Prediction system, display device for identifying an operating state of an installation, method of executing an information processing device, and non-transient, tangible computer program product.

Abstract

A prediction system includes a display device for identifying the operating state of a target device, a device execution method, and a program. A prediction system includes a storage unit that stores a history of the operating state of each of a plurality of target devices and attribute information indicating an attribute of each of the plurality of target devices; a first acquisition unit that acquires an attribute information filter condition in which at least one attribute information included in the attribute information of a prediction target device is specified; and a second acquisition unit that acquires an operating state filter condition in which at least one operating state included in a history of the operating state of the prediction target device is specified.An extraction unit that extracts a history of the operating state of a target device satisfying the attribute information filter condition and the operating state filter condition of the plurality of target devices, with reference to the storage unit; and an estimation unit that predicts the operating state of the prediction target device based on the extracted operating state history.

Description

1 / 19 “PREDICTION SYSTEM, DISPLAY DEVICE FOR IDENTIFYING AN INSTALLATION'S OPERATING STATE, METHOD OF EXECUTING AN INFORMATION PROCESSING DEVICE AND COMPUTER PROGRAM PRODUCT, NON-TRANSITORY, TANGIBLE” Field of Invention

[001] Certain embodiments of the invention relate to a prediction system that predicts an operating state of a target device. Background of the Invention

[002] In the related technique, a system for predicting the future behavior of a target device and a component was proposed based on data from an operation of a target device, such as an installation.

[003] For example, in PTL 1, a feature change prediction system for generating a neural circuit model by learning information about changes in the characteristics of various components in a plurality of facilities over time and predicting a future component feature change pattern based on time similarity to each of a plurality of feature change patterns over time is disclosed. Furthermore, for example, in PTL 2, a system is disclosed in which a similar facility is selected from a plurality of facilities and a specific performance index is monitored from operating data. List of citations Patent Literature

[004] [PTL 1] Japanese Patent No. 2758976

[005] [PTL 2] Publication of Unexamined Japanese Patent No. (20)04-290774 Petition 870250063502, dated 07 / 23 / 2025, page 14 / 44 2 / 19 Description of the Invention Technical problem

[006] However, the future behavior of the target device, such as an installation, can be significantly affected not only by its previous operating state, but also by factors such as the target device's specifications and the environment in which the target device is placed. These factors can be said to be information that indicates a category to which the target device belongs when the target device is classified according to various criteria, i.e., attribute information.

[007] Therefore, an objective of the embodiments of the invention is to provide a prediction system capable of predicting a future operating state of a target device based on attribute information of the target device. Solution to the problem

[008] According to one aspect of the embodiments of the invention, a prediction system is provided including a storage unit that stores a history of an operating state of each of a plurality of target devices and attribute information indicating an attribute of each of the plurality of target devices; a first acquisition unit that acquires an attribute information filter condition in which at least one attribute information included in the attribute information of a prediction target device is specified; a second acquisition unit that acquires an operating state filter condition in which at least one operating state included in a history of an operating state of the prediction target device is specified;An extraction unit that extracts a history of an operating state of a target device satisfying the attribute information filter condition and the operating state filter condition of the plurality of target devices, with reference; Petition 870250063502, dated 07 / 23 / 2025, page 15 / 44 3 / 19 to the storage unit; and an estimation unit that predicts the operating state of the target prediction device based on historical data extracted from the operating state.

[009] According to the aspect, the operating state history of the target device that satisfies the attribute information filter condition specifying the target device's attribute information is extracted from the operating state history of each of the plurality of target devices, and the operating state of the predicted target device is predicted based on the operating state history. Therefore, it is possible to predict the future operating state by considering the target device's attribute information. Advantageous Effects of the Invention

[0010] According to embodiments of the invention, it is possible to provide a prediction system capable of predicting the future operating state of a target device based on attribute information of the target device. Brief Description of the Drawings

[0011] Figure 1 is a schematic diagram that illustrates an example of an implementation of a prediction system (1) according to the implementation method.

[0012] Figure 2 is a table that illustrates an example of an attribute information table.

[0013] Figure 3 is a graph that illustrates an example of an operating status history table.

[0014] Figure 4 is a flowchart that illustrates an example of an operating flow through the prediction system (1) according to the implementation method.

[0015] Figure 5 is a view that illustrates an example of a screen. Petition 870250063502, dated 07 / 23 / 2025, page 16 / 44 4 / 19 (500) displayed in a display unit (13).

[0016] Figure 6A is a view that illustrates an example of a screen (600) displayed on the display unit (13).

[0017] Figure 6B is a view illustrating an example of a screen (700) displayed on the display unit (13). Description of Embodiments of the Invention

[0018] Preferred embodiments of the embodiments of the invention will be described with reference to the accompanying drawings (in each figure, those that have the same reference number have the same or a similar configuration). (1) Configuration (1-1) Forecasting System (1)

[0019] Figure 1 is a schematic diagram illustrating an example of an embodiment of a prediction system (1) according to embodiments of the invention. As illustrated in Figure 1, the prediction system (1) includes a server (10) and at least one installation (20). Here, the installation (20) is an example of a “target device”. The type of installation (20) is not particularly limited and may include an oilseed plant, a chemical plant, a pharmaceutical plant, a food plant, a paper manufacturing plant, and the like. Furthermore, the elements constituting the installation (20) are not particularly limited and may include storage equipment for fuel and raw materials, equipment that uses fuel and raw materials, or treats and processes fuel and raw materials, and a piping system connecting each element.The target device to which the prediction system (1) can be applied is not limited to various installations and can be any device, such as an industrial machine.

[0020] The server (10) and each installation (20) are connected a Petition 870250063502, dated 07 / 23 / 2025, page 17 / 44 5 / 19 to the other so that they can communicate through a communication network such as the Internet. When distinguishing each installation (20), each installation (20) can be referred to as “installation (20A)”, “installation (20B)” and the like, and when each installation (20) is generically referred to, each installation (20) can simply be referred to as “installation (20)” (1-2) Server (10)

[0021] The server (10) is an example of an information processing device that manages a history of an operating state (operating state history) of each installation (20). In this example, the server (10) is configured to include, for example, one information processing device, and the server (10) can be configured to include a plurality of information processing devices. Here, the information processing device is a device capable of performing various types of information processing, such as a computer provided with a processor and a storage area. Each part illustrated in Figure 1 can be performed, for example, using a storage area or executing a program stored in the storage area by a processor.

[0022] The server (10) includes, for example, a server communication unit (11), an operation unit (12), a display unit (13), a storage unit (14) and a processing unit (15).

[0023] The server communication unit (11) includes a communication interface circuit to connect the server (10) to the communication network. The server communication unit (11) provides data, such as a history of an operating state (operating state history) received from each facility (20) to the processing unit (15).

[0024] The operating unit (12) can be any device, Petition 870250063502, dated 07 / 23 / 2025, page 18 / 44 6 / 19 provided that the server (10) can be operated and is, for example, a touch panel, a key button or similar. The user can enter characters, numbers, symbols and the like using the operating unit (12). When the operating unit (12) is operated by the user, the operating unit (12) generates a signal corresponding to the operation. The generated signal is provided to the processing unit (15) as a user instruction.

[0025] The display unit (13) can be any device, provided that the display unit (13) can display a figure, an image or the like, and is, for example, a liquid crystal display, an organic electroluminescence (EL) display or the like. The display unit (13) displays an image corresponding to the image data provided by the processing unit (15), an image corresponding to the image data and the like.

[0026] The storage unit (14) includes, for example, at least one semiconductor memory, a magnetic disk device and an optical disk device. The storage unit (14) stores a driver program, an operating system program, an application program, data and the like used for processing by the processing unit (15). For example, the storage unit (14) stores a communication device driver program or similar that controls the server's communication unit (11) as a driver program. The various programs can be installed on the storage unit (14) from a computer-readable portable recording medium, such as a CD-ROM or DVD-ROM, using a known setup program or similar.

[0027] The storage unit (14) stores, as data, an attribute information table, an operating state history table and the like, which will be described later. In addition, the storage unit (14) stores display data from various screens such as Petition 870250063502, dated 07 / 23 / 2025, page 19 / 44 7 / 19 data. In addition, the storage unit (14) temporarily stores data related to the predetermined processing.

[0028] Figure 2 is a table that illustrates an example of an attribute information table. The attribute information table is a table for managing attribute information for each installation. Here, the attribute information of the installation (20) is, for example, information that indicates a category (attribute) to which the installation (20) belongs when the installation (20) is classified according to various criteria. The “attribute” may be referred to as an “external state”, an “incidental state”, an “external incidental state”, or similar.

[0029] In the attribute information table, for example, assign installation information (20), such as “Installation ID”, “Region”, “Climate”, “Manufacturing Time”, “User”, “Fuel Type”, “Model”, “Designer”, “Maintenance Person”, and the like are recorded. The “Installation ID” is an identification (ID) information to identify the installation (20). The “Region” is the information that indicates the region where the installation (20) is installed. The “Climate” is information that indicates the climate of the region where the installation (20) is installed. The “Manufacturing Time” is information that indicates the time when the installation (20) was manufactured and can be expressed by, for example, a year, a year and month, a year, month and date, or the like. The “model” is a type of installation (20) such as a machine and, for example, the model, method and type and “designer” are information that indicates a person (individual, company and the like) who designed the installation (20).The “person who performs maintenance” is the information that indicates a person (individual, company, and the like) who performs maintenance on the installation (20). The attribute information table is not limited to the item described above and may include other attribute information.

[0030] Figure 3 is a graph that illustrates an example of a Petition 870250063502, dated 07 / 23 / 2025, page 20 / 44 8 / 19 Operation Status History Table. The operation status history table is a table for managing the operation status history for each installation (20). As illustrated in Figure 3, in the operation status history table, the operation status history is represented by a plurality of rectangular cells C for each installation. In the operation status history table, the horizontal axis indicates an elapsed time from a reference time. Here, the reference time can be randomly defined by the administrator or similar, and can be, for example, the start of operation, the installation initialization (20) or similar (including restart after a pause period for inspection, in addition to the first initialization).Furthermore, in the operating status history table, each cell (C) indicates the operating status of the installation (20) over elapsed time (each cell (C) can be at a point in time or can be a period with a predetermined width) and the type of operating status is distinguished by the pattern in cell (C). The time period held by a cell (C) can be randomly defined in units of, for example, seconds, minutes, hours, days, weeks, and the like. Operating statuses are not limited to these and may include, for example, normal operation, an accident occurrence (during accidents such as fuel shortage, appearance of foreign matter, temperature increase, temperature drop, cooler trip, fuel system trip, explosion, and blackout), an alarm occurrence (during other alarms such as balance trip level alarm), an operational stoppage, and an occurrence of any other event.

[0031] The processing unit (15) includes one or more processors and their peripheral circuits. The processing unit (15) comprehensively controls the overall operation of the server (10) and is, for example, a central processing unit (CPU). The unit of Petition 870250063502, dated 07 / 23 / 2025, page 21 / 44 9 / 19 processing (15) controls the operation of the server communication unit (11) and similar, so that various server processing (10) operations are executed by an appropriate procedure based on the program and similar stored in the storage unit (14). The processing unit (15) executes the processing based on a program (operating system program, driver program, application program and similar) stored in the storage unit (14). In addition, the processing unit (15) can execute a plurality of programs (application programs and similar) in parallel.

[0032] The processing unit (15) includes a collection portion (151), a first acquisition unit (152a), a second acquisition unit (152b), an extraction unit (153), an estimation unit (154), a display processing unit (155) and the like. Each of these units included in the processing unit (15) is a functional module assembled by a program running on the processor included in the processing unit (15). Alternatively, each of these units included in the processing unit (15) may be mounted on the server (2) as a standalone integrated circuit, microprocessor or firmware.

[0033] The collection portion (151) collects (receives) the operating state history of the installation (20) from each installation (20) and records the operating state history in the operating state history table stored in the storage unit (14) or similar. The time at which the collection or recording processing of the collection portion (151) is executed is not particularly limited and may be, for example, a predetermined periodic or aperiodic time, or when an administrator or similar enters a command to execute the processing via the operation unit (12).

[0034] A receiving unit (152) receives, for example, Petition 870250063502, dated 07 / 23 / 2025, page 22 / 44 10 / 19 various filter conditions entered by the user via the operating unit (12). Here, the filter condition is a condition that the installation (20) or the operating state history of the installation (20) must satisfy in order to extract (filter) a desired operating state history from the operating state history table.

[0035] The first acquisition unit (152a) acquires the attribute information filter condition, which is a condition related to the attribute information of the installation (20). Here, the attribute information filter condition is a condition that the installation (20) must satisfy in order to extract (filter) a history of the desired operating state from the operating state history table and is a condition in which at least one attribute information included in the attribute information of the target prediction device is specified. The attribute information included in the attribute information filter condition may be, for example, the attribute information listed in the description above of Figure 2 described above, or any other attribute information. The first acquisition unit (152a) acquires the attribute information filter condition, for example, by receiving the attribute information filter condition input from the user via the operating unit (12).

[0036] The second acquisition unit (152b) acquires the operating state filter condition which is a condition related to the operating state of the facility (20). Here, the operating state filter condition is a condition that the operating state history of the facility (20) must satisfy in order to extract (filter) a desired operating state history from the operating state history table. In the operating state filter condition, at least one operating state included in the operating state history of the target prediction device is specified. Furthermore, in the operating state filter condition, the order of occurrence of Petition 870250063502, dated 07 / 23 / 2025, page 23 / 44 11 / 19 each operating state can be specified.

[0037] The extraction unit (153) extracts the operating state history of the installation (20) that satisfies the attribute information filter condition received by the first acquisition unit (152a) and the operating state filter condition received by the second acquisition unit (152b) with reference to the storage unit (14). Furthermore, when extracting the operating state history according to the operating state filter condition described above, the extraction unit (153) can only extract when the operating state duration time (when the operating state is intermittent, the duration time can be the total history time of each operating state) specified as the operating state filter condition is equal to or greater than a predetermined limit.

[0038] The estimation unit (154) predicts the operating state of the target prediction device (installation) based on the operating state history extracted by the extraction unit (153). A method of predicting the operating state by the estimation unit (154) is not particularly limited and can be, for example, a prediction by statistical analysis, a prediction by a probability density function, a prediction based on Bayesian theory or similar. More specifically, for example, the estimation unit (154) can calculate the probability of occurrence of the operating state for each hour by statistically analyzing the operating state history extracted by the extraction unit (153) (for example, the extracted operating state history is aggregated for each hour and then normalized). Depending on the probability of occurrence, it is possible to predict the operating state of the target prediction device (installation) at a given point in the future.Alternatively, for example, the estimation unit (154) can perform machine learning using the operating state history extracted by the extraction unit (153) as data. Petition 870250063502, dated 07 / 23 / 2025, page 24 / 44 12 / 19 learning to generate a learning model and insert the history of the target prediction device's (installation) operating state into the learning model to produce the future operating state of the target prediction device. More specifically, for example, the estimation unit (154) can generate a learning model that inserts time series data from the operating state history and produces the future operating state by learning the recurrent neural network (RNN) using the operating state history extracted by the extraction unit (153) as learning data. Depending on the future operating state, it is possible to predict the operating state of the target prediction device (installation) at a given point in the future.

[0039] The display processing unit (155) causes the display unit (13) to display various screens based on the display data of the various screens stored in the storage unit (14). (1-3) Installation (20)

[0040] The installation (20) includes an operating unit (21), several sensors (22), a measurement control system (23), and an installation communication unit (24). The operating unit (21) includes a main device that constitutes the installation (20) and includes, for example, several modules, such as a combustion chamber and a heat exchange chamber, a piping system connecting each module, and the like. The sensor (22) is installed in each location in the operating unit (21), detects various physical quantities of the operating unit (21), and provides the detection results to the measurement control system (23). The measurement control system (23) generates a history of the operating state based on the detection result provided from the sensor (22). Specifically, the measurement control system (23) analyzes the detection result provided by the sensor (22) to determine the operating state of the operating unit (21) in which Petition 870250063502, dated 07 / 23 / 2025, page 25 / 44 13 / 19 the sensor (22) is installed and then generates an operating state history which is a time series change in the determined operating state. The measurement control system (23) transmits the operating state history from the operating unit (21) to the server (10) via the installation communication unit (24). (2) Operation Processing

[0041] Next, an example of the operation processing of the prediction system (1) according to the embodiment will be described with reference to Figures 4 to 6. Figure 4 is a flowchart illustrating an example of an operation flow by the prediction system (1) according to the embodiment. Figure 5 is a view illustrating an example of a screen (500) displayed on the display unit (13). Figure 6 is a view illustrating an example of a screen (600) displayed on the display unit (13). Hereafter, the individual installations (20) may be referred to as an “installation A”, an “installation B”, and so on.

[0042] Here, it is assumed that time (T1) has passed since the initialization of the installation (X), and the operating state of the installation (X) after time (T1) is the target of the prediction. Furthermore, it is assumed that the collection portion (151) of the server (10) collects the operating state history of the installation (20) from each installation (20) in advance and records the operating state history in the operating state history table stored in the storage unit (14). (S100)

[0043] First, the first acquisition unit (152a) of the server (10) acquires the attribute information filter condition. Specifically, for example, the first acquisition unit (152a) acquires the attribute information filter condition when it receives the attribute information filter condition input in response to the unit's operation. Petition 870250063502, dated 07 / 23 / 2025, page 26 / 44 14 / 19 operation (12) by the user. In this case, the server's display processing unit (155) (10) causes the display unit (13) to display the screen (500) illustrated in Figure 5, for example, based on the display data stored in the storage unit (14). As illustrated in Figure 5, the screen (500) includes a display unit (501) for the attribute information filter condition, a display unit (502) for the operating state filter condition, and a display unit (503) for the extracted installation operating state history (20). The display unit (501) displays the content of the attribute information filter condition acquired by the first acquisition unit (152a). In the example illustrated in Figure 5, the display unit (501) displays the attribute information filter conditions where the region is “cold area”, the fuel is “high water content”, and the model is “small”. (S101)

[0044] Next, the extraction unit (153) refers to the attribute information table stored in the storage unit (14), identifies the installation (20) that satisfies the attribute information filter condition acquired in (S100), and then extracts the operating state history of the specified installation (20) from the operating state history table. (S102)

[0045] Next, the second acquisition unit (152b) of the server (10) receives the designation of the installation (20) as the prediction target device in response to the operation of the operation unit (12) by the user. Specifically, the second acquisition unit (152b) receives information input to specify the installation (20) specified by the user as the prediction target device (e.g., installation name (20), identification information and the like). Petition 870250063502, dated 07 / 23 / 2025, page 27 / 44 15 / 19 (S103)

[0046] Next, the second acquisition unit (152b) of the server (10) acquires the operating state filter condition by generating the operating state filter condition based on the operating state history of the specified facility (20) with reference to the operating state history table stored in the storage unit (14). For example, the second acquisition unit (152b) can select at least one operating state included in the operating state history of the facility (20) as the prediction target device and use the selected operating state as the operating state filter condition. In particular, the second acquisition unit (152b) can use all operating states included in the operating state history of the facility (20) as the prediction target device as the operating state filter condition.

[0047] As illustrated in Figure 5, the display unit (502) of screen (500) displays the contents of the operating state filter condition generated by the second acquisition unit (152b). The display unit (502) displays the contents of the operating state filter condition acquired by the second acquisition unit (152b). In the example illustrated in Figure 5, “operating state Φ”, “operating state Χ”, and “operating state Ψ” are displayed on the display unit (502) as operating state filter conditions. This is because the operating state history of the installation (X) includes the history of “operating state Φ”, “operating state Χ”, and “operating state Ψ”, respectively. (S104)

[0048] Next, the extraction unit (153) extracts the operating state history that satisfies the operating state filter condition generated in (S103) from the operating state history extracted in (S101). Petition 870250063502, dated 07 / 23 / 2025, page 28 / 44 16 / 19

[0049] As illustrated in Figure 5, the display unit (503) of screen (500) displays the operating state history of installation (20) extracted as an installation that satisfies the attribute information filter condition and the operating state filter condition (specifically, the operating state history of installation A, installation C, installation E and installation F). (S105)

[0050] Next, the estimation unit (154) predicts the operating state of the prediction target device based on the operating state history of the facility (20) extracted in (S101). Specifically, for example, the estimation unit (154) can calculate the probability of occurrence of the operating state for each hour by statistically analyzing the extracted operating state history. Alternatively, for example, the estimation unit (154) can perform machine learning using the operating state history extracted by the extraction unit (153) as learning data to generate a learning model and insert the operating state history of the prediction target device (facility) into the learning model to generate an output indicating the future operating state of the prediction target device (facility). (S106)

[0051] Next, the display processing unit (155) causes the display unit (13) to display the prediction result by the estimation unit (154) and the operation processing of the prediction system (1) is terminated.

[0052] Figure 6A is an example of a screen (600) illustrating a prediction result displayed on the display unit (13) by the display processing unit (155) when the estimation unit (154) calculates the probability of occurrence of an operating state. As illustrated in Figure 6A, the screen (600) includes a display unit (601) for the Petition 870250063502, dated 07 / 23 / 2025, page 29 / 44 17 / 19 probability of occurrence of the operating state calculated by the estimation unit (154) and a display unit (602) for the history of the operating state of the target prediction device. The display unit (601) displays the time series change of the probability of occurrence of each operating state calculated by the estimation unit (154). In the example illustrated in Figure 6A, the probability of occurrence Pφ(t) of operating state φ, the probability of occurrence Px(t) of operating state Χ, the probability of occurrence Pψ(t) of operating state ψ and the probability of occurrence PΩ(t) of operating state Ω are illustrated.

[0053] The display unit (602) displays the operating state history of the installation (X), which is a target device for operating state prediction. Specifically, the display unit (602) displays the operating state history of the installation (X) from the start of operation to time lapse (T1). Here, after time (T1), it is possible to predict the specific operating state of the installation (X) with the probability of occurrence based on the probability of occurrence displayed in the display unit (601). In the example illustrated in Figure 6A, in the installation (X) at future time T2 (> T1), the probability of becoming operating state Ω is Ρω (T2), and the probability of becoming operating state Ψ is Ρψ (T2).

[0054] Figure 6B is an example of a screen (700) illustrating a prediction result displayed on the display unit (13) by the display processing unit (155) when the estimation unit (154) makes a prediction using a machine learning model. As illustrated in Figure 6B, the screen (700) includes a display unit (701) for time series change of the operating state of the facility (X), which is a prediction target device. The display unit (701) displays the history of the operating state of the facility (X) up to the current time (T1). The history of the operating state of the facility (X) up to the current time (T1) are Petition 870250063502, dated 07 / 23 / 2025, pages 30 / 44 18 / 19 the learning data in the machine learning performed by the estimation unit (154). In addition, the display unit (701) displays the future operating state as an output obtained by introducing the operating state history of the facility (X) into the learning model generated by the estimation unit (154) using the learning data.

[0055] In the embodiment described above, the second acquisition unit (152b) receives the designation of the facility (20) as the prediction target device (S102) and then generates the operating state filter condition based on the operating state history of the specified facility (20) (S103) to acquire the operating state filter condition. However, the second acquisition unit (152b) can acquire the operating state filter condition input from the user, for example, by operating the operating unit (12).

[0056] The embodiments described above are for the purpose of facilitating the understanding of the embodiments of the invention and are not intended to limit the interpretation of the embodiments of the invention. Each element included in the embodiment and the arrangement, material, condition, shape, size and the like are not limited to those exemplified and may be altered as appropriate. Furthermore, it is possible to partially substitute or combine the configurations illustrated in different embodiments. List of Reference Signals: prediction system server, server communication unit, operating unit, display unit, storage unit, processing unit. Petition 870250063502, dated 07 / 23 / 2025, page 31 / 44 19 / 19 151 collection portion 152a first acquisition unit 152b second acquisition unit 153 extraction unit 154 estimation unit 155 Display processing unit, 20A, 20B, 20C Installation operating unit sensor measurement control system Installation communication unit Petition 870250063502, dated 07 / 23 / 2025, pages 32 / 44

Claims

1 / 5 Claims 1. PREDICTION SYSTEM (1) comprising: a storage unit (14) that stores a history of an operating state of each of a plurality of facilities and attribute information indicating an attribute of each of the plurality of facilities (20); a first acquisition unit (152a) that acquires an attribute information filter condition in which at least one attribute information included in the attribute information of a prediction target facility is specified; a second acquisition unit (152b) that acquires an operating state filter condition in which at least one operating state included in a history of an operating state of the prediction target facility is specified;the prediction system (1) characterized by further comprising: an extraction unit (153) that extracts a history of an operating state of a facility satisfying the attribute information filter condition and the operating state filter condition of the operating state history of the plurality of facilities (20), with reference to the storage unit (14); and an estimation unit (154) that statistically analyzes the extracted operating state history and calculates a time series change of a probability of occurrence of the operating state of the target installation for prediction.

2. PREDICTION SYSTEM (1), according to claim 1, characterized by: the first acquisition unit (152a) acquiring the attribute information filter condition upon receiving an input of the attribute information filter condition.

3. PREDICTION SYSTEM (1), according to any one of claims 1 to 2, characterized in that: the second acquisition unit (152b) receives a designation of the target installation for prediction and generates the operating state filter condition based on the operating state history of the target installation for prediction stored in the storage unit (14).

4. PREDICTION SYSTEM (1), according to any one of claims 1 to 2, characterized in that: the second acquisition unit (152b) acquires the attribute information filter condition by receiving an input from the operating state filter condition.

5. PREDICTION SYSTEM (1), according to claim 1, further characterized by comprising: a display unit (13) that displays the time series change of the probability of occurrence calculated by the estimation unit (154).

6. PREDICTION SYSTEM (1), according to any one of claims 1 to 5, characterized in that: a plurality of operating states are specified in the operating state filter condition, and the operating state filter condition includes an order of occurrence of the plurality of operating states.

7. PREDICTION SYSTEM (1), according to claim 1, characterized in that: each of the plurality of installations and the installation targeted for prediction being a boiler.

8. DISPLAY DEVICE FOR IDENTIFYING A Petition 870250063502, dated 23 / 07 / 2025, page 34 / 44 3 / 5 OPERATING STATE OF A FACILITY, characterized in that: the display device displays a time series change in the probability of occurrence of an operating state of a target installation for prediction that is calculated by statistical analysis of a history of the operating state of the target installation extracted from a history of the operating state of the plurality of installations (20) as satisfying an attribute information filter condition in which at least one attribute information included in the attribute information of the target installation for prediction is specified and an operating state filter condition in which at least one operating state included in a history of the operating state of the target installation for prediction is specified from the history of the operating state and attribute information of each of a plurality of installations (20).

9. METHOD OF EXECUTING AN INFORMATION PROCESSING DEVICE, characterized in that the device includes a storage unit (14) that stores a history of an operating state of each of a plurality of target facilities and attribute information indicating an attribute of each of the plurality of target facilities, the method comprising executing: a step of acquiring an attribute information filter condition in which at least one attribute information included in the attribute information of a prediction target facility is specified; a step of acquiring an operating state filter condition in which at least one operating state included in a history of an operating state of the prediction target facility is specified;a step of extracting a history of an operating state of a target facility satisfying the attribute information filter condition and the operating state filter condition of the history of the operation of the plurality of target facilities, with reference to the storage unit; and a step of statistically analyzing the extracted operating state history and calculating a time series change of a probability of occurrence of the operating state of the predicting target facility.

10. NON-TRANSIENT, TANGIBLE COMPUTER PROGRAM PRODUCT, characterized in that it is for making an information processing device including a storage unit (14) that stores a history of an operating state of each of a plurality of target facilities and attribute information indicating an attribute of each of the plurality of target facilities function as: a first acquisition unit (152a) that acquires an attribute information filter condition in which at least one attribute information included in the attribute information of a prediction target facility is specified; a second acquisition unit (152b) that acquires an operating state filter condition in which at least one operating state included in a history of an operating state of the prediction target facility is specified;an extraction unit (153) that extracts a history of an operating state of a target facility satisfying the attribute information filter condition and the operating state filter condition of the operating state history of the plurality of target facilities, with reference to the storage unit (14); and an estimation unit (154) that statistically analyzes the extracted operating state history and calculates a temporal series change of a probability of occurrence of the target facility's operating state for prediction. Petition 870250063502, dated 23 / 07 / 2025, page 36 / 44 5 / 5

Images