Laser management server and laser management method

Abstract

SOLUTION: A laser management server for a laser device includes: a query input processor for generating a first query item requiring external information and a second query item without requiring external information; an agent action processor for receiving the first query item and generating a first agent response; an equipment agent processor for receiving the second query item from the query input processor, receiving the first agent response from the agent action processor, and generating a query item prompt related to the second query item; and a large language model processor for receiving the query item prompt, and generating a query item response. The equipment agent processor receives the query item response and comprises an equipment control processor for performing transmission to the laser device.EFFECT: According to a laser management system, onward transition of laser performance of a laser device can be predicted by a laser performance prediction model.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a laser management server and a laser management method. [Background technology]

[0002] In recent years, semiconductor exposure devices have been required to improve their resolution in response to the miniaturization and high integration of semiconductor integrated circuits. To this end, the wavelength of light emitted from exposure light sources has been shortened. For example, KrF excimer laser devices that output laser light with a wavelength of approximately 248 nm and ArF excimer laser devices that output laser light with a wavelength of approximately 193 nm are used as gas laser devices for exposure.

[0003] The spectral linewidth of the spontaneously oscillating light from KrF excimer laser devices and ArF excimer laser devices is as wide as 350 to 400 pm. Therefore, if a projection lens is constructed using a material that transmits ultraviolet light, such as KrF and ArF laser light, chromatic aberration may occur. As a result, resolution may decrease. Therefore, it is necessary to narrow the spectral linewidth of the laser light output from the gas laser device to a level where chromatic aberration is negligible. Therefore, a line narrowing module (LNM) containing a line narrowing element (e.g., an etalon or grating) may be installed inside the laser resonator of the gas laser device to narrow the spectral linewidth. Hereinafter, a gas laser device with a narrowed spectral linewidth is referred to as a line narrowing gas laser device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2019 / 240906 [Patent Document 2] Japanese Patent Application Laid-Open No. 2006-24765 [Patent Document 3] Overview of International Publication No. 2020 / 161865

[0005] A laser management server for a laser device according to one aspect of the present disclosure includes a transceiver processor that receives a query from an external device, a query input processor that receives the query from the transceiver processor, breaks down the query, and generates a first query item that requires external information and a second query item that does not require external information, an agent action processor that receives the first query item from the query input processor, acquires necessary information from unstructured data including a manual and a maintenance report for the laser device, and structured data including operation data of the laser device and at least one of a prediction result of the life of consumables of the laser device using a life prediction model and a prediction result of laser performance of the laser device using a laser performance prediction model, and generates a first agent response that is a response to the first query item, and an agent action processor that receives the second query item from the query input processor, acquires necessary information from unstructured data including a manual and a maintenance report for the laser device, and structured data including operation data of the laser device and at least one of a prediction result of the life of consumables of the laser device using a life prediction model and a prediction result of laser performance of the laser device using a laser performance prediction model, and generates a first agent response that is a response to the first query item. a device agent processor that receives a query item from a query input processor and a first agent response from an agent action processor and generates a query item prompt for a second query item; and a large scale language model processor that receives the query item prompt from the device agent processor and generates a query item response that is a response to the query item prompt, wherein the device agent processor receives the query item response from the large scale language model processor and generates a first control signal for controlling a laser device based on the first agent response and the query item response, and further comprises a device control processor that receives the first control signal from the device agent processor and transmits the first control signal to the laser device.

[0006] A laser management method for a laser device according to another aspect of the present disclosure includes a first step in which a transceiver processor receives a query from outside; a second step in which a query input processor breaks down the query and generates a first query item that requires external information and a second query item that does not require external information; a third step in which an agent action processor receives the first query item from the query input processor, acquires necessary information from unstructured data including a manual and a maintenance report of the laser device, and structured data including operation data of the laser device and at least one of a prediction result of a lifespan of consumables of the laser device using a lifespan prediction model and a prediction result of laser performance of the laser device using a laser performance prediction model, and generates a first agent response that is a response to the first query item; and a third step in which the device agent processor executes the second query. a fourth step of receiving a query item from the query input processor and a first agent response from the agent action processor, and generating a query item prompt for the second query item; a fifth step of the large scale language model processor receiving the query item prompt from the device agent processor and generating a query item response that is a response to the query item prompt; a sixth step of the device agent processor receiving the query item response from the large scale language model processor and generating a first control signal for controlling a laser device based on the first agent response and the query item response; and a seventh step of the device control processor receiving the first control signal from the device agent processor and transmitting the first control signal to the laser device. [Brief explanation of the drawings]

[0007] Some embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying drawings, in which: [Figure 1] FIG. 1 is a diagram showing the configuration of an exemplary laser device. [Figure 2] FIG. 2 is a diagram showing the configuration of a laser management system according to a comparative example. [Figure 3]FIG. 3 is a diagram illustrating a laser management system according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an operation flow of the laser management system according to the first embodiment. [Figure 5] FIG. 5 is a diagram showing examples of query items generated from a user's query according to the first embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of control of the laser device by the laser management server according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing the configuration of a laser management system according to a modified example of the first embodiment. [Figure 8] FIG. 8 is a diagram showing an operation flow of a laser management system according to a modified example of the first embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of control of the laser device by the laser management server according to the second embodiment. Embodiment

[0008] -table of contents- 1. Explanation of terms 2. Comparative Example 2.1 Laser device 2.1.1 Configuration 2.1.2 Operation 2.2 Laser Management System 2.2.1 Configuration 2.2.2 Operation 2.2.3 Challenges 3. Embodiment 1 3.1 Configuration 3.2 Operation 3.2.1 Operation flow of the laser management system 3.2.2 Laser device control flow 3.3 Actions and Effects 4. Modification of the First Embodiment 4.1 Configuration 4.2 Operation 4.3 Actions and Effects 5. Embodiment 2 5.1 Configuration 5.2 Operation 5.3 Actions and Effects 6.Other Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. The embodiments described below show some examples of the present disclosure and do not limit the content of the present disclosure. Furthermore, not all of the configurations and operations described in each embodiment are necessarily essential as the configurations and operations of the present disclosure. Note that the same components are given the same reference symbols, and redundant explanations will be omitted.

[0009] 1. Explanation of terms The terms used in this specification are defined as follows: "Standard software" is application software that performs at least one task of managing, monitoring, and analyzing a specific device based on predefined functionality and display specifications.

[0010] A "web app" is application software that can be accessed over the internet using a web browser. Web apps can be accessed on a variety of devices, including PCs, smartphones, and tablets, as long as they are connected to the internet, without the need to install application software.

[0011] A "standard operation screen" is a pre-designed standard user interface (UI) in application software.

[0012] An "interactive operation screen" is an operation screen in which a user asks questions or gives commands in natural language, and the application software responds to the questions or commands from the user.

[0013] "Unstructured data" is data that lacks regularity or continuity and is difficult to manage in a typical database or table. Examples of unstructured data include text documents, images, and audio files.

[0014] "Operation data" is operational information generated by the laser device.

[0015] A "specialized information processor" is a chat agent with advanced expertise in a specific field. Unlike general chat agents, a specialized information processor can respond appropriately to conversations related to terms and concepts in a specialized field.

[0016] A "query" is an inquiry or instruction received by the entire system from a user. A query is an instruction string written in natural language that specifies the information to be obtained and the format in which that information is to be provided, or that specifies the operation to be performed on the laser device. An example of a query is "Report a detailed operational diagnosis of laser 65400011 in standard format."

[0017] A "query response" is a result written in natural language that a system returns in response to a specific query. Depending on the content, the query response may contain not only text but also graphs, images, and other formats.

[0018] The Large Language Model Processor (LLM) performs natural language processing using an AI (Artificial Intelligence) model trained on large amounts of text data. The LLM understands and executes complex language tasks.

[0019] A "prompt" is a natural language text instruction or question that you send to an LLM so that the LLM knows what to respond to or what task to perform.

[0020] The Query Input Processor (QIP) analyzes the user's request (query) and performs the process of replacing the query with an appropriate input prompt for the LLM.

[0021] The "Response Output Processor (ROP)" performs processing to configure the content returned as the LLM's reply response in a format and content that conforms to the user's specifications.

[0022] The Agent Action Processor (AAP) analyzes the output of the LLM, obtains the information necessary to form an appropriate response from external sources, and performs the process of assembling an appropriate response that matches the user's query.

[0023] 2. Comparative Example 2.1 Laser device 2.1.1 Configuration 1 is a diagram showing the configuration of an exemplary laser apparatus 10. The laser apparatus 10 is a discharge-pumped gas laser apparatus and includes an oscillator (OSC) 20, an amplifier (AMP) 50, a monitor module 70, and a laser processor 80. The processor of the present disclosure is a processing device that includes a storage device in which a control program is stored and a CPU that executes the control program. The processor is specially configured or programmed to perform various processes.

[0024] The OSC 20 includes a line narrowing module (LNM) 22 , a chamber 24 , an output coupler (OC) 26 , a pulsed power module (PPM) 28 , and a charger 32 .

[0025] The LNM 22 includes prisms 36 and 38, a grating 42, and a rotation stage 44 that rotates the prism 38. The LNM 22 controls the central wavelength of the pulsed laser light by rotating the prism 38 to change the angle of incidence on the grating 42.

[0026] The chamber 24 includes a pair of discharge electrodes 46, 47 and two windows 48, 49 through which the laser light passes. An excimer laser gas is introduced into the chamber 24. The excimer laser gas includes, for example, a rare gas (Ar gas or Kr gas), a halogen gas (F2 gas), and a buffer gas (Ne gas).

[0027] The OC26 is a partial reflector that reflects part of the pulsed laser light and transmits the other part.

[0028] The LNM 22 and the OC 26 together constitute an optical resonator, and the chamber 24 is disposed on the optical path of the optical resonator.

[0029] The AMP 50 includes a rear mirror (RM) 52 , a chamber 54 , an output coupler (OC) 56 , a pulsed power module (PPM) 58 , and a charger 62 .

[0030] The RM 52 is a partial reflector that reflects part of the pulsed laser beam and transmits the other part. The reflectance of the RM 52 may be 80% to 90%.

[0031] The chamber includes a pair of discharge electrodes 64, 65 and two windows 66, 67 through which the laser light passes. An excimer laser gas is introduced into the chamber .

[0032] The OC 56 is a partial reflector that reflects and transmits a part of the pulsed laser light. The reflectance of the OC 56 may be 10% to 30%.

[0033] The RM 52 and the OC 56 together constitute an optical resonator, and the chamber 54 is disposed on the optical path of the optical resonator. The optical resonator may be a Fabry-Perot type optical resonator.

[0034] The monitor module 70 includes beam splitters 72 and 74, a spectral detector 76 that measures the wavelength and spectral linewidth of the pulsed laser light, and an optical sensor 78 that detects the pulse energy of the pulsed laser light. The spectral detector 76 may be an etalon spectrometer. The optical sensor 78 may be a photodiode.

[0035] 2.1.2 Operation The laser processor 80 receives a target center wavelength λt and a target pulse energy Et from an external device such as an exposure device (not shown). Then, the laser processor 80 sets the charging voltage V1 of the charger 32 and the charging voltage V2 of the charger 62 so as to obtain a pulsed laser beam having the target pulse energy Et.

[0036] A first charging capacitor (not shown) in the PPM 28 is charged with a charging voltage V1, and a second charging capacitor (not shown) in the PPM 58 is charged with a charging voltage V2.

[0037] When the laser processor 80 receives a light emission trigger Trt from an external device such as an exposure device, it sends a light emission trigger Tr1 to the switch 33 in the PPM 28. When the switch 33 operates, the charge stored in the first charging capacitor is converted into a high-voltage pulse corresponding to the charging voltage V1 in the PPM 28 and applied between the discharge electrodes 46 and 47 in the chamber 24.

[0038] As a result, a discharge occurs between the discharge electrodes 46 and 47 in the chamber 24, exciting the laser gas. Then, the wavelength narrowed by the optical resonator composed of the OC 26 and the LNM 22 is output from the OSC 20 as seed light with an ultraviolet wavelength of 150 nm to 380 nm. The wavelength of the seed light may be the oscillation wavelength of an ArF excimer laser or a KrF excimer laser.

[0039] In addition, when the laser processor 80 receives the light emission trigger Trt, it sends a light emission trigger Tr2 to the switch 59 of the PPM 58 so that a discharge occurs between the discharge electrodes 64, 65 when the seed light output from the OSC 20 enters the discharge space of the chamber 54 of the AMP 50.

[0040] When the switch 59 is operated, the charge stored in the second charging capacitor is converted into a high voltage pulse corresponding to the charging voltage V2 in the PPM 58 and applied between the discharge electrodes 64 and 65 in the chamber 54.

[0041] As a result, a discharge occurs between the discharge electrodes 64, 65 in the chamber 54, and the laser gas is excited. At this timing, the seed light output from the OSC 20 passes through the RM 52 and enters the discharge space in the chamber 54. The incident seed light is amplified by the optical resonator composed of the RM 52 and the OC 56, and is output from the AMP 50.

[0042] The pulsed laser light output from the AMP 50 enters the monitor module 70. A portion of the pulsed laser light that enters the monitor module 70 is reflected by a beam splitter 72, and a further portion is reflected by a beam splitter 74 and enters a spectrum detector 76. The pulsed laser light that passes through the beam splitter 74 then enters an optical sensor 78.

[0043] The spectrum detector 76 measures the central wavelength of the pulsed laser light, and the optical sensor 78 measures the pulse energy of the pulsed laser light.

[0044] The laser processor 80 may control the rotation stage 44 in the LNM 22 so that the center wavelength measured by the spectrum detector 76 becomes the target center wavelength λt. The rotation stage 44 may be a rotation stage including a piezoelectric element.

[0045] The laser processor 80 may control the charging voltage V2 output from the charger 62 so that the pulse energy measured by the optical sensor 78 becomes the target pulse energy Et.

[0046] 2.2 Laser Management System 2.2.1 Configuration 2 is a diagram showing the configuration of a laser management system 100 according to a comparative example. The comparative example of the present disclosure is a configuration that the applicant recognizes as being known only by the applicant, and is not a publicly known example that the applicant acknowledges. The laser management system 100 performs at least one of management, monitoring, and analysis of the laser device 10.

[0047] The laser management system 100 includes a laser device 10, an operation data server 104, a laser management server 110, and a terminal 150.

[0048] The operation data server 104 is a data server in which operation data of the laser device 10 is stored.

[0049] The terminal 150 is, for example, a personal computer, a smartphone, a tablet, or the like.

[0050] The laser management server 110 includes a standard software processor (SSP) 128 on which the standard software 122 is stored.

[0051] The SSP 128 acquires operational data of the laser device 10 from the operational data server 104 via the network.

[0052] The standard software 122 is provided in the form of a web application that is operated via a network.

[0053] The standard operation screen 124 of the standard software 122 is displayed on the terminal 150 and is designed so that the user can operate it.

[0054] 2.2.2 Operation The laser device 10 transmits the operation data to the operation data server 104, and the operation data server 104 stores the operation data.

[0055] The laser management server 110 receives a request from the user via the standard operation screen 124 to view predetermined information, etc.

[0056] The standard software 122 of the laser management server 110 uses the accumulated operational data to perform analysis of a specific laser device 10. The standard software 122 provides the user with at least one of the functions of managing, monitoring, and analyzing a predetermined laser device 10.

[0057] The routine software 122 of the laser management server 110 displays the requested information and the like on a routine operation screen 124 .

[0058] The user views the information on the routine operation screen 124 .

[0059] Different standard software 122 or standard operation screen 124 are provided depending on the purpose of each of different users, such as a field service engineer (FSE), an equipment owner, and a research and development engineer.

[0060] 2.2.3 Challenges When controlling the laser apparatus 10, such as by changing parameters, the FSE accesses the operation data server 104, which stores operation data for the laser apparatus 10, via the standard operation screen 124 and examines the operation data stored in the operation data server 104. The FSE then determines control values ​​for parameter changes for the laser apparatus 10. At this time, the FSE estimates future laser characteristics (laser performance) based on the number of pulses or date and time, and future laser performance after the parameter change. Here, the laser characteristics include, for example, the pulse energy, center wavelength, spectral linewidth, gas pressure in the chamber, applied voltage between electrodes, and the number of pulses used for each component of the pulsed laser light output from the laser apparatus 10. The laser performance may include an index related to the performance of the laser apparatus 10.

[0061] However, even for an experienced FSE, it is difficult to estimate the future laser performance of the laser device 10.

[0062] Furthermore, if there is a difference in the information acquired by the FSE, the control signal for the laser device 10 will vary and become unstable.

[0063] 3. Embodiment 1 3.1 Configuration Fig. 3 is a diagram showing a laser management system 100A according to embodiment 1. Differences between the configuration shown in Fig. 3 and Fig. 2 will be described.

[0064] Comparing laser management system 100A and laser management system 100, the differences are the configuration within laser management server 110A, the fact that laser management server 110A is connected to document server 106 and AI prediction processing device 108, and the fact that control signals such as parameter changes are sent from laser management server 110A to laser device 10. Note that the term "management" in this disclosure includes the concept of "control."

[0065] The laser management server 110A includes a sending and receiving processor (SRP) 130, a query input processor (QIP) 132, a large-scale language model processor (LLM) 134, an agent action processor (AAP) 136, an equipment agent processor (EAP) 138, and an equipment control processor (ECP) 140.

[0066] The SRP 130, the QIP 132, the LLM 134, the AAP 136, the EAP 138, and the ECP 140 may be application software or hardware such as a CPU. Each application software may be implemented as a single processor.

[0067] User input and output is performed on the interactive operation screen 126 of the terminal 150 through the SRP 130 .

[0068] The SRP 130 performs input and output to the interactive screen 126 of the terminal 150 .

[0069] The ECP 140 is capable of communicating with the laser device 10 .

[0070] The document server 106 stores unstructured data such as manuals and maintenance reports for the laser device 10. The document server 106 includes a laser device technical document database (DB).

[0071] The AI ​​prediction processing device 108 includes at least one of a life prediction model for predicting the life of consumables of the laser device 10 and a laser performance prediction model for predicting future laser performance of the laser device 10.

[0072] The lifespan prediction model may be a trained model created by, for example, the machine learning method described in Patent Document 3. The machine learning method described in Patent Document 3 creates a learning model for predicting the lifespan of consumables in the laser device 10. The method includes acquiring first lifespan-related information including data on lifespan-related parameters of the consumables recorded corresponding to different numbers of oscillation pulses during a period from when the consumables are first used until they are replaced, dividing the first lifespan-related information into multiple levels representing the degree of deterioration of the consumables according to the number of oscillation pulses, and creating training data in which the first lifespan-related information is associated with the levels representing the degree of deterioration, performing machine learning using the training data to create a learning model that predicts the degree of deterioration of the consumables from the data on the lifespan-related parameters, and saving the created learning model. For each consumable scheduled for replacement in the laser device 10, the AI ​​prediction processing device 108 can predict the lifespan of each consumable scheduled for replacement by using the corresponding lifespan prediction model based on the lifespan-related information of the consumables.

[0073] The learning model is, for example, a neural network model, and is essentially a program that causes a computer to execute a process for predicting the degree of deterioration of consumables of the laser device 10.

[0074] The AI ​​prediction processing device 108 can predict the lifespan of each consumable item scheduled for replacement in the laser device 10 by using a corresponding lifespan prediction model based on the lifespan-related information of the consumable item.

[0075] The laser performance prediction model is a trained model that can predict future changes in the laser performance of the laser device 10 according to the number of pulses or date and time in any part replacement scenario.

[0076] At least one of the operational data server 104 and the document server 106 may be implemented within the laser management server 110A.

[0077] Terminal 150 may be connected to laser management server 110A via a network, or may be connected via a wired cable or wirelessly.

[0078] The interactive operation screen 126 of the terminal 150 may be displayed on the monitor screen of the laser management server 110A.

[0079] The other configurations may be the same as those in FIG.

[0080] 3.2 Operation 3.2.1 Operation flow of the laser management system 4 is a diagram showing an operation flow of the laser management system 100A according to embodiment 1. The operation flow of the laser management system 100A will be described with reference to FIG.

[0081] The SRP 130 receives a query W0 from the terminal 150.

[0082] The QIP 132 decomposes the query W0 received from the SRP 130 to generate a first query term W1 that requires external information and a second query term W2 that does not require external information.

[0083] Figure 5 shows examples of query items generated from a user's query. Figure 5 shows examples of the first query item W1 and the second query item W2 generated when the query W0 is "Change the target value of the chamber gas pressure to extend the chamber life of the OSC of laser 65400011 by 2 Bpls." Note that "laser 65400011" is a name that identifies the laser model.

[0084] In this case, the QIP 132 breaks down the received query W0 into six query items. The query item with item number 1 is "Information about the model of laser 65400011," the query item with item number 2 is "Information about changing the gas pressure in the chamber of laser 65400011," the query item with item number 3 is "Determining how to change the gas pressure in the chamber based on the information," the query item with item number 4 is "Analysis of the operating data of laser 65400011," the query item with item number 5 is "Prediction of performance when the target value of gas pressure is changed," and the query item with item number 6 is "Determining the target value of gas pressure based on the information."

[0085] Of these six query items, query items with item numbers 1, 2, 4, and 5 are difficult to answer using LLM134 alone and require external information to obtain an appropriate answer, so they are classified as the first query item W1. Query items with item numbers 3 and 6 do not require external information to be answered, so they are classified as the second query item W2.

[0086] In this case, external information refers to information present in at least one of the operational data server 104, the document server 106, and the AI ​​prediction processing device 108. The criterion for determining whether a query item requires external information is, for example, whether a highly accurate response can be generated by the LLM 134 alone. For query items classified as the first query item W1, it is difficult to generate a highly accurate response by the LLM 134 alone. For query items classified as the second query item W2, it is possible to generate a highly accurate response by the LLM 134 alone. A highly accurate response is a response that is based on facts and has few misidentifications or errors.

[0087] Depending on the content of the query W0 received from the SRP 130, there may be cases where only one of the first query item W1 and the second query item W2 is generated.

[0088] The QIP 132 sends a second query item W2 to the EAP 138 .

[0089] The QIP 132 sends the first query term W1 to the AAP 136. The first query term W1 may also be sent to the EAP 138 for use in verifying external information.

[0090] The AAP 136 receives the first query item W1 from the QIP 132 and assigns a corresponding external information processing program to the first query item W1. The external information processing program acquires necessary information from the outside (at least one of the operational data server 104, the document server 106, and the AI ​​prediction processing device 108), analyzes the acquired information, and summarizes the results.

[0091] For example, for the first query item W1 of item number 2 in Fig. 5, AAP 136 obtains the manual for laser 65400011 from document server 106, analyzes it, and compiles the results. For the first query item W1 of item number 4 in Fig. 5, AAP 136 obtains the voltage (HV) applied between discharge electrodes 46 and 47 in chamber 24 of OSC 20 of laser 65400011, the gas pressure in chamber 24 of OSC 20, and the total number of shots in the apparatus from operation data server 104, analyzes them, and compiles the results. For the first query item W1 of item number 5 in Figure 5, AAP136 acquires operation data of laser 65400011 from the operation data server 104, transmits the acquired operation data to the AI ​​prediction processing device 108, and acquires predicted results of laser performance such as the applied voltage (HV) and gas pressure between the discharge electrodes 46 and 47 in the chamber 24 of OSC20 when the target value of the gas pressure in the chamber of OSC20 is changed based on the operation data, analyzes the acquired results, and summarizes the results.

[0092] The AAP 136 executes all the external information processing programs assigned to it. The AAP 136 performs external information configuration processing to compile all the information and generate a first agent response W3. The AAP 136 also performs processing while communicating with the LLM 134 as necessary.

[0093] The AAP 136 sends the first agent response W3 to the EAP 138 .

[0094] The EAP 138 receives the second query term W2 from the QIP 132 and the first agent response W3 from the AAP 136 .

[0095] The EAP 138 may receive the first agent response W3 from the AAP 136 and verify whether it contains the required information.

[0096] The EAP 138 generates a first query item prompt W4 related to the response to the second query item W2. The first query item prompt W4 related to the second query item W2 in item number 3 in Figure 5 includes, for example, the manual for the laser device 10 and a prompt such as "How do I change the target value of the gas pressure in the chamber of the OSC of laser 65400011?"

[0097] The LLM 134 receives the first query item prompt W4 from the EAP 138 and generates a first query item response W5 that is a response to the first query item prompt W4. The first query item response W5 to the first query item prompt W4 of the second query item W2 of item number 3 in FIG. 5 is, for example, "How to change the target value of the gas pressure in the chamber of the OSC of laser 65400011."

[0098] The EAP 138 generates a first control signal W6 for the laser device 10 based on the first query item response W5 and the first agent response W3. The first control signal W6 is a control signal that means, for example, "change the target value of the gas pressure in the OSC chamber from P1 to P2."

[0099] The EAP 138 transmits the generated first control signal W6 to the ECP 140.

[0100] The ECP 140 receives the first control signal W6 from the EAP 138 and transmits the first control signal W6 to the laser device 10.

[0101] 3.2.2 Laser device control flow 6 is a flowchart showing an example of control of the laser device 10 by the laser management server 110A according to embodiment 1. The method including steps S1 to S7 shown in FIG. 6 is an example of the "laser management method" in the present disclosure.

[0102] In step S1, the SRP 130 receives a query W0 from the outside. Step S1 is an example of the "first step" in this disclosure.

[0103] In step S2, the QIP 132 decomposes the query W0 to generate a first query term W1 that requires external information and a second query term W2 that does not require external information. Step S2 is an example of the “second step” in this disclosure.

[0104] In step S3, the AAP 136 receives the first query item W1 from the QIP 132, acquires necessary information from unstructured data including the manual and maintenance report of the laser device 10, and structured data including operation data of the laser device 10 and at least one of a prediction result of the lifespan of consumables of the laser device 10 using a lifespan prediction model and a prediction result of laser performance of the laser device 10 using a laser performance prediction model, and generates a first agent response W3 that is a response to the first query item W1. Step S3 is an example of a "third step" in this disclosure.

[0105] In step S4, EAP 138 receives the second query term W2 from QIP 132, receives the first agent response W3 from AAP 136, and generates a first query term prompt W4 related to the second query term W2. Step S4 is an example of a "fourth step" in this disclosure.

[0106] In step S5, the LLM 134 receives a first query item prompt W4 from the EAP 138 and generates a first query item response W5 that is a response to the first query item prompt W4. Step S5 is an example of the “fifth step” in this disclosure.

[0107] In step S6, the EAP 138 receives the first query item response W5 from the LLM 134 and generates a first control signal W6 for controlling the laser device 10 based on the first agent response W3 and the first query item response W5. Step S6 is an example of the "sixth step" in this disclosure.

[0108] In step S7, the ECP 140 receives the first control signal W6 from the EAP 138 and transmits the first control signal W6 to the laser device 10. Step S7 is an example of the "seventh step" in this disclosure.

[0109] 3.3 Actions and Effects According to the laser management system 100A, the laser performance prediction model can predict future changes in the laser performance of the laser device 10. Therefore, the FSE can easily estimate the future laser performance of the laser device 10.

[0110] In the laser management system 100A, the QIP 132 decomposes the query W0 to generate a first query item W1 that requires external information and a second query item W2 that does not require external information. In the laser management system 100A, the AAP 136 acquires the required external information, and the EAP 138 generates a first control signal W6 for the laser device 10 based on the acquired external information. As a result, the laser management system 100A can stably acquire valid information, and the control of the laser device 10 is also stably performed.

[0111] 4. Modification of the First Embodiment 4.1 Configuration Fig. 7 is a diagram showing the configuration of a laser management system 100B according to a modification of embodiment 1. Differences between the configuration shown in Fig. 7 and Fig. 3 will be described.

[0112] Comparing laser management system 100A and laser management system 100B, the difference is that the QIP 132 and LLM 134, the AAP 136 and LLM 134, and the EAP 138 and SRP 130 communicate with each other. The other configurations may be similar to the configuration of laser management system 100A shown in FIG. 3.

[0113] 4.2 Operation 8 is a diagram showing the operation flow of the laser management system 100B. Regarding the operation flow of the laser management system 100B shown in FIG. 8, differences from FIG. 4 will be described.

[0114] The QIP 132 may generate a selection prompt W7 when performing linguistic processing to generate the first query term W1 and the second query term W2. The selection prompt W7 may be, for example, "break down the query into terms."

[0115] The LLM 134 may receive the screening prompt W7 from the QIP 132 and generate a screening response W8 that is a response to the screening prompt W7. The screening response W8 may be, for example, an itemized query item as shown in FIG.

[0116] The QIP 132 may receive a screening response W8 from the LLM 134.

[0117] When AAP 136 acquires the unstructured data and generates first agent response W3, AAP 136 may generate unstructured data prompt W9. Unstructured data prompt W9 may include, for example, external information from the manual for laser device 10 and a prompt such as, "Where can I find information on how to change the target value for the chamber gas pressure of the OSC of laser 65400011?"

[0118] The LLM 134 may receive the unstructured data prompt W9 from the AAP 136 and generate an unstructured data response W10 that is a response to the unstructured data prompt W9. The unstructured data response W10 may be, for example, "The method for changing the target value of the gas pressure in the chamber of the OSC of laser 65400011 is described from page AA, line BB to page CC, line DD."

[0119] The AAP 136 may receive the unstructured data response W10 from the LLM 134. The AAP 136 analyzes the unstructured data response W10 received from the LLM 134 and generates a first agent response W3. In this case, the AAP 136 allocates an appropriate external information processing program and generates the first agent response W3 from the results.

[0120] The EAP 138 may send a first control signal W6 to the SRP 130.

[0121] The SRP 130 may transmit the first control signal W6 received from the EAP 138 to the terminal 150. The first control signal W6 is displayed on the interactive operation screen 126 of the terminal 150.

[0122] The EAP 138 may transmit the first agent response W3 or the first query item response W5 to the SRP 130. The EAP 138 may construct a query response based on the first agent response W3 and the first query item response W5 and transmit the constructed query response to the SRP 130. The EAP 138 may generate a query response by combining the first agent response W3 generated by the AAP 136 and the first query item response W5 generated by the LLM 134. The SRP 130 may transmit at least one of the first agent response W3, the first query item response W5, and the query response received from the EAP 138 to the terminal 150. At least one of the first agent response W3, the first query item response W5, and the query response may be displayed on the interactive operation screen 126 of the terminal 150.

[0123] The interactive operation screen 126 of the terminal 150 may display a message to the user. The message may include a comment regarding at least one of the first control signal W6, the first agent response W3, the first query item response W5, and the query response. The comment may include a diagram, a table, or the like. The laser management system 100B may generate at least one of the first control signal W6, the first agent response W3, the first query item response W5, and the query response corresponding to the content of the query W0. The content of the query W0 is intended for at least one of the functions of management, monitoring, and analysis.

[0124] Other operations may be the same as those in FIG.

[0125] 4.3 Actions and Effects The laser management system 100B has the same effects as the laser management system 100A.

[0126] According to the laser management system 100B, the language processing functions of the QIP 132 and the AAP 136 are further improved compared to the laser management system 100A.

[0127] 5. Embodiment 2 5.1 Configuration The configuration of the laser management system according to the second embodiment may be similar to the configuration of the laser management system 100B.

[0128] 5.2 Operation Fig. 9 is a flowchart showing an example of control of the laser device 10 by the laser management server according to embodiment 2. Differences between Fig. 9 and Fig. 6 will be described. In Fig. 9, steps S8 to S12 are added after step S7.

[0129] After a predetermined time has elapsed after step S7, in step S8, the AAP 136 acquires operation data of the laser device 10 after transmitting the first control signal W6. The operation data of the laser device 10 is stored in the operation data server 104. Step S8 is an example of the "eighth step" in the present disclosure.

[0130] In step S9, the AAP 136 generates a second agent response that is a response to the first query item W1. Step S9 is an example of the "ninth step" in the present disclosure. The AAP 136 may analyze operational data of the laser device 10 to generate the second agent response to the first query item W1. The second agent response may be different from the first agent response W3.

[0131] In step S10, the EAP 138 receives a second agent response from the AAP 136 and determines whether or not the first control signal W6 needs to be changed based on the second agent response. If the determination in step S10 is "YES," the process proceeds to step S11. If the determination in step S10 is "NO," the process ends. Step S10 is an example of the "tenth step" in the present disclosure.

[0132] In step S11, the EAP 138 generates a second control signal for controlling the laser device 10 based on the first query item response W5 and the second agent response. Step S11 is an example of the “eleventh step” in the present disclosure.

[0133] In step S12, the ECP 140 receives a second control signal from the EAP 138 and transmits the second control signal to the laser device 10. Step S12 is an example of the "twelfth step" in the present disclosure.

[0134] The control flow from step S8 to step S12 may be repeated multiple times.

[0135] The other steps may be the same as those in FIG.

[0136] 5.3 Actions and Effects The laser management system according to the second embodiment has the same effects as the laser management systems 100A and 100B.

[0137] The laser management system of embodiment 2 acquires operational data of the laser device 10 after transmitting the first control signal W6 and generates a second control signal as necessary, thereby making the control of the laser device 10 even more stable.

[0138] 6.Other The above description is intended to be illustrative rather than limiting. Thus, it will be apparent to one skilled in the art that modifications can be made to the disclosed embodiments without departing from the scope of the claims. It will also be apparent to one skilled in the art that the disclosed embodiments can be used in combination.

[0139] Terms used throughout this specification and claims should be construed as "open ended" unless expressly stated otherwise. For example, words such as "comprise," "have," "comprise," and "equip" should be construed as meaning "without excluding the presence of elements other than those listed." In addition, the modifier "a" should be construed as meaning "at least one" or "one or more." In addition, the term "at least one of A, B, and C" should be construed as "A," "B," "C," "A+B," "A+C," "B+C," or "A+B+C." Furthermore, it should be construed to include combinations of these with elements other than "A," "B," and "C."

Claims

1. A laser management server for a laser device, a transceiver processor for receiving queries from the outside; a query input processor that receives the query from the transceiver processor, decomposes the query, and generates a first query term that requires external information and a second query term that does not require external information; an agent action processor that receives the first query item from the query input processor, acquires necessary information from unstructured data including a manual and a maintenance report of the laser device, and structured data including operation data of the laser device and at least one of a prediction result of a lifespan of a consumable of the laser device using a lifespan prediction model and a prediction result of laser performance of the laser device using a laser performance prediction model, and generates a first agent response that is a response to the first query item; a device agent processor that receives the second query term from the query input processor and the first agent response from the agent action processor and generates a query term prompt for the second query term; a large scale language model processor that receives the query item prompt from the device agent processor and generates a query item response that is a response to the query item prompt; the device agent processor receives the query term response from the large scale language model processor, and generates a first control signal for controlling the laser device based on the first agent response and the query term response; a device control processor that receives the first control signal from the device agent processor and transmits the first control signal to the laser device; A laser management server comprising:

2. 2. The laser management server of claim 1, The agent action processor acquiring operation data of the laser device after transmitting the first control signal; generating a second agent response that is a response to the first query term; The device agent processor: receiving the second agent response from the agent action processor, and determining whether the first control signal needs to be changed based on the second agent response; If it is determined in the determination that the first control signal needs to be changed, the device agent processor generates a second control signal for controlling the laser device based on the query item response and the second agent response; The device control processor receiving the second control signal from the device agent processor and transmitting the second control signal to the laser device; Laser management server.

3. 2. The laser management server of claim 1, the query input processor generates a selection prompt when processing the first query term and the second query term; the large scale language model processor receives the screening prompt from the query input processor and generates a screening response that is a response to the screening prompt; The query input processor receives the filtered response from the large scale language model processor.

4. 2. The laser management server of claim 1, the agent action processor, upon obtaining the unstructured data and generating the first agent response, generates an unstructured data prompt; the large scale language model processor receives the unstructured data prompt from the agent action processor and generates an unstructured data response that is a response to the unstructured data prompt; The agent action processor receives unstructured data responses from the large scale language model processor.

5. 5. The laser management server of claim 4, The unstructured data prompt includes the unstructured data.

6. 2. The laser management server of claim 1, The device agent processor sends the first control signal to the transceiver processor.

7. 2. The laser management server of claim 1, the transceiver processor receives the first control signal from the device agent processor and transmits the first control signal to an external device; Laser management server.

8. 2. The laser management server of claim 1, the transceiver processor receives the query from a terminal connected via a network; Laser management server.

9. 9. The laser management server of claim 8, accepting the query from an interactive operation screen of the terminal; Laser management server.

10. 10. The laser management server of claim 9, the first control signal is displayed on an interactive operation screen of the terminal; Laser management server.

11. A laser management method for a laser device, comprising: A first step in which a transceiver processor receives a query from an external device; a second step in which a query input processor decomposes the query to generate a first query term requiring external information and a second query term not requiring external information; a third step in which an agent action processor receives the first query item from the query input processor, acquires necessary information from unstructured data including the manual and maintenance report of the laser device, and structured data including operation data of the laser device and at least one of a prediction result of the life of consumables of the laser device using a life prediction model and a prediction result of laser performance of the laser device using a laser performance prediction model, and generates a first agent response that is a response to the first query item; a fourth step in which a device agent processor receives the second query term from the query input processor and the first agent response from the agent action processor and generates a query term prompt for the second query term; a fifth step in which a large scale language model processor receives the query item prompt from the device agent processor and generates a query item response that is a response to the query item prompt; a sixth step of the device agent processor receiving the query term response from the large scale language model processor and generating a first control signal for controlling the laser device based on the first agent response and the query term response; a seventh step in which a device control processor receives the first control signal from the device agent processor and transmits the first control signal to the laser device; A laser management method comprising:

12. The laser management method according to claim 11 further comprises: an eighth step in which the agent action processor acquires operation data of the laser device after transmitting the first control signal; a ninth step in which the agent action processor generates a second agent response that is a response to the first query term; a tenth step in which the device agent processor receives the second agent response from the agent action processor and determines whether the first control signal needs to be changed based on the second agent response; an eleventh step in which, if it is determined in the tenth step that the first control signal needs to be changed, the device agent processor generates a second control signal for controlling the laser device based on the query item response and the second agent response; a twelfth step in which the device control processor receives the second control signal from the device agent processor and transmits the second control signal to the laser device; A laser management method comprising:

13. The laser management method according to claim 11, In the second step, when the query input processor performs linguistic processing to generate the first query term and the second query term, a selection prompt is generated; the large scale language model processor receives the screening prompt from the query input processor and generates a screening response that is a response to the screening prompt; The query input processor receives the filtered response from the large scale language model processor.

14. The laser management method according to claim 11, In the third step, when the agent action processor obtains the unstructured data and generates the agent response, an unstructured data prompt is generated; the large scale language model processor receives the unstructured data prompt from the agent action processor and generates an unstructured data response that is a response to the unstructured data prompt; The agent action processor receives an unstructured data response from the large scale language model processor.

15. The laser management method according to claim 14, The unstructured data prompt includes the unstructured data.

16. The laser management method according to claim 11, The device agent processor sends the first control signal to the transceiver processor.

17. The laser management method according to claim 11, The sixth step of the laser management method includes the transceiver processor receiving the first control signal from the device agent processor and transmitting the first control signal to the outside.

18. 12. The laser management method of claim 11, the first step includes the transceiver processor receiving the query from a terminal connected via a network; Laser management methods.

19. 20. The laser management method of claim 18, comprising: accepting the query from an interactive operation screen of the terminal; Laser management methods.

20. 20. The laser management method of claim 19, comprising: the first control signal is displayed on an interactive operation screen of the terminal; Laser management methods.

Images