Information processing device, information processing method, and program

Abstract

To provide an information processing apparatus that efficiently acquires an operation rule for controlling an operation of a plant.SOLUTION: An information processing apparatus 100 comprises: an information search unit 105 that searches one or more operation rules of one or more second plant (water purification plant Pn) associated with a status detected for a first plant (water purification plant PA); an extraction unit 103 that extracts one or more second properties being different from first properties being one or more properties of one or more factors affecting an operation of a first plant, of second properties being one or more properties of one or more factors affecting operation of a second plant, in which an operation rule is searched, for each of one or more operation rules; a determination unit 106 that determines whether or not the second property occurs for each of the extracted one or more second properties; and a rule search unit 102 that searches one or more operation rules in which a second property determined to occur is extracted.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] Embodiments of the present invention relate to an information processing apparatus, an information processing method, and a program. [Background Art]

[0002] For example, in plants such as waterworks plants (water purification plants, sewage treatment plants, etc.), techniques have been proposed for controlling operations corresponding to detected states of each monitoring and control target using operation rules. The operation rules are, for example, rules described in advance in a knowledge graph format having a description pattern of IF-THEN rules.

[0003] In waterworks plants, for example, due to the influence of global warming, a phenomenon in which raw water changes in quality may occur. For example, due to changes in the migratory routes of migratory birds, some waterworks plants may experience raw water quality alteration in which organic components derived from feces and urine, which did not exist previously, become mixed into the raw water. As a result, predetermined operation rules cannot be applied, which can lead to situations where the plant cannot be appropriately controlled. [Prior Art Documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent No. 7002978 [Patent Document 2] Japanese Unexamined Patent Application Publication No. 2023-139389 [Summary of the Invention] [Problem to be Solved by the Invention]

[0005] As a countermeasure for cases where predetermined operation rules cannot be applied, for example, it is conceivable to acquire an operation rule applicable to a newly occurring situation from another plant and divert the same.

[0006] The present invention aims to provide an information processing device, an information processing method, and a program that can efficiently acquire operating rules for controlling the operation of a plant. [Means for solving the problem]

[0007] The information processing device of the embodiment includes a processing unit. The processing unit searches for one or more operation rules of one or more second plants related to the situation detected for the first plant. For each of the one or more operation rules, the processing unit extracts one or more second properties, which are properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, that are different from the first properties, which are properties of one or more factors that affect the operation of the first plant. For each of the one or more extracted second properties, the processing unit determines whether or not the second property occurred. The processing unit selects one or more operation rules from which the second property that was determined to have occurred was extracted. [Brief explanation of the drawing]

[0008] [Figure 1] Block diagram of an information processing device. [Figure 2] A diagram showing an example of a data structure for property data. [Figure 3] Flowchart of information processing. [Figure 4] A diagram illustrating a concrete example of information processing. [Figure 5] A diagram illustrating an example of searching for an action rule. [Figure 6] A diagram showing an example of the display screen. [Figure 7] A diagram showing an example of a diagrammatic display screen. [Figure 8] A diagram illustrating examples of basic knowledge about water supply and water source-related knowledge. [Figure 9] A diagram illustrating an example of the process for extracting candidate new properties. [Figure 10] A diagram illustrating the details of the process for searching for status information. [Figure 11] A diagram illustrating examples of water treatment plant attributes. [Figure 12] A diagram for explaining details of processing for determining whether diversion is possible. [Figure 13] A diagram for explaining a specific example of processing for determining whether diversion is possible. [Figure 14] A diagram for explaining a specific example of processing for determining whether diversion is possible. [Figure 15] A hardware configuration diagram of an information processing apparatus. Mode for Carrying Out the Invention

[0009] Preferred embodiments of an information processing apparatus according to the present invention will be explained in detail below with reference to the accompanying drawings.

[0010] As a method for identifying the cause why an used operation rule cannot be applied, the following method is generally known. - A method of attempting to detect unprecedented trends by analyzing plant monitoring control logs - A method of collecting related information describing inapplicable situations

[0011] Note that the operation rules include, for example, operation rules and operation know-how. The operation rules are, for example, rules incorporated in automatic control of a plant, and rules that serve as a basis for operator's judgment. The operation know-how is, for example, rules that serve as options for an operator's judgment.

[0012] With the above-described methods, elements that are not focused on (elements that are not monitored because they are not of interest, and are not recorded in monitoring control logs) are unlikely to be targeted for analysis and information collection, and there are cases where such elements are not identified as candidate causes, and it may take a long time to identify the cause. In addition, if the conditions for information collection are not properly described, unfocused elements may not become targets for information collection.

[0013] Hereinafter, an example in which the plant to be monitored and controlled is a water purification plant will be mainly described. A water purification plant is an example of a plant in which inputs for operation control change due to environmental degradation and the like. Applicable plants are not limited to waterworks plants such as water purification plants, and may be any other plants.

[0014] Hereinafter, a water purification plant (first plant) that is an object of operation (operation, monitoring) is referred to as a water purification plant PA, and one or more other water purification plants (second plants) different from the water purification plant PA are referred to as a water purification plant Pn (n is an integer of 1 or more).

[0015] The information processing apparatus according to the embodiment includes, for example, the following functions (F1) to (F3). (F1) Information on the properties of factors that can affect a situation to be investigated (situation to be investigated) that has occurred in the water purification plant PA is acquired from knowledge data such as operation rules of other water purification plants Pn (candidates for search are obtained). (F2) Information on new properties of factors that can affect the operation of the water purification plant PA is extracted by collating the acquired property information with information indicating the occurrence status of the properties of factors that can affect the operation of the water purification plant PA (search candidates are narrowed down). (F4) An operation rule applicable to the situation to be investigated is acquired (searched) from the operation rules of other water purification plants Pn including rules related to the extracted new properties.

[0016] The situation to be investigated corresponds to an unforeseen situation (defect situation) that has occurred in the water purification plant PA. Factors that can affect the operation of the water purification plant PA include, for example, the geology, ecosystem, and climate of the water source (input source) of the water purification plant PA. The information on the properties of factors is, for example, information indicating the amount of components to be removed in water treatment, the presence or absence of events related to the generation or increase / decrease of components, and the properties of events. The information indicating the occurrence status of the properties of factors is, for example, information indicating the occurrence status of events related to the generation or increase / decrease of components.

[0017] The above functions make it possible to search for and acquire operation rules applicable to environmental degradation that has not been experienced and was not a subject of interest.

[0018] The operation rules are represented, for example, in the form of a knowledge graph with a description pattern of IF-THEN rules. (F1) and (F3) can be implemented by scanning the knowledge graph using the description pattern, and by similarity determination of the structure and meaning of the subgraphs to be compared. The structure and meaning of a subgraph refers, for example, to the meaning of the nodes in the subgraph, and the direction in which they are connected by meaningful links.

[0019] (F2) can be implemented, for example, by generating fill-in-the-blank query sentences (prompts) from a knowledge graph to instruct a Large Language Model (LLM), and then extracting information from the LLM using the generated query sentences. This function utilizes the property that knowledge graphs can be converted to and from natural language texts.

[0020] Figure 1 is a block diagram showing an example of the configuration of an information processing device 100 according to an embodiment. As shown in Figure 1, the information processing device 100 is connected to the data to be searched 200 via a network 300. The information processing device 100 includes an acquisition unit 101, a rule search unit 102, an extraction unit 103, a generation unit 104, an information retrieval unit 105, a determination unit 106, a selection unit 107, an output control unit 108, and a storage unit 120.

[0021] The search target data 200 corresponds to the data that the information retrieval unit 105 searches. The search target data 200 is public data, such as news articles. The search target data 200 may include data indicating whether or not a factor that could affect the operation of a water treatment plant has occurred, and the date and time of its occurrence. For this reason, the search target data 200 can be used as the search target for information to determine whether or not a certain characteristic has occurred.

[0022] Network 300 can be any type of network, such as the Internet. Network 300 can be a wired network, a wireless network, or a network that combines both wired and wireless elements.

[0023] The memory unit 120 stores various types of information used in the information processing device. For example, the memory unit 120 stores the following information for each water treatment plant. • Driving pattern data • Equipment configuration data • Property data • Rule data • Business record data

[0024] Operation pattern data is data that indicates the pattern of one or more operations (operations) at a water treatment plant. For example, operation pattern data indicates the equipment and location where operations such as chlorine injection are performed. The substance injected is not limited to chlorine; it may be any other substance. Furthermore, the operation is not limited to the injection of a substance. For example, operations such as the injection of activated carbon, the injection of coagulants, the injection of neutralizing agents, and the agitation of water may be performed at a water treatment plant.

[0025] Equipment configuration data refers to data indicating one or more pieces of equipment that make up a water treatment plant. Examples of such equipment include water intake channels, intake wells, activated carbon contact tanks, mixing tanks, coagulation tanks, sedimentation tanks, sludge tanks, water supply channels, filtration tanks, backwash tanks, chemical mixing tanks, treated water reservoirs, and distribution reservoirs. The equipment configuration data may also refer to data indicating equipment present in the relevant water treatment plant from among these equipment configurations (standard equipment configurations).

[0026] Property data is data that shows the properties of factors that may affect the operation of a water treatment plant. Figure 2 shows an example of the data structure of property data 121. As shown in Figure 2, property data 121 includes the factor and the properties of that factor at each water treatment plant. Note that in Figure 2, property data for multiple water treatment plants is displayed together, but the property data may be stored separately for each water treatment plant.

[0027] Rule data is data that shows the operating rules established for each water treatment plant. As mentioned above, rule data may be represented in knowledge graph format. Examples of rule data (operating rules) represented in knowledge graph format will be discussed later.

[0028] Operational record data is data that records the past operations of each water treatment plant. Operational record data can be in any format, but for example, it could be electronic data representing a daily work log. Operational record data may record whether or not factors that could affect the operation of the water treatment plant occurred, as well as the date and time of such occurrence. Therefore, operational record data can be used as a search target for information to determine whether or not a certain characteristic occurred.

[0029] The storage unit 120 can be composed of any commonly used storage medium, such as flash memory, memory card, RAM (Random Access Memory), HDD (Hard Disk Drive), and optical disc. Some or all of the data stored in the storage unit 120 may be stored in physically different storage media, or in different storage areas of the same physically storage medium.

[0030] Furthermore, some or all of the data in the storage unit 120 may not be stored in the information processing device 100, but may be configured to be acquired, for example, from a storage unit in the control system that controls each water treatment plant.

[0031] Returning to the explanation of Figure 1, the acquisition unit 101 acquires various types of information used by the information processing device 100. For example, the acquisition unit 101 acquires information indicating the detected survey target status for the water treatment plant PA. The method by which the acquisition unit 101 acquires information can be any method, but for example, a method of receiving information from the control systems of each water treatment plant connected via the network 300 can be applied.

[0032] The rule search unit 102 searches for one or more operating rules of other water treatment plants Pn that are related to the acquired survey target status. The method for searching for operating rules related to the survey target status may be any method. If the operating rules are represented in knowledge graph format as described above, the rule search unit 102 searches for operating rules related to the survey target status by comparing the survey target status converted to knowledge graph format with the operating rules represented in knowledge graph format.

[0033] For example, the rule search unit 102 generates a knowledge graph representing the situation under investigation from the situation under investigation. The rule search unit 102 searches the rule data stored in the storage unit 120 for operation rules that include knowledge graphs (subgraphs) similar to the generated knowledge graph.

[0034] The extraction unit 103 uses the retrieved operation rules to extract one or more properties that are different from one or more properties C1 (first properties) of one or more factors that affect the operation of the water treatment plant PA. For example, for each of the one or more operation rules, the extraction unit 103 extracts one or more properties C2 that are different from property C1 from one or more properties C2 of one or more factors that affect the operation of the water treatment plant Pn for which the operation rule was retrieved.

[0035] The generation unit 104 generates a query statement (search statement, search query) for searching for information about the extracted property C2. The method for generating the query statement can be any method, but for example, the following method can be applied. • A method for generating prompts to query other systems that perform searches. These other systems could be, for example, systems utilizing artificial intelligence (AI). • A method for generating inquiry statements using a fill-in-the-blank template.

[0036] The information retrieval unit 105 performs a search for information using the generated query. For example, the information retrieval unit 105 searches for status information indicating the occurrence of property C2, using at least one of the search target data 200 and the business record data of each water treatment plant as search targets.

[0037] The determination unit 106 determines whether or not property C2 has occurred for each of the one or more properties C2 extracted by the extraction unit 103. For example, the determination unit 106 determines that property C2 has occurred if the information retrieval unit 105 retrieves situational information indicating that property C2 has occurred.

[0038] The determination unit 106 may determine whether property C2 occurred at a location identified based on the location (address) where the water treatment plant PA is located. The location identified based on the address is, for example, the address itself or a location within a certain range including the address. The determination unit 106 may also identify a period during which the occurrence of property C2 affects the operation of the water treatment plant PA and determine whether property C1 occurred during the identified period. In this case, the information retrieval unit 105 may generate a query statement that further includes conditions regarding the location and period. If the determination unit 106 retrieves situational information indicating that property C2 occurred at the location and period specified as conditions based on such a query statement, it determines that property C2 occurred at that location and period.

[0039] The selection unit 107 selects one or more operation rules from which the property C2 determined to have occurred by the determination unit 106 has been extracted.

[0040] The operating rules selected in this manner may be repurposed as operating rules applicable to newly arising situations. The selection unit 107 may further select more appropriate operating rules from the selected operating rules for use in water treatment plant PAs. In this case, the determination unit 106 and the selection unit 107 may further include the following functions.

[0041] For example, the determination unit 106 determines whether the attributes of water treatment plant PA are similar to the attributes of water treatment plant Pn, where the selected operating rules are defined. The attributes include one or more pieces of equipment included in the water treatment plant, the operating sequence of multiple pieces of equipment included in the water treatment plant, and some or all of the operating patterns of the water treatment plant.

[0042] The determination unit 106 may determine similarity by prioritizing attributes with higher priority than other attributes according to the priority of each attribute. For example, the following order of priority may be set: (1) One or more facilities included in the water treatment plant (2) The sequence of operations of multiple pieces of equipment included in the water treatment plant (3) Driving patterns

[0043] The determination unit 106 may calculate a similarity score that represents the degree of similarity between the attributes of water treatment plant PA and the attributes of water treatment plant Pn for which the selected operating rules are defined, and use the similarity score to determine whether or not they are similar. The similarity score is calculated, for example, by the number of matching elements among the multiple elements included in the attribute. For example, if the attribute is one or more pieces of equipment, the similarity score may be calculated based on the number of matching pieces of equipment. The determination unit 106 may determine that the attributes of water treatment plant PA and the attributes of water treatment plant Pn for which the selected operating rules are defined are similar if the similarity score is equal to or greater than a predetermined threshold.

[0044] The selection unit 107 selects the operation rules that are determined to be similar. The selection unit 107 may further select (extract) the parts of the selected operation rules that can be repurposed for the operation of the water treatment plant PA, and output the operation rules of the selected parts.

[0045] The output control unit 108 controls the output of various types of information used by the information processing device 100. For example, the output control unit 108 outputs (displays) a display screen for presenting the selected operation rule to a display device such as a display. The method of information output by the output control unit 108 is not limited to this, and any other method may be used. For example, a method of transmitting information to an external device connected via the network 300 may be used.

[0046] At least a portion of each of the above parts (acquisition unit 101, rule search unit 102, extraction unit 103, generation unit 104, information retrieval unit 105, determination unit 106, selection unit 107, and output control unit 108) may be implemented by one or more processing units. Each of the above parts may be implemented by, for example, one or more processors. For example, each of the above parts may be implemented by having a processor such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit) execute a program, i.e., by software. Each of the above parts may be implemented by a processor such as a dedicated IC (Integrated Circuit), i.e., by hardware. Each of the above parts may be implemented by using both software and hardware. When multiple processors are used, each processor may implement one of the above parts, or two or more of the above parts.

[0047] The information processing device 100 may be composed of one physical device or multiple physical devices. For example, the information processing device 100 may be built on a cloud environment. Furthermore, each part of the information processing device 100 may be distributed and provided on multiple devices.

[0048] Next, we will describe the information processing performed by the information processing device 100 of this embodiment. Figure 3 is a flowchart showing an example of information processing in this embodiment.

[0049] The acquisition unit 101 acquires information on the detected survey target status for the water treatment plant PA (step S101). The rule search unit 102 generates a knowledge graph representing the survey target status (step S102). The rule search unit 102 searches for operation rules for other water treatment plants Pn that are similar to the knowledge graph (step S103).

[0050] The extraction unit 103 obtains the properties C2 of the factors related to the searched operating rule (step S104). The extraction unit 103 extracts the properties C2 from the obtained properties C2 that are not present in the properties C1 of the water treatment plant PA under investigation (step S105).

[0051] The generation unit 104 generates a query statement to search for the occurrence status of the extracted property C2 (step S106). The information retrieval unit 105 searches for status information indicating the occurrence status of the extracted property C2 using the generated query statement (step S107).

[0052] The determination unit 106 determines that property C2 has occurred if it finds situational information indicating that property C2 has occurred. In this case, the following processes are executed. Although not shown in Figure 3, if no situational information indicating that property C2 has occurred is found, the following processes are not executed, and the information processing ends.

[0053] The selection unit 107 selects an operation rule that matches the searched situation (step S108). For example, the selection unit 107 selects one or more operation rules from which the property C2 determined to have occurred has been extracted. The selection unit 107 further selects (extracts) operation rules from the selected operation rules that can be repurposed for operation at the water treatment plant PA (step S109).

[0054] The output control unit 108 outputs the selected operation rule (step S110) and terminates the information processing.

[0055] Next, a specific example of information processing according to this embodiment will be further described. Figure 4 is a diagram illustrating a specific example of information processing according to the embodiment.

[0056] As described above, the rule search unit 102 searches for operating rules of other water treatment plants Pn related to the investigated situation (malfunction situation) that occurred at the water treatment plant PA, which is the plant under investigation (step S201). In the following, other water treatment plants Pn whose operating rules were found may be referred to as potential source plants. Also, the found operating rules may be referred to as potential reuse rules.

[0057] The repurposing candidate rule 122 in Figure 4 shows an example of a retrieved operation rule. The repurposing candidate rule 122 is stored, for example, in the storage unit 120. The repurposing candidate rule includes a rule number, a source candidate for repurposing, and a repurposing candidate. The rule number is identification information that identifies the operation rule. The source candidate for repurposing is identification information that identifies the water treatment plant from which the operation rule was retrieved. The repurposing candidate is information indicating whether or not to adopt the operation rule for repurposing. For example, a value (e.g., "x") is set for the repurposing candidate if it is adopted, and no value is set if it is not adopted.

[0058] Figure 4 shows an example where two operational rules identified by rule numbers "#1-1" and "#1-5" were retrieved from water treatment plant P1, and one operational rule identified by rule number "#3-4" was retrieved from water treatment plant P3.

[0059] The extraction unit 103 extracts the difference (new property candidate) between the property C2 of the source candidate that has a conversion candidate rule and the property C1 of the water treatment plant PA (step S202). For example, suppose that property data as shown in Figure 2 has been obtained for each water treatment plant. In this case, the property C2 of the source candidate water treatment plant P1 is "high in manganese" and "migratory summer birds," and the property C2 of the source candidate water treatment plant P3 is "high in manganese." Combining the two, the property C2 of the source candidate becomes "high in manganese" and "migratory summer birds." These properties C2 are not included in the property C1 of the water treatment plant PA, which is "high in iron" and "winter snowfall." Therefore, the extraction unit 103 extracts "high in manganese" and "migratory summer birds" as the difference (new property candidate).

[0060] Figure 4 shows an example of a new property candidate 123, which is property C2 extracted as a difference. The new property candidate 123 is stored, for example, in the memory unit 120. The occurrence status indicates whether or not each property that is a new property candidate has occurred. The occurrence status is then set depending on whether or not situation information has been retrieved. For example, the occurrence status is set to a value (e.g., "x") if situation information indicating that a property of the new property candidate has occurred is retrieved, and no value is set if it is not retrieved.

[0061] The information retrieval unit 105 searches for status information (new biomass occurrence information) regarding the occurrence of new property candidates at the water source of the water treatment plant PA (step S203). Suppose that status information for "summer bird migration" among the new property candidates is retrieved. In this case, for example, the information retrieval unit 105 sets a value for the presence or absence of occurrence corresponding to "summer bird migration". New property candidate 123b in Figure 4 shows the state in which a value has been set for the presence or absence of occurrence.

[0062] The selection unit 107 selects a conversion candidate rule for a source candidate that includes the newly confirmed candidate property as a property (step S204). In the example in Figure 4, the conversion candidate rule for water treatment plant P1, a source candidate that includes the newly confirmed candidate property "migratory birds," as a property is selected.

[0063] Specifically, two operation rules identified by the rule numbers "#1-1" and "#1-5" are selected. For example, the selection unit 107 sets a value for the repurposing candidate corresponding to the selected operation rule. Figure 4 shows the repurposing candidate rule 122b in the state where a value has been set for the repurposing candidate.

[0064] In some cases, it is possible to determine whether or not a rule relating to the generated properties is included for each operation rule. In such cases, the selection unit 107 may exclude operation rules that do not include a rule relating to the generated properties from the selection and select operation rules that do include a rule relating to the generated properties. For example, suppose that only the operation rule identified by the rule number "#1-1" includes a rule relating to the generated properties. In this case, the selection unit 107 selects the operation rule identified by the rule number "#1-1" and sets a value for the repurposing candidate corresponding to the selected operation rule. The repurposing candidate rule 122c in Figure 4 shows the state in which a value has been set for the repurposing candidate in this way.

[0065] Let's explain using the following example of a malfunction. Despite controlling the operation of the water treatment plant PA as before, "the residual chlorine concentration in the treated water at the sedimentation tank outlet has decreased and the management standards are not being met."

[0066] In such cases, an IF-THEN type operating rule, such as "increase the amount of chlorine injected, and the residual chlorine concentration of the treated water at the sedimentation tank outlet will rise to meet the management standard," is searched from the operating rules of other water treatment plants Pn. This allows the manager of the water treatment plant PA to know where (at which facility) in the water treatment plant the amount of chlorine injected should be increased and by how much.

[0067] Figure 5 shows an example of searching for operation rules. First, the rule search unit 102 converts data indicating the situation under investigation (e.g., text data) into a knowledge graph. Graph 511 in Figure 5 shows an example of a knowledge graph representing the situation under investigation.

[0068] Any method can be used to convert data showing the status of the surveyed subjects into a knowledge graph, but for example, the following method can be applied. This method uses a Large-Scale Language Model (LLM) for generative AI and separation prompts. This makes it possible to eliminate inconsistencies in notation. Separation prompts are, for example, prompts for separating an IF-THEN format knowledge graph into data representing the IF situation and data representing the THEN situation. Alternatively, separation prompts may be prompts for separating the data of the IF situation into data representing the object of the situation, data representing the state of the object, and data representing the location of the object. The unit of separation may be, for example, a node in the knowledge graph or a set of nodes. The result of the separation is, for example, data represented by triples in the knowledge graph. A method for converting text data into a knowledge graph according to a grammar and schema that defines the structure of the knowledge graph. A method for generating a knowledge graph using input methods such as an editor that creates data for the knowledge graph. A method for converting entered survey data into a knowledge graph using input means, including syntax forms that can be converted into knowledge graphs.

[0069] Graph 500 in Figure 5 shows an example of a knowledge graph representing a searchable behavior rule. As shown in Figure 5, graph 500 includes node 501, which represents a state corresponding to an IF condition, and two nodes 502 and 503, which represent states corresponding to a THEN condition for node 501. Node 502 corresponds to the case where the IF condition is met (OK). Node 503 corresponds to the case where the IF condition is not met (NG).

[0070] The rule search unit 102 can search for an action rule that fits graph 511 by comparing graph 500 and graph 511, both of which are knowledge graphs that have IF-THEN rule description patterns. In the example in Figure 5, since the part with node 503 as the parent node is the same as graph 511, graph 500 is searched as a graph that fits graph 511.

[0071] The survey subject status may be entered using the input method described above. Figure 6 shows an example of a display screen that can be used for inputting the survey subject status and displaying the processing results based on the survey subject status.

[0072] As shown in Figure 6, the display screen 600 includes, as elements for question input, an input field 601, a content confirmation button 602, a confirmation result field 603, a diagram display button 604, and a search button 605. The display screen 600 also includes, as elements for displaying processing results, an output field 611, a reference display button 612, output fields 621 and 622, a reuse / edit button 623, a reuse feasibility output field 624, and a diagram display button 625.

[0073] Input field 601 is an input field for entering text data indicating the status of the subject of the survey. When the content confirmation button 602 is pressed, the output control unit 108 outputs information (OK or NG) indicating whether the data entered in input field 601 can be converted into a knowledge graph to the confirmation result field 603.

[0074] When the diagram display button 604 is pressed, the output control unit 108 outputs a diagram display screen for displaying a knowledge graph converted from the surveyed situation.

[0075] Figure 7 shows an example of a diagrammatic display screen. The diagrammatic display screen includes the text 701 entered as the subject of the survey and the conversion result 702. The conversion result 702 corresponds to the knowledge graph obtained by converting the text 701.

[0076] The user can verify whether the converted knowledge graph is correct (i.e., usable for searching) through the diagrammatic display screen. The correctness of the knowledge graph can be verified, for example, by including basic nodes that represent the meaning of IF-THEN rules (nodes that represent the target of the rule, the state of the target, the location of the target, etc.) and edges (relationships between nodes) that also represent the meaning of IF-THEN rules.

[0077] A function may be provided to compare the text re-converted from the conversion result 702 with the input text 701. The user can verify the accuracy of the knowledge graph by checking whether the re-converted text and text 701 have the same meaning. The text comparison function may be implemented using a Large-Scale Language Model (LLM) of a generative AI.

[0078] The system may include a function for editing knowledge graphs. In this case, for example, the edited knowledge graph could be used to search for related behavioral rules.

[0079] Returning to the explanation of Figure 6, when the search button 605 is pressed, the rule search unit 102 uses the converted knowledge graph to search for operation rules related to the knowledge graph as candidate rules for reuse. Subsequently, for example, through the processing in steps S202 to S204 of Figure 4, new property candidates and reuse source candidates are obtained. These processing results are displayed on the display screen 600.

[0080] Output field 611 is a field for displaying the searched new property candidates. If the reference display button 612 is pressed, the output control unit 108 may output a screen showing the details of the new property candidates.

[0081] Output fields 621 and 622 are for displaying the name (station name) of the water treatment plant that is a candidate for conversion, and an overview of that water treatment plant.

[0082] If the reuse edit button 623 is pressed, the output control unit 108 may display an editing screen for editing the data of the reuse candidate rule to generate a new operation rule.

[0083] The reusability output field 624 is a field for outputting the result of determining whether the corresponding reusability candidate rule is reusable or not. For example, in step S109 above (details will be described later), the reusability candidate rule of water treatment plant Pn, a source candidate for reusability that has similar attributes to water treatment plant PA, is determined to be a reusable operating rule. Attributes include, for example, the operating pattern and equipment configuration. The "Operation" and "Equipment" fields in the reusability output field 624 indicate that the determination of reusability was made based on the similarity (common points) of the operating pattern and equipment configuration, respectively. For example, if a checkmark is displayed in the reusability output field 624, it indicates that it has been determined to be reusable because the operating rules are similar.

[0084] If the diagram display button 625 is pressed, the output control unit 108 may further display a diagram display screen for showing the result of converting the candidate rules for reuse into a knowledge graph and an interpretation of the knowledge graph.

[0085] If there is no checkmark in the conversion feasibility output field 624, the diagram display screen may show a note indicating how to handle the operation rules due to the fact that the attributes of the water treatment plant PA under investigation and the candidate water treatment plant Pn from which the conversion is being made are not similar, for example, the following: "Since the rules are for a plant that is not highly similar to the plant being investigated, we recommend that if you repurpose them, you should only use the control operation direction (=increase, decrease, stop, etc.) as a reference."

[0086] The displayed annotations may change depending on the checkbox pattern in the reusability output field 624, as shown below. Neither "Operation" nor "Equipment" is checked. • Only "Driving" is checked. • Only "Equipment" is checked.

[0087] In the process of extracting candidate new properties, knowledge data separate from the operating rules may be referenced to extract properties that could be factors in malfunction situations (such as a decrease in residual chlorine). The knowledge data may include, for example, basic knowledge of water supply and knowledge related to water sources. Basic knowledge of water supply represents basic knowledge obtained in the past regarding water supply. Knowledge related to water sources represents knowledge obtained in the past regarding water sources.

[0088] Figure 8 shows examples of basic water supply knowledge and water source-related knowledge. As shown in Figure 8, basic water supply knowledge 125 is information that associates a basic knowledge number with the basic knowledge itself. The basic knowledge number is identification information that identifies the basic knowledge.

[0089] Water source-related knowledge 126 includes the alternative knowledge number, the raw water components under management, the alternative target, the direction of impact, the time of impact onset, and the duration of impact. The alternative knowledge number is identification information that identifies the water source-related knowledge.

[0090] The controlled raw water components represent the components that are subject to management at the water source. The substitute represents a substitute that can replace the properties of factors that may affect the operation of the water treatment plant. The direction of influence represents the direction of the influence of the substitute on the controlled raw water components. The direction of influence can be, for example, an increase in the component or a decrease in the component. The time of influence onset represents the time from when the property corresponding to the substitute occurs until the influence on the controlled raw water components appears. The duration of influence represents the time from when the influence appears until the influence ends.

[0091] Figure 9 shows an example of the process for extracting new property candidates using knowledge data (basic knowledge of water supply, knowledge related to water sources).

[0092] The extraction unit 103 inputs the survey target status acquired by the acquisition unit 101 (step S301). Similarly to the above, an example will be described in which the survey target status indicating "the residual chlorine concentration of the treated water at the sedimentation tank outlet has decreased and the management standards are not met" is input.

[0093] The extraction unit 103 extracts new property candidates from the property data stored in the storage unit 120, which are the difference between the property C2 of the candidate source for conversion and the property C1 of the water treatment plant PA (step S302). This process corresponds to step S202 in Figure 4.

[0094] The extraction unit 103 searches the water supply basic knowledge 125 for information that matches the input survey target situation (step S303). The search can be performed using, for example, the following methods.

[0095] First, the extraction unit 103 converts the basic water supply knowledge into an IF-THEN format knowledge graph and separates the knowledge graph into data representing the IF situation and data representing the THEN situation. This process can be performed using a Large-Scale Language Model (LLM) of the generation AI and a separation prompt. Note that the basic water supply knowledge may be stored in advance, separated into data representing the IF situation and data representing the THEN situation. In the basic water supply knowledge 125 in Figure 8, for example, data 801 corresponds to the data representing the IF situation, and data 802 corresponds to the data representing the THEN situation.

[0096] The extraction unit 103 identifies the water supply basic knowledge that includes the input survey target situation within the data representing the THEN situation among the water supply basic knowledge represented in an IF-THEN format knowledge graph. The extraction unit 103 acquires the data representing the IF situation of the identified water supply basic knowledge.

[0097] The extraction unit 103 searches for water source-related knowledge that has the same situation as the IF situation of the acquired basic water supply knowledge (step S304). For example, the extraction unit 103 acquires water source-related knowledge that includes the IF situation data acquired in step S303. In the water source-related knowledge 126 in Figure 8, for example, data 811 corresponds to water source-related knowledge that includes the IF situation data. The extraction unit 103 may further convert the IF situation data into a knowledge graph including subject, predicate, and object item data through syntactic analysis, etc., and compare it with each element of the water source-related knowledge.

[0098] The extraction unit 103 selects a new property candidate from among the new property candidates extracted in step S302 that is identical to a substitute target included in the acquired water source-related knowledge (step S305).

[0099] The extraction process shown in Figure 9 allows us to extract properties that exist in water treatment plant Pn but not in water treatment plant PA, and that could potentially cause the input malfunction.

[0100] In step S203 of Figure 4, the location and duration of the occurrence of property C2 (candidate new property) may also be used as conditions for searching for situational information. The duration can be identified, for example, by referring to knowledge data (water source-related knowledge).

[0101] Figure 10 is a diagram illustrating the details of the process of searching for status information (step S203).

[0102] The generation unit 104 generates a query statement to check whether or not a new property candidate has been generated (step S401). First, the generation unit 104 prepares the following data. • Location of the water source for the water treatment plant PA • Names of candidate new properties • Confirmation period for the emergence of new candidate properties

[0103] The location of the water source for each water treatment plant can be identified, for example, from information stored for each water treatment plant in the memory unit 120. The location is an example of a place identified based on the location where the water treatment plant exists. The name of the new property candidate can be obtained, for example, by the extraction process shown in Figure 9. The confirmation period for the occurrence of the new property candidate can be determined from the effect onset time and effect duration included in the water source-related knowledge. For example, when confirming from the present, the shortest time in the retrospective period is defined as the effect onset time, the longest time in the retrospective period is defined as the effect onset time + effect duration, and the period between the shortest and longest times is defined as the confirmation period. The confirmation period is an example of a period identified as the period during which the occurrence of the new property candidate (property C2) affects the operation of the water treatment plant.

[0104] The generation unit 104 uses the prepared data to generate a query statement that includes location as a location condition and confirmation period as a period condition. In the case of generating a query prompt for the generation AI as the query statement, for example, the following query statement is generated. Please list the sources from which the following information is found. • Location: Lake Okutama and surrounding areas • Event: Summer birds arrive • Period: May 2023 to November 2023

[0105] The information retrieval unit 105 uses the generated query to search for status information indicating whether or not a new property candidate has occurred (step S402).

[0106] The determination unit 106 uses the search results for situation information to determine whether or not a new property candidate has occurred (step S403). As described above, the determination unit 106 determines that property C2 has occurred, for example, when situation information indicating that a new property candidate (property C2) has occurred is found.

[0107] If inaccurate information may be retrieved, the determination unit 106 may use the confidence level (score) of the retrieved situational information to determine whether or not property C2 has occurred. For example, the determination unit 106 may determine that property C2 has occurred if the number of retrieved situational information items is equal to or greater than a preset threshold.

[0108] Next, we will explain in detail the process (step S109) for extracting operating rules that can be repurposed for the operation of the PA at the water treatment plant. In this process, it is determined whether or not the rules can be repurposed based on whether the equipment included in the water treatment plant, the order of equipment operation, and attributes including the operating pattern are similar.

[0109] Figure 11 is a diagram illustrating an example of water treatment plant attributes. The upper part of Figure 11 shows the attributes of water treatment plant PA. The upper part of Figure 11 also shows the attributes of water treatment plant P1, a candidate for conversion. Data 1101 shows an example of a standard equipment configuration. The standard equipment configuration represents the standard equipment configuration for a water treatment plant. Data 1102 shows an example of an equipment configuration adopted at water treatment plant PA. In this way, each water treatment plant may adopt some of the configurations from the standard equipment configuration. Note that the upper part of Data 1102 represents the configuration, and the lower part represents the operating method of the corresponding configuration (normal, slow, rapid, etc.). Data 1103 shows an example of an operating pattern adopted at water treatment plant PA. Figure 11 shows an example of an operating pattern indicating the equipment (location) where operating operations such as chlorine injection are performed. The attributes (equipment configuration, operating pattern) for water treatment plant P1 are specified in a similar format.

[0110] The determination unit 106 determines whether the operating rules can be repurposed based on whether the equipment configuration and attributes such as the operating pattern are similar to each other. Similarity includes, for example, the following situations: • About the equipment configuration Example 1: The configuration and system of the original water treatment plant Pn and the water treatment plant PA under investigation are identical. Example 2: The configuration of the water treatment plant PA under investigation encompasses the configuration of the water treatment plant Pn from which it was converted. • About the driving pattern Example 1: The operating patterns of the original water treatment plant Pn and the water treatment plant PA under investigation are identical. Example 2: The operating pattern of the water treatment plant PA under investigation encompasses the operating pattern of the original water treatment plant Pn.

[0111] Figure 12 is a diagram illustrating the details of the process for determining whether or not a material can be repurposed.

[0112] The determination unit 106 obtains the equipment configuration and operating pattern for the plant under investigation (water treatment plant PA) and the candidate water treatment plant Pn from which it is to be converted, for example, from the operating pattern data and equipment configuration data stored in the storage unit 120 (step S501).

[0113] The determination unit 106 obtains an action from the candidate repurposing rule (step S502). As shown in Figure 5, the action rule in the knowledge graph includes "Action" as an element. "Action" corresponds to the operation of the water treatment plant. The determination unit 106 obtains the "Action" included in the candidate repurposing rule as an action.

[0114] The selection unit 107 selects a candidate rule for conversion whose acquired operation is included in the operating pattern of the water treatment plant PA (step S503).

[0115] The determination unit 106 determines the commonalities (similarity) in the equipment configuration between the water treatment plant PA and the candidate for conversion (step S504). The determination unit 106 also determines the commonalities in the operating patterns between the water treatment plant PA and the candidate for conversion (step S505). The determination unit 106 may also assign a conversion feasibility flag to set the conversion feasibility output field 624 on the display screen 600 in Figure 6, for example.

[0116] The selection unit 107 selects a candidate repurposing rule that corresponds to the candidate repurposing source determined to be similar (step S506).

[0117] Next, we will explain a specific example of the process for determining whether or not a material can be repurposed. Figures 13 and 14 are diagrams illustrating a specific example of the process for determining whether or not a material can be repurposed.

[0118] Figure 13 shows an example of the following operation rule 1300. Note that arrow 1301 in Figure 13 represents the operation corresponding to A2 Action below. • IF: The raw water taken from the source contains more odor-producing algae with a dominant viable microorganism than normal. Action: Reduce chlorine injection in the intake well (A1) Increase the amount of chlorine injected before the filtration pond (A2) ·THEN: The residual chlorine concentration of the treated water at the sedimentation tank outlet falls below the control standard. The residual chlorine concentration of the treated water in the water reservoir will be within the water quality standards. No musty odor is detected in the purified water from the water treatment reservoir.

[0119] Figure 14 shows an example of the following operation rule 1400. Note that arrow 1401 in Figure 14 represents the operation corresponding to Action A3 below. • IF: The raw water taken from the source contains more odor-producing algae with a dominant viable microorganism than normal. Action: Reduce chlorine injection in the intake well (A1) Increase the amount of chlorine injected into the chemical mixing tank (A3) ·THEN: The residual chlorine concentration of the treated water at the sedimentation tank outlet falls below the control standard. The residual chlorine concentration of the treated water in the water reservoir will be within the water quality standards. No musty odor is detected in the purified water from the water treatment reservoir.

[0120] The Actions A2 and A3 differ between operation rule 1300 and operation rule 1400.

[0121] Assume that operation rule 1300 and operation rule 1400 are found as candidate rules for repurposing. In this case, the determination unit 106 obtains A1 and A2 from operation rule 1300 as Actions, and obtains A1 and A3 from operation rule 1400 as Actions (step S502 in Figure 12).

[0122] As shown in Figure 11, the operating pattern of the water treatment plant PA includes the operation "Chlorine (pre)" corresponding to the injection of chlorine in the intake well (A1), and the operation "Chlorine (post)" corresponding to the injection of chlorine in the chemical mixing tank (A3). On the other hand, the operating pattern of the water treatment plant PA does not include the operation corresponding to the injection of chlorine before the filtration tank (A2).

[0123] Therefore, the selection unit 107 selects operation rule 1400, which includes A1 and A3, as a candidate rule for conversion that includes operations included in the operation pattern of the water treatment plant PA (step S503 in Figure 12).

[0124] In steps S504 and S505 of Figure 12, commonalities in equipment configuration and operating patterns are determined between the water treatment plant PA and the candidate for conversion. In the example of the attributes of the water treatment plant PA and the candidate for conversion (water treatment plant P1) shown in Figure 11, the determination unit 106 determines the commonalities (similarity) between the two, for example, as follows. • About the equipment configuration Example 1: The configuration and method of water treatment plant P1 and the water treatment plant PA under investigation are not identical. Example 2: The configuration of water treatment plant PA under investigation does not include the configuration of water treatment plant P1. • About the driving pattern Example 1: The operating patterns of water treatment plant P1 and the water treatment plant PA under investigation are not identical. Example 2: The operating pattern of the water treatment plant PA under investigation does not include the operating pattern of water treatment plant P1.

[0125] In this example, the determination unit 106 determines that the attributes between the water treatment plant PA and the candidate for conversion (water treatment plant P1) are not similar. In this case, the selection unit 107 does not select a conversion candidate rule corresponding to the candidate for conversion (water treatment plant P1).

[0126] Thus, in this embodiment, even if an event is unprecedented and outside the scope of interest for a particular plant (water treatment plant PA), knowledge (operational rules) acquired from another plant (water treatment plant Pn) that has experienced a similar event can be obtained. The operational rules are acquired based on information related to the factors of the event (situational information regarding water treatment plant PA). Therefore, strategies on how to respond to events that were previously outside the scope of interest can be acquired without relying on individual knowledge, for example. As a result, more appropriate control of water treatment plant PA becomes possible. Furthermore, strategies can be obtained according to the degree of similarity in equipment configuration with the original plant (water treatment plant Pn).

[0127] As described above, according to the embodiment, it is possible to efficiently acquire operating rules for controlling the operation of a plant (such as a water treatment plant).

[0128] Next, the hardware configuration of the information processing device of the embodiment will be described using Figure 15. Figure 15 is an explanatory diagram showing an example of the hardware configuration of the information processing device of the embodiment.

[0129] The information processing device of this embodiment includes a control device such as a CPU (Central Processing Unit) 51, a storage device such as a ROM (Read Only Memory) 52 and a RAM (Random Access Memory) 53, a communication interface 54 that connects to a network for communication, and a bus 61 that connects each part.

[0130] The program to be executed in the information processing device of this embodiment is provided pre-installed in a ROM 52 or the like.

[0131] The program executed by the information processing device of this embodiment may be configured to be provided as a computer program product by recording it in an installable or executable file format onto a computer-readable recording medium such as a CD-ROM (Compact Disk Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk Recordable), or a DVD (Digital Versatile Disk).

[0132] Furthermore, the program executed by the information processing device of the embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading it via the network. Alternatively, the program executed by the information processing device of the embodiment may be provided or distributed via a network such as the Internet.

[0133] The program executed in the information processing device of this embodiment can cause the computer to function as a component of the information processing device described above. This computer can read the program from a computer-readable storage medium onto the main memory and execute it using the CPU 51.

[0134] An example of the configuration of the embodiment is described below. (Configuration Example 1) Search for one or more operating rules of one or more second plants related to the situation detected for the first plant. For each of the one or more operation rules, extract one or more second properties that are properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, which are different from the first properties that are properties of one or more factors that affect the operation of the first plant. For each of the one or more extracted second properties, determine whether or not the second property has occurred. Select one or more of the operation rules from which the second property determined to have occurred has been extracted. Processing section An information processing device equipped with the following features. (Configuration example 2) The aforementioned processing unit, Of the second properties mentioned above, properties that could cause the aforementioned situation are extracted based on knowledge data. For each of the one or more of the aforementioned operating rules, one or more of the aforementioned second properties are extracted from the aforementioned second properties that are different from the aforementioned first property and that can cause the aforementioned situation. The information processing device described in Configuration Example 1. (Configuration Example 3) The aforementioned processing unit, Determine whether the attributes of the first plant and the attributes of the second plant on which the selected operating rules are defined are similar. Select the operation rule that is determined to be similar. An information processing device as described in Configuration Example 1 or 2. (Configuration example 4) The aforementioned attributes include one or more pieces of equipment included in the plant, the sequence of operations of multiple pieces of equipment included in the plant, and some or all of the operating patterns. The information processing device described in Configuration Example 3. (Configuration example 5) The aforementioned attributes include one or more pieces of equipment included in the plant, the sequence of operations of multiple pieces of equipment included in the plant, and the operating pattern. Priority is assigned to one or more pieces of equipment included in the plant, the order of operation of multiple pieces of equipment included in the plant, and the order of operating patterns. The aforementioned processing unit, Prioritizing the attribute with a higher priority than other attributes, it is determined whether the attributes of the first plant and the attributes of the second plant, for which the selected operation rule is defined, are similar. An information processing device as described in Configuration Example 3 or 4. (Configuration example 6) The aforementioned processing unit, Search for situational information that indicates the circumstances under which the second property described above occurs, When the situational information indicating that the second property has occurred is retrieved, it is determined that the second property has occurred. An information processing device as described in any one of Configuration Examples 1 to 5. (Configuration example 7) The aforementioned processing unit, The system retrieves the status information from at least one of the following: record data that records the past operations of multiple plants, including the first plant and the second plant, and public data which is publicly available data including news. The information processing device described in Configuration Example 6. (Configuration example 8) The aforementioned processing unit, For each of the one or more extracted second properties, it is determined whether or not the second property occurred at a location identified based on the location where the first plant is located. An information processing device as described in any one of Configuration Examples 1 to 7. (Configuration example 9) The aforementioned processing unit, Using knowledge data for one or more of the aforementioned factors, for each of the extracted one or more of the aforementioned second properties, the period during which the occurrence of the aforementioned second property affects the operation of the first plant is identified. For each of the one or more extracted second properties, it is determined whether or not the second property occurred during a specified period. An information processing device as described in any one of Configuration Examples 1 to 8. (Configuration example 10) The aforementioned processing unit, By comparing the situation represented in knowledge graph format with the operation rules represented in knowledge graph format, one or more operation rules related to the situation are retrieved. An information processing device as described in any one of Configuration Examples 1 to 9. (Configuration Example 11) An information processing method performed by an information processing device, A step of searching for one or more operating rules of one or more second plants related to the conditions detected for the first plant, For each of the one or more operation rules, the steps include: extracting one or more second properties from among the one or more properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, which are different from the first properties that are one or more properties of one or more factors that affect the operation of the first plant; For each of the one or more extracted second properties, a step of determining whether or not the second property has occurred, The steps include selecting one or more of the operation rules from which the second property determined to have occurred has been extracted, Information processing methods including (Configuration Example 12) On the computer, A step of searching for one or more operating rules of one or more second plants related to the conditions detected for the first plant, For each of the one or more operation rules, the steps include: extracting one or more second properties from among the one or more properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, which are different from the first properties that are one or more properties of one or more factors that affect the operation of the first plant; For each of the one or more extracted second properties, a step of determining whether or not the second property has occurred, The steps include selecting one or more of the operation rules from which the second property determined to have occurred has been extracted, A program to execute.

[0135] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0136] 100 Information Processing Devices 101 Acquisition Department 102 Rule Search Section 103 Extraction part 104 Generation part 105 Information Retrieval Department 106 Judgment section 107 Selection Section 108 Output Control Unit 120 Storage section 200 searchable data 300 Networks

Claims

1. Search for one or more operating rules of one or more second plants related to the conditions detected for the first plant. For each of the one or more aforementioned operation rules, extract one or more second properties that are properties of one or more factors that affect the operation of the second plant for which the operation rule was retrieved, and that are different from the first properties that are properties of one or more factors that affect the operation of the first plant. For each of the one or more extracted second properties, it is determined whether or not the second property has occurred. Select one or more of the operation rules from which the second property determined to have occurred has been extracted. Processing section An information processing device equipped with the following features.

2. The aforementioned processing unit, Of the second properties mentioned above, properties that could be the cause of the situation are extracted based on knowledge data. For each of the one or more of the aforementioned operating rules, one or more of the aforementioned second properties are extracted from the aforementioned second properties that are different from the aforementioned first property and that can cause the aforementioned situation. The information processing apparatus according to claim 1.

3. The aforementioned processing unit, Determine whether the attributes of the first plant and the attributes of the second plant on which the selected operating rules are defined are similar. Select the operation rule that is determined to be similar. The information processing apparatus according to claim 1.

4. The aforementioned attributes include one or more pieces of equipment included in the plant, the sequence of operations of multiple pieces of equipment included in the plant, and some or all of the operating patterns. The information processing apparatus according to claim 3.

5. The aforementioned attributes include one or more pieces of equipment included in the plant, the operating sequence of multiple pieces of equipment included in the plant, and the operating pattern. Priority is assigned to one or more pieces of equipment included in the plant, the order of operation of multiple pieces of equipment included in the plant, and the order of operating patterns. The aforementioned processing unit, Prioritizing the attribute with a higher priority than other attributes, it is determined whether the attributes of the first plant and the attributes of the second plant, for which the selected operation rule is defined, are similar. The information processing apparatus according to claim 3.

6. The aforementioned processing unit, Search for situational information that indicates the circumstances under which the second property described above occurs, When the situational information indicating that the second property has occurred is retrieved, it is determined that the second property has occurred. The information processing apparatus according to claim 1.

7. The aforementioned processing unit, The system retrieves the status information from at least one of the following: record data that records the past operations of multiple plants, including the first plant and the second plant, and public data which is publicly available data including news. The information processing apparatus according to claim 6.

8. The aforementioned processing unit, For each of the one or more extracted second properties, it is determined whether or not the second property occurred at a location identified based on the location where the first plant is located. The information processing apparatus according to claim 1.

9. The aforementioned processing unit, Using knowledge data for one or more of the aforementioned factors, for each of the extracted one or more of the aforementioned second properties, the period during which the occurrence of the aforementioned second property affects the operation of the first plant is identified. For each of the one or more extracted second properties, it is determined whether or not the second property occurred during a specified period. The information processing apparatus according to claim 1.

10. The aforementioned processing unit, By comparing the situation represented in knowledge graph format with the operation rules represented in knowledge graph format, one or more operation rules related to the situation are retrieved. The information processing apparatus according to claim 1.

11. An information processing method performed by an information processing device, A step of searching for one or more operating rules of one or more second plants related to the conditions detected for the first plant, For each of the one or more operation rules, the step of extracting one or more second properties that are properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, and that are different from the first properties that are properties of one or more factors that affect the operation of the first plant; For each of the one or more extracted second properties, a step of determining whether or not the second property has occurred, The steps include selecting one or more of the operation rules from which the second property determined to have occurred has been extracted, Information processing methods including

12. On the computer, A step of searching for one or more operating rules of one or more second plants related to the conditions detected for the first plant, For each of the one or more operation rules, the step of extracting one or more second properties that are properties of one or more factors that affect the operation of the second plant for which the operation rule was searched, and that are different from the first properties that are properties of one or more factors that affect the operation of the first plant; For each of the one or more extracted second properties, a step of determining whether or not the second property has occurred, The steps include selecting one or more of the operation rules from which the second property determined to have occurred has been extracted, A program to execute.

Images