Monitoring screen generation system, monitoring screen generation method, and monitoring screen generation program

Abstract

To reduce a load on a worker who performs the task of selecting and displaying a plurality of monitoring screens.SOLUTION: A monitoring screen generation system 100 includes: a monitoring control device 3 having a function of displaying a plurality of monitoring screens on a dashboard; and a database device 1. The database device 1 includes: a learned model storage unit 12 that stores a learned model generated by learning an actual result in which one of the monitoring screens and another monitoring screen are displayed on the dashboard; an inference unit 13 that, when a dashboard creation request including designated screen information indicating one of the monitoring screens is received, extracts by means of the learned model a monitoring screen having high relevance to the monitoring screen indicated by the designated screen information; and an output unit 14 that sets, as monitoring screens to be displayed on the dashboard, the monitoring screen indicated by the designated screen information and the monitoring screen extracted by the inference unit, determines a configuration of the dashboard, based on the monitoring screen to be displayed on the dashboard and a template, and transmits a determination result to the monitoring control device.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present disclosure relates to a monitoring screen generating system, a monitoring screen generating method, and a monitoring screen generating program that generate a monitoring screen to be displayed by a monitoring control device. [Background technology]

[0002] In water treatment facilities such as water supply and sewerage plants, monitors use monitoring and control equipment to monitor and control the water treatment plant. During monitoring work, various monitoring screens are displayed on the display unit of the monitoring and control equipment, and the status of the facility is grasped by monitoring the contents displayed on each screen.

[0003] For example, Patent Document 1 describes an online monitoring device that, when it detects a change in the status of a monitored object such as equipment or facilities, selects the required monitoring screen from multiple screen candidates related to the detected status change, and automatically switches and displays each selected monitoring screen in a predetermined order. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-106432 Summary of the Invention [Problem to be solved by the invention]

[0005] The online monitoring device described in Patent Document 1 eliminates the need to switch between multiple related monitoring screens during monitoring work. However, it has the problem of not being able to handle cases where the contents of multiple monitoring screens are displayed simultaneously.

[0006] In monitoring work, displaying multiple monitoring screens on the display unit of a monitoring control device, each displaying related monitoring items, eliminates the need to switch between screen displays and allows monitors to simultaneously check multiple monitoring items, which is expected to improve work efficiency. However, displaying multiple monitoring screens requires selecting the monitoring screens that are most needed from among many monitoring screens and then displaying the selected monitoring screens in an appropriate layout. Therefore, it is desirable to realize technology that can reduce the workload of displaying multiple monitoring screens, each displaying items necessary for monitoring work, on the display unit.

[0007] The present disclosure has been made in view of the above, and aims to provide a monitoring screen generation system that can reduce the workload of selecting and displaying multiple monitoring screens. [Means for solving the problem]

[0008] In order to solve the above-mentioned problems and achieve the objectives, the monitoring screen generation system of the present disclosure comprises a monitoring control device having a function of displaying multiple monitoring screens on a dashboard, and a database device connected to the monitoring control device via a communication network, wherein the database device comprises: a learned model memory unit that stores a learned model generated by learning the actual display of one of the multiple monitoring screens and other monitoring screens on the dashboard; an inference unit that, when it receives a dashboard creation request from the monitoring control device including specified screen information indicating one of the monitoring screens to be displayed on the dashboard, uses the learned model to extract monitoring screens that are highly relevant to the monitoring screen indicated by the specified screen information; and an output unit that determines the configuration of the dashboard based on the monitoring screen indicated by the specified screen information and the monitoring screen extracted by the inference unit as the monitoring screens to be displayed on the dashboard, and transmits the determination result to the monitoring control device. [Effects of the Invention]

[0009] The monitoring screen generation system according to the present disclosure has the effect of reducing the workload of selecting and displaying multiple monitoring screens. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating a configuration example of a monitoring screen generation system according to a first embodiment. [Figure 2] FIG. 10 is a diagram illustrating a first example of a monitoring screen displayed by the monitoring control device according to the first embodiment. [Figure 3] FIG. 10 is a diagram illustrating a second example of a monitoring screen displayed by the monitoring control device according to the first embodiment. [Figure 4] FIG. 10 is a diagram illustrating a third example of a monitoring screen displayed by the monitoring control device according to the first embodiment. [Figure 5] FIG. 1 is a diagram illustrating an example of a dashboard in which a monitoring control device according to a first embodiment simultaneously displays a plurality of monitoring screens. [Figure 6] FIG. 1 is a diagram illustrating an outline of the operation of the monitoring screen generation system according to the first embodiment. [Figure 7] FIG. 1 is a diagram illustrating an example of the configuration of a database device and a computing device of a monitoring screen generation system according to a first embodiment. [Figure 8] FIG. 1 is a diagram illustrating an example of data stored in a data storage unit of the database device according to the first embodiment. [Figure 9] FIG. 1 is a diagram showing an example of a plurality of templates represented by screen layout pattern data stored in a data storage unit of the database device according to the first embodiment; [Figure 10] FIG. 10 is a diagram for explaining a specific example of the operation of the inference unit of the database device according to the first embodiment; [Figure 11] 1 is a flowchart illustrating an example of an operation of the monitoring screen generation system according to the first embodiment to generate a trained model. [Figure 12] 1 is a flowchart showing an example of an operation of the monitoring screen generation system according to the first embodiment to generate a dashboard. [Figure 13] FIG. 10 is a diagram illustrating an example of a screen displayed by the monitoring control device according to the first embodiment; [Figure 14]FIG. 10 is a diagram illustrating an example of dashboard configuration data generated by an output unit of the database device according to the first embodiment. [Figure 15] FIG. 10 is a diagram illustrating an example of data stored in a data storage unit of the database device according to the second embodiment. [Figure 16] FIG. 10 is a diagram for explaining data output from a trained model used by a database device according to a second embodiment. [Figure 17] FIG. 10 is a diagram illustrating an overview of the overall operation of the monitoring screen generation system according to the third embodiment. [Figure 18] FIG. 1 is a diagram illustrating an example of the hardware configuration of a database device in a monitoring screen generation system. DETAILED DESCRIPTION OF THE INVENTION

[0011] A monitoring screen generating system, a monitoring screen generating method, and a monitoring screen generating program according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0012] Embodiment 1 FIG. 1 is a diagram illustrating an example of the configuration of a monitoring screen generation system 100 according to a first embodiment. The monitoring screen generation system 100 includes a database device 1, a calculation device 2, and a plurality of monitoring control devices 3. The database device 1, the calculation device 2, and each monitoring control device 3 are connected to a communication network 150, and can transmit and receive various signals, such as control signals and data signals, to and from other devices. In the example illustrated in FIG. 1, there are a plurality of monitoring control devices 3, but there may be only one. A water treatment facility 4, which is an example of a facility to be monitored and controlled, is also connected to the communication network 150.

[0013] The monitoring control device 3 is used by a supervisor who monitors and controls the water treatment facility 4. The monitoring control device 3 is realized, for example, by a stationary personal computer (hereinafter referred to as a PC), a portable laptop computer, a tablet terminal, or the like, by executing a dedicated program. The monitoring control device 3 may be a dedicated device specialized for monitoring and control work. The monitoring control device 3 has the function of simultaneously displaying multiple monitoring screens. When the monitoring control device 3 simultaneously displays multiple monitoring screens, the multiple monitoring screens are displayed together on a dashboard. The monitoring control device 3 can, for example, display, together on the dashboard, a monitoring screen for monitoring the entire water treatment facility 4, a monitoring screen for monitoring some of the equipment that makes up the water treatment facility 4, and a monitoring screen for checking and changing the settings of the equipment provided in the water treatment facility 4. Note that the facility to be monitored and controlled is not limited to the water treatment facility 4.

[0014] The combination of monitoring screens to be displayed on the dashboard and the layout of each monitoring screen are basically decided by the monitor using the monitoring control device 3, but may also be decided by the monitoring screen generation system 100. In other words, the monitoring screen generation system 100 has a function to automatically decide the configuration of the dashboard to be displayed by the monitoring control device 3. The monitoring screen generation system 100 decides the configuration of the dashboard based on the monitor's usage history of the monitoring control device 3. The usage history of the monitoring control device 3 includes screen display history data, which is data on monitoring screens that the monitoring control device 3 has displayed in the past in accordance with the monitor's operations. The screen display history data is stored in the database device 1.

[0015] The monitoring screen generation system 100 also has a function of generating a dashboard with a different configuration for each monitor who uses the monitoring control device 3 and displaying it on the monitoring control device 3. In the monitoring screen generation system 100, the generation of a dashboard with a different configuration for each monitor is performed based on the usage history of the monitoring control device 3 for each monitor.

[0016] In the monitoring screen generation system 100, when the selection of monitoring screens to be displayed on the dashboard and the determination of the arrangement of the monitoring screens on the dashboard are automatically performed, the selection of the monitoring screens and the determination of the arrangement are performed by the database device 1. The database device 1 selects the monitoring screens to be displayed on the dashboard using a trained model generated by learning using the screen display history data of the monitoring control device 3, and further determines the arrangement of the selected monitoring screens. The trained model used by the database device 1 is generated by the calculation device 2. Details of the operation by which the calculation device 2 generates the trained model and the operation by which the database device 1 uses the trained model will be described later.

[0017] 2 to 4 show examples of monitoring screens displayed by the monitoring control device 3. Fig. 2 is a diagram showing a first example of a monitoring screen displayed by the monitoring control device 3 according to the first embodiment, Fig. 3 is a diagram showing a second example of a monitoring screen displayed by the monitoring control device 3 according to the first embodiment, and Fig. 4 is a diagram showing a third example of a monitoring screen displayed by the monitoring control device 3 according to the first embodiment.

[0018] A monitoring screen 201 of a first example shown in Fig. 2 is a graphic screen that allows a monitor to monitor the status of the water treatment facility 4. A monitoring screen 202 of a second example shown in Fig. 3 is a trend graph screen that allows a monitor to monitor changes over time in the status of equipment, which is facilities or devices, that are included in the water treatment facility 4. A monitoring screen 203 of a third example shown in Fig. 4 is a control panel screen that allows a monitor to monitor and control the status of the equipment, which is included in the water treatment facility 4.

[0019] For example, the monitor causes the monitoring control device 3 to simultaneously display the monitoring screen 202 shown in FIG. 3 and the monitoring screen 203 shown in FIG. 4, monitors changes in the status of the equipment on the trend graph screen of the monitoring screen 202, and simultaneously adjusts the operating parameters of the equipment on the control panel screen of the monitoring screen 203.

[0020] Fig. 5 is a diagram showing an example of a dashboard in which the monitoring control device 3 according to the first embodiment simultaneously displays multiple monitoring screens. Dashboard 205 in the example shown in Fig. 5 includes monitoring screen 206 that shows the status of facility devices, monitoring screen 207 that displays a trend graph, and monitoring screen 208 that displays a control panel. By having monitoring control device 3 display dashboard 205, a monitor can monitor the current status of the facility devices that are the subject of monitoring control on monitoring screen 206, while also monitoring changes over time in the status of the facility devices on monitoring screen 207. Furthermore, the monitor can also adjust operating parameters of the facility devices on monitoring screen 208 while monitoring the status of the facility devices that are the subject of monitoring control.

[0021] Next, an overview of the overall operation of the monitoring screen generating system 100 will be described with reference to Fig. 6. Fig. 6 is a diagram showing an overview of the operation of the monitoring screen generating system 100 according to the first embodiment. It is assumed that the database device (DB device) 1 shown in Fig. 6 collects and stores screen display history data of the monitoring control device 3 and information of users who are monitors who have used the monitoring control device 3 (hereinafter referred to as user information) from the monitoring control device 3.

[0022] In the monitoring screen generation system 100, first, (1) the database device 1 outputs the stored screen display history data and user information to the arithmetic device 2. Next, (2) the arithmetic device 2 generates a trained model based on the input data (user information, screen display history data) from the database device 1, and outputs it to the database device 1.

[0023] Next, (3) the monitoring control device 3 transmits a dashboard creation request to the database device 1. The dashboard creation request is transmitted when the monitor using the monitoring control device 3 performs a predetermined operation. Next, (4) the database device 1, which has received the dashboard creation request, creates dashboard configuration data based on the trained model generated by the arithmetic device 2 and transmits the dashboard configuration data to the monitoring control device 3. Finally, (5) the monitoring control device 3 displays a dashboard tailored to the monitoring screen currently being monitored, based on the dashboard configuration data received from the database device 1. The monitoring screen currently being monitored is the monitoring screen being monitored by the monitor when the monitoring control device 3 transmits the dashboard creation request to the database device 1. In the following description, the monitoring screen currently being monitored or the monitoring screen associated with the monitoring screen currently being monitored may be referred to as the estimation target screen. In the example shown in FIG. 6, the monitoring control device 3 transmits the dashboard creation request while displaying the monitoring screen 201. The dashboard creation request includes information about the estimation target screen. After transmitting the dashboard creation request and receiving the dashboard configuration data, the monitoring control device 3 generates a dashboard 205 based on the received dashboard configuration data and displays the dashboard 205, created by combining multiple monitoring screens, instead of the monitoring screen 201. Details of the dashboard configuration data will be described later, but the dashboard configuration data includes information on monitoring screens related to the estimated target screen (hereinafter referred to as related screens) and information on the layout of the estimated target screen and related screens.

[0024] Next, a description will be given of the configurations of the database device 1 and the arithmetic device 2 of the monitoring screen generating system 100. Fig. 7 is a diagram showing an example of the configurations of the database device 1 and the arithmetic device 2 of the monitoring screen generating system 100 according to the first embodiment.

[0025] As shown in FIG. 7, the database device 1 includes a data storage unit 11, a trained model storage unit 12, an inference unit 13, and an output unit .

[0026] 8 is a diagram illustrating an example of data stored in the data storage unit 11 of the database device 1 according to the first embodiment. As illustrated in FIG. 8, the data storage unit 11 stores screen display history data 111, screen information metadata 112, and screen layout pattern data 113.

[0027] The screen display history data 111 includes a user ID (Identification), which is identification information of the monitor who used the monitoring control device 3, a timestamp indicating the time when the monitoring control device 3 displayed the monitoring screen, and screen information, which is identification information of the monitoring screen displayed by the monitoring control device 3. The time when the monitoring screen indicated by the timestamp was displayed is, for example, the time when the display of the monitoring screen began. The screen display history data 111 in FIG. 8 indicates that the monitoring control device 3 used by user #1 displayed screen A at 12:00:00 on February 1, 2023, screen C at 12:00:10 on February 1, 2023, and screen D at 12:00:15 on February 1, 2023. The screen display history data 111 also indicates that the monitoring control device 3 used by user #2 displayed screen B at 14:30:40 on February 2, 2023, and that the monitoring control device 3 used by user #3 displayed screen A at 09:25:03 on February 10, 2023, etc.

[0028] The database device 1 collects the user ID, timestamp, and screen information stored in the data storage unit 11 as the screen display history data 111 from the monitoring control device 3 at a predetermined timing. The database device 1 may collect the user ID, timestamp, and screen information at any timing. For example, the database device 1 communicates with the monitoring control device 3 at a predetermined timing and collects data that has not been collected at the start of communication, specifically, user IDs, timestamps, and screen information that is not held in the data storage unit 11, from the monitoring control device 3. The database device 1 may also collect unacquired data from the monitoring control device 3 periodically, such as daily or weekly. If the monitoring screen generation system 100 includes multiple monitoring control devices 3, the database device 1 collects the user IDs, timestamps, and screen information from all the monitoring control devices 3. The database device 1 may also collect the user IDs, timestamps, and screen information each time the monitoring control device 3 displays a monitoring screen. For example, the monitoring control device 3 may transmit the user ID, timestamp, and screen information to the database device 1 each time it displays a monitoring screen in accordance with an operation by a monitor, and the database device 1 receives and stores the information.

[0029] The screen information metadata 112 is metadata for each monitoring screen that can be displayed by the monitoring control device 3, and includes screen information, screen type, and signal information. The screen information is identification information for each monitoring screen that can be displayed by the monitoring control device 3. The screen type is information indicating the type of each monitoring screen that can be displayed by the monitoring control device 3. The signal information is identification information for signals that can be monitored by a monitor on each monitoring screen that can be displayed by the monitoring control device 3. The signals that can be monitored by a monitor represent the status of equipment included in the water treatment facility 4. If the equipment is a pump, examples of signals that can be monitored by a monitor include a signal indicating the operating status of the pump and a signal indicating the rotation speed of the pump. If the equipment is a sensor, examples of signals that can be monitored by a monitor include a signal indicating a measured temperature value and a detected value of water quality. The screen information metadata 112 may further include the display size of each monitoring screen that can be displayed by the monitoring control device 3. The screen information metadata 112 is data that is stored in advance in the data storage unit 11.

[0030] The screen layout pattern data 113 represents a screen layout pattern on a dashboard when the monitoring control device 3 collectively displays multiple monitoring screens on the dashboard. There are multiple screen layout patterns. The data storage unit 11 stores multiple templates corresponding to the multiple screen layout patterns as the screen layout pattern data 113. FIG. 9 shows examples of screen layout pattern templates. FIG. 9 is a diagram showing an example of multiple templates represented by the screen layout pattern data 113 held by the data storage unit 11 of the database device 1 according to the first embodiment. Templates A and B shown in FIG. 9 are used when an estimation target screen and two monitoring screens related to the estimation target screen are simultaneously displayed, and templates C and D are used when an estimation target screen and one monitoring screen related to the estimation target screen are simultaneously displayed. Which template to use when simultaneously displaying an estimation target screen and a monitoring screen related to the estimation target screen is determined based on the screen type of each monitoring screen to be simultaneously displayed. The screen layout pattern data 113 is also data pre-stored in the data storage unit 11.

[0031] The trained model storage unit 12 acquires from the calculation device 2 the trained model that is generated by the calculation device 2 performing learning using the screen display history data, and stores it.

[0032] The inference unit 13 uses the learned model stored in the learned model storage unit 12 to infer evaluation values ​​for each of multiple candidates for monitoring screens (associated screens) to be displayed on the dashboard together with the monitoring screen being monitored by the monitor using the monitoring control device 3 or the estimation target screen, which is the monitoring screen associated with the monitoring screen. In the following description, the candidates for associated screens will be referred to as candidate screens. The evaluation value represents the relevance between the candidate screen and the estimation target screen, and the larger the evaluation value, the more frequently a candidate screen will be displayed on the dashboard together with the estimation target screen.

[0033] Furthermore, the inference unit 13 selects related images of the estimation target image from among the candidate images based on the evaluation value of each of the plurality of candidate images obtained by inference. Specifically, the inference unit 13 selects a predetermined number of candidate images in descending order of the evaluation value, and sets these as related images.

[0034] A specific example of the case where the inference unit 13 selects two related screens will be described with reference to FIG. 10 . FIG. 10 is a diagram for explaining a specific example of the operation of the inference unit 13 of the database device 1 according to the first embodiment. As shown in FIG. 10 , when the estimation target screen is screen A, the candidate screens are screen B, screen C, screen D, and screen E, and their evaluation values ​​are 98.25, 42.16, 74.32, and 12.50, respectively. The inference unit 13 selects screen B, which has the highest evaluation value, and screen D, which has the second highest evaluation value. While the example of selecting the two monitoring screens with the highest evaluation values ​​has been described here, the selection may be limited to monitoring screens with evaluation values ​​equal to or greater than a predetermined value. For example, the two monitoring screens with the highest evaluation value may be selected after limiting the selection to monitoring screens with evaluation values ​​equal to or greater than 80. In this case, if there is one candidate screen with an evaluation value equal to or greater than 80, as in the example shown in FIG. 10 , only the candidate screen with the highest evaluation value (screen B) is selected as the related screen. The selection conditions for related screens, such as the number of related screens that the inference unit 13 selects based on the evaluation value and the lower limit of the evaluation value for related screens, may be set by the monitor using the monitoring control device 3.

[0035] The output unit 14 creates dashboard configuration data indicating the configuration of the dashboard to be displayed by the monitoring control device 3 based on the inference result (result of selection of the related screen) by the inference unit 13, and outputs the dashboard configuration data to the monitoring control device 3.

[0036] In creating the dashboard configuration data, the output unit 14 determines the layout of the estimation target screen and related screens on the dashboard based on the screen information metadata 112 and the screen layout pattern data 113 stored in the data storage unit 11. For example, when there are two related screens, the output unit 14 selects template A or template B shown in FIG. 9 to determine the layout of each screen. The template to select is determined taking into consideration the screen type in the screen information metadata 112, i.e., the types of estimation target screen and related screens to be displayed on the dashboard. Since it is predetermined for each type of monitoring screen whether the monitoring screen is horizontally or vertically elongated, the output unit 14 selects a template taking into consideration the screen shape derived from each type of monitoring screen. It is assumed that the output unit 14 knows the screen shape for each type of monitoring screen. The output unit 14 also determines the layout of each screen in a similar manner when there is only one related screen.

[0037] The calculation device 2 includes a data acquisition unit 21 and a model generation unit 22.

[0038] The data acquisition unit 21 acquires the screen display history data 111 stored in the data storage unit 11 of the database device 1 .

[0039] The model generation unit 22 performs a learning process using the screen display history data 111 acquired by the data acquisition unit 21, and generates a learned model that the inference unit 13 of the database device 1 described above uses to infer the evaluation values ​​of candidate screens.

[0040] Next, the operation of the monitoring screen generation system 100 to generate a trained model and to generate a dashboard using the trained model will be described.

[0041] [Generation of trained model] FIG. 11 is a flowchart showing an example of the operation of the monitoring screen generating system 100 according to the first embodiment to generate a trained model.

[0042] First, the data acquisition unit 21 of the arithmetic device 2 acquires learning data (step S11). Specifically, the data acquisition unit 21 acquires the screen display history data 111 from the data storage unit 11 of the database device 1.

[0043] Next, the model generation unit 22 of the arithmetic device 2 performs a learning process (step S12). Specifically, the model generation unit 22 performs the learning process according to learning data created based on the screen display history data 111 acquired by the data acquisition unit 21, and generates a learned model that calculates an evaluation value of a candidate screen of a dashboard displayed by the monitoring control device 3. The model generation unit 22 generates a learned model for each user, i.e., for each monitor who uses the monitoring control device 3. The evaluation value of a candidate screen can be, for example, the probability that it will be displayed together with the estimation target screen. The probability that a candidate screen will be displayed together with the estimation target screen can be calculated based on the timestamp and screen information included in the screen display history data 111. By analyzing the timestamp, it is possible to identify the monitoring screens that were displayed together. For example, the model generation unit 22 extracts, from the screen display history data 111, the screen information and timestamp of the monitoring screen displayed by the monitoring control device 3 when user #1 used the monitoring control device 3, and calculates an evaluation value for each candidate screen when one of the monitoring screens indicated by the extracted screen information is set as the estimation target screen and the remaining are set as candidate screens. Then, a trained model corresponding to user #1 is generated by learning the relationship between the estimation target screen and the evaluation value of each candidate screen. The model generation unit 22 calculates the evaluation value of each candidate screen when it is set as the estimation target screen for all monitoring screens indicated by the screen information extracted from the screen display history data 111, and learns the relationship between the estimation target screen and the evaluation value of each candidate screen. When information indicating one of the monitoring screens that can be displayed by the monitoring control device 3 is input, the trained model is configured to output the evaluation values ​​of the remaining monitoring screens. The model generation unit 22 also generates trained models corresponding to users other than user #1 in a similar manner.

[0044] Next, the trained model storage unit 12 of the database device 1 stores the trained model (step S13). Specifically, the trained model storage unit 12 acquires the trained model generated by the model generation unit 22 of the arithmetic device 2 in step S12 from the model generation unit 22 and stores it.

[0045] [Dashboard generation behavior] FIG. 12 is a flowchart showing an example of an operation of the monitoring screen generating system 100 according to the first embodiment to generate a dashboard.

[0046] First, the database device 1 acquires the inference data output from the monitoring control device 3 (step S21). Specifically, the database device 1 acquires the user ID of the monitor using the monitoring control device 3 from which the inference data was acquired, and the screen information of the estimation target screen. The inference data is output from the monitoring control device 3 at a predetermined timing. The database device 1 acquires the inference data when it is output from the monitoring control device 3.

[0047] For example, when the monitoring control device 3 receives a predetermined operation from an observer, the monitoring control device 3 outputs the user ID of the observer who received the operation and screen information of the estimation target screen as inference data. The monitoring control device 3 transmits the inference data in the dashboard creation request described with reference to FIG. 6. For example, as shown in FIG. 13, when a graphic screen is displayed on the monitoring screen 201 and one device on the graphic screen is selected by the observer, the monitoring control device 3 displays a window 210 for the observer to specify a monitoring screen for the selected device. FIG. 13 is a diagram illustrating an example of a screen displayed by the monitoring control device 3 according to the first embodiment. In the example of FIG. 13, three monitoring screens (an operation setting window 211, a one-tag window 212, and a trend window 213) are displayed in the window 210. When one of the monitoring screens displayed in the window 210 is specified by clicking or the like, the monitoring control device 3 determines the specified screen as the estimation target screen and transmits a dashboard creation request including the screen information of the specified screen (estimation target screen) and the observer's user ID to the database device 1.

[0048] Next, the inference unit 13 of the database device 1 inputs the inference data into the learned model stored in the learned model storage unit 12 (step S22) to obtain an inference result. Specifically, the inference unit 13 inputs the screen information of the estimation target screen into the learned model corresponding to the monitor using the monitoring control device 3, among the learned models for each user stored in the learned model storage unit 12, and accordingly obtains an evaluation value for each of the multiple candidate screens output from the learned model.

[0049] Next, the inference unit 13 of the database device 1 outputs data of related screens of the estimation target screen (step S23). Specifically, the inference unit 13 extracts a predetermined number of candidate screens with high evaluation values ​​from among the candidate screens as related screens of the estimation target screen, and outputs the data of the related screens to the output unit 14.

[0050] Next, the output unit 14 of the database device 1 generates dashboard configuration data (step S24). Specifically, the output unit 14 determines the layout on the dashboard of the estimation target screen and the related screen extracted by the inference unit 13, and generates dashboard configuration data indicating the determination result. The output unit 14 generates, for example, dashboard configuration data having the layout shown in FIG. 14. FIG. 14 is a diagram illustrating an example of the dashboard configuration data generated by the output unit 14 of the database device 1 according to the first embodiment. The dashboard configuration data shown in FIG. 14 includes a user ID, a configuration screen, and a display position. The user ID is set to the user ID of the monitor using the monitoring control device 3 that has transmitted the dashboard creation request. The configuration screen is set to identification information (screen information) of each monitoring screen (the estimation target screen and related screen) that constitutes the dashboard. The display position is set to position information that indicates the layout of each monitoring screen that constitutes the dashboard. Note that although the layout of the monitoring screen is represented by coordinates on the dashboard in FIG. 14, the layout of the monitoring screen may be represented using other information.

[0051] The output unit 14 transmits the generated dashboard configuration data to the monitoring control device 3.

[0052] Next, the monitoring control device 3 generates a dashboard (step S25). Specifically, the monitoring control device 3 generates the dashboard by arranging each monitoring screen corresponding to the configuration screen information at the position indicated by the display position information, based on the configuration screen information and display position information included in the dashboard configuration data received from the database device 1. The monitoring control device 3 displays the generated dashboard.

[0053] When generating a dashboard, the monitoring control device 3 may adjust the display size of each monitoring screen based on at least one of the following: the type of monitoring screen to be displayed, the combination of monitoring screens to be displayed, and the number of signals monitored in each monitoring screen to be displayed. For example, the display size of a monitoring screen that monitors a large number of signals may be increased compared to other monitoring screens, and the display size of a monitoring screen that monitors a small number of signals may be decreased compared to other monitoring screens. This prevents inconveniences such as variations in visibility among the monitoring screens displayed on the dashboard. It also prevents the need for manual adjustment of the size of each monitoring screen displayed on the dashboard to standardize visibility, thereby reducing the workload of the monitoring personnel. The display size adjustment of each monitoring screen displayed on the dashboard may be performed by the output unit 14 of the database device 1. In this case, the output unit 14 transmits information about the adjusted display size of the monitoring screen together with the dashboard configuration data.

[0054] As described above, the monitoring screen generation system 100 according to the present embodiment includes a database device 1, a calculation device 2, and a monitoring control device 3. The calculation device 2 performs a learning process using screen display history data created by recording, together with timestamps, information about the monitoring screens displayed on the monitoring control device 3 by an observer using the monitoring control device 3 during monitoring work. In the learning process using the screen display history data, the calculation device 2 generates, for each observer, a trained model for calculating an evaluation value for each candidate monitoring screen to be displayed on the dashboard together with the estimation target screen, which is the monitoring screen specified by the observer. The database device 1 uses the trained model to select a monitoring screen to be displayed on the dashboard together with the estimation target screen by the monitoring control device 3, and determines the layout of the estimation target screen and the related screen, which is the selected monitoring screen. The monitoring screen generation system 100, which operates in this manner, allows an observer to easily select and arrange the necessary monitoring screens when multiple monitoring screens need to be checked simultaneously during monitoring work, thereby improving work efficiency, reducing workload, and improving observer convenience.

[0055] In this embodiment, the monitoring screen generation system 100 including the arithmetic device 2 that generates a trained model has been described, but the arithmetic device 2 may be configured to be provided outside the monitoring screen generation system 100. That is, the database device 1 may transmit the screen display history data 111 to a device provided outside the monitoring screen generation system 100 and having the same functions as the arithmetic device 2, and request the device to generate a trained model.

[0056] Embodiment 2 Next, a monitoring screen generation system according to embodiment 2 will be described. The configuration of the monitoring screen generation system is the same as that of embodiment 1. In this embodiment, the description of the parts common to embodiment 1 will be omitted, and only the parts different from embodiment 1 will be described.

[0057] The monitoring screen generating system 100 according to the second embodiment differs from the first embodiment in the learning data used to generate the trained model and the inference data used to calculate the evaluation value.

[0058] Fig. 15 is a diagram illustrating an example of data stored in the data storage unit 11 of the database device 1 according to the second embodiment. In Fig. 15, the same reference numerals are assigned to data common to the data stored in the data storage unit 11 of the database device 1 according to the first embodiment shown in Fig. 8.

[0059] 15, the data storage unit 11 of the database device 1 according to the second embodiment holds screen display history data 111a, screen information metadata 112, and screen layout pattern data 113. That is, the data storage unit 11 of the database device 1 according to the second embodiment holds screen display history data 111a having a different configuration from the screen display history data 111 held by the data storage unit 11 of the database device 1 according to the first embodiment.

[0060] The screen display history data 111a includes a user ID, a timestamp, a time period during which monitoring was performed using the monitoring control device 3, the weather when monitoring was performed using the monitoring control device 3, whether or not an alarm occurred during the time period during which monitoring was performed using the monitoring control device 3, and screen information. The screen display history data 111a is the screen display history data 111 held in the data storage unit 11 of the database device 1 according to the first embodiment, to which three pieces of information, namely, time period, weather, and whether or not an alarm occurred, have been added. An alarm is notified to a monitor via the monitoring control device 3 when any abnormality is detected in the water treatment facility 4 that is the object of monitoring and control. Note that since the time period can be determined from the timestamp, the screen display history data 111a may be configured not to include information on the time period, and the time period may be determined from the timestamp.

[0061] The model generation unit 22 of the arithmetic device 2 according to the second embodiment performs a learning process using the screen display history data 111a as learning data to generate a learned model for each user. This learned model is configured to output evaluation values ​​for the remaining monitoring screens when information indicating one of the monitoring screens that can be displayed by the monitoring control device 3 (corresponding to the estimation target screen) and conditions defined by the time period, weather, and whether or not an alert is issued are input.

[0062] When the database device 1 according to the second embodiment receives a dashboard creation request from the monitoring control device 3, the request includes a user ID, a timestamp, a time zone, weather, whether or not an alert is present, and screen information, the inference unit 13 determines a monitoring screen to be displayed on the dashboard together with the estimation target screen indicated by the received screen information. Specifically, the inference unit 13 inputs the screen information indicating the estimation target screen, the time zone, weather, and whether or not an alert is present, into a trained model corresponding to the monitor using the monitoring control device 3, among the trained models for each user stored in the trained model storage unit 12, and acquires evaluation values ​​for each of multiple candidate screens output from the trained model accordingly. For example, the inference unit 13 acquires evaluation value data having the configuration shown in FIG. 16 using the trained model. FIG. 16 is a diagram for explaining data output from the trained model used by the database device 1 according to the second embodiment. FIG. 16 illustrates an example of an evaluation value output from the trained model when screen information indicating the estimation target screen A and conditions indicating time zone = daytime, weather = sunny, and whether or not an alert is present are input into the trained model corresponding to the monitor of user #1. For the sake of explanation, the user ID, estimation target, and conditions are those shown in Fig. 16. The trained model outputs the screen information of the candidate screen and the evaluation value.

[0063] In this way, the monitoring screen generating system 100 according to the second embodiment performs a learning process using the screen display history data 111a shown in Fig. 15 as learning data, and generates a learned model. The screen display history data 111a is configured by adding information on the time period, weather, and whether or not an alert is present to the screen display history data 111 used in the learning process in the monitoring screen generating system 100 according to the first embodiment. Therefore, compared to the first embodiment, it is possible to generate a dashboard that displays a monitoring screen that is more suited to the usage status of the monitoring control device 3.

[0064] Embodiment 3 Next, a monitoring screen generation system according to embodiment 3 will be described. The configuration of the monitoring screen generation system is the same as that of embodiments 1 and 2. In this embodiment, the description of the parts common to embodiments 1 and 2 will be omitted, and only the parts different from embodiments 1 and 2 will be described.

[0065] FIG. 17 is a diagram illustrating an outline of the overall operation of the monitoring screen generating system 100 according to the third embodiment.

[0066] In the above-described first and second embodiments, a trained model is generated for each monitor, and when the monitoring control device 3 determines the monitoring screen to be displayed on the dashboard, the trained model corresponding to the monitor currently using the monitoring control device 3 is used. In contrast, the monitoring screen generation system 100 according to the present embodiment allows the monitoring control device 3 to select a trained model to be used when determining the monitoring screen to be displayed on the dashboard. That is, as shown in FIG. 17 , when the monitoring control device 3 of the monitoring screen generation system 100 according to the present embodiment receives an operation from the monitor to select one of the monitoring screens to be displayed on the dashboard as the estimation target screen, the monitoring control device 3 also receives an operation to specify which trained model corresponding to which monitor should be used to generate the dashboard. Then, the monitoring control device 3 transmits a dashboard creation request to the database device 1, which includes screen information of the estimation target screen and the user ID of the specified monitor.

[0067] In the database device 1, the inference unit 13 calculates an evaluation value of the candidate screen using a trained model corresponding to the user ID included in the received dashboard creation request, and selects a related screen of the estimation target screen from among the candidate screens. Note that the trained model used to calculate the evaluation value may be the trained model described in the first embodiment or the trained model described in the second embodiment.

[0068] In this way, the monitoring screen generation system 100 according to the third embodiment accepts designation of the trained model to be used when determining the configuration of the dashboard from a monitor who is a user of the monitoring control device 3. This enables, for example, an inexperienced monitor to perform monitoring work using a monitoring screen with the same configuration as a monitoring screen used by an experienced monitor, which is expected to improve work efficiency.

[0069] Embodiment 4 Next, a monitoring screen generation system according to embodiment 4 will be described. The configuration of the monitoring screen generation system is the same as that of embodiments 1 to 3. In this embodiment, the description of the parts common to embodiments 1 to 3 will be omitted, and only the parts different from embodiments 1 to 3 will be described.

[0070] In the first and second embodiments described above, the model generation unit 22 of the arithmetic device 2 performs learning processing using all data included in the screen display history data 111 or 111a stored in the data storage unit 11 of the database device 1. In contrast, the monitoring screen generation system 100 according to this embodiment allows the model generation unit 22 to select data to use in the learning processing. Specifically, the monitor can specify the period of time during which data included in the screen display history data 111 or 111a should be created. This makes it possible to limit learning to data created within the past year. When the configuration of a facility under monitoring control changes, the types of monitoring screens displayed simultaneously during monitoring may change, or the necessity for displaying them simultaneously may change. In this case, the evaluation values ​​of candidate screens to be displayed on the dashboard may become far removed from the actual situation, making it impossible to generate an appropriate dashboard. For example, a monitoring screen that is not necessarily required for monitoring may be displayed.

[0071] By making it possible to specify the period during which the data used in the learning process was created, it becomes possible to prevent a decrease in the reliability of the dashboard generation operation due to changes in the configuration of the facility under monitoring and control.

[0072] The timing for receiving, from the monitor, the specification of the period during which the data used in the learning process was created is not limited. The monitor can specify the period at any time. When the monitoring control device 3 receives, from the monitor, the specification of the period during which the data used in the learning process was created, it notifies the calculation device 2 of the specified period. The monitoring control device 3 may notify the calculation device 2 of the period via the database device 1. In the calculation device 2 that has received the notification of the period during which the data used in the learning process was created, the data acquisition unit 21 extracts data created during the notified period from the screen display history data 111 or 111a, and the model generation unit 22 generates a trained model using the extracted data. The model generation unit 22 outputs the generated trained model to the database device 1. The database device 1 stores the trained model received from the model generation unit 22 in the trained model storage unit 12. If the database device 1 receives a trained model while an old trained model is stored in the trained model storage unit 12, it discards the old trained model.

[0073] As described above, in the monitoring screen generating system 100 according to the fourth embodiment, the monitoring control device 3 receives a period specified by the monitor, and the model generating unit 22 of the computing device 2 performs a learning process using data created during the period specified by the monitor to generate a trained model. This makes it possible to prevent a trained model from being generated based on training data that includes inappropriate data.

[0074] Next, we will explain the hardware configuration that realizes the database device 1 and the arithmetic device 2 of the monitoring screen generation system 100. Note that the database device 1 and the arithmetic device 2 can be realized by similar hardware. Therefore, we will explain the hardware that realizes the database device 1, and will omit a detailed explanation of the hardware that realizes the arithmetic device 2.

[0075] 18 is a diagram showing an example of the hardware configuration of the database device 1 of the monitoring screen generating system 100. The database device 1 is made up of, for example, a processor 91, a memory 92, and a communication circuit 93 shown in FIG.

[0076] The processor 91 is a CPU (Central Processing Unit, also known as a central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor)), a system LSI (Large Scale Integration), etc. The memory 92 is a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), or flash memory, a magnetic disk, etc. The communication circuit 93 is an electronic circuit for connecting to a communication network and transmitting and receiving data, etc.

[0077] When the database device 1 is composed of a processor 91, a memory 92, and a communication circuit 93, the inference unit 13 and the output unit 14 of the database device 1 are realized by the processor 91 executing a program for operating as each of these units. The program for operating as the inference unit 13 and the output unit 14 is stored in advance in the memory 92. The processor 91 operates as the inference unit 13 and the output unit 14 by reading the program from the memory 92 and executing it.

[0078] The programs stored in memory 92 for operating as the inference unit 13 and the output unit 14 may be provided to users, etc., in a form written on a storage medium such as a CD (Compact Disc)-ROM or a DVD (Digital Versatile Disc)-ROM, or may be provided to users, etc. via a network.

[0079] The data storage unit 11 and the trained model storage unit 12 of the database device 1 are realized by a memory 92.

[0080] 18, the programs for operating as the data acquisition unit 21 and the model generation unit 22 can be stored in the memory 92. That is, the programs for operating as the data acquisition unit 21 and the model generation unit 22 are read from the memory 92 and executed by the processor 91, thereby realizing the calculation unit 2.

[0081] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0082] Various aspects of the present disclosure are summarized below as appendices.

[0083] (Appendix 1) a monitoring control device having a function of displaying a plurality of monitoring screens on a dashboard; a database device connected to the monitoring control device via a communication network; Equipped with The database device a trained model storage unit that stores a trained model generated by learning a performance record in which one of the plurality of monitoring screens and another of the monitoring screens are displayed on the dashboard; an inference unit that, when receiving a dashboard creation request from the monitoring control device, the inference unit extracts, using the trained model, a monitoring screen that is highly relevant to the monitoring screen indicated by the designated screen information; an output unit that sets the monitoring screen indicated by the specified screen information and the monitoring screen extracted by the inference unit as monitoring screens to be displayed on the dashboard, determines a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmits the determination result to the monitoring control device; A monitoring screen generation system comprising: (Appendix 2) the output unit determines an arrangement of the monitoring screen to be displayed on the dashboard based on the type of the monitoring screen to be displayed on the dashboard and the number of signals to be monitored on the monitoring screen to be displayed on the dashboard. 2. A monitoring screen generation system according to claim 1. (Appendix 3) the trained model storage unit stores a plurality of trained models individually created for a plurality of monitors who use the monitoring control device, the inference unit performs the extraction using a trained model associated with the monitor using the monitoring control device that is the sender of the dashboard creation request; 3. The monitoring screen generation system according to claim 1 or 2. (Appendix 4) the trained model storage unit stores a plurality of trained models individually created for a plurality of monitors who use the monitoring control device, the inference unit performs the extraction using a trained model associated with the monitor identified by the user identification information included in the dashboard creation request; user identification information indicating a monitor who is different from the monitor using the monitoring control device can be transmitted in the dashboard creation request; 3. The monitoring screen generation system according to claim 1 or 2. (Appendix 5) a computing device that generates the trained model; Furthermore, The database device a data storage unit for storing screen display history data including identification information of a monitor using the monitoring control device, screen information indicating a monitoring screen displayed by the monitoring control device, and a timestamp indicating the date and time when the monitoring control device displayed the monitoring screen; Equipped with The arithmetic device performs a learning process using learning data created based on the screen display history data, and generates the trained model. 5. A monitoring screen generation system according to any one of claims 1 to 4. (Appendix 6) a computing device that generates the trained model; Furthermore, The database device a data storage unit for storing screen display history data including identification information of a monitor using the monitoring control device, screen information showing the monitoring screen displayed by the monitoring control device, a timestamp showing the date and time when the monitoring screen was displayed by the monitoring control device, the weather when monitoring was performed using the monitoring control device, and alarm presence / absence information showing whether an abnormality occurred in the monitored and controlled object when monitoring was performed using the monitoring control device; Equipped with The arithmetic device performs a learning process using learning data created based on the screen display history data, and generates the trained model. 5. A monitoring screen generation system according to any one of claims 1 to 4. (Appendix 7) The computing device creating the learning data based on data that was created during a period designated by the monitor, among data included in the screen display history data; 7. The monitoring screen generation system according to claim 5 or 6. (Appendix 8) A monitoring screen generation method executed by a database device of a monitoring control device having a function of displaying a plurality of monitoring screens on a dashboard and a database device connected to the monitoring control device via a communication network, comprising: A first step of storing a trained model generated by learning a performance of one of the plurality of monitoring screens and another of the monitoring screens being displayed on the dashboard; a second step of extracting, when a dashboard creation request including designated screen information indicating one of the monitoring screens to be displayed on the dashboard is received from the monitoring control device, a monitoring screen that is highly relevant to the monitoring screen indicated by the designated screen information using the trained model; a third step of setting the monitoring screen indicated by the specified screen information and the monitoring screen extracted in the second step as monitoring screens to be displayed on the dashboard, determining a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmitting the determination result to the monitoring control device; A monitoring screen generating method comprising: (Appendix 9) 1. A monitoring screen generation program for implementing a database device of a monitoring screen generation system, the database device being connected to a monitoring control device via a communication network, the monitoring screen generation program comprising: A first step of storing a trained model generated by learning a performance of one of the plurality of monitoring screens and another of the monitoring screens being displayed on the dashboard; a second step of extracting, when a dashboard creation request including designated screen information indicating one of the monitoring screens to be displayed on the dashboard is received from the monitoring control device, a monitoring screen that is highly relevant to the monitoring screen indicated by the designated screen information using the trained model; a third step of setting the monitoring screen indicated by the specified screen information and the monitoring screen extracted in the second step as monitoring screens to be displayed on the dashboard, determining a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmitting the determination result to the monitoring control device; a monitoring screen generating program for causing a computer constituting the database device to execute the above-mentioned program; [Explanation of symbols]

[0084] 1 database device, 2 calculation device, 3 monitoring control device, 4 water treatment facility, 11 data storage unit, 12 trained model memory unit, 13 inference unit, 14 output unit, 21 data acquisition unit, 22 model generation unit, 100 monitoring screen generation system, 150 communication network.

Claims

1. a monitoring control device having a function of displaying a plurality of monitoring screens on a dashboard; a database device connected to the monitoring control device via a communication network; Equipped with The database device a trained model storage unit that stores a trained model generated by learning a performance record in which one of the plurality of monitoring screens and another of the monitoring screens are displayed on the dashboard; an inference unit that, when receiving a dashboard creation request from the monitoring control device, the inference unit extracts a monitoring screen that is highly relevant to the monitoring screen indicated by the specified screen information, using the trained model; an output unit that sets the monitoring screen indicated by the specified screen information and the monitoring screen extracted by the inference unit as monitoring screens to be displayed on the dashboard, determines a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmits the determination result to the monitoring control device; A monitoring screen generation system comprising:

2. the output unit determines an arrangement of the monitoring screen to be displayed on the dashboard based on the type of the monitoring screen to be displayed on the dashboard and the number of signals to be monitored on the monitoring screen to be displayed on the dashboard.

2. The monitoring screen generating system according to claim 1.

3. the trained model storage unit stores a plurality of trained models individually created for a plurality of monitors who use the monitoring control device, the inference unit performs the extraction using a trained model associated with the monitor using the monitoring control device that is the sender of the dashboard creation request; 2. The monitoring screen generating system according to claim 1.

4. the trained model storage unit stores a plurality of trained models individually created for a plurality of monitors who use the monitoring control device, the inference unit performs the extraction using a trained model associated with the monitor identified by the user identification information included in the dashboard creation request; user identification information indicating a monitor who is different from the monitor using the monitoring control device can be transmitted in the dashboard creation request; 2. The monitoring screen generating system according to claim 1.

5. a computing device that generates the trained model; Furthermore, The database device a data storage unit for storing screen display history data including identification information of a monitor using the monitoring control device, screen information indicating a monitoring screen displayed by the monitoring control device, and a timestamp indicating the date and time when the monitoring control device displayed the monitoring screen; Equipped with The arithmetic device performs a learning process using learning data created based on the screen display history data, and generates the trained model.

2. The monitoring screen generating system according to claim 1.

6. a computing device that generates the trained model; Furthermore, The database device a data storage unit for storing screen display history data including identification information of a monitor using the monitoring control device, screen information showing the monitoring screen displayed by the monitoring control device, a timestamp showing the date and time when the monitoring screen was displayed by the monitoring control device, the weather when monitoring was performed using the monitoring control device, and alarm presence / absence information showing whether an abnormality occurred in the monitored and controlled object when monitoring was performed using the monitoring control device; Equipped with The arithmetic device performs a learning process using learning data created based on the screen display history data, and generates the trained model.

2. The monitoring screen generating system according to claim 1.

7. The computing device creating the learning data based on data that was created during a period designated by the monitor, among data included in the screen display history data; 7. The monitoring screen generating system according to claim 5 or 6.

8. A monitoring screen generation method executed by a database device of a monitoring control device having a function of displaying a plurality of monitoring screens on a dashboard and a database device connected to the monitoring control device via a communication network, comprising: A first step of storing a trained model generated by learning a performance of one of the plurality of monitoring screens and another of the monitoring screens being displayed on the dashboard; a second step of extracting, when a dashboard creation request including designated screen information indicating one of the monitoring screens to be displayed on the dashboard is received from the monitoring control device, a monitoring screen that is highly relevant to the monitoring screen indicated by the designated screen information using the trained model; a third step of setting the monitoring screen indicated by the specified screen information and the monitoring screen extracted in the second step as monitoring screens to be displayed on the dashboard, determining a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmitting the determination result to the monitoring control device; A monitoring screen generating method comprising:

9. 1. A monitoring screen generation program for implementing a database device of a monitoring screen generation system, the database device being connected to a monitoring control device via a communication network, the monitoring screen generation program comprising: A first step of storing a trained model generated by learning a performance of one of the plurality of monitoring screens and another of the monitoring screens being displayed on the dashboard; a second step of extracting, when a dashboard creation request including designated screen information indicating one of the monitoring screens to be displayed on the dashboard is received from the monitoring control device, a monitoring screen that is highly relevant to the monitoring screen indicated by the designated screen information using the trained model; a third step of setting the monitoring screen indicated by the specified screen information and the monitoring screen extracted in the second step as monitoring screens to be displayed on the dashboard, determining a configuration of the dashboard based on the monitoring screen to be displayed on the dashboard and a template, and transmitting the determination result to the monitoring control device; a monitoring screen generating program for causing a computer constituting the database device to execute the above-mentioned program;

Images