Information processing device, information processing method, and program

Abstract

To provide an information processing device that can estimate the factors behind a phenomenon based on events described in text. [Solution] This information processing device comprises a question input unit into which questions inquiring about the factors of a phenomenon are input, an artificial intelligence interface unit that inputs a set of sentences representing the causal relationships of events and the questions input into the question input unit into a large-scale language model and obtains answers to the questions from the large-scale language model, and an output unit that outputs the answers obtained by the artificial intelligence interface unit.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Techniques for estimating the causes of occurring phenomena are known. In Patent Document 1, regarding the causal relationship of phenomena in a process, using a knowledge model expressed in a network format connecting nodes with events occurring in the process and data collected from the process, a technique for estimating the cause of a phenomenon is disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technique of Patent Document 1, there is a problem that if an event is not set as a node, the cause of the phenomenon may not be estimated.

[0005] The present disclosure has been made in view of such circumstances, and provides an information processing apparatus, an information processing method, and a program capable of estimating the cause of a phenomenon based on an event described in a sentence.

Means for Solving the Problems

[0006] This disclosure is made to solve the problems described above, and one aspect of this disclosure provides an information processing device comprising: a question input unit into which a question inquiring about the factors of a phenomenon is input; an artificial intelligence interface unit that inputs a set of sentences representing the causal relationships of events and the question input into the question input unit into a large-scale language model and obtains an answer to the question from the large-scale language model; and an output unit that outputs the answer obtained by the artificial intelligence interface unit.

[0007] One aspect of this disclosure provides an information processing method comprising: a first step in which a question inquiring about the factors of a phenomenon is input; a second step in which a set of sentences representing the causal relationships of events and the question input in the first step are input into a large-scale language model and answers to the questions are obtained from the large-scale language model; and a third step in which answers obtained in the second step are output.

[0008] One aspect of this disclosure provides a program that causes a computer to function as a question input unit into which questions inquiring about the factors of a phenomenon are input, an artificial intelligence interface unit that inputs a set of sentences representing the causal relationships of events and the questions input to the question input unit into a large-scale language model and obtains answers to the questions from the large-scale language model, and an output unit that outputs the answers obtained by the artificial intelligence interface unit. [Effects of the Invention]

[0009] According to this disclosure, information processing devices, information processing methods, and programs can estimate the factors of a phenomenon based on events described in text. [Brief explanation of the drawing]

[0010] [Figure 1] This is a schematic block diagram showing the configuration of the factor response system 100 according to the first embodiment of this disclosure. [Figure 2] This table shows an example of the contents stored in the causal relationship storage unit 12 in the same embodiment (Part 1). [Figure 3] This table shows an example of the contents stored in the causal relationship storage unit 12 in the same embodiment (part 2). [Figure 4]This is a flowchart illustrating an example of the operation of the information processing device 10 in the same embodiment (part 1). [Figure 5] This is a flowchart illustrating an example of the operation of the information processing device 10 in the same embodiment (part 2). [Figure 6] This is a schematic block diagram showing the configuration of the factor response system 100 in a second embodiment of this disclosure. [Figure 7] This is a tree diagram showing an example of data representing the causal relationships of events in the same embodiment. [Figure 8] This is a schematic block diagram showing the configuration of the factor response system 100 in a third embodiment of this disclosure. [Figure 9] This table shows an example of the contents stored in the causal relationship storage unit 12 in the same embodiment. [Figure 10] This is an example of an image (part 1) displayed by the output unit 14 in the same embodiment. [Figure 11] This is an example of an image (part 2) displayed by the output unit 14 in the same embodiment. [Figure 12] This is an example of an image (part 3) displayed by the output unit 14 in the same embodiment. [Figure 13] This is an explanatory diagram illustrating the hardware configuration of each device according to each embodiment. [Modes for carrying out the invention]

[0011] <First Embodiment> Embodiments of this disclosure will be described below with reference to the drawings. Figure 1 is a schematic block diagram showing the configuration of a factor answering system 100 according to a first embodiment of this disclosure. When a question inquiring about the factors of a phenomenon is input to the factor answering system 100, it uses an artificial intelligence unit 30 having artificial intelligence (AI) functionality to output the answer. In this embodiment, the factor answering system 100 will be described using the example of a question inquiring about the factors of a phenomenon in a coal-fired power plant, but the question may also be a question inquiring about the factors of a phenomenon in other things such as factories, information processing systems and other equipment, industrial products, living organisms, etc.

[0012] The factor answering system 100 comprises an information processing device 10 and an artificial intelligence unit 30. When a question inquiring about the cause of a phenomenon is input to the information processing device 10, it inputs the question along with a set of sentences representing the causal relationship of the events to the artificial intelligence unit 30. The information processing device 10 obtains the answer to the question from the artificial intelligence unit 30 and outputs the answer. For example, the question might be, "What is the reason why the mill differential pressure is rising even though the air damper is open?" and the answer to the question might be, "The following causes can be assumed for the mill differential pressure rising even though the air damper is open: 1. Increase in mill differential pressure due to coal accumulation inside: This may be due to wear of the grinding section, increased coal moisture content, or a decrease in pressurized oil pressure, which reduces the grinding capacity of the mill. 2. Decrease in primary air flow rate due to coal accumulation inside: The accumulation of coal obstructs the flow of primary air, causing a decrease in the primary air flow rate. ...Other phenomena such as XX can also be observed." Furthermore, the information processing device 10 may generate questions to inquire about the causes of the phenomenon based on data acquired from the plant equipment 20. The information processing device 10 may be implemented by one or more computers reading and executing a program.

[0013] The information processing device 10 includes a question input unit 11, a causal relationship memory unit 12, an artificial intelligence I / F (Interface) unit 13, an output unit 14, and a question generation unit 15. The question input unit 11 receives an input of a question that inquires about the cause of a phenomenon. For the input of this question, an input device such as a keyboard, a mouse, or a touch panel may be used, or it may be input by receiving from another device. The phenomenon in the question is a phenomenon detected by monitoring equipment (equipment of a coal-fired power plant).

[0014] The causal relationship memory unit 12 stores a group of sentences representing the causal relationship of events. Further, the causal relationship memory unit 12 may store a sentence representing the type of an event for the events in the group of sentences representing the causal relationship of events. Note that the events are events related to equipment. The types of events may include causes, internally occurring events, and instrument-detected events. A cause is an event that becomes the cause of a phenomenon. An internally occurring event is an event that occurs in the equipment but is not detected by an instrument. An instrument-detected event is an event detected by an instrument for monitoring the state of the equipment.

[0015] The artificial intelligence I / F unit 13 inputs an input sentence group including at least a group of sentences representing the causal relationship of events and the question input to the question input unit 11 to the artificial intelligence unit 30, and obtains an answer to the question from the artificial intelligence unit 30. This answer is an answer regarding the cause of the phenomenon inquired about in the question. Further, this answer may include an event that can be further confirmed. An event that can be confirmed is an event different from the phenomenon inquiring about the cause in the question, and the type is an instrument-detected event. Further, the artificial intelligence I / F unit 13 may input a sentence inquiring about an event that can be confirmed other than the phenomenon inquired about in the question to the artificial intelligence unit 30 in addition to the above-mentioned group of sentences and the question. An event that can be confirmed is an instrument-detected event, and a sentence representing the type of the event stored in the causal relationship memory unit 12 may be input to the artificial intelligence unit 30 in addition to the sentence inquiring about the event that can be confirmed, the above-mentioned group of sentences, and the above-mentioned question.

[0016] The output unit 14 outputs the response acquired by the artificial intelligence interface unit 13. This response may be displayed on a screen or transmitted to another device. The question generation unit 15 generates questions to be input to the question input unit 11 based on the detection results of instruments installed in the plant equipment 20. For example, the question generation unit 15 may store questions corresponding to each of several conditions and select a question from among the stored questions that corresponds to the condition satisfied by the detection results of the instruments installed in the plant equipment 20.

[0017] The plant equipment 20 is equipment for a coal-fired power plant and includes instruments for monitoring the status of the equipment. The plant equipment 20 provides the detection results of the instruments, such as the measured values ​​of the instruments, to the information processing device 10 via a communication network or the like.

[0018] The artificial intelligence unit 30 (large-scale language model) refers to artificial intelligence equipped with intelligent functions such as reasoning and judgment, and its operating environment. The artificial intelligence unit 30 comprises a model control unit 31 and a trained model storage unit 32. The artificial intelligence unit 30 is a model and its operating environment configured to output an answer corresponding to a question when a group of sentences representing the causal relationships of events and a question entered into the question input unit 11 are input. When the artificial intelligence unit 30 receives a group of sentences representing the causal relationships of events and a question entered into the question input unit 11 from the artificial intelligence interface unit 13, it outputs an answer based on the group of sentences, the question, and the trained model described later.

[0019] The trained model storage unit 32 stores the trained model. The trained model includes model information, which will be described later. The trained model may also include model parameters, which are information that defines the behavior of the model, such as constraints, weighting variables, and evaluation functions.

[0020] The models may include, for example, NN (Neural Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), VAE (Variational Autoencoder), GAN (Generative Adversarial Networks), Diffusion models, Transformers, LLM (Large Language Model), VLM (Visual Language Model), BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-trained Transformer), and CLIP (Contrastive Language Image Pre-training). Note that the above models are not mutually exclusive; for example, LLM, VLM, BERT, and GPT are included in Transformers. Also, for example, Transformers are included in NNs. Furthermore, the learning algorithm and model may be a combination of multiple types. Models also include what are called multimodal models, which are trained by combining multiple different types of data.

[0021] The model control unit 31, upon acquiring a set of sentences representing the causal relationships of events and a question entered into the question input unit 11, outputs an answer corresponding to the question based on the set of sentences, the question, and the trained model. In other words, the model control unit 31, upon acquiring a set of sentences representing the causal relationships of events and a question entered into the question input unit 11, generates and outputs an answer corresponding to the question using the model shown by the trained model.

[0022] The trained model and other information used by the artificial intelligence unit 30 may be prepared in advance, or they may be acquired via the network as needed.

[0023] Figure 1 shows the case where the artificial intelligence unit 30 is located outside the information processing device 10. However, the system is not limited to this configuration, and part or all of the artificial intelligence unit 30 may be located inside the information processing device 10. In the case where part or all of the artificial intelligence unit 30 is located inside the information processing device 10, the information processing device 10 may have an artificial intelligence interface unit 13 that also functions as a model control unit 31.

[0024] Furthermore, the trained model storage unit 32 may consist of multiple databases connected via a network.

[0025] Figure 2 is a table showing an example of the contents stored in the causal relationship memory unit 12 in this embodiment (Part 1). The example in Figure 2 is a group of sentences that represent the causal relationships of events stored in the causal relationship memory unit 12. The sentences that represent the causal relationships of the events shown in the figure are: "A leak in the water injection valve seat causes an increase in the moisture content of the coal.", "Rainfall on the coal storage area causes an increase in the moisture content of the coal.", "A leak in the pressurized oil valve seat causes a decrease in pressurized oil pressure.", "An increase in the moisture content of the coal causes a decrease in crushing capacity.", etc.

[0026] Figure 3 is a table showing an example of the contents stored in the causal relationship memory unit 12 in this embodiment (part 2). The example in Figure 3 is a group of sentences that represent the types of events stored in the causal relationship memory unit 12. The sentences that represent the types of events shown in Figure 3 are: "Wear of the grinding unit is a cause.", "Water injection valve seat leak is a cause.", "Increased coal moisture content is an internally occurring event.", "Decreased grinding capacity is an internally occurring event.", "Columbarium accumulation inside is an internally occurring event.", and "Increased differential pressure is an instrument-detected event."

[0027] Figure 4 is a flowchart illustrating an example of the operation (part 1) of the information processing device 10 in this embodiment. Figure 4 is a flowchart for the case when a question inquiring about the cause of a phenomenon is input from an external source. First, the question input unit 11 acquires the input question (step Sa1). Next, the artificial intelligence interface unit 13 reads a group of sentences representing the causal relationships of events from the causal relationship memory unit 12 (step Sa2), and inputs the question acquired in step Sa1 and the group of sentences read in step Sa2 to the artificial intelligence unit 30 (step Sa3). Next, the artificial intelligence interface unit 13 acquires the answer to the input in step Sa3 from the artificial intelligence unit 30 (step Sa4). Next, the output unit 14 outputs the answer acquired in step Sa4.

[0028] Figure 5 is a flowchart illustrating an example of the operation of the information processing device 10 in this embodiment (part 2). Steps Sa2 to Sa5 in Figure 5 are the same as steps Sa2 to Sa5 in Figure 4, so their explanation is omitted. First, the question generation unit 15 acquires instrument detection data from the plant equipment 20 (step Sb1). Next, the question generation unit 15 determines whether the set conditions satisfy the detection data acquired in step Sb1 (step Sb2).

[0029] If it is determined in step Sb2 that the condition is not met (step Sb2-No), the process returns to step Sb1. If it is determined in step Sb2 that the condition is met (step Sb2-Yes), the question generation unit 15 generates a question inquiring about the cause of the phenomenon and inputs it to the question input unit 11 (step Sb3). The question generated in step Sb3 may be a question corresponding to the condition met in step Sb2. Next, the question input unit 11 retrieves the question input in step Sb3 (step Sb4). Steps Sa2 to Sa5 thereafter are the same as in Figure 4.

[0030] <Second Embodiment> Figure 6 is a schematic block diagram showing the configuration of the factor response system 100 in the second embodiment of this disclosure. The factor response system 100 in this embodiment is substantially the same as the factor response system 100 in the first embodiment, but differs in that it includes a document generation unit 16 and does not include a question generation unit 15.

[0031] The information processing device 10 includes a question input unit 11, a causal relationship storage unit 12, an artificial intelligence interface unit 13, an output unit 14, and a document generation unit 16. The question input unit 11, the causal relationship storage unit 12, the artificial intelligence interface unit 13, and the output unit 14 are the same as in the first embodiment, so their description is omitted. The document generation unit 16 acquires data representing the causal relationships of events and generates a group of sentences representing the causal relationships of events based on this data. The document generation unit 16 stores the generated group of sentences in the causal relationship storage unit 12. The group of sentences generated by the document generation unit 16 may include sentences representing the causal relationship between a factor and an internally occurring event, sentences representing the causal relationship between a factor and an instrument-detected event, and sentences representing the causal relationship between an internally occurring event and an instrument-detected event. The document generation unit 16 may also generate a group of sentences representing the type of event based on the data representing the causal relationships of events and store them in the causal relationship storage unit 12. Furthermore, the document generation unit 16 may generate these sets of documents for each piece of equipment or trouble event.

[0032] Figure 7 is a tree diagram showing an example of data representing the causal relationships between events in this embodiment. In Figure 7, rectangles F1 to F6 are events of type cause, rectangles IN1 to IN6 are events of type internal occurrence, and rectangles M1 to M9 are events of type instrument detection. The arrows connecting the rectangles indicate the causal relationships between the events corresponding to each rectangle. For example, the arrow from rectangle F1 to rectangle IN2 indicates that the event "grinding part wear" corresponding to rectangle F1 causes the event "reduction in grinding capacity" corresponding to rectangle IN2. Such a tree diagram may be represented by data showing the event corresponding to each rectangle and data showing which rectangle the arrow from that rectangle connects to, or by data showing the event corresponding to the rectangle and data showing which rectangle the arrow to that rectangle connects to.

[0033] The document generation unit 16 has the function of editing and creating a tree diagram as shown in Figure 7. By editing and creating the tree diagram, it may obtain data representing the causal relationships of events and, based on this data, generate a set of sentences representing the causal relationships of events and a set of sentences representing the types of events. Thus, the information processing device 10 in this embodiment includes a document generation unit 16 that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of events based on that data. This allows the user to easily generate a set of sentences representing the causal relationships of events.

[0034] <Third Embodiment> Figure 8 is a schematic block diagram showing the configuration of the factor response system 100 in the third embodiment of this disclosure. The factor response system 100 in this embodiment is substantially the same as the factor response system 100 in the second embodiment, except that the output unit 14 outputs the portion representing the events included in the response in a way that allows for the identification of the type of event, and the causal relationship storage unit 12 stores information indicating the type of each event. The output unit 14 uses the information stored in the causal relationship storage unit 12 in order to output the type of event in a way that allows for the identification.

[0035] The information processing device 10 includes a question input unit 11, a causal relationship storage unit 12, an artificial intelligence interface unit 13, an output unit 14, and a document generation unit 16. The question input unit 11, the causal relationship storage unit 12, the artificial intelligence interface unit 13, and the document generation unit 16 are the same as in the second embodiment, so their description is omitted. The output unit 14 outputs the portion representing the events included in the answer acquired by the artificial intelligence interface unit 13, in a manner that allows for the identification of the type of event. In order to output the type of event in a manner that allows for the identification of the type of event, the output unit 14 may use information indicating the type of each event stored in the causal relationship storage unit 12.

[0036] If the answer is "The following causes can be assumed for the mill differential pressure rising despite the air damper being open: 1. Increase in mill differential pressure due to coal accumulation inside: This may be due to wear of the grinding section, increased coal moisture content, or a decrease in pressurized oil pressure, which reduces the grinding capacity of the mill. 2. Decrease in primary air flow rate due to coal accumulation inside: The accumulation of coal obstructs the flow of primary air, resulting in a decrease in primary air flow rate. ...Other phenomena such as XX may also be observed," then when displaying the answer, the output unit 14 may display the answer in a way that allows identification of the type by changing the color of the text or the background color of the text according to the type: "wear of the grinding section" which is a cause, "increased coal moisture content", "decreased grinding capacity", "coal accumulation inside" which are internal events, and "decrease in pressurized oil pressure", "decrease in primary air flow rate", "decrease in primary air flow rate" which are instrument-detected events. This allows the user to easily understand the type of phenomenon included in the answer.

[0037] Furthermore, the output unit 14 may display the equipment components corresponding to the events included in the answer in an image representing the equipment configuration in an identifiable manner. When the output unit 14 displays the equipment components corresponding to the events included in the answer in an identifiable manner, it may also display the type of the event in an identifiable manner. In order to display the type of event in an identifiable manner, the output unit 14 may use information indicating the type of each event stored in the causal relationship storage unit 12. Furthermore, the causal relationship storage unit 12 stores information indicating the correspondence between events and equipment components, and the output unit 14 may use this information. In addition, the output unit 14 may display the events included in the answer in an identifiable manner in an image representing the causal relationship of events.

[0038] The causal relationship storage unit 12 stores information indicating the type of each event included in the set of sentences representing the causal relationships of events. The event types include at least factors, internally occurring events, and instrument-detected events. This information indicating the type may be generated by the document generation unit 16 based on data representing the causal relationships of events.

[0039] Figure 9 is a table showing examples of the contents stored in the causal relationship memory unit 12 in this embodiment. The examples shown in Figure 9 are examples of information indicating the type of each event stored in the causal relationship memory unit 12. The causal relationship memory unit 12 stores the event "wear of the grinding part" in association with the type "factor". The causal relationship memory unit 12 stores the event "water injection valve seat leak" in association with the type "factor". The causal relationship memory unit 12 stores the event "increase in coal moisture content" in association with the type "internal occurrence event". The causal relationship memory unit 12 stores the event "decrease in grinding capacity" in association with the type "internal occurrence event". The causal relationship memory unit 12 stores the event "coal accumulation inside" in association with the type "internal occurrence event". The causal relationship memory unit 12 stores the event "increase in differential pressure" in association with the type "instrument detection event".

[0040] Figure 10 shows an example image (part 1) displayed by the output unit 14 in this embodiment. Image G1 in Figure 10 is a diagram of the equipment configuration displayed by the output unit 14, and the equipment components include "coal storage," "crusher," "boiler," "turbine," "generator," "denitrification equipment," "dust collector," and "desulfurization equipment." In image G1, only the "crusher," which is a component corresponding to the event of the factor included in the answer, is displayed in a different color from the other components. Note that this color may correspond to the accuracy of the answer's inference. In that case, the question inquiring about the cause of the phenomenon may include wording inquiring about the accuracy of the answer's inference. Components corresponding to internally occurring events and components corresponding to instrument-detected events included in the answer may also be displayed in colors according to their type or according to the accuracy of the answer's inference. In this way, by displaying an equipment configuration diagram like image G1, the output unit 14 allows the user to easily understand the components corresponding to the events included in the answer.

[0041] Figure 11 shows an example image (part 2) displayed by the output unit 14 in this embodiment. Image G2 in Figure 11 is a diagram showing the causal relationships of the events displayed by the output unit 14. In image G2, the events included in the answer, "wear of the grinding unit," "increase in coal moisture content," "decrease in pressurized oil pressure," "decrease in grinding capacity," "accumulation of coal inside," "increase in differential pressure," and "decrease in primary air flow rate," are displayed in a different color from the other events. Note that this color may correspond to the inference accuracy of the answer. In that case, the question asking about the cause of the phenomenon may include wording asking about the inference accuracy of the answer. In this way, by having the output unit 14 display a diagram showing the causal relationships of events like image G2, the user can easily grasp the events included in the answer and their causal relationships.

[0042] Figure 12 is an example (third) of an image displayed by the output unit 14 in this embodiment. The example in Figure 12 is a list of multiple phenomena that occurred in the equipment (alarm list) displayed by the output unit 14. In this list, the time of occurrence of the phenomenon in the equipment (date and time in Figure 12), the phenomenon (occurring event in Figure 12), and the events included in the answer to the question inquiring about the cause of the phenomenon (estimated cause in Figure 12) are all included in the same row. The color of the estimated cause column may be a color corresponding to the inference accuracy of the answer. In that case, the question inquiring about the cause of the phenomenon may include wording inquiring about the inference accuracy of the answer. In this way, the output unit 14 may display multiple phenomena that occurred in the equipment and the events included in the answer corresponding to each of the multiple phenomena.

[0043] Furthermore, the information processing devices 10 in the first to third embodiments may be combined. For example, the information processing devices 10 in the second and third embodiments may also include a question generation unit 15, and the information processing devices 10 in the first and second embodiments may also include a causal relationship storage unit 12 and an output unit 14 in the third embodiment.

[0044] Figure 13 is an explanatory diagram illustrating the hardware configuration of each device according to each embodiment. Each device is an information processing device 10 and an artificial intelligence unit 30 in each of the first to third embodiments. Each device comprises an input / output module I, a memory module M, and a control module P. The input / output module I is implemented by including some or all of a communication module H11, a connection module H12, a pointing device H21, a keyboard H22, a display H23, buttons H3, a microphone H41, a speaker H42, a camera H51, or a sensor H52. The memory module M is implemented by including a drive H7. The memory module M may further comprise some or all of a memory H8. The control module P is implemented by including a memory H8 and a processor H9. These hardware components are connected to each other via a bus so as to be able to communicate with each other, and are powered by a power supply H6.

[0045] The connection module H12 is a digital input / output port such as USB (Universal Serial Bus). The pointing device H21, keyboard H22, and display H23 may be touch panels. The sensor H52 is an accelerometer, gyroscope, GPS receiver module, proximity sensor, etc. The power supply H6 is a power supply unit that supplies the electricity necessary to operate each device. The power supply H6 may be a battery. The drive H7 is an auxiliary storage medium such as a hard disk drive or solid state drive. The drive H7 may be a non-volatile memory such as EEPROM or flash memory, or a magneto-optical disk drive or flexible disk drive. Furthermore, the drive H7 is not limited to one built into each device, for example, but may also be an external storage device connected to the connector of the connection module H12. The memory H8 is a main memory medium such as random access memory. Note that the memory H8 may be cache memory. The memory H8 stores instructions when they are executed by one or more processors H9. The processor H9 is the CPU (Central Processing Unit). The processor H9 may be an MPU (microprocessing unit) or a GPU (graphics processing unit). The processor H9 reads programs and various data from drive H7 via memory H8 and performs calculations to execute instructions stored in one or more memory H8s.

[0046] Input / output module I is used in the information processing device 10, artificial intelligence unit 30, etc. Control module P is used for the implementation of each part of the information processing device 10 and artificial intelligence unit 30. In this specification, the descriptions of the information processing device 10 and artificial intelligence unit 30 may be replaced with the description of control module P.

[0047] This disclosure may also be in the following embodiments. (1) One embodiment of the present disclosure is an information processing device comprising: a question input unit into which a question inquiring about the factors of a phenomenon is input; an artificial intelligence interface unit that inputs a group of sentences representing the causal relationship of events and the question input to the question input unit into a large-scale language model and obtains an answer to the question from the large-scale language model; and an output unit that outputs the answer obtained by the artificial intelligence interface unit.

[0048] (2) Another embodiment of the present disclosure is the information processing apparatus described in (1), wherein the types of events include factors, internally occurring events, and instrument-detected events, and the response is a response relating to the factors.

[0049] (3) Another embodiment of the present disclosure is the information processing device described in (2), wherein the response further includes verifiable events.

[0050] (4) Another embodiment of the present disclosure is the information processing device described in (3), wherein the verifiable event is a different event from the phenomenon for which the cause is inquired in the question, and is of the type of instrument detection event.

[0051] (5) Another embodiment of the present disclosure is an information processing device according to any one of (1) to (4), wherein the phenomenon is a phenomenon detected by monitoring of equipment, and the event is an event relating to the equipment.

[0052] (6) Another embodiment of the present disclosure is an information processing device as described in (5), comprising a question generation unit that generates the question based on the detection results of an instrument installed in the equipment, and a question input unit that receives the question generated by the question generation unit.

[0053] (7) Another embodiment of the present disclosure is an information processing device comprising: a document generation unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of events based on the data; and an artificial intelligence interface unit that inputs an input sentence set including at least the set of sentences generated by the document generation unit into a large-scale language model and obtains a response to the input sentence set from the large-scale language model.

[0054] (8) Another embodiment of the present disclosure is the information processing apparatus described in (7), wherein the types of events include factors, internally occurring events, and instrument-detected events, and the group of documents generated by the document generation unit includes documents representing the causal relationship between the factors and the internally occurring events, documents representing the causal relationship between the requirements and the instrument-detected events, and documents representing the causal relationship between the internally occurring events and the instrument-detected events.

[0055] (9) Another embodiment of the present disclosure is an information processing device as described in (7) or (8), wherein the document generation unit generates the document set for each piece of equipment or trouble event.

[0056] (10) Another embodiment of the present disclosure is an information processing device comprising an artificial intelligence interface unit that inputs a question inquiring about the cause of a phenomenon to a large-scale language model and obtains an answer to the question from the large-scale language model, and an output unit that outputs the answer obtained by the artificial intelligence interface unit, wherein the output unit outputs a portion representing an event included in the answer in a manner that identifies the type of the event.

[0057] (11) Another embodiment of the present disclosure is the information processing apparatus described in (10), wherein the question is a question inquiring about the cause of a phenomenon relating to equipment, and the output unit displays in an image representing the configuration of the equipment the components corresponding to the events included in the answer are identifiable.

[0058] (12) Another embodiment of the present disclosure is an information processing device as described in (10) or (11), wherein the question is a question inquiring about the cause of a phenomenon occurring in the equipment, and the output unit displays a plurality of phenomena occurring in the equipment and events included in the answer corresponding to each of the plurality of phenomena.

[0059] (13) Another embodiment of the present disclosure is an information processing device according to any one of (10) to (12), comprising a question input unit into which the question is input, wherein the artificial intelligence I / F unit inputs a set of sentences representing the causal relationship of events and the question input into the question input unit to the large-scale language model, and obtains an answer to the question from the large-scale language model.

[0060] (14) Another embodiment of the present disclosure is an information processing device as described in (13), comprising a document generation unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of the events based on the data.

[0061] (15) Another embodiment of the present disclosure is an information processing device according to any one of (10) to (14), wherein the output unit displays the events included in the answer in an image representing the causal relationship of events in an identifiable manner.

[0062] (16) Another embodiment of the present disclosure is an information processing device according to any one of (10) to (15), wherein the types of events include at least factors, internally occurring events, and instrument-detected events.

[0063] (17) Another embodiment of the present disclosure is an information processing method comprising: a first step of inputting a question inquiring about the factors of a phenomenon; a second step of inputting a set of sentences representing the causal relationship of events and the question input in the first step into a large-scale language model and obtaining an answer to the question from the large-scale language model; and a third step of outputting the answer obtained in the second step.

[0064] (18) Another embodiment of the present disclosure is an information processing method comprising: a first step of acquiring data representing the causal relationships of events and generating a set of sentences representing the causal relationships of the events based on the data; and a second step of inputting an input sentence set, which includes at least the set of sentences generated in the first step, into a large-scale language model and obtaining a response to the input sentence set from the large-scale language model.

[0065] (19) Another embodiment of the present disclosure is an information processing method comprising: a first step of inputting a question inquiring about the factors of a phenomenon into a large language model and obtaining an answer to the question from the large language model; and a second step of outputting the answer obtained in the first step, wherein in the second step, the portion representing the event included in the answer is output in a manner that identifies the type of the event.

[0066] (20) Another embodiment of the present disclosure is a program that causes a computer to function as a question input unit into which questions inquiring about the factors of a phenomenon are input, an artificial intelligence interface unit that inputs a set of sentences representing the causal relationships of events and the questions input to the question input unit into a large-scale language model and obtains answers to the questions from the large-scale language model, and an output unit that outputs the answers obtained by the artificial intelligence interface unit.

[0067] (21) Another embodiment of the present disclosure is a program that causes a computer to function as an artificial intelligence interface (I / F) unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of events based on the data, inputs an input sentence set including at least the set of sentences generated by the document generation unit into a large-scale language model, and obtains a response to the input sentence set from the large-scale language model.

[0068] (22) Another embodiment of the present disclosure is a program that causes a computer to function as an artificial intelligence interface unit that inputs a question inquiring about the factors of a phenomenon into a large language model and obtains an answer to the question from the large language model, and an output unit that outputs the answer obtained by the artificial intelligence interface unit, wherein the output unit outputs a portion of the answer that represents an event, such that the type of the event can be identified.

[0069] Alternatively, the information processing device 10 may be realized by recording a program for realizing the functions of the information processing device 10 shown in Figures 1, 6, and 8 onto a computer-readable recording medium, and then loading and executing the program recorded on this recording medium into a computer system. Here, "computer system" includes hardware such as the operating system and peripheral devices.

[0070] Furthermore, "computer system" shall also include the homepage provisioning environment (or display environment) if a WWW system is being used. Furthermore, "computer-readable recording media" refers to portable media such as flexible disks, magneto-optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computer systems. Moreover, "computer-readable recording media" also includes those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs over networks such as the Internet or communication lines such as telephone lines, and those that hold programs for a certain period of time, such as volatile memory inside computer systems that act as servers or clients in such cases. In addition, the above-mentioned programs may be for the purpose of realizing some of the functions described above, and may also be able to realize the above-mentioned functions in combination with programs already recorded in the computer system.

[0071] While embodiments of this disclosure have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and may include design changes and the like that do not depart from the gist of this disclosure. [Explanation of Symbols]

[0072] 10 Information Processing Devices 11 Question Input Section 12. Causal Relationship Memory Unit 13 Artificial Intelligence I / F Department 14 Output section 15 Question generation part 16 Document Generation Unit 20 Plant Equipment 30. Artificial Intelligence Department 31 Model Control Unit 32. Pre-trained model memory unit

Claims

1. A question input section where questions inquiring about the causes of the phenomenon are entered, An artificial intelligence interface unit inputs a set of sentences representing the causal relationships of events and the question entered into the question input unit into a large-scale language model, and obtains answers to the question from the large-scale language model. The output unit outputs the response acquired by the artificial intelligence interface unit. An information processing device equipped with the following features.

2. The types of events include factors, internally occurring events, and instrument-detected events. The above response is a response regarding the above factors. The information processing apparatus according to claim 1.

3. The above response includes further verifiable events, The information processing apparatus according to claim 2.

4. The aforementioned verifiable event is a different event from the phenomenon whose cause is being inquired about in the aforementioned question, and its type is the instrument detection event. The information processing apparatus according to claim 3.

5. The aforementioned phenomenon was detected through monitoring of the equipment. The aforementioned event is an event relating to the aforementioned equipment. The information processing apparatus according to claim 1.

6. The equipment includes a question generation unit that generates the question based on the detection results of an instrument installed in the equipment, The question input unit receives the question generated by the question generation unit. The information processing apparatus according to claim 5.

7. A document generation unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of the events based on said data, An artificial intelligence interface unit inputs an input document set, which includes at least the document set generated by the document generation unit, into a large-scale language model, and obtains a response to the input document set from the large-scale language model. An information processing device equipped with the following features.

8. The types of events include factors, internally occurring events, and instrument-detected events. The group of documents generated by the document generation unit includes documents that express the causal relationship between the factor and the internally occurring event, documents that express the causal relationship between the factor and the instrument-detected event, and documents that express the causal relationship between the internally occurring event and the instrument-detected event. The information processing apparatus according to claim 7.

9. The document generation unit generates the set of documents for each piece of equipment or trouble event. The information processing apparatus according to claim 7.

10. An artificial intelligence interface unit inputs a question inquiring about the factors of a phenomenon into a large-scale language model and obtains an answer to the question from the large-scale language model. The output unit outputs the response acquired by the artificial intelligence interface unit. Equipped with, The output unit outputs the portion representing the events included in the response in a manner that allows for the identification of the type of event. Information processing device.

11. The aforementioned question is a question inquiring about the factors causing the phenomenon related to the equipment. The output unit displays, in an image representing the configuration of the equipment, the components corresponding to the events included in the answer in an identifiable manner. The information processing apparatus according to claim 10.

12. The aforementioned question is a question inquiring about the cause of the phenomenon that occurred in the equipment. The output unit displays a plurality of phenomena that occurred in the equipment and the events included in the response corresponding to each of the plurality of phenomena. The information processing apparatus according to claim 10.

13. The system includes a question input unit into which the aforementioned question is entered, The artificial intelligence interface unit inputs a set of sentences representing the causal relationships of events and the question entered into the question input unit into the large-scale language model, and obtains answers to the questions from the large-scale language model. The information processing apparatus according to claim 10.

14. The system includes a document generation unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of the events based on the data. The information processing apparatus according to claim 13.

15. The output unit displays the events included in the answer in an image representing the causal relationship of the events in an identifiable manner. The information processing apparatus according to claim 10.

16. The types of the aforementioned events include at least factors, internally occurring events, and instrument-detected events. The information processing apparatus according to claim 10.

17. The first step involves inputting a question inquiring about the cause of the phenomenon, A second step involves inputting a set of sentences representing the causal relationships of events and the question entered in the first step into a large-scale language model, and obtaining answers to the question from the large-scale language model. A third step of outputting the answer obtained in the second step above, An information processing method having

18. A first step involves obtaining data representing the causal relationship of events and generating a set of sentences representing the causal relationship of the events based on said data, The second step involves inputting an input sentence set, which includes at least the sentence set generated in the first step, into a large-scale language model, and obtaining a response to the input sentence set from the large-scale language model. An information processing method having

19. The first step involves inputting a question inquiring about the factors of a phenomenon into a large-scale language model, and obtaining an answer to the said question from the large-scale language model. A second step of outputting the answer obtained in the first step, Equipped with, In the second step described above, the portion representing the events included in the answer is output in a way that allows the type of the event to be identified. Information processing methods.

20. Computers, A question input section where questions inquiring about the causes of the phenomenon are entered. An artificial intelligence interface unit inputs a set of sentences representing the causal relationships of events and the questions entered into the question input unit into a large-scale language model, and obtains answers to the questions from the large-scale language model. Output unit that outputs the response acquired by the artificial intelligence interface unit. A program designed to function as such.

21. Computers, A document generation unit that acquires data representing the causal relationships of events and generates a set of sentences representing the causal relationships of the events based on said data. An artificial intelligence interface unit inputs an input document set, which includes at least the document set generated by the document generation unit, into a large-scale language model, and obtains a response to the input document set from the large-scale language model. A program designed to function as such.

22. Computers, An artificial intelligence interface unit inputs a question inquiring about the factors of a phenomenon into a large-scale language model and obtains an answer to the said question from the large-scale language model. Output unit that outputs the response acquired by the artificial intelligence interface unit. It is a program designed to function as such. The output unit outputs the portion representing the events included in the response in a manner that allows for the identification of the type of event. program.

Images