WO2021090572A1 - 資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム - Google Patents

資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム Download PDF

Info

Publication number
WO2021090572A1
WO2021090572A1 PCT/JP2020/034261 JP2020034261W WO2021090572A1 WO 2021090572 A1 WO2021090572 A1 WO 2021090572A1 JP 2020034261 W JP2020034261 W JP 2020034261W WO 2021090572 A1 WO2021090572 A1 WO 2021090572A1
Authority
WO
WIPO (PCT)
Prior art keywords
plan
route
organization
information
template
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/034261
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
勇樹 前川
友恵 富山
健一郎 岡田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to US17/642,151 priority Critical patent/US11836657B2/en
Priority to EP20885583.3A priority patent/EP4056452A4/en
Priority to AU2020379335A priority patent/AU2020379335B2/en
Publication of WO2021090572A1 publication Critical patent/WO2021090572A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
    • B61L27/10—Operations, e.g. scheduling or time tables
    • B61L27/12—Preparing schedules
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
    • B61L27/10—Operations, e.g. scheduling or time tables
    • B61L27/18—Crew rosters; Itineraries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Definitions

  • the present invention generates a list of plan creation patterns and a recommendation model of the plan creation pattern from the actual values of the resource operation plan for the resource operation plan creation support device, the resource operation plan creation support method, and the program.
  • the present invention relates to a technique capable of supporting the creation of a high-quality resource operation plan by sequentially acquiring a plan creation pattern suitable for an input value from the recommended model.
  • this operation reorganization plan can be planned only by the person in charge who has experience in dealing with the unique restrictions of each route to be operated, and the validity of the plan can be verified.
  • the number of experienced personnel tends to decrease, and if an operation reorganization plan cannot be planned, the number of trains in operation after the disruption of operation will have to be reduced, which will seriously hinder the maintenance of transportation capacity. There is a risk.
  • the operation reorganization plan is a problem of determining the usage plan (route) of each train by allocating the trains to each train without any shortage according to the change of the operation plan.
  • These problem classes are generally proved to be difficult to calculate (NP-hard), and it is known that the optimum solution cannot be obtained in a realistic time (first problem).
  • NP-hard NP-hard
  • there are different restrictions to be observed for each line such as the arrangement of lines in the station yard, the presence or absence of lines that can be turned back, the combination of trains that can be stopped and the lines, etc.
  • the modeling itself is complicated, and the cost of model development is high (second issue).
  • the plan results created with the conventional model cannot be applied, and it is difficult to continue using the model once created (third issue).
  • Patent Document 1 describes versatility and performance scalability for a railway depot premises work plan having the same problems as the operation rearrangement plan.
  • An automatic proposal method for on-site work plans that emphasizes practicality is disclosed.
  • Patent Document 2 discloses a work plan support method that supports easier registration of a business template with respect to the method of Patent Document 1.
  • business templates representing work processes that can be selected by the organization and candidates for time constraints are prepared for each organization, and each business template is integrated into one plan for on-site work. Make a plan.
  • JP-A-2007-196880 Japanese Unexamined Patent Publication No. 2008-221918 Japanese Unexamined Patent Publication No. 2005-178742
  • Patent Document 1 and Patent Document 2 make a realistic plan while ensuring the feasibility by sequentially updating the PERT (Project Evaluation and Review Technique) network using the business template.
  • PERT Project Evaluation and Review Technique
  • Patent Document 1 since it is necessary to prepare a business template in advance, it is difficult to model for automatic creation of a work plan on the premises, and the cost for model development is large. (Second issue). In addition, since it is necessary to update the business template as appropriate, it is difficult to continue to use the model once created (third issue).
  • the present invention has been made in consideration of the above points, and it is possible to automatically generate a model that recommends the route of the organization, automatically select the route suitable for the target organization, and create an operation reorganization plan. It is intended to propose possible resource operation plan creation support devices, resource operation plan creation support methods, and programs.
  • the following resource operation plan creation support device for creating an operation rearrangement plan for a target organization group.
  • This resource operation plan creation support device is a learning information storage unit that stores the plan result information of the existing operation reorganization plan, and a route recommendation processing unit that generates a route recommendation model, which is a model for recommending routes, as a pre-learning function.
  • a plan creation function a plan creation processing unit that selects a route template suitable for the organization of the planning target and creates an operation rearrangement plan based on the route recommendation model generated by the route recommendation processing unit, and the plan. It includes a screen processing unit that outputs a plan result display screen that displays the operation rearrangement plan created by the creation processing unit.
  • the route recommendation processing unit further includes the route learning data including the input format and the route template for each input format specified by the user based on the plan result information stored in the learning information storage unit.
  • a route learning data set generation unit that generates a set
  • a route recommendation model generation unit that generates a route recommendation model including a classifier that learns the route template according to the input format from the route learning data set.
  • the plan creation processing unit For each organization to be planned, the plan creation processing unit generates an organization input value according to the input format of the route recommendation model from the information about the organization, and uses the organization input value as the route recommendation model.
  • a template priority list creation unit that creates a template priority list that summarizes the priorities for each route template that is input to the classifier and is obtained as an output of the classifier, and the template priority list created for each organization. Based on the above, the route template having the higher priority is preferentially selected in the template priority list, the plan is created for each organization, and the operation arrangement plan is created for all the organizations to be planned. It has a template and a template.
  • the following resource operation plan creation support method for creating an operation rearrangement plan for a target organization group includes a learning information storage step for storing the plan result information of the existing operation reorganization plan and a route recommendation processing step for generating a route recommendation model which is a model for recommending a route as a pre-learning function.
  • a plan creation function a plan creation process step of selecting a route template suitable for the organization of the plan target and creating an operation rearrangement plan based on the route recommendation model generated in the route recommendation process step, and the plan. It includes a plan result display step for displaying the operation rearrangement plan created in the creation process step.
  • the route recommendation processing step is based on the plan result information stored in the learning information storage step, and the route learning data including the input format and the route template for each input format specified by the user.
  • the route recommendation model including a route learning data set generation step for generating a set and a classifier for learning the route template according to the input format from the route learning data set generated in the route learning data set generation step.
  • the plan creation processing step generates an organization input value according to the input format of the route recommendation model from the information about the organization for each organization to be planned.
  • the template priority list creation step of inputting the organization input value into the classifier of the route recommendation model and creating a template priority list summarizing the priorities for each route template obtained as the output of the classifier, and Based on the template priority list created for each organization, the route template having the higher priority is preferentially selected in the template priority list to create a plan for each organization, and all the organizations to be planned are created. It has an operation reorganization plan creation step for creating the operation reorganization plan for the above.
  • the following program for creating an operation rearrangement plan of a target organization group has a learning information storage step that stores the plan result information of the existing operation rearrangement plan, a route recommendation processing step that generates a route recommendation model that is a model for recommending routes, and a plan creation function as a pre-learning function.
  • a plan creation process step for selecting a route template suitable for the organization of the plan target and creating an operation rearrangement plan based on the route recommendation model generated in the route recommendation process step, and creating the plan creation process step. It is provided with a plan result display step for displaying the operation rearrangement plan and a program for causing a computer to execute.
  • the program for executing the route recommendation processing step obtains the input format and the route template for each input format specified by the user based on the plan result information stored in the learning information storage step. It has a process of generating a route learning data set including, and a process of generating the route recommendation model including a classifier that learns the route template according to the input format from the generated route learning data set.
  • the program that executes the plan creation processing step generates an organization input value according to the input format of the route recommendation model from the information about the organization for each organization to be planned, and uses the organization input value as the route.
  • the template priority list includes a process of preferentially selecting the route template having a high priority, creating a plan for each organization, and creating an operation rearrangement plan for all the organizations to be planned. ..
  • FIG. 1 is a block diagram showing a configuration example of a resource operation plan creation support device according to an embodiment of the present invention.
  • the resource operation plan creation support device 1 according to the present embodiment is a computer system, and as shown in FIG. 1, for example, a CPU (Central Processing Unit) 11, a memory 12, a storage unit 13, a communication unit 14, and an input unit 15. , And a display unit 16, and each configuration is connected to each other by a communication line 17.
  • a CPU Central Processing Unit
  • the CPU 11 is an example of a processing device that executes various programs 100 stored in the memory 12 which is the main storage device of the resource operation plan creation support device 1. Each function is realized by the CPU 11 executing various programs 100 stored in the memory 12.
  • FIG. 1 shows a route recommendation processing unit 110, an operation rearrangement plan creation processing unit 120, a function switching processing unit 130, and a screen processing unit 140 as each functional unit in the resource operation plan creation support device 1 according to the present embodiment. Has been done.
  • the route recommendation processing unit 110 has a function of performing "route recommendation processing" for generating a model (route recommendation model) that recommends a route according to an input format as a pre-learning function. It includes a learning plan result reading unit 111, an input format selection unit 112, a route learning data set generation unit 113, a route recommendation model generation unit 114, and a route recommendation model storage unit 115. Details of each functional unit will be clarified in the description of specific processing described later.
  • the operation rearrangement plan creation processing unit 120 has a function as a plan creation function of performing a "plan creation process" for automatically selecting a route template suitable for the target organization based on the route recommendation model and creating an operation rearrangement plan.
  • more detailed functions include an operation rearrangement plan target reading unit 121, a route recommendation model selection unit 122, a template priority list creation unit 123, an operation rearrangement plan creation unit 124, and an operation rearrangement plan storage unit 125. Details of each functional unit will be clarified in the description of specific processing described later.
  • the function switching processing unit 130 has a function of switching between the above-mentioned pre-learning function and the plan creation function.
  • the screen processing unit 140 generates various screens to be output to the display unit 16 in accordance with the execution of the processing by each of the above processing units, and also inputs the screen output to the display unit 16 via the input unit 15. Has a function to accept.
  • Specific screens generated by the screen processing unit 140 include a function selection screen 141, a learning plan result selection screen 142, an input format selection screen 143, a recommended model attribute information correction screen 144, a plan information selection screen 145, and a route recommendation. Examples include a model selection screen 146 and a plan result display screen 147. Details of each screen will be clarified in the description of specific processing described later.
  • the storage unit 13 is a storage device that stores various information, for example, an auxiliary storage device of the resource operation plan creation support device 1.
  • planning information 201 learning plan result information 202, route learning data set information 203, route recommendation model information 204, planning target organization information 205, route template priority list information. 206, operation reorganization plan temporary information 207, and plan result information 208 are shown. Details of each information will be described later.
  • the above information may be stored in an external storage area (for example, on the cloud, an external database, etc.) connected via the communication network 20.
  • the communication unit 14 is a communication interface connected to the communication network 20, and connects the resource operation plan creation support device 1 and the external device via the communication network 20 so as to be communicable.
  • the input unit 15 is an input device that receives an input operation by the user, such as a mouse or a keyboard. Further, the display unit 16 is a display device such as a display. As described above, various screens generated by the screen processing unit 140 are displayed on the display unit 16, and when a user performs a predetermined operation on this screen via the input unit 15, the screen is displayed. The operation is reflected on the screen.
  • FIG. 2 is a diagram showing an example of planning information.
  • the plan information 201 is information that stores a list of organization information to be planned by date.
  • the formation information is registered for each formation (for each formation ID), and has information such as the starting station, the ending station, the vehicle type, and the work content, as shown in FIG. 2, for example.
  • FIG. 3 is a diagram showing an example of learning plan result information.
  • the learning plan result information 202 stores the plan result information of the existing operation rearrangement plan stored in the plan result information 208 for pre-learning. Therefore, the learning plan result information 202 and the plan result information 208 may be considered to be the same data format.
  • the learning plan result information 202 stores information related to the plan result by date, and can be composed of the plan result information 2021, the route information 2022, and the plan evaluation value 2023.
  • the plan result information 2021 is a graph display of the route for each organization.
  • Route information 2022 is generated by extracting trains assigned to each plan target date and organization from the plan result information 2021.
  • the route information 2022 may be generated from the plan result information 2021 as needed, or may be generated in advance and stored in the learning plan result information 202.
  • the plan evaluation value 2023 holds the evaluation value according to a predetermined evaluation item (for example, "compliance rate of operational constraints") with respect to the operation reorganization plan.
  • FIG. 4 is a diagram showing an example of the route learning data set information.
  • the route learning data set information 203 stores a data set (route learning data set) that summarizes a plurality of information related to the operation rearrangement plan.
  • the route learning data set is generated from the planning result of the known (existing) operation reorganization plan based on the input format selected by the user, and the route learning data set information 203 contains the route learning data set for each input format. Multiple sets are retained.
  • each data set of the route learning data set information 203 contains one set of four pieces of information: an input format 2031, an organization input value 2032, a route template 2033, and a route correct answer value 2034. And.
  • the route learning data set information 203 is generated by the route learning data set generation unit 113.
  • the input format 2031 is information indicating a combination of input items (input format) that is valid among a plurality of input items related to the operation rearrangement plan, and is a selection result by the user on the input format selection screen 143 (see FIG. 13). Is generated to reflect.
  • the selectable input format displayed on the input format selection screen 143 is described as a combination of "category” and "input value item", and the selection result by the user is "state”. Is reflected in.
  • Each item of the input format that can be selected on the input format selection screen 143 shall be registered in advance.
  • the organization input value 2032 is a list format of actual values (raw values) for each organization based on the learning plan result read from the learning plan result information 202 for each item of the input format described in the input format 2031. Save with.
  • the route template 2033 stores a list of a plurality of route templates with identification numbers (route template identification numbers).
  • the route template is generated by the route learning data set generation unit 113 repeating the search and update by the predetermined search key for the route extracted from the learning plan result read from the learning plan result information 202. To.
  • the route correct answer value 2034 holds the information of the route template corresponding to the plan result for each organization.
  • the route correct answer value 2034 shown in FIG. 4 whether or not the route template corresponds to the planning result is described in the “corresponding state”, and in this corresponding state, the route learning data set generation unit 113 informs the route template 2033. Judgment is made by comparing each retained premises template with the route of each organization shown in the learning plan result.
  • FIG. 5 is a diagram showing an example of route recommendation model information.
  • the route recommendation model information 204 stores a model (route recommendation model) that recommends a route according to the input format.
  • the route recommendation model is configured as a set of a plurality of information described later, and these are generated from the route learning data set information 203. Therefore, the route recommendation model information 204 holds a plurality of sets of route recommendation models for each input format.
  • each route recommendation model of the route recommendation model information 204 has four pieces of information of the input format 2041, the classifier 2042, the route template 2043, and the attribute information 2044 as one set. ..
  • the input format 2041, the classifier 2042, and the route template 2043 are generated by the route recommendation model generation unit 114 based on the route learning data set information 203, and the attribute information 2044 is input via the recommended model attribute information correction screen 144. Generated accordingly.
  • the input format 2041 and the route template 2043 are the same as the input format 2031 and the route template 2033 of the route learning data set information 203 described with reference to FIG. 4, and the description thereof will be omitted.
  • the classifier 2042 is a classifier that learns the route template 2043 according to the input format 2031 by using the existing operation rearrangement plan (which may be replaced with the route learning data set) as training data.
  • the classifier 2042 is not limited to a specific type of classifier, and machine learning may be used, or a predetermined classification rule, statistical processing, or the like may be used.
  • a neural network is used for the classifier 2042, the graph structure and the weight of each side are stored, and when a decision tree is used, the tree structure and the classification rule (if-then) when branching to each branch are used.
  • the rule may be stored. Since the format differs depending on the type of classifier, a unified format is not presented here. In FIG. 19, which will be described later, an image of a classifier 2042 using a simple neural network is shown as an example.
  • Attribute information 2044 holds attribute information for each route recommendation model.
  • the attribute information 2044 holds a name of the route recommendation model, a creation date and time, a tag given as an attribute of the route recommendation model, and a memo for the route recommendation model.
  • FIG. 6 is a diagram showing an example of planning target organization information.
  • the plan target organization information 205 holds the organization information related to the target organization of the operation reorganization plan.
  • the planned target formation information 205 holds the ID, the starting station, the ending station, the vehicle type, and the presence / absence of predetermined work for the target formation.
  • the planning target organization information 205 can be created by extracting from the planning information 201.
  • FIG. 7 is a diagram showing an example of the route template priority list information.
  • the route template priority list information 206 is information indicating the priority for each route template 2033 (or route template 2043) in the creation of the operation rearrangement plan, and the template priority list creation unit 123 inputs the organization input value 2032. Generated from the output of a given classifier 2042. In the case of FIG. 7, the priority is indicated by a numerical value between "0" and "1", and the closer the numerical value is to "1", the higher the priority.
  • the operation reorganization plan temporary information 207 is temporary information regarding the operation reorganization plan stored in the middle of the process of the plan creation process, and examples thereof will be omitted.
  • the plan result information 208 is specific because the learning plan result information 202 and the plan result information 208 may have the same data format as described above in the description of the learning plan result information 202 illustrated in FIG. An example is omitted.
  • FIG. 8 is a flowchart showing an example of a processing procedure of the entire processing in the resource operation plan creation support device 1 shown in FIG. Further, FIG. 9 is a diagram showing the relationship between the functional unit related to the pre-learning function and the data, and FIG. 10 is a diagram showing the relationship between the functional unit related to the plan creation function and the data.
  • the function selection screen 141 is displayed on the display unit 16, and the function switching processing unit 130 determines the selected function (mode) based on the user's selection on the function selection screen 141 (step S101). ).
  • FIG. 11 is an example of the function selection screen. As shown in FIG. 11, on the function selection screen 141, two functions (modes) of pre-learning for creating a route recommendation model and planned learning for creating an operation rearrangement plan are displayed so as to be selectable, and the user can select any of them. By selecting the function and pressing the "Start" button, the function selection is confirmed.
  • step S101 If the function selected in step S101 is not in the planning mode, that is, in the pre-learning mode (NO in step S101), the process proceeds to step S102, and the pre-learning function is mainly performed by the route recommendation processing unit 110. (Steps S102 to S107).
  • the function selected in step S101 is the plan creation mode (YES in step S101)
  • the process proceeds to step S108, and the operation rearrangement plan creation processing unit 120 mainly executes the processing by the plan creation function. (Steps S108 to S116).
  • the route recommendation processing unit 110 determines whether or not to create a route recommendation model (step S102 in FIG. 8).
  • the process proceeds to step S103, and the route recommendation process is actually started.
  • the route recommendation model is not created (NO in step S102)
  • the process ends without performing any special process.
  • the process of step S102 is a process for reconfirming whether or not the route recommendation model is really created when the pre-learning mode is selected in step S101. For example, a confirmation screen (not shown) is displayed. Then, the determination may be made based on the user's response to it. When such reconfirmation is unnecessary, the process of step S102 may be skipped.
  • the learning plan result selection screen 142 is displayed on the display unit 16, and the learning plan result reading unit 111 is for learning based on the user's selection on the learning plan result selection screen 142.
  • the planning result is selected (step S103).
  • FIG. 12 is an example of a learning plan result selection screen.
  • the learning plan result selection screen 142 information about the existing plan result stored in the learning plan result information 202 is displayed, and the user is selected from among the displayed plurality of plan results. Selects one or more desired plan results and presses the "Read learning plan result specification file” button to confirm the selection.
  • the learning plan result information 202 stores the existing plan result information stored in the plan result information 208 in the previously executed plan creation process. Further, as shown as "type" in FIG.
  • the learning plan result information 202 (the same applies to the plan result information 208) includes not only the actual plan results that can be said to be the collective knowledge of the know-how so far, but also the actual plan results.
  • the plan results obtained by the simulation of the resource operation plan creation support device 1 can also be saved, and the learning plan results can be selected from these various plan results.
  • the learning plan result reading unit 111 selects the learning plan result by reading the plan result selected on the learning plan result selection screen 142 from the learning plan result information 202.
  • the learning plan result selection screen 142 not only the “date” indicating the creation date and time of the plan result to be selected, but also the “type”, the “plan evaluation value”, and the like. By displaying information that can be used as a judgment criterion when the user makes a selection, the user's judgment can be assisted and more appropriate selection can be supported.
  • the input format selection screen 143 is displayed on the display unit 16, and the input format selection unit 112 selects the input format based on the user's selection on the input format selection screen 143 (step S104).
  • FIG. 13 is an example of the input format selection screen.
  • the input format used for creating the route recommendation model is displayed so as to be selectable, and the user selects an arbitrary input format and clicks the "Read input format specification file” button. By pressing, the selection of the input format is confirmed.
  • the items of the input format that can be selected are the "individual organization” category for individual organization, the "whole plan” category for the overall operation reorganization plan, and the "external environment” other than the above categories. It is classified into the category of. Of these, the category of external environment can include external factors such as weather and snowfall, and when these external information is selected, weather information is externally provided via the network (communication network 20). It suffices to acquire open data such as (see also FIG. 17 described later).
  • the resource operation plan creation support device 1 by making such an external environment selectable as an input format, it is possible to create a more accurate operation arrangement plan.
  • step S104 the route learning data set generation unit 113 determines the data set of the operation rearrangement plan based on the learning plan result selected in step S103 and the input format selected in step S104.
  • the route learning data set information 203) is generated (step S105).
  • the process of step S105 is called a path learning data set generation process, and the details thereof will be described later with reference to FIGS. 15 to 17.
  • the route recommendation model generation unit 114 generates a route recommendation model based on the route learning data set information 203 generated in step S105 (step S106).
  • the process of step S106 is called a route recommendation model generation process, and the details thereof will be described later with reference to FIGS. 18 and 19.
  • the display unit 16 displays the recommendation model attribute information correction screen 144 for the route recommendation model generated in step S106, and is requested to input the attribute information of the route recommendation model. Then, after inputting the attribute information, when the save is instructed by the user operation on the recommended model attribute information correction screen 144, the route recommendation model storage unit 115 transfers the route recommendation model to which the attribute information is added to the route recommendation model information 204. It is saved (step S107), and the route recommendation process ends.
  • FIG. 14 is an example of the recommended model attribute information correction screen.
  • various attribute information (see also attribute information 2044 in FIG. 5) is provided to the user for the route recommendation model generated by the route recommendation model generation unit 114. Is displayed so that it can be added or modified. Then, after the user adds or modifies the attribute information of the route recommendation model on the recommended model attribute information modification screen 144, the registered contents of the attribute information are confirmed by pressing the "save and end" button. In response to this confirmation operation, the route recommendation model storage unit 115 stores the route recommendation model in the route recommendation model information 204 with the confirmed contents.
  • FIG. 9 shows the relationship between each related functional unit and the data in an easy-to-understand manner.
  • the template priority list creation unit 123 is shown by a broken line. This is because the process of creating the route template priority list information 206 by the template priority list creation unit 123 is a pre-learning function (route recommendation). It means that it is executed by the plan creation function (plan creation process) instead of the process).
  • the template priority list creation unit 123 uses the route recommendation model information 204 generated by the route recommendation process, and at the time of the plan creation process, the priority of the route template is based on the organization input value according to the input format. It has a function to create an attached list (route template priority list information 206). That is, the timing at which the template priority list creation unit 123 creates the above list is at the time of the plan creation process, but due to the illustration, FIG. 10 showing the plan creation function (plan creation process) shows the template priority list creation. Part 123 is not described.
  • FIG. 15 is a flowchart showing an example of a processing procedure of the route learning data set generation process.
  • the route learning data set generation process is the process in step S105 of FIG. 8, and is a process in which the route learning data set generation unit 113 generates a route learning data set in which information on the operation rearrangement plan is summarized. ..
  • step S121 whether or not the route learning data set generation unit 113 has performed the operations (processes) of steps S124 to S128, which will be described later, for all the learning plan results selected in step S103 of FIG. Is determined (step S121). If there is a learning plan result in which the above operation has not been performed, including the first time, the process proceeds to step S122, and the plan result information (learning plan result information 202) corresponding to the unoperated learning plan result is acquired. After that, the process proceeds to step S123. On the other hand, when the above operation is completed for all the selected learning plan results, the process proceeds to step S129.
  • step S123 the route learning data set generation unit 113 determines whether or not the operations (processes) of steps S124 to S128, which will be described later, have been performed for all the formations included in the plan result information acquired in step S122. To do.
  • the process proceeds to step S124, and if the above operations are completed for all the knitting, the process returns to step S121.
  • step S124 the route learning data set generation unit 113 acquires the organization information regarding the next organization and the route of the organization.
  • the route learning data set generation unit 113 generates an organization input value from the organization information acquired in step S124 according to the input format selected (designated) via the input format selection screen 143 in step S104 of FIG. (Step S125).
  • the selected (designated) input format is added to the list of the input format 2031.
  • the route learning data set generation unit 113 updates the route template 2033 based on the route acquired in step S124 (step S126).
  • the route learning data set generation unit 113 generates a route correct answer value based on the route acquired in step S124 (step S127).
  • the route learning data set generation unit 113 adds the organization input value generated in step S125 and the route correct answer value generated in step S127 to the respective lists (organization input value 2032, route correct answer value 2034) (step). S128).
  • step S129 the route learning data set generation unit 113 adds or updates various information added or updated in the previous processing in the route learning data set generation process (specifically, the input format 2031 added in step S125, step S126).
  • the route template 2033 updated in step 2, the organization input value 2032 added in step S128, and the route correct answer value 2034) are stored in the storage unit 13 as the route learning data set information 203.
  • FIGS. 16 and 17 show specific examples of a procedure for generating (adding, updating) various information included in the route learning data set information 203 by the route learning data set generation process described above.
  • FIG. 16 is a diagram for explaining a method of generating a route template.
  • the learning plan result (plan result information 2021-1) is acquired from the learning plan result information 202 according to the selection in step S103 of FIG. 8, and the selected organization (book).
  • the route information 2022-1 is extracted for the organization I) (step S124).
  • the route learning data set generation unit 113 uses a predetermined search key (“order”, “original route ID”, “in-route order”, “arrival station”) included in the extracted route information 2022-1. , "Train route type”, "Train type” column) to search the existing route template 2033-1 read from the route learning data set information 203.
  • the route learning data set generation unit 113 does not update the route template when there is a route template whose search key matches by the above search.
  • the route learning data set generation unit 113 creates a new route template based on the extracted route information 2022-1 when there is no route template whose search key matches in the search for the existing route template 2033-1. , Add (step S126).
  • the route learning data set generation unit 113 can perform the route learning data set information.
  • the route template 2033 stored in 203 can be updated.
  • FIG. 17 is a diagram for explaining a method of generating an input format, an organization input value, and a route correct answer value.
  • the learning plan result (plan result information 2021-1) is acquired from the learning plan result information 202 according to the selection of step S103 in FIG. Further, although not shown in FIG. 17, the organization information and the route for the selected organization (organization I in this example) are extracted from the plan result information 2021-1 (step S124).
  • the route learning data set generation unit 113 uses the organization input value 2032 from the organization information extracted in step S124 according to the input format selected (designated) via the input format selection screen 143 in step S104 of FIG. -1 is generated (step S125).
  • a route learning data set is generated as shown in FIG. 7 as "acquisition of external environment information”.
  • the unit 113 acquires desired external environment information via the communication network 20, and uses this to generate the organization input value 2032-1.
  • the route learning data set generation unit 113 converts the route information of each organization extracted in step S124 (similar to the route information 2022-1 in FIG. 16) into the route template updated in step S126 (the route template in FIG. 16).
  • the corresponding state is determined by collating with 2033-1). Then, the relationship between the identification number of each route template and the corresponding state (corresponding / not applicable) is generated as the route correct answer value 2034-1 (step S127).
  • the route learning data set generation unit 113 adds the organization input value 2032-1 generated in step S125 and the route correct answer value 2034-1 generated in step S127 to their respective lists (step S128), and selects the input format.
  • the route learning data set information 203 By registering in the route learning data set information 203 together with the input format selected (designated) via the screen 143 (step S129), the input format 2031, the organization input value 2032, and the route correct answer value 2034 can be generated. ..
  • FIG. 18 is a flowchart showing a processing procedure example of the route recommendation model generation process.
  • the route recommendation model generation process is the process in step S106 of FIG. 8, and is the process in which the route recommendation model generation unit 114 generates the route recommendation model.
  • the route recommendation model generation unit 114 acquires the route learning data set information 203 stored in the storage unit 13 (step S131).
  • the route recommendation model generation unit 114 acquires a list of the organization input value 2032 and the route correct answer value 2034 from the route learning data set information 203 acquired in step S131 (step S132).
  • the route recommendation model generation unit 114 determines whether or not the operations (processes) of steps S134 and S135, which will be described later, have been performed for all the organization input values included in the list acquired in step S132 (step S133). ). Here, if there is an unoperated organization input value, the process proceeds to step S134, and if the above operation is completed for all the organization input values, the route recommendation model generation process is terminated.
  • step S134 the route recommendation model generation unit 114 acquires the next organization input value and the route correct answer value corresponding to the organization input value from the list of organization input values 2032 acquired in step S132.
  • the route recommendation model generation unit 114 uses the organization input value acquired in step S134 as an input and the route correct answer value acquired in step S134 as a teacher to generate a classifier by any learning means, and generates a classifier for the route recommendation model. Use as a classifier (step S135).
  • the route recommendation model generation unit 114 uses the input format 2031 and the route template 2033 stored as a set with the organization input value and the route correct answer value used for generating the classifier in the route learning data set information 203.
  • the attribute information of the route recommendation model is added by a user operation via the recommended model attribute information correction screen 144 later.
  • step S135 When the process of step S135 is completed, the process returns to step S133, and as described above, the route recommendation model generation unit 114 determines whether the operations (processes) for all the organization input values have been completed. Therefore, until the determination of YES is obtained in step S133 and the route recommendation model generation process is completed, the route recommendation model generation unit 114 repeatedly executes the processes of steps S134 to S135 for each organization input value. , For each organization input value included in the list of organization input values 2032 acquired in step S132 (in other words, for each operation rearrangement plan stored as a set in the route learning data set information 203), the input format of the route recommendation model. , Sorters, and route templates can be generated.
  • FIG. 19 shows a specific example of a procedure for registering various information included in the route recommendation model information 204 by the route recommendation model generation process and the subsequent storage process (step S107 in FIG. 8) described above.
  • FIG. 19 is a diagram for explaining a method of generating various information included in the route recommendation model information.
  • a simple neural network is used as the classifier.
  • the route recommendation model generation unit 114 from the route learning data set information 203, pairs the organization input value and the route correct answer value (organization input value 2032-2, route correct answer value 2034-2). (Step S134).
  • the route recommendation model generation unit 114 updates the parameters (side weights) of the neural network using the gradient descent method with the organization input value 2032-2 as the input value and the route correct answer value 2034-2 as the teacher value. ..
  • This parameter update process is common in neural networks, and although detailed description thereof will be omitted, the classifier 2042-2 is updated by this update process (step S135).
  • the route recommendation model generation unit 114 can perform the route recommendation model.
  • a classifier can be generated.
  • the route recommendation model generation unit 114 uses the input format 2031 and the route template 2033 stored in the route learning data set information 203 as a set with each pair of the route recommendation models. Input format and route template.
  • these various types of information are subjected to the user operation on the recommendation model attribute information correction screen 144, and then various information of the route recommendation model information 204 (input format 2041, It is registered as a classifier 2042, a route template 2043). Further, the attribute information input by the user on the recommended model attribute information correction screen 144 is registered as the attribute information 2044.
  • the resource operation plan creation support device 1 inputs from a plurality of plan results stored in the learning plan result information 202 by executing the route recommendation process as a pre-learning function.
  • a model that recommends a route according to the input format by generating a route learning data set for each input format specified (selected) by the user on the format selection screen 143 and learning based on the route learning data set (route recommendation).
  • Model can be generated automatically. That is, the resource operation plan creation support device 1 can generate a recommendation model effective for plan creation from various learning data including actual plans and simulation results.
  • plan information selection screen 145 is displayed on the display unit 16, and the operation rearrangement plan target reading unit 121 selects the plan creation target based on the user's selection on the plan information selection screen 145. (Step S108 in FIG. 8).
  • FIG. 20 is an example of the plan information selection screen.
  • a target for creating a plan can be selected from the plan information stored in the plan information 201.
  • the selection of the plan creation target is confirmed.
  • the operation rearrangement plan target reading unit 121 acquires a list of organization information corresponding to the selected plan information from the plan information 201.
  • the route recommendation model selection screen 146 is displayed on the display unit 16, and the route recommendation model selection unit 122 selects the route recommendation model based on the user's selection on the route recommendation model selection screen 146 (step S109).
  • FIG. 21 is an example of a route recommendation model selection screen. As shown in FIG. 21, on the route recommendation model selection screen 146, it is displayed so that the route recommendation model to be used for the current plan creation can be selected from the route recommendation models stored in the route recommendation model information 204. ing. On the route recommendation model selection screen 146, the user selects one route recommendation model according to the current plan creation and presses the "plan creation start” button, so that the selection of the route recommendation model is confirmed. To give a specific example of the user selecting a route recommendation model according to the plan creation, when the plan information of "normal day” of "YYYY year” is selected on the plan information selection screen 145, the route recommendation model is selected. On the screen 146, a route recommendation model with a tag (attribute information) of "YYY year compliant" and "normal day orientation" may be selected.
  • a route recommendation model with a tag (attribute information) of "YYY year compliant" and "normal day orientation” may be selected.
  • route recommendation model selection screen 146 not only the name of the route recommendation model to be selected but also the user makes a judgment such as “tag” or “memo”. By displaying information that can be used as a reference, the user's judgment can be assisted and more appropriate selection can be supported. The same applies to the plan information selection screen 145 of FIG. 20 described above.
  • the route recommendation model selection unit 122 acquires the selected route recommendation model from the route recommendation model information 204.
  • the operation reorganization plan creation processing unit 120 selects one of the plurality of organizations included in the list of organization information acquired in step S108 for which no plan has been created. , Select as the next target organization (step S110).
  • the operation rearrangement plan creation unit 124 generates the planning target organization information 205 based on the organization information regarding the selected next organization.
  • the selection of the next organization in step S110 is repeatedly executed until the planning is completed for all the organizations included in the list of organization information, but each time, the organization related to the selected next organization is executed. Information is sequentially added to the planning target organization information 205.
  • the operation rearrangement plan creation processing unit 120 (for example, the template priority list creation unit 123 or the operation rearrangement plan creation unit 124) generates the organization input value information according to the input format of the route recommendation model (step S111).
  • the template priority list creation unit 123 inputs the organization input value information generated in step S111 into the classifier of the route recommendation model, and generates the route template priority list information 206 based on the output (step S112). ).
  • the operation reorganization plan creation unit 124 adds the route template related to the selected target organization to the operation reorganization plan based on the route template priority list information 206 acquired in step S112, and executes the plan creation (step). S113).
  • the operation rearranging plan creation unit 124 refers to the priority shown in the route template priority list information 206, and is selecting from the route templates 2043 of the route recommendation model information 204 in order from the route template having the highest priority. Select as a route template for the target organization of.
  • the method of planning is not limited to a specific method, and conventionally known planning techniques can be used. Specifically, for example, a genetic algorithm or the like can be used.
  • step S114 determines whether or not a feasible plan has been obtained by creating the plan in step S113 (step S114). If a feasible plan is obtained (YES in step S114), the process proceeds to step S116, and if a feasible plan is not obtained (NO in step S114), the process proceeds to step S116 through step S115.
  • step S115 the operation rearrangement plan creation unit 124 requests the user to manually create a plan, assuming that the selected target organization cannot automatically create a plan (plan creation impossible organization).
  • the request to the user can be realized by displaying a predetermined screen on the display unit 16, and when the plan is manually created by the user, the operation arrangement plan creation unit 124 adds this to the operation arrangement plan.
  • step S115 is prepared as an exception process. The reason is that, in the present embodiment, when a plan that can be implemented by creating a plan using one route template cannot be created, the plan creation using the route template having a high priority is repeated in sequence, which is realistic. This is because it is unlikely that a non-planning organization will occur.
  • step S116 the operation rearrangement plan storage unit 125 determines whether or not the plan creation is completed for all the formations included in the list of formation information acquired in step S108.
  • the operation reorganization plan storage unit 125 adds the operation reorganization plan created for the selected target organization to the operation reorganization plan temporary information 207.
  • the process returns to step S110.
  • step S110 the next knitting is selected from the unfinished knitting, and the processes of steps S111 to S115 are performed on the selected next knitting.
  • steps S110 to S116 a plan is created for each organization, and the created operation rearrangement plan is sequentially added to the operation rearrangement plan temporary information 207.
  • the operation reorganization plan storage unit 125 stores the operation reorganization plan accumulated in the operation reorganization plan temporary information 207 in the plan result information 208. End the planning process.
  • the operation rearrangement plan created in the plan creation process is displayed to the user by displaying the plan result display screen 147 on the display unit 16 before storing the operation rearrangement plan in the plan result information 208. You may try to do it. Further, on the plan result display screen 147, the user may be able to select whether or not to save the displayed operation reorganization plan in the plan result information 208, and the recommendation used for creating the operation reorganization plan. A function that can modify the attribute information of the model may be provided.
  • FIG. 22 is an example of the plan result display screen.
  • the operation reorganization plan created in the plan creation process and accumulated in the operation reorganization plan temporary information 207 is displayed.
  • the saving of the operation rearrangement plan being displayed in the plan result information 208 is confirmed.
  • the "Modify the attribute information of the recommended model used" button is pressed, the attribute information of the route recommendation model used when creating the operation rearrangement plan being displayed is newly displayed, etc. Therefore, the user can modify the attribute information.
  • plan evaluation value is displayed together with the operation rearrangement plan.
  • the planned evaluation value is an evaluation value based on a predetermined evaluation item (for example, "compliance rate of operational constraints") for the operation reorganization plan, and for example, the operation reorganization plan creation processing unit 120 executes the evaluation.
  • a predetermined evaluation item for example, "compliance rate of operational constraints”
  • the operation reorganization plan creation processing unit 120 executes the evaluation.
  • FIG. 10 shows the relationship between each related functional unit and the data in an easy-to-understand manner.
  • an arrow is connected from the plan result information 208 to the learning plan result information 202.
  • FIG. 23 is a diagram for explaining a method of generating route template priority list information.
  • a list of organization information corresponding to the selected plan information is acquired from the plan information 201, and the next organization of step S110 is selected.
  • One organization information (the part surrounded by the broken line in FIG. 23) is extracted from the list of organization information according to the above, and the planning target organization information 205-3 is generated.
  • the route recommendation model 2040-3 is acquired from the route recommendation model information 204.
  • the organization input value information is generated from the organization information of the planned target organization information 205-3 (step S111).
  • the knitting input value information for example, the knitting input value 2032-1 shown in FIG. 17 can be referred to.
  • FIG. 23 shows that the external environment information can be acquired and reflected in the generation of the organization input value information.
  • the organization input value information generated as described above is given as an input to the classifier 2042-3 constituting the route recommendation model 2040-3, and the output value is set as the priority, so that the route template priority list is used.
  • Information 206 is generated (step S112).
  • FIG. 24 is a diagram for explaining a method of generating plan result information.
  • FIG. 24 shows the continuation of the procedure shown in FIG. 23, and the common configurations are designated by the same reference numerals.
  • step S113 of FIG. 8 the planned target organization information 205-3, the route template 2043-3 constituting the route recommendation model 2040-3, and the route template priority list information 206 are input as predetermined. Planning is executed by the method of.
  • the route template 2043-3 input in the plan creation is selected according to the priority of the route template priority list information 206. Specifically, for example, the route template 2043-3 is sequentially input in descending order of priority until a feasible plan can be created, and the plan creation is executed.
  • the operation reorganization plan is added to the operation reorganization plan temporary information 207, and the plan creation is repeated for the next organization in the same manner.
  • the operation rearrangement plan for each organization accumulated in the operation rearrangement plan temporary information 207 can also be used as an input for the plan creation.
  • the operation reorganization plan accumulated in the operation reorganization plan temporary information 207 is saved in the plan result information 208, and the plan creation process is completed.
  • the user may be made to decide whether or not to save the plan result display screen 147.
  • the resource operation plan creation support device 1 executes the plan creation process as the plan creation function, and is based on the organization information of the plan target and the input format specified (selected) by the user. , It is possible to flexibly generate a prioritized list of route templates (route template priority list information 206) using the route recommendation model generated by the pre-learning function, and further, using a route template based on this priority. By creating a plan for each target organization, it is possible to recommend a model close to the training data used in the pre-learning function for the target organization.
  • the resource operation plan creation support device 1 automatically generates a route recommendation model in the pre-learning function, and uses the above recommendation model in the plan creation function. By using it, it is possible to automatically select a route template suitable for the target organization and create an operation rearrangement plan.
  • the resource operation plan creation support device 1 based on the recommendation model generated by the pre-learning function, not only the operation arrangement plan is created by the plan creation function, but also the created plan result is used.
  • a predetermined evaluation is performed on the subject, and the evaluation result (planned evaluation value) is stored in the plan result information 208 together with the plan result.
  • the information stored in the plan result information 208 is also stored in the learning plan result information 202 and used for the subsequent pre-learning function, so that it can be fed back to the pre-learning function.
  • the pre-learning function can generate a recommended model by following the result of the planning function.
  • the resource operation plan creation support device 1 according to the present embodiment can repeat feedback between the pre-learning function and the plan creation function, so that the accuracy of the product can be automatically improved.
  • the resource operation plan creation support device 1 it is possible to create an operation arrangement plan in which a plurality of decision variables are intricately intertwined, while considering various user choices. Therefore, it is possible to solve the first problem described above as a problem of the prior art.
  • resource operation plan creation support device 1 it is possible to automatically create an operation rearrangement plan for which it was difficult to model the problem itself.
  • the second problem that has been solved can be solved.
  • the resource operation plan creation support device 1 generates a plurality of recommended models according to the selection of the original data in the pre-learning function, and a plurality of recommended models to be used for the plan creation in the plan creation function. Since you can select from the candidates, even if there is an environmental change such as a timetable revision or a change in equipment, you can easily respond to the environmental change by adding the original data and changing the selection destination. Can be created. That is, it is not necessary to recreate the model at a great cost every time the environment changes, and the third problem described above as a problem of the prior art can be solved.
  • the present invention is not limited to the above-described embodiment, and includes various modifications.
  • the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. Further, it is possible to add / delete / replace a part of the configuration of the embodiment with another configuration.
  • each of the above configurations, functions, processing units, processing means, etc. may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor of the computer interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.
  • SSD Solid State Drive
  • control lines and information lines are shown in the drawings as necessary for explanation, and not all control lines and information lines are shown in the product. In practice, almost all configurations may be considered interconnected.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Mechanical Engineering (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Manufacturing & Machinery (AREA)
  • Train Traffic Observation, Control, And Security (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2020/034261 2019-11-08 2020-09-10 資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム Ceased WO2021090572A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/642,151 US11836657B2 (en) 2019-11-08 2020-09-10 Resource management planning support device, resource management planning support method, and programs
EP20885583.3A EP4056452A4 (en) 2019-11-08 2020-09-10 DEVICE FOR SUPPORTING THE CREATION OF A RESOURCE OPERATIONS PLAN, METHOD FOR SUPPORTING THE CREATION OF A RESOURCE OPERATIONS PLAN AND PROGRAM
AU2020379335A AU2020379335B2 (en) 2019-11-08 2020-09-10 Resource operation plan creation support device, resource operation plan creation support method, and program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019203593A JP7227118B2 (ja) 2019-11-08 2019-11-08 資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム
JP2019-203593 2019-11-08

Publications (1)

Publication Number Publication Date
WO2021090572A1 true WO2021090572A1 (ja) 2021-05-14

Family

ID=75849841

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/034261 Ceased WO2021090572A1 (ja) 2019-11-08 2020-09-10 資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム

Country Status (5)

Country Link
US (1) US11836657B2 (https=)
EP (1) EP4056452A4 (https=)
JP (1) JP7227118B2 (https=)
AU (1) AU2020379335B2 (https=)
WO (1) WO2021090572A1 (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7799421B2 (ja) * 2021-10-04 2026-01-15 株式会社日立製作所 計画整理案立案装置、計画整理案立案装置による計画整理案立案方法及びコンピュータプログラム
CN116843525B (zh) * 2023-08-28 2023-12-15 湖南强智科技发展有限公司 一种智能自动排课方法、系统、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11143938A (ja) * 1997-11-04 1999-05-28 Hitachi Ltd 資源割当計画作成方法及び資源割当計画作成システム
JP2005178742A (ja) 2003-11-27 2005-07-07 Hitachi Ltd 車両基地構内入換計画作成装置、方法及びプログラム
JP2007196880A (ja) 2006-01-27 2007-08-09 Toshiba Corp 構内作業計画システム、方法およびプログラム
JP2008221918A (ja) 2007-03-09 2008-09-25 Toshiba Corp 作業計画支援システム、方法およびプログラム
JP2016203873A (ja) * 2015-04-24 2016-12-08 株式会社日立製作所 資源運用計画支援装置および資源運用計画支援方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0827811B2 (ja) * 1985-02-28 1996-03-21 株式会社日立製作所 輸送計画作成方法およびシステム
US9233696B2 (en) * 2006-03-20 2016-01-12 General Electric Company Trip optimizer method, system and computer software code for operating a railroad train to minimize wheel and track wear
JP2006511394A (ja) * 2002-12-20 2006-04-06 ユニオン スイッチ アンド シグナル インコーポレーテッド 動的最適化交通プランニング方法及びシステム
US7734493B1 (en) * 2005-04-28 2010-06-08 Southwest Airline Co. Tuning a schedule of transportation resources using mathematical programming
US8583462B2 (en) * 2010-06-23 2013-11-12 Canadian National Railway Company Method and system for assessing penalties associated with an employee without a job assignment
JP5869276B2 (ja) * 2011-09-27 2016-02-24 株式会社日立製作所 資源運用計画作成装置及びその方法、及びプログラム
US20140088865A1 (en) * 2012-09-27 2014-03-27 Siemens Industry, Inc. Apparatus and method for predicting arrival times in a transportation network
EP3243726B1 (en) * 2016-05-09 2020-07-15 ALSTOM Transport Technologies Traffic management method and traffic management system
WO2018027304A1 (en) * 2016-08-12 2018-02-15 Hatch Ltd. System and method for optimizing a rail system
US10532754B2 (en) * 2016-10-31 2020-01-14 Ge Global Sourcing Llc System for controlling or monitoring a vehicle system along a route
AU2020344482B2 (en) * 2019-09-13 2022-06-02 Technological Resources Pty. Limited Method and apparatus for operation of railway systems

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11143938A (ja) * 1997-11-04 1999-05-28 Hitachi Ltd 資源割当計画作成方法及び資源割当計画作成システム
JP2005178742A (ja) 2003-11-27 2005-07-07 Hitachi Ltd 車両基地構内入換計画作成装置、方法及びプログラム
JP2007196880A (ja) 2006-01-27 2007-08-09 Toshiba Corp 構内作業計画システム、方法およびプログラム
JP2008221918A (ja) 2007-03-09 2008-09-25 Toshiba Corp 作業計画支援システム、方法およびプログラム
JP2016203873A (ja) * 2015-04-24 2016-12-08 株式会社日立製作所 資源運用計画支援装置および資源運用計画支援方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4056452A4

Also Published As

Publication number Publication date
AU2020379335A1 (en) 2022-03-31
JP2021075161A (ja) 2021-05-20
EP4056452A4 (en) 2024-02-21
US20220327451A1 (en) 2022-10-13
AU2020379335B2 (en) 2023-05-18
US11836657B2 (en) 2023-12-05
EP4056452A1 (en) 2022-09-14
JP7227118B2 (ja) 2023-02-21

Similar Documents

Publication Publication Date Title
JP6605929B2 (ja) 資源運用計画支援装置および資源運用計画支援方法
CN108021107B (zh) 生产辅助系统、生产辅助方法以及生产辅助程序
JP6682223B2 (ja) 計画管理システム及び計画管理方法
JP6853134B2 (ja) 生産支援システム、及び生産支援方法
WO2021111694A1 (ja) ダイヤ作成システム、及びダイヤ作成方法
JP3928268B2 (ja) 運行機材の運用計画作成方法及びシステム
JP2012168739A (ja) 資源運用計画作成装置および資源運用計画作成方法
JP2021088205A5 (https=)
JP2021018610A (ja) 情報処理装置、プログラム、情報処理方法及び学習済みモデル
WO2021090572A1 (ja) 資源運用計画作成支援装置、資源運用計画作成支援方法、及びプログラム
WO2023286425A1 (ja) 運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム
Marzouk et al. Assessing design process in engineering consultancy firms using lean principles
JP2021075161A5 (https=)
US20220171908A1 (en) Support system and support method supporting system construction
Gericke et al. Towards a framework of choices made during the lifecycles of process models
CN114902253A (zh) 多主体协同计划系统及多主体协同计划方法
JP2010146091A (ja) ワークフロー改善システム、ワークフロー改善方法、およびワークフロー改善プログラム
JP6889130B2 (ja) 運転整理支援システムおよび運転整理支援方法
Laudati Tailored implementation of SAFe and scrum in a real-world project: a case study
JP2006163514A (ja) 要員選定支援システム及びそれに適用されるプログラム
JPH04184602A (ja) 生産計画作成システムおよび生産計画作成方法
US20260111012A1 (en) Apparatus for providing digital production plan information, method thereof, and computationally implementable storage medium for storing a software for providing digital production plan information
Ducharlet et al. A Recommendation System-Based Framework for Enhancing Human-Machine Collaboration in Industrial Timetabling Rescheduling: Application in Preventive Maintenance
KR20050110087A (ko) 작성 목적에 따른 기술 로드맵 자동 생성 시스템
Rosenwinkel et al. Simulation-base finite capacity scheduling: a case study

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20885583

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020379335

Country of ref document: AU

Date of ref document: 20200910

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020885583

Country of ref document: EP

Effective date: 20220608