the acquisition means by referring to the transport number model, The transport interval model is referenced to derive the transport interval based on the target property information acquired by the acquisition means and the derived number of transports, The transportation capacity is derived based on the target property information acquired by the acquisition means and the derived number of transportations by referring to the transportation capacity model, A transportation plan is derived based on the derived transportation intervals and transportation capacity. A derivation system characterized by:

5. The derivation system according to claim 1 or claim 2, The property information includes information on the structure of the building, identification information on the components used, materials, specifications, locations of use, methods of use, manufacturing locations, or accessories. A derivation system characterized by:

6. 6. The derivation system of claim 5, The specifications for the components to be used include information indicating the slope of the roof, the roofing material, or the shape of the composite roof. A derivation system characterized by:

7. A deriving device that derives a transportation plan for a transportation means that transports materials necessary for building construction, an acquisition means for acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A means for accessing a trained model that stores the relationship between actual property information, which is property information on buildings that have already been constructed, and transportation records by transportation means; Equipped with The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; and a plan deriving means for deriving a transportation plan for a transportation means for transporting materials required for constructing a building indicated by the target property information, based on the target property information acquired by the acquisition means, by referring to the trained model. A derivation device characterized by:

8. A derivation program for deriving a transportation plan for transportation means for transporting materials required for the construction of a building in a computer, On the computer, an acquisition step of acquiring target property information, which is property information related to a building that is a target for deriving a transportation plan; A step of accessing a trained model that stores the relationship between actual property information, which is property information of a constructed building, and transportation records by transportation means; It is designed to execute The trained model is generated by machine learning using training data in which selected elements selected in advance from a plurality of elements included in the past property information based on the relevance to the transport past are used as input data and the corresponding transport past is used as a label; Based on the target property information acquired in the acquisition step, a transportation plan for a transportation means for transporting materials required for constructing the building indicated by the target property information is derived by referring to the trained model. A derivation program characterized by:

Images