Maintenance Improvement Support Device and Maintenance Improvement Support Method

Abstract

To provide a maintenance improvement support apparatus and a maintenance improvement support method for properly simulating a maintenance operation.SOLUTION: A maintenance improvement support apparatus 100 includes: a simulation setting generation unit 111 which generates, based on a maintenance operation log database 130 which is a record of executed maintenance operations, setting information 300 for simulation of a maintenance work; a simulation unit 113 which executes simulation using an asset agent and a worker agent; and a worker deficit handling unit 114, an agent combination processing unit 115, and an excessive work resolution processing unit 116 which are configured to detect a state of the asset agent or the worker agent that violates regulations in an operation knowledge database 140 to correct the setting information 300.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a maintenance improvement support device and a maintenance improvement support method for presenting improvement measures for maintenance work.

Background Art

[0002] In many fields such as infrastructure, railways, industrial equipment, and medical equipment, maintenance such as repair and regular inspection is continuously performed after the introduction of assets such as facilities and equipment. By continuing maintenance, the asset can maintain its predetermined functions and performance. In maintenance, it is necessary to analyze the state of the target asset and the execution status of maintenance, and to formulate and execute an appropriate maintenance work design. Also, in order for the maintenance work to be executed as planned in the actual business, a design and plan including the maintenance organization and maintenance equipment are required.

[0003] However, in the maintenance business, it is not easy to design the scale and layout of an appropriate maintenance organization because it is necessary to perform various maintenance operations on a large number and variety of assets or assets arranged over a wide area. In particular, in recent years, it has been necessary to introduce a maintenance process different from the conventional one in consideration of the effects and operation of IoT (Internet of Things) technology. Along with this, the business resources for maintenance, such as the number of personnel, required skills, and tools, change greatly, so the complexity of maintenance work design is increasing.

[0004] If an appropriate maintenance work design is not formulated, necessary work may not be executed due to a shortage of workers, inappropriate maintenance execution intervals, or inappropriate diagnosis of the asset state, and safety and operation problems may occur. Alternatively, it is conceivable that the profitability of the business deteriorates due to an increase in costs due to excessive maintenance, and as a result, continuous use of the asset becomes impossible. For this reason, a technology for supporting an appropriate maintenance work design is required.

[0005] Examples of technologies that support the formulation of business improvement plans for asset operation and maintenance and the estimation of their effects include those described in Patent Documents 1 and 2. Patent Document 1 describes a plant operation management support system that simulates future operation costs and the like from past operation data in order to formulate an asset introduction plan in a plant and is used for formulating a plant introduction plan. Patent Document 2 describes a life cycle cost management support system for a plant that predicts operation costs and maintenance costs based on the combination of operation conditions for operating an asset and operators in the plant and presents an optimal combination.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] In maintenance business design, it is necessary to determine the specific number of personnel in the maintenance organization, the items and details of maintenance work, the content and scale of IoT introduction, etc. to an appropriate scale that can ensure profitability while ensuring that maintenance work is carried out reliably. However, in maintenance business, there is a high degree of contingency in the occurrence of failures and delays during maintenance work, and the effect of the introduced IoT is determined by the balance within a large number of operations, so it is difficult to actually carry out an appropriate business design. Therefore, it is conceivable to build a simulation model of the current maintenance business to enable the reproduction of the business, and then incorporate future business plans and IoT introduction plans into the simulation model to verify whether an appropriate business design is being carried out. In order to simulate the maintenance business, settings for reproducing various elements such as assets targeted by the business, workers in charge of the business, and IoT are created. In addition, it is necessary to sequentially set the relationships between assets, work content, and workers, and the man-hours and difficulty of creating the settings are high.

[0008] Therefore, a method of generating simulation settings from the logs (histories) of existing maintenance operations (maintenance work) and the ledgers of facilities and personnel can be considered. However, since there are missing records in the maintenance operation logs and maintenance operations for which records are not left due to a short recording period, the generation of simulation settings may not be properly executed. Then, problems such as the risk of executing an inaccurate simulation and the problem that although the amount of each maintenance operation is small, a large number of assets are extracted and the calculation amount becomes enormous occur. For this reason, it is desirable to extract and improve the deficiencies and inefficiencies of the simulation settings and perform the settings appropriately.

[0009] The present invention has been made in view of such a background, and an object thereof is to provide a maintenance improvement support device and a maintenance improvement support method for appropriately performing a simulation of maintenance work.

Means for Solving the Problems

[0010] To solve the above-described problems, a maintenance improvement support device according to the present invention includes an asset that is a maintenance target in maintenance work, a worker in charge of the maintenance work, and a task that is the maintenance work performed by the worker on the asset. Based on a maintenance operation log database that is an execution record of the maintenance work, a simulation setting generation unit that generates setting information for performing a simulation of the maintenance work, an asset agent that is an agent indicating the asset, and an agent T A simulation unit that executes a simulation of the maintenance work using a worker agent that is an agent indicating the worker, and a reproducibility improvement processing unit that detects a state of the asset agent or the worker agent that violates the regulations in a business knowledge database including regulations when performing the maintenance work and corrects the setting information are provided. he simulation setting generation unit generates task setting information, which is setting information in which the asset, the pattern of failures occurring in the asset, and the task performed by the worker corresponding to the failure are associated, from the maintenance work log database, and generates worker assignment setting information, which is setting information in which the worker, the asset that is the target of the task performed by the worker, and the task are associated, from the maintenance work log database. The simulation unit causes the failure to occur in the asset agent according to the pattern of failures included in the task setting information, and determines the assignment to the asset agent corresponding to the asset and the worker agent corresponding to the worker associated with the task for the task corresponding to the failure. The worker agent executes a simulation of performing the task on the asset agent. When the activity level of the worker agent during the simulation execution exceeds a specified value contrary to the regulation in the business knowledge database, the reproducibility improvement processing unit includes an excessive work elimination processing unit that adds the task performed by the worker corresponding to the worker agent included in the worker assignment setting information and the asset that is the target thereof to the worker assignment setting information of a worker whose activity level is lower than the regulation, different from the worker. In addition, the maintenance improvement support device according to the present invention includes an asset that is a maintenance target in maintenance work, a worker in charge of the maintenance work, and a task that is the maintenance work performed by the worker on the asset. Based on a maintenance work log database that is a record of the execution of the maintenance work, a simulation setting generation unit that generates setting information for performing a simulation of the maintenance work, a simulation unit that executes a simulation of the maintenance work using an asset agent that is an agent indicating the asset and a worker agent that is an agent indicating the worker, and a reproducibility improvement processing unit that detects a state of the asset agent or the worker agent that violates a regulation in a business knowledge database including regulations when performing the maintenance work and corrects the setting information. The simulation setting generation unit generates task setting information that is setting information in which the asset, a pattern of a failure occurring in the asset, and the task performed by the worker corresponding to the failure are associated from the maintenance work log database, and generates worker assignment setting information that is setting information in which the worker, the asset that is the target of the task performed by the worker, and the task are associated from the maintenance work log database. The simulation unit causes the failure to occur in the asset agent according to the pattern of the failure included in the task setting information, and determines an assignment to the asset agent corresponding to the asset and the worker agent corresponding to the worker associated with the task for the task corresponding to the failure. The worker agent executes a simulation of performing the task on the asset agent. When a period from when the failure in the task setting information for the asset agent during simulation execution occurs until the corresponding task is not performed is longer than the regulation of the business knowledge database, the reproducibility improvement processing unit searches for an agent indicating the worker who performs the task, and includes the task and the asset corresponding to the asset agent in the worker assignment setting information corresponding to the worker indicated by the agent indicating the worker. It is provided with a work deficiency countermeasure processing unit for adding.

Effects of the Invention

[0011] According to the present invention, it is possible to provide a security improvement support device and a security improvement support method for appropriately performing simulation of security operations. Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Modes for Carrying Out the Invention

[0013] <<Overview of Maintenance Improvement Support Device>> The maintenance improvement support device in the following embodiment for implementing the present invention will be described. The maintenance improvement support device generates setting information necessary for executing a simulation of maintenance operations from a maintenance operation log database that is a history of maintenance operations (maintenance work). The setting information includes asset setting information, task setting information, worker setting information, and work assignment setting information. Next, the maintenance improvement support device executes an agent-based simulation (multi-agent simulation) based on the setting information.

[0014] The maintenance operation log database does not necessarily contain all information related to actual assets and workers, and may contain missing or incomplete information in the setting information. While executing the simulation, the maintenance improvement support device detects a state that violates the regulations of maintenance operations, such as a long asset failure period or a worker with concentrated work, and corrects the setting information. By using the corrected setting information, the maintenance operation simulation can be appropriately executed. In addition, the correction content of the setting information includes the addition of workers and maintenance operations (tasks) that workers need to be in charge of in the future, and can be used as reference information for planning maintenance operations.

[0015] <<Configuration of Maintenance Improvement Support Device>> FIG. 1 is a functional block diagram of a maintenance improvement support device 100 according to the present embodiment. The maintenance improvement support device 100 is a computer and includes a control unit 110, a storage unit 120, and an input / output unit 180. User interface devices such as a display, a keyboard, and a mouse are connected to the input / output unit 180. The input / output unit 180 may include a communication device and be capable of data transmission and reception with other devices. Further, a media drive may be connected to the input / output unit 180 to enable data exchange using a recording medium.

[0016] <<Maintenance Improvement Support Device: Storage Unit>> The storage unit 120 includes storage devices such as a ROM (Read Only Memory), a RAM (Random Access Memory), and an SSD (Solid State Drive). The storage unit 120 stores a maintenance operation log database 130, a business knowledge database 140, a plan database 150, agent data 160, setting information 300, and a program 128.

[0017] The program 128 includes descriptions of procedures for a work - responsible person deficiency handling (refer to FIG. 12 described later), an agent integration process (refer to FIG. 13 described later), and an overwork resolution process (refer to FIG. 14 described later). Regarding the agent data 160 and the setting information 300, they will be described later together with the control unit 110. Hereinafter, the maintenance operation log database 130, the business knowledge database 140, and the plan database 150 will be described.

[0018] ≪Storage Unit: Maintenance Operation Log Database≫ FIG. 2 is a data configuration diagram of the maintenance operation log database 130 according to the present embodiment. The maintenance operation log database 130 records maintenance operations (maintenance work) such as failure response and regular inspection performed on assets such as facilities and equipment. The maintenance operation log database 130 is, for example, tabular data. One row (record) indicates a maintenance operation (task) and includes columns (attributes) of identification information (described as ID in FIG. 2), operation type, task, asset, model, location, worker, base, start date and time, and end date and time.

[0019] The identification information is an identification number assigned to each maintenance operation. The operation type is the type of maintenance operation. The task is the name of the maintenance operation and is a breakdown of the operation type. The asset is the identification information of the asset that is the target of the maintenance operation, the model is the model of the asset, and the location is the installation location of the asset. The worker is the identification information of the worker who performed the maintenance operation, and the base is the base to which the worker belongs. The start date and time is the start date and time of the maintenance operation, and the end date and time is the end date and time of the maintenance operation.

[0020] The two records with an identification number of "2" indicate that "Worker 2" and "Worker 3" based at "Office A" performed a maintenance task (task) identified as "Fault Handling 2" on an asset located at "Site A" with a model number of "ATM-A" and an identification number of "ATM2" from 18:00 to 20:00 on January 1, 2020.

[0021] ≪Memory Unit: Business Knowledge Database≫ Figure 3 is a data configuration diagram of the business knowledge database 140 according to this embodiment. The business knowledge database 140 stores rules and guidelines for performing maintenance operations, as well as information (regulations) for judging the status of assets and workers. The simulation of the maintenance operation is executed to meet the regulations in the business knowledge database 140. Conversely, if a state that does not meet the regulations occurs during the simulation execution, a process to eliminate the state (see FIGS. 12 to 14 described later) is started.

[0022] ≪Memory Unit: Plan Database≫ Figure 4 is a data configuration diagram of the plan database 150 according to this embodiment. The plan database 150 includes future change plans for maintenance operations, such as plans for adding and disposing of assets, increasing and decreasing the number of workers, and changing the maintenance operations assigned to workers.

[0023] ≪Maintenance Improvement Support Device: Control Unit≫ Returning to Figure 1, the description of the control unit 110 will be continued. The control unit 110 includes a CPU (Central Processing Unit) and is provided with a simulation setting generation unit 111, an agent generation unit 112, a simulation unit 113, a work assignment deficiency handling unit 114, an agent combination processing unit 115, and an overwork elimination processing unit 116. The following will be described in order.

[0024] In this embodiment, multi-agent simulation is adopted as a method for simulating security operations. Specifically, agents are generated that individually simulate the operations of objects existing in the real world, such as assets and workers. Each agent performs its respective defined operations and develops over time in relation to other agents to reproduce security operations.

[0025] <<Security Improvement Support Device: Control Unit: Simulation Setting Generation Unit>> The simulation setting generation unit 111 generates setting information 300 (see FIG. 1) necessary for executing the simulation of security operations by referring to the security operation log database 130. The setting information 300 is asset setting information 320 (see FIG. 7), task setting information 330 (see FIG. 8), worker setting information 340 (see FIG. 9), and work responsibility setting information 350 (see FIG. 10), which will be described later.

[0026] FIG. 5 is a flowchart of the simulation setting generation process according to this embodiment. The process of the simulation setting generation unit 111 will be described with reference to FIG. 5. In step S11, the simulation setting generation unit 111 displays a simulation setting screen 310 (see FIG. 6 described later) on a display connected to the input / output unit 180, and acquires from the user the range of the security operation log database 130 to be referred to and the range of the simulation.

[0027] FIG. 6 is a screen configuration diagram of the simulation setting screen 310 according to this embodiment. In area 311, the period for referring to the security operation log database 130 is specified. In area 312, the type of asset to be the simulation target is specified. In area 313, the region where the asset to be the simulation target is installed is specified. In area 314, the period for performing the simulation is specified. When the "Start" button is pressed, the simulation starts after the generation of the setting information 300. In FIG. 6, the asset type is specified in area 312, but it may also be the identification information of the asset individual. Further, instead of the area designation in area 313, the name of the worker or the company to which the worker belongs (maintenance organization name) may be specified.

[0028] Returning to FIG. 5, in step S12, the simulation setting generation unit 111 accesses the maintenance work log database 130 (see FIG. 2) and acquires records (maintenance work records, maintenance work history) for the period specified in area 311 (see FIG. 6).

[0029] In step S13, the simulation setting generation unit 111 generates asset setting information 320 (see FIG. 7 described later). FIG. 7 is a data configuration diagram of the asset setting information 320 according to the present embodiment. The asset setting information 320 is, for example, data in a table format, and one row (record) represents an asset and includes columns (attributes) for the identification information of the asset, the model, and the installation location. The simulation setting generation unit 111 extracts the attributes of the asset, model, and location from the maintenance work log database 130 (see FIG. 2) and generates the asset setting information 320.

[0030] Returning to FIG. 5, in step S14, the simulation setting generation unit 111 generates task setting information 330 (see FIG. 8 described later). FIG. 8 is a data configuration diagram of the task setting information 330 according to the present embodiment. The task setting information 330 is, for example, data in a table format, and one row (record) represents a task (maintenance work) and includes columns (attributes) for the model of the asset to be maintained, the work type, the task (task name), the occurrence pattern, and the work time.

[0031] The simulation setting generation unit 111 extracts the attributes of the model, work type, and task from the maintenance work log database 130 (see FIG. 2) and generates the attributes of the model, work type, and task of the task setting information 330. Further, the simulation setting generation unit 111 extracts the attributes of the start date and time and the end date and time from the maintenance work log database 130, calculates the work time, and generates the attribute of the work time of the task setting information 330.

[0032] The simulation setting generation unit 111 generates a task occurrence pattern by aggregating the frequencies of tasks for each asset. At this time, when looking at individual assets, for example, it may be difficult to accurately estimate the occurrence pattern of tasks with a low occurrence rate due to a low failure rate, etc., because there are not enough samples within the period of the maintenance operation records to be referred to. Therefore, the simulation setting generation unit 111 may obtain an accurate pattern by taking an aggregation for each model of the asset and each classification of the installation area. In addition, the simulation setting generation unit 111 may access information sources related to assets other than the maintenance operation log database 130 and take an aggregation for each classification such as the classification of users and the usage period of the assets to obtain an accurate pattern.

[0033] As the occurrence pattern, for example, for a task that is "fault response 1" in the maintenance operation record, its occurrence frequency is counted and set as random task occurrence. For example, the first record indicates that for an asset with a model of "ATM-A", a task of "fault response 1" occurs at a rate of once every 2000 hours on average, indicating that the average time between failures of the fault is 2000 hours. Also, in the case of regular inspections, the average of the inspection cycles is used as the cycle. When the occurrence frequency of faults and the regular inspection cycle change depending on the period (number of years) after introduction, an occurrence pattern corresponding to the number of years since introduction may be included.

[0034] Returning to FIG. 5, in step S15, the simulation setting generation unit 111 generates worker setting information 340 (see FIG. 9 to be described later). FIG. 9 is a data configuration diagram of the worker setting information 340 according to the present embodiment. The worker setting information 340 is, for example, data in a table format, and one row (record) indicates a worker and includes the identification information of the worker and columns (attributes) of the bases. The simulation setting generation unit 111 extracts the attributes of the workers and the bases in the maintenance operation log database 130 and generates the worker setting information 340.

[0035] Returning to FIG. 5, in step S16, the simulation setting generation unit 111 generates the work assignment setting information 350 (see FIG. 10 described later). FIG. 10 is a data configuration diagram of the work assignment setting information 350 according to the present embodiment. The work assignment setting information 350 is, for example, data in a table format, and one row (record) indicates a task (maintenance work) assigned to a worker, and includes columns (attributes) of worker identification information, assets, and tasks. The simulation setting generation unit 111 extracts the attributes of workers, assets, and tasks from the maintenance operation log database 130 and generates the work assignment setting information 350.

[0036] ≪Maintenance improvement support device: Control unit: Agent generation unit≫ Returning to FIG. 1, the agent generation unit 112 generates agents 200 (see FIG. 11 described later) for each asset and each worker in the agent data 160 according to the setting information 300 generated by the simulation setting generation unit 111.

[0037] FIG. 11 is a diagram showing the data configuration of the agent data 160 according to the present embodiment. The agent generation unit 112 generates asset agents 210 corresponding to each asset shown in the asset setting information 320 (see FIG. 7). The agent generation unit 112 also generates worker agents 220 corresponding to each worker shown in the worker setting information 340 (see FIG. 9). In addition, the agent generation unit 112 generates a work plan agent 230 that assigns tasks to workers and a regular inspection work generation agent 240 that generates requests for regular inspection work for each asset. The asset agent 210, the worker agent 220, the work plan agent 230, and the regular inspection work generation agent 240 are collectively referred to as the agent 200. Details of the configuration of the agent 200 will be described later.

[0038] The agent generation unit 112 adds, deletes, and changes the asset agents 210 and worker agents 220 according to the plans for addition, deletion, and transfer of responsibility of assets and workers in the plan database 150 (see FIG. 4). This is executed at the scheduled date and time in the plan database 150 based on the in-simulation time in the simulation unit 113 described later. In addition, the simulation unit 113 may perform the addition, deletion, and change of the asset agents 210 and worker agents 220 after the start of the execution of the simulation.

[0039] ≪Maintenance improvement support device: Control unit: Simulation unit≫ The simulation unit 113 operates the agents 200 in the agent data 160 generated by the agent generation unit 112 to execute the simulation of the maintenance work. The simulation unit 113 executes the time update process for each agent 200. Driven by this, processes such as the update of the internal state of the agent 200 and the interaction between the agents 200 are executed.

[0040] Although the agent 200 is data stored in the agent data 160, it is operated by the simulation unit 113, its internal state changes, and it acts on other agents 200. Therefore, when describing the processes performed by the simulation unit 113, it may be described as if the agent 200 performs the processes mainly. For example, it may be described as "the asset agent 210 requests the work plan agent 230 to perform a task for troubleshooting" or "the state update unit 211 of the asset agent 210 updates the internal state". Such descriptions are the same for the work assignment deficiency handling unit 114, agent combination processing unit 115, and overwork elimination processing unit 116 described later, and the processes performed by these functional units may be described as if the agent 200 performs them. In addition, there may be cases where the asset included in the setting information 300 is identified with the asset agent 210 or the worker is identified with the worker agent 220.

[0041] <<Simulation Section: Asset Agent>> Agent 200 (see Fig. 11) is composed of different types such as asset agent 210 and worker agent 220, and their configurations and operations are different. The state update unit 211 of the asset agent 210 is set with a failure response task for each asset and performs probabilistic occurrence processing of the task. For example, in the asset agent 210 corresponding to the model "ATM-A", the task "Failure Response 1" randomly occurs at a rate of once every 2000 hours in the simulation internal time in the simulation unit 113 (see Fig. 8). At the same time as the task occurs, it is considered that a failure has occurred, and the state update unit 211 updates the internal state to the "failure state".

[0042] The interaction unit 212 of the asset agent 210 notifies the work plan agent 230 of a request for response to the task generated by the state update unit 211. Also, when the worker agent 220, which will be described later, executes a task on the asset agent 210, the interaction unit 212 notifies this to the state update unit 211. Then, the state update unit 211 determines that the failure response task has been executed and the asset has become operable, and updates the internal state to the "normal state". In this way, the interaction unit 212 performs cooperation processing with other agents 200. The state monitoring unit 213 and the reproducibility improvement unit 214 of the asset agent 210 will be described later. In the above description, the asset agent 210 is the main body and the state update unit 211 and the interaction unit 212 are described as functioning. However, in the processing on the maintenance improvement support device 100, the simulation unit 113 accesses the data of the asset agent 210 and performs processing.

[0043] <<Simulation Section: Regular Inspection Work Generation Agent>> The regular inspection task generation agent 240 performs the generation process of regular inspection tasks for each asset agent 210. Specifically, the regular inspection task generation agent 240 refers to the task setting information 330 (see FIG. 8) and performs the periodic generation process of regular inspection tasks for each asset agent 210. Next, when the regular inspection task generation agent 240 notifies the asset agent 210 of the generation of a regular inspection task, the status update unit 211 of the asset agent 210 updates the status to the "awaiting regular inspection status". Also, the regular inspection task generation agent 240 notifies the work plan agent 230 of a request for handling the regular inspection task.

[0044] ≪Simulation section: Work plan agent≫ Based on requests for failure handling tasks from the asset agent 210 and requests for regular inspection tasks from the regular inspection task generation agent 240, the work plan agent 230 assigns tasks to the worker agent 220 considering the number of required personnel, the responsible workers or skills for each task, and constraints such as the start date and end date of execution, as well as the tasks already assigned to the workers, and notifies the worker agent 220 of the assigned tasks.

[0045] ≪Simulation section: Worker agent≫ When the status update unit 221 of the worker agent 220 receives a task notification from the work plan agent 230, it stores the task as work responsibility information. Also, the status update unit 221 is in the "waiting / resting status" during times when there are no tasks scheduled for execution, such as failure handling tasks or regular inspection tasks. The status update unit 221 transitions to the "task execution status" when executing the assigned task. In the "task execution status", through the interaction unit 222, the worker agent 220 executes the task for the asset agent 210. Then, the status update unit 211 of the asset agent 210 updates the internal status from the "failure status" or "awaiting regular inspection status" to the "normal status". The status monitoring unit 223 and the reproducibility improvement unit 224 in the worker agent 220 will be described later.

[0046] As described above, a task for troubleshooting occurs in the asset agent 210 and is notified to the work plan agent 230. Also, a task for regular inspection occurs in the regular inspection work generation agent 240 and is notified to the asset agent 210 and the work plan agent 230. The work plan agent 230 assigns the task to the worker agent 220, and the assigned worker agent 220 executes the task on the asset agent, thereby completing the troubleshooting task and the regular inspection task. The state of the state update unit 211 of the asset agent 210 returns to the "normal state". By operating the agent 200 in this way (more precisely, by the simulation unit 113 operating the agent 200), a simulation of the maintenance work is executed.

[0047] In other words, the simulation executed by the simulation unit 113 proceeds as follows. (1) A failure occurs in the asset agent 210 according to the failure pattern included in the task setting information 330. (2) Regarding the task corresponding to this failure, the assignment of the task to the asset agent 210 (asset) and the worker agent 220 (worker) set in the work assignment setting information 350 to be in charge of the task is determined. (3) The worker agent 220 performs the task on the asset agent 210.

[0048] However, in order to perform a simulation without defects in simulation and with high accuracy, there are several problems. The main problems are those caused by the lack of simulation setting information 300, those related to calculation efficiency such as the amount of calculation, and excessive work concentration on workers. Below, as a process for improving reproducibility to solve these problems, a work assignment deficiency countermeasure process, an agent integration process, and an excessive work elimination process will be described.

[0049] ≪Maintenance Improvement Support Device: Control Unit: Work Assignment Deficiency Countermeasure Processing Unit≫ As a first problem, there may be a defect in the operator setting information 350 (see FIG. 10). Then, even if the asset agent 210 requests a failure response task, the work plan agent 230 cannot assign the worker agent 220, and the task is not executed. In response to such a defect in the operator setting information 350, the operator defect response processing unit 114 executes operator defect response processing.

[0050] FIG. 12 is a flowchart of the operator defect response processing according to the present embodiment. The operator defect response processing unit 114 (reproducibility improvement processing unit) operates the agent 200 in parallel with the simulation unit 113 to execute the operator defect response processing. In step S21, the state monitoring unit 213 of the asset agent 210 monitors the internal state in the state update unit 211, and proceeds to step S22 when the "failure state" or "waiting for regular inspection state" is not updated for a certain period of time (step S21 → YES). Such a state where the internal state of the state update unit 211 is not updated occurs when there is a defect in the operator setting information 350 (see FIG. 10) and the failure response task or regular inspection task is not executed. Note that the above-mentioned certain period of time is defined as the "maximum waiting time for task execution" in the business knowledge database 140 (see FIG. 3).

[0051] In the following processing, it is assumed that the asset agent 210 and the worker agent 220 exchange requests and scores via the interaction units 212 and 222. Also in the agent integration processing and overwork elimination processing described later, it is assumed that the asset agent 210 and the worker agent 220 communicate with other agents 200 via the interaction units 212 and 222. In step S22, the reproducibility improvement unit 214 of the asset agent 210 inquires all the worker agents 220 about the possibility of taking charge of its own failure response task or regular inspection task.

[0052] In step S23, the reproducibility improvement unit 224 of each worker agent 220 calculates the score of the possibility of being in charge of the task received in the inquiry and returns it to the asset agent 210. As a method for calculating the score, for example, if the task received in the inquiry includes a task of the same type as the tasks already handled by the worker agent 220, a high score is given. Also, if the distance between the location of the asset agent 210 (refer to the location of the asset setting information 320 shown in FIG. 7) and the base of the worker agent 220 (refer to the base of the worker setting information 340 shown in FIG. 9) is close, a high score is given. In addition, the smaller the working hours of the current month calculated by the state monitoring unit 223 of the worker agent 220 is compared with the standard working hours per month in the business knowledge database 140 (refer to FIG. 3), the higher the score is given assuming there is more spare capacity. Also, when the working hours of the current month exceed the sum of the standard working hours per month and the overtime hours per month in the business knowledge database 140, the lowest score is given.

[0053] In step S24, the reproducibility improvement unit 214 of the asset agent 210 requests the worker agent 220 with a score higher than a certain value among the received scores to be in charge of the task. In step S25, the reproducibility improvement unit 224 of the worker agent 220 adds the task to the work responsibility information it stores and the work responsibility setting information 350 (refer to FIG. 10). By this additional modification, the deficiency in the work responsibility setting information 350 is eliminated.

[0054] The certain value of the score in step S24 is a preset value, but it may also be calculated from the scores for the tasks already handled by the worker agent 220 (tasks in the work responsibility setting information 350 of the worker). Specifically, in step S23, the reproducibility improvement unit 224 calculates and returns the scores for the tasks already handled by the asset agent 210 in addition to the task in the inquiry. In step S24, the reproducibility improvement unit 214 sets the average value or a value of a certain ratio of the scores for the received tasks already handled as the certain value.

[0055] ≪Features of the Work Responsibility Deficiency Handling Unit≫ As described above, when the period during which no task is performed after a failure occurs in the task setting information 330 for the asset agent 210 during simulation execution is longer than the regulation of the business knowledge database 140, the worker agent 220 that performs the task is searched for, and the task and the asset are added to the worker assignment setting information 350. The reproducibility improvement units 214 and 224 (more precisely, the worker assignment defect handling unit 114) detect a defect in the worker assignment setting information 350 and correct the worker assignment setting information 350.

[0056] In this way, the maintenance improvement support device 100 includes a worker assignment defect handling unit 114 (reproducibility improvement processing unit) that detects the state of the asset agent 210 that violates the regulations in the business knowledge database 140 including the regulations when performing maintenance operations and corrects the setting information (worker assignment setting information 350). Here, violating the regulations in the business knowledge database 140 (see FIG. 3) means that the period during which no task is performed after a failure occurs is equal to or longer than the "maximum task execution waiting time".

[0057] By using such a method, even when the assets or workers are frequently changed in the settings of the plan database 150, or when the quality of the maintenance operation log database 130 is low and there are many defects in the generated worker assignment setting information and it is difficult to correct them, the worker assignment setting information 350 is improved by the reproducibility improvement units 214 and 224 during simulation execution, and a simulation without defects can be realized.

[0058] ≪Maintenance Improvement Support Device: Control Unit: Agent Integration Processing Unit≫ The second problem occurs when the number of assets included in the asset setting information 320 (see FIG. 7) generated by the simulation setting generation unit 111 becomes extremely large. When the number of assets is large, the amount of calculation for the simulation increases, making it difficult to execute the simulation within practical time and memory consumption. Such a second problem occurs in a situation where there are a large number of assets with a very low individual failure rate. For example, electronic terminals such as network devices and tablet devices are numerous because a large number of the same type of devices are installed to cover an entire office or factory, or distributed to individuals. Although they are numerically more numerous than precision machines such as factory manufacturing equipment and ATMs, their failure rate is low, so there are few failure responses and no regular inspections are carried out.

[0059] For such a large number of assets, the agent aggregation processing unit 115 executes agent aggregation processing to reduce the asset agents 210. The agent aggregation processing unit 115 performs agent aggregation processing on the asset agents 210 to merge a plurality of asset agents 210 determined to be of the same type and replace them with one asset agent 210. By this processing, the amount of calculation and memory consumption consumed by the asset agents 210 can be reduced.

[0060] FIG. 13 is a flowchart of the agent aggregation processing according to the present embodiment. The agent aggregation processing unit 115 (reproducibility improvement processing unit) operates the agents 200 in parallel with the simulation unit 113 to execute agent aggregation processing. In step S31, the state monitoring unit 213 of the asset agent 210 monitors the state update unit 211 and calculates the total (activity amount) of the execution frequency of the failure response task and the regular inspection task by the worker agent 220, and the frequency of becoming the "failure state" and the "regular inspection waiting state". If the calculated frequency is lower than the low task execution frequency threshold defined in the business knowledge database 140 (see FIG. 3) (step S31 → YES), the process proceeds to step S32. Such a state occurs because maintenance work on the asset agent 210 is rarely executed.

[0061] In step S32, the reproducibility improvement unit 214 of the asset agent 210 sends a notification indicating that it wishes to perform a merging process to other asset agents 210. At this time, if other asset agents also wish to perform a merging process simultaneously, they will have similarly sent notifications indicating their wishes. Note that the notification may include the identification information of the asset agent 210 and the mode (status) included in the status update unit 211, etc. In step S33, if there is a notification from another asset agent 210 (step S33 → YES), the reproducibility improvement unit 214 of the asset agent 210 proceeds to step S34; if there is no notification (step S33 → NO), the agent merging process ends.

[0062] In step S34, the reproducibility improvement unit 214 determines whether merging is possible. Criteria for determination include that the asset agents 210 are of the same model (refer to the model described in FIG. 7), or that the mode (status) included in the status update unit 211 is the same, etc. Also, if the installation locations of the asset agents 210 (refer to the locations described in FIG. 7) are the same or geographically close, it may be determined that merging is possible. If the reproducibility improvement unit 214 determines that merging is possible (step S34 → YES), it proceeds to step S35; if not (step S34 → NO), the agent merging process ends.

[0063] In step S35, the reproducibility improvement unit 214 merges with the mergeable asset agent 210. Specifically, the reproducibility improvement unit 214 inherits the mode in the state update unit 211 of the asset agent 210 that is the merge target with itself, and generates a new asset agent 210 having the total failure occurrence rate and the periodic inspection request before the merge. In addition, the reproducibility improvement unit 214 changes the asset setting information 320 (see FIG. 7). For example, when the models are the same, the failure occurrence frequency of the failure mode may be changed to the total value (harmonic mean of the mean time between failures) and merged. Further, the reproducibility improvement unit 214 rewrites the information regarding the asset before the merge in the work-in-charge setting information 350 (see FIG. 10) to the new asset agent 210.

[0064] ≪Features of Agent Merge Processing≫ By the agent merge processing, since the asset agent 210 to be merged becomes one asset agent 210, the calculation amount and the memory usage amount can be reduced. This process is repeatedly executed while the total of the execution frequency of the task and the frequencies of "failure state" and "periodic inspection task" is lower than the low task execution frequency threshold. Therefore, the number of asset agents 210 is reduced until the minimum number of asset agents 210 is reached, and the calculation amount and the memory usage amount can be reduced.

[0065] As described above, the maintenance improvement support device 100 includes an agent merge processing unit 115 (reproducibility improvement unit 214, reproducibility improvement processing unit) that detects the state of an asset agent that violates the regulations in the business knowledge database including the regulations when executing maintenance operations and corrects the setting information (asset setting information 320, work-in-charge setting information 350). Here, violating the regulations in the business knowledge database (see FIG. 3) means that the total of the execution frequency of the failure response task and the periodic inspection task, and the frequencies of "failure state" and "periodic inspection waiting state" are lower than the "low task execution frequency threshold" defined in the business knowledge database 140 (see FIG. 3).

[0066] ≪Maintenance Improvement Support Device: Control Unit: Overwork Elimination Processing Unit≫ The third problem is that the number of generated worker agents 220 is too small, or tasks concentrate on a small number of worker agents 220, resulting in an abnormally long task execution time for the worker agents 220 (overwork). This is because the maintenance service log database 130 (see FIG. 2) contains data for a limited period. In reality, even if 10 people are responsible for the maintenance services for assets, only, for example, less than half of the records may remain during that period. Generally, since there are legal and physical limits to the working hours that workers can execute, simulations that reproduce abnormally long working hours are not accurate and are problematic for use in business plans.

[0067] For such a small number of workers, the overwork elimination processing unit 116 executes overwork elimination processing to address this. The overwork elimination processing unit 116 increases the number of worker agents 220 to eliminate the situation where the task execution time becomes abnormally long.

[0068] FIG. 14 is a flowchart of the overwork elimination processing according to the present embodiment. The overwork elimination processing unit 116 (reproducibility improvement processing unit) operates the agent 200 to execute overwork elimination processing in parallel with the simulation unit 113. In step S41, the status monitoring unit 223 of the worker agent 220 monitors the status update unit 221, calculates the time in the "task execution status", and if it is overwork (step S41 → YES), proceeds to step S42. As a method for detecting overwork from statistics, for example, the overtime hours outside the working hours regarded as overtime are calculated from the task execution time to calculate the monthly overtime hours, and if it exceeds the upper limit value recorded in the business knowledge database 140 (see FIG. 3), it is determined as overwork.

[0069] In step S42, the reproducibility improvement unit 224 of the worker agent 220 inquires of other worker agents 220 about the delegability of the tasks it is responsible for. The inquiry may include the name and type of the task, the model of the asset agent 210 targeted by the task, and the like.

[0070] In step S43, the reproducibility improvement unit 224 of the worker agent 220 that received the inquiry returns a score indicating the possibility of work transfer. As a method for calculating the score, there is a method of increasing the score as the difference between the monthly working hours and overtime hours of the worker agent 220 and the upper limit value recorded in the business knowledge database 140 becomes larger. Also, the score may be increased as the distance from the base of the inquired worker agent 220 is closer. Alternatively, it may be set to return a higher score as the similarity of the model and task type of the target asset agent 210 is higher. Also, if the working hours of the current month exceed the sum of the standard working hours per month and the overtime hours per month in the business knowledge database 140, the lowest score is set.

[0071] In step S44, the reproducibility improvement unit 224 of the worker agent 220 that made the inquiry determines whether transfer is possible. Specifically, if all of the returned scores are less than a predetermined value, the reproducibility improvement unit 224 determines that transfer is not possible (step S44→NO) and proceeds to step S45. If a score equal to or higher than the predetermined value is returned, the reproducibility improvement unit 224 determines that transfer is possible (step S44→YES) and proceeds to step S46. In step S45, the reproducibility improvement unit 224 of the worker agent 220 that made the inquiry generates a new worker agent 220. Next, the reproducibility improvement unit 224 makes the work assignment setting information 350 of this new worker agent 220 have all or part of its own work assignment setting information 350.

[0072] In step S46, the reproducibility improvement unit 224 of the worker agent 220 that made the inquiry determines the work assignment setting information 350 (see FIG. 10) to be added to the worker agent 220 with the highest received score (hereinafter referred to as the transfer destination candidate). Specifically, the reproducibility improvement unit 224 compares its own work assignment setting information 350 with the work assignment setting information 350 of the transfer destination candidate. If there are assets and tasks that the transfer destination candidate does not handle, among its own work assignment setting information 350, it selects the task with the largest workload (the task time in the task setting information 330 described in FIG. 8 is the longest), or a task randomly selected from the work assignment setting information 350, and determines to add it to the transfer destination candidate.

[0073] In step S47, the reproducibility improvement unit 224 of the worker agent 220 that made the inquiry requests the worker agent 220 of the transfer destination candidate to add a task. In step S48, the reproducibility improvement unit 224 of the worker agent 220 of the transfer destination candidate adds a task to its own work assignment setting information 350. As a result, the transfer destination candidate will be responsible for that task hereafter.

[0074] ≪Features of the excessive work elimination process≫ In the excessive work elimination process, when the activity level of the worker agent 220 is greater than the regulation in the business knowledge database 140, the tasks performed by the worker agent 220 (worker) included in the work assignment setting information 350 and the assets that are the targets thereof are added to the work assignment setting information of the worker agent 220 whose activity level is smaller than the regulation, different from the said worker agent 220. By this excessive work elimination process, the burden on the worker agent 220 that was performing excessive maintenance work is dispersed, and the workload is optimized. The excessive work elimination process is repeated until no excessive workload is detected for the worker agent 220, so that the worker agent 220 that generates excessive work can be eliminated. By correcting the deficiencies in the worker setting information 340 and the work assignment setting information 350 caused by the defects in the maintenance business log database 130, an appropriate maintenance business simulation can be executed.

[0075] In this way, the maintenance improvement support device 100 includes an overwork elimination processing unit 116 (reproducibility improvement processing unit) that detects the state of the worker agent that violates the regulations in the business knowledge database including the regulations when performing maintenance work and modifies the setting information (work assignment setting information 350). Here, violating the regulations in the business knowledge database (see FIG. 3) means that the overtime hours calculated from the time in the "task execution state" are equal to or greater than (or larger than) the value of the regulation of "monthly overtime hours of workers" in the business knowledge database 140 (see FIG. 3).

[0076] ≪Features of the Maintenance Improvement Support Device≫ The simulation setting generation unit 111 generates setting information 300 required for executing the simulation of the maintenance work from the maintenance work log database 130. The setting information 300 includes asset setting information 320, task setting information 330, worker setting information 340, and work assignment setting information 350. Next, the agent generation unit 112 generates an agent 200 based on the setting information. Subsequently, the simulation unit 113 operates (operates) the agent 200 to execute the simulation.

[0077] The maintenance work log database 130 does not necessarily contain all information related to actual assets and workers, and there may be problems with the setting information. The work assignment deficiency handling unit 114 eliminates the deficiency of the work assignment setting information 350 when the "failure state" or "awaiting regular inspection state" of the asset agent 210 continues for a certain period of time. The agent merging processing unit 115 merges the asset agents 210 when the execution frequency of the inspection tasks and the frequency of the failure state in the asset agent 210 are low, reducing the calculation amount and memory usage of the simulation. The overwork elimination processing unit 116 newly adds a worker agent 220 or adds a task to the work assignment setting information 350 of the existing worker agent 220 when the task amount of the worker agent 220 is excessive, so that the tasks can be distributed among the worker agents 220.

[0078] In this way, until problems such as the failure state continuing for a certain period of time or longer are no longer detected, the work responsible loss response process, the agent integration process, and the excessive work elimination process are repeated, thereby generating appropriate setting information 300. Subsequently, an appropriate maintenance operation simulation can be executed.

[0079] <<Variant Example: Evaluation Unit>> The simulation unit 113 may save the start and end of tasks and changes in the state of the asset agent 210 as event logs. At the same time, modifications to the setting information 300 may also be saved as event logs. Further, the maintenance improvement support device 100 may include an evaluation unit that performs statistical processing and visualization processing of the event logs and presents them to the user. For example, the evaluation unit may calculate and present to the user the time from the occurrence of a failure to the completion of the failure response task, the average overtime hours, the maximum overtime hours, and the maximum continuous working hours of the workers. The evaluation unit may also present to the user the modification history / modification content (added tasks, additional history) of the worker setting information 340 and the work responsible setting information 350.

[0080] Modifications to the worker setting information 340 and the work responsible setting information 350 indicate changes in the assets and types (work types) of maintenance work (tasks) assigned to workers due to changes in the maintenance business situation such as the addition or deletion of assets in the plan database 150 and the increase or decrease of workers. The event log indicates a situation where proper maintenance of the assets has not been carried out due to changes in the maintenance business situation, and the modifications to the worker setting information 340 and the work responsible setting information 350 present the countermeasures required at that time. As a result, the user of the maintenance improvement support device 100 can formulate plans for future asset addition or disposal and worker employment and education plans.

[0081] <<Variant Example: Simulation Execution by Agent>> In the above-described embodiment, the simulation unit 113, the work-assigned defect handling unit 114, the agent integration processing unit 115, and the overwork elimination processing unit 116 operate on the data of the agent 200 (agent data 160) to execute simulations and reproducibility improvement processes. On the other hand, the agent 200 may be provided with a processing module to execute simulations and reproducibility improvement processes. Also, other execution forms of agent simulations may be used.

[0082] ≪Modification Example: Modification of Setting Information≫ In the above-described embodiment, the setting information 300 is modified by the reproducibility improvement process. Each of the asset agent 210 and the worker agent 220 may hold information such as the model and task related to itself inside the agent, and modify the information as the simulation and reproducibility improvement processes are executed. Regarding the form of holding the information related to the agent, an appropriate form may be adopted according to the execution form of the agent simulation.

[0083] ≪Modification Example: Task Setting Information≫ The maintenance work log database 130 records tasks (details of work types), and the simulation setting generation unit 111 generates task setting information 330 (see FIG. 8) for each of these tasks. However, regarding fault handling, at the start of work, the details of the fault are uncertain, or there may be a high degree of uncertainty in the details of the investigation, repair, and replacement work, so there is a possibility that a task (details of work type), which is a detailed classification code, is not recorded.

[0084] In such a case, in the present invention, for the purpose of finally simulating and evaluating the execution status of the maintenance work, it is conceivable to improve the simulation accuracy by subdividing the detailed task definition by generating different task definitions based on either or both of the occurrence pattern and the load of each task. For example, it is conceivable to classify tasks with similar times by classifying them into short, medium, and long working hours or by clustering the working hours. Also, since the number of workers required to execute the work needs to be distinguished when performing worker allocation in the simulation, it is necessary to subdivide the regular tasks for each required number of personnel.

[0085] <<Variant Example: Work Responsible Setting Information>> The work responsible setting information 350 (see FIG. 10) shows the assets and tasks assigned to the workers, but it may be simplified. For example, instead of individual assets, they may be aggregated by the location where they are installed, or aggregated by model. Also, instead of individual tasks, they may be simplified by distinguishing them by work type, skill, etc. For example, records of work responsible setting information with the same or nearby asset installation locations, the same or nearby asset models, or the same or nearby task types may be merged to reduce the number of records of work responsible setting information. By reducing the setting information 300 in this way, the efficiency of simulation execution is improved.

[0086] Also, the work responsible setting information 350 is generated based on the maintenance work log database 130. For this reason, there may be no assets or tasks that a certain worker is actually responsible for in the actual maintenance business design in the maintenance work log database 130, and the work responsible setting may not be generated. Therefore, workers with a high similarity in the assets and tasks they are responsible for may be presumed to have the same scope of responsibility for assets and tasks in the maintenance business design, and the union of the assets and tasks they are both responsible for may be obtained to complement the missing work responsible setting. By clustering workers with records of similar assets and tasks, it is possible to generate work responsible setting information 350 that is closer to reality and has no omissions.

[0087] <<Modification Example: Periodic Inspection Task>> In the above-described embodiment, the periodic inspection task generation agent 240 performs the task generation process for periodic inspection, but each asset agent 210 may perform it. For example, the state update unit 211 of the asset agent 210 counts the time from the previous periodic inspection to the current time, and when the periodic inspection cycle is exceeded, it considers that the inspection is not completed and the operation is not possible, and updates the internal state of the asset agent to the "waiting for periodic inspection state". Further, the state update unit 211 may request a periodic inspection to the work plan agent 230 via the interaction unit 212.

[0088] <<Modification Example: Agent Merging Process>> In the above-described embodiment, the agent merging processing unit 115 performs agent merging processing on the asset agent 210 with a low execution frequency of inspection tasks and periodic inspection tasks and a low frequency of becoming the "failure state" or "waiting for periodic inspection state". When the frequency is lower than a predetermined value and it is considered that the influence on the simulation is small, the agent merging processing unit 115 may simply delete the asset agent 210 instead of merging, and delete it from the asset setting information 320.

[0089] Regarding the worker agent 220, the agent merging processing unit 115 may merge worker agents 220 with a low task execution frequency (activity level) and the same or nearby bases (refer to the bases in the worker setting information 340 shown in FIG. 9) into one worker agent 220. Whether the task execution frequency is low may be determined based on, for example, the "standard working hours per month for workers" in the business knowledge database 140 (refer to FIG. 3) or the time obtained by multiplying a predetermined value of the "standard working hours per month for workers". Also, when the frequency is lower than a predetermined value and it is considered that the influence on the simulation is small, the agent merging processing unit 115 may simply delete the worker agent 220 instead of merging, and delete it from the worker setting information 340.

[0090] In this way, when the activity levels of the asset agents 210 and worker agents 220 during the execution of the simulation are lower than the specified value in violation of the regulations in the business knowledge database 140, the agent combination processing unit 115 combines them with other asset agents 210 or worker agents 220 whose activity levels are lower than the specified value. Further, when the activity level (execution frequency of tasks) of the asset agents 210 or worker agents 220 during the execution of the simulation is lower than a predetermined value, the agent combination processing unit 115 may delete the asset agents 210 or worker agents 220. By combining or deleting the asset agents 210 or worker agents 220, the calculation amount and memory usage amount of the simulation can be reduced, and the processing time can be shortened.

[0091] ≪Other Modification Examples≫ As described above, some embodiments of the present invention have been described. However, these embodiments are merely examples and do not limit the technical scope of the present invention. For example, although the maintenance improvement support device 100 stores the maintenance work log database 130, the business knowledge database 140, and the plan database 150, it may access this information in an external device. The work responsible defect handling unit 114, the agent combination processing unit 115, and the overwork elimination processing unit 116 may be a single functional unit (reproducibility improvement processing unit).

[0092] The present invention can take various other embodiments, and furthermore, various changes such as omission and substitution can be made without departing from the gist of the present invention. These embodiments and their modifications are included in the scope and gist of the invention described in this specification and the like, and are also included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0093] 100 Maintenance improvement support device 111 Simulation setting generation unit 112 Agent generation unit 113 Simulation unit 114 Operation Responsible Defect Response Processing Unit (Reproducibility Improvement Processing Unit) 115 Agent Integration Processing Unit (Reproducibility Improvement Processing Unit) 116 Overwork Elimination Processing Unit (Reproducibility Improvement Processing Unit) 130 Maintenance Business Log Database 140 Business Knowledge Database 150 Plan Database 210 Asset Agent 220 Worker Agent 300 Setting Information 320 Asset Setting Information 330 Task Setting Information 340 Worker Setting Information 350 Operation Responsible Setting Information

Claims

1. An asset to be protected in a security operation, a worker in charge of the security operation, and a task that is the security operation performed by the worker on the asset, and based on a security operation log database that is an execution record of the security operation, a simulation setting generation unit that generates setting information for performing a simulation of the security operation; A simulation unit that executes a simulation of the security operation using an asset agent that is an agent indicating the asset and a worker agent that is an agent indicating the worker; A reproducibility improvement processing unit that detects a state of the asset agent or the worker agent that violates a regulation in a business knowledge database including regulations when performing the security operation and corrects the setting information; The simulation setting generation unit: Generates task setting information, which is setting information in which the asset, a pattern of a failure occurring in the asset, and the task performed by the worker corresponding to the failure are associated, from the security operation log database; Generates worker assignment setting information, which is setting information in which the worker, the asset that is the target of the task performed by the worker, and the task are associated, from the security operation log database; The simulation unit: Causes the failure to occur in the asset agent according to the pattern of the failure included in the task setting information; For the task corresponding to the failure, determines an assignment to the asset agent corresponding to the asset included in the worker assignment setting information and the worker agent corresponding to the worker associated with the task; Executes a simulation in which the worker agent performs the task on the asset agent; The reproducibility improvement processing unit: When the activity level of the worker agent during simulation execution exceeds a specified value in violation of the regulations in the business knowledge database, a task performed by the worker corresponding to the worker agent included in the worker assignment setting information and the asset that is the target thereof are added to the worker assignment setting information of a worker whose activity level is lower than the specified value, different from the worker, and includes an excessive work elimination processing unit; A security improvement support device.

2. Including assets to be maintained in maintenance operations, workers responsible for the maintenance operations, and tasks that are the maintenance operations performed by the workers on the assets, based on a maintenance operation log database that is a record of the execution of the maintenance operations, a simulation setting generation unit that generates setting information for performing a simulation of the maintenance operations A simulation unit that executes a simulation of the maintenance operations using an asset agent that is an agent indicating the asset and a worker agent that is an agent indicating the worker A reproducibility improvement processing unit that detects a state of the asset agent or the worker agent that violates a regulation in a business knowledge database including regulations when performing the maintenance operations and corrects the setting information The simulation setting generation unit Generates task setting information, which is setting information in which the asset, a pattern of a failure occurring in the asset, and the task performed by the worker corresponding to the failure are associated, from the maintenance operation log database Generates worker assignment setting information, which is setting information in which the worker, the asset that is the target of the task performed by the worker, and the task are associated, from the maintenance operation log database The simulation unit According to the pattern of the failure included in the task setting information, the failure occurs in the asset agent For the task corresponding to the failure, an assignment to an asset agent corresponding to the asset included in the worker assignment setting information and a worker agent corresponding to the worker associated with the task is determined The worker agent executes a simulation of performing the task on the asset agent The reproducibility improvement processing unit When the period from when a failure in the task setting information for the asset agent during simulation execution occurs until the corresponding task is not performed is longer than the regulation of the business knowledge database, searches for an agent indicating the worker who performs the task, and adds the task and the asset corresponding to the asset agent to the worker assignment setting information of the worker corresponding to the agent indicating the worker. It includes a work deficiency countermeasure processing unit Maintenance improvement support device

3. The maintenance operation log database including at least any one of the installation location of the asset, the model of the asset, and the type of the task, the simulation setting generation unit, merges the work-assigning setting information in which the installation location of the asset is the same, the model of the asset is the same, and the type of the task is the same, and reduces the number of pieces of the work-assigning setting information The preservation improvement support device according to claim 1 or 2.

4. The reproducibility improvement processing unit, comprises an agent merging processing unit that deletes the agent when the activity amount of the agent during the simulation execution is smaller than a predetermined value The preservation improvement support device according to claim 1 or 2.

5. The reproducibility improvement processing unit, comprises an agent merging processing unit that merges the agent with other agents whose activity amount is smaller than the specified value when the activity amount of the agent during the simulation execution violates the regulations in the business knowledge database and is smaller than the specified value The preservation improvement support device according to claim 1 or 2.

6. The simulation unit, increases or decreases the asset agent and the worker agent based on a plan database that is a future increase or decrease plan of the asset and the worker The preservation improvement support device according to any one of claims 1 to 5.

7. comprises an evaluation unit that displays a history of additions to the work-assigning setting information The preservation improvement support device according to claim 1 or 2.

8. The preservation improvement support device, including an asset that is a preservation target in the preservation business, a worker who is in charge of the preservation business, and a task that the worker performs on the asset, and based on a preservation business log database that is an execution record of the preservation business, generating setting information for performing a simulation of the preservation business; executing a simulation of the preservation business using an asset agent that is an agent indicating the asset and a worker agent that is an agent indicating the worker; detecting a state of the asset agent or the worker agent that violates the regulations in the business knowledge database including the regulations when performing the preservation business, and modifying the setting information, and in the step of generating setting information for performing a simulation of the preservation business, Generating task setting information, which is setting information in which the asset, the pattern of a failure occurring in the asset, and the task performed by the worker corresponding to the failure are associated, from the maintenance business log database; Executing a step of generating worker-in-charge setting information, which is setting information in which the worker, the asset that is the target of the task performed by the worker, and the task are associated, from the maintenance business log database; In the step of executing the simulation of the maintenance business; Causing the failure to occur in the asset agent according to the pattern of the failure included in the task setting information; Determining an assignment to a worker agent corresponding to the worker associated with the task and an asset corresponding to the asset agent for the task corresponding to the failure, which is included in the worker-in-charge setting information; Executing a step of executing a simulation in which the worker agent performs the task on the asset agent; In the step of modifying the setting information; When the activity level of the worker agent during the execution of the simulation exceeds a specified value contrary to the specification in the business knowledge database, adding the task performed by the worker corresponding to the worker agent included in the worker-in-charge setting information and the asset that is the target thereof to the worker-in-charge setting information of a worker whose activity level is lower than the specification, different from the worker; Maintenance improvement support method.

9. A maintenance improvement support device, Generating setting information for performing a simulation of the maintenance business based on a maintenance business log database, which is an execution record of the maintenance business, and includes an asset that is a maintenance target in the maintenance business, a worker who is in charge of the maintenance business, and a task that is the maintenance business performed by the worker on the asset; Executing a simulation of the maintenance business using an asset agent that is an agent indicating the asset and a worker agent that is an agent indicating the worker; Detecting a state of the asset agent or the worker agent contrary to the specification in the business knowledge database including the specification when performing the maintenance business, and modifying the setting information. In the step of generating setting information for simulating the maintenance operation, generating task setting information which is setting information in which the asset, the pattern of a failure occurring in the asset, and the task performed by the worker corresponding to the failure are associated with each other from the maintenance operation log database; executing a step of generating worker assignment setting information which is setting information in which the worker, the asset which is the target of the task performed by the worker, and the task are associated with each other from the maintenance operation log database; In the step of executing the simulation of the maintenance operation, causing the failure to occur in the asset agent according to the pattern of the failure included in the task setting information; for the task corresponding to the failure, determining an assignment to the asset agent corresponding to the asset and the worker agent corresponding to the worker associated with the task, which are included in the worker assignment setting information; executing a step of executing a simulation in which the worker agent performs the task on the asset agent; In the step of modifying the setting information, when a period from the occurrence of the failure in the task setting information for the asset agent during the simulation execution until the corresponding task is not performed is longer than the regulation of the business knowledge database, searching for an agent indicating the worker who performs the task, and adding the task and the asset corresponding to the asset agent to the worker assignment setting information of the worker corresponding to the agent indicating the worker; Maintenance improvement support method.

Images