Laser management server and laser management method

Abstract

The invention provides a laser management server and a laser management method. A laser management server of a laser device includes: a transmission / reception processor that receives an inquiry from the outside; an inquiry input processor which receives and decomposes the inquiry and generates a first inquiry item requiring external information and a second inquiry item not requiring external information; an agent behavior processor that receives the first inquiry item, acquires information from the unstructured data and the structured data, and generates a first agent response; a device agent processor which receives the second inquiry item from the inquiry input processor, receives the first agent response from the agent behavior processor, and generates an inquiry item cue related to the second inquiry item; the large-scale language model processor receives inquiry item cues and generates inquiry item responses, the device intelligent agent processor receives the inquiry item responses and generates first control signals, and the laser management server further comprises a device control processor which receives the first control signals and sends the first control signals to the laser device.

Description

Technical Field

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

[0002] In recent years, semiconductor exposure equipment has been required to achieve higher resolution as semiconductor integrated circuits become increasingly miniaturized and highly integrated. Consequently, there has been a trend toward shorter wavelengths of light emitted from exposure light sources. For example, gas lasers used for exposure include KrF excimer lasers, which output laser light with a wavelength of approximately 248 nm, and ArF excimer lasers, which output laser light with a wavelength of approximately 193 nm.

[0003] The spectral line width of the natural oscillation light of KrF excimer laser devices and ArF excimer laser devices is relatively wide, ranging from 350 to 400 pm. Therefore, when a projection lens is constructed using a material that transmits ultraviolet light such as KrF and ArF laser light, chromatic aberration may sometimes occur. As a result, the resolution may be reduced. Therefore, it is necessary to narrow the spectral line width of the laser light output from the gas laser device to a level where chromatic aberration is invisible. Therefore, in order to narrow the spectral line width, a narrowing module (Line Narrowing Module: LNM) containing narrowing elements (etalon, grating, etc.) is sometimes included in the laser resonator of the gas laser device. Hereinafter, a gas laser device with a narrowed spectral line width is referred to as a narrowed gas laser device.

[0004] Patent Document 1: International Publication No. 2019 / 240906

[0005] Patent Document 2: Japanese Patent Application Laid-Open No. 2006-24765

[0006] Patent Document 3: International Publication No. 2020 / 161865 Summary of the Invention

[0007] A laser management server for a laser device according to one aspect of the present disclosure comprises: a transceiver processor that receives inquiries from the outside; a query input processor that receives inquiries from the transceiver processor, decomposes the inquiries, and generates a first query item that requires external information and a second query item that does not require external information; an agent behavior processor that receives the first query item from the query input processor, obtains required information from unstructured data and structured data, and generates a first agent response as a response to the first query item, wherein the unstructured data includes a manual and a maintenance report of the laser device, and the structured data includes operating data of the laser device, a prediction result of the life of consumables of the laser device based on a life prediction model, and laser performance of the laser device based on a laser performance prediction model. at least one of the predicted results; a device intelligent agent processor, which receives the second query item from the query input processor and the first intelligent agent response from the intelligent agent behavior processor, and generates a query item prompt word related to the second query item; and a large-scale language model processor, which receives the query item prompt word from the device intelligent agent processor, and generates a query item response as a response to the query item prompt word. The device intelligent agent processor receives the query item response from the large-scale language model processor, and generates a first control signal for controlling the laser device based on the first intelligent agent response and the query item response. The laser management server also has a device control processor, which receives the first control signal from the device intelligent agent processor and sends the first control signal to the laser device.

[0008] A laser management method for a laser device according to another aspect of the present disclosure comprises the following steps: a first step in which a transceiver processor receives an inquiry from the outside; a second step in which an inquiry input processor decomposes the inquiry to generate a first inquiry item requiring external information and a second inquiry item not requiring external information; a third step in which an agent behavior processor receives the first inquiry item from the inquiry input processor, obtains required information from unstructured data and structured data, and generates a first agent response as a response to the first inquiry item, wherein the unstructured data includes a manual and a maintenance report of the laser device, and the structured data includes working data of the laser device, a prediction result of the life of consumables of the laser device based on a life prediction model, and laser performance of the laser device based on a laser performance prediction model. at least one of the prediction results that can be predicted; in step 4, the device agent processor receives the second query item from the query input processor and receives the first agent response from the agent behavior processor, and generates a query item prompt word related to the second query item; in step 5, the large-scale language model processor receives the query item prompt word from the device agent processor, and generates a query item response as a response to the query item prompt word; in step 6, the device agent processor receives the query item 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 item response; and in step 7, the device control processor receives the first control signal from the device agent processor and sends the first control signal to the laser device. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Several embodiments of the present disclosure are described below by way of example only with reference to the accompanying drawings.

[0010] Figure 1 is a diagram showing the structure of an exemplary laser device.

[0011] Figure 2 1 is a diagram showing the configuration of a laser management system according to a comparative example.

[0012] Figure 3 This is a diagram showing the laser management system according to the first embodiment.

[0013] Figure 4 This is a diagram showing the operation flow of the laser management system according to the first embodiment.

[0014] Figure 5 This is a diagram showing an example of inquiry items generated in response to an inquiry from a user according to the first embodiment.

[0015] Figure 6 This is a flowchart showing an example of control of the laser device by the laser management server according to the first embodiment.

[0016] Figure 7This is a diagram showing the configuration of a laser management system according to a modified example of the first embodiment.

[0017] Figure 8 This is a diagram showing the operation flow of the laser management system according to the modified example of the first embodiment.

[0018] Figure 9 This is a flowchart showing an example of control of the laser device by the laser management server according to the second embodiment. DETAILED DESCRIPTION

[0019] - Contents - 1. Explanation of terms

[0020] 2. Comparative Example

[0021] 2.1 Laser device

[0022] 2.1.1 Structure

[0023] 2.1.2 Action

[0024] 2.2 Laser Management System

[0025] 2.2.1 Structure

[0026] 2.2.2 Action

[0027] 2.2.3 Topics

[0028] 3. Implementation Method 1

[0029] 3.1 Structure

[0030] 3.2 Action

[0031] 3.2.1 Action flow of laser management system

[0032] 3.2.2 Laser device control process

[0033] 3.3 Function / Effect

[0034] 4. Modification of Implementation 1

[0035] 4.1 Structure

[0036] 4.2 Action

[0037] 4.3 Action / Effect

[0038] 5. Implementation Method 2

[0039] 5.1 Structure

[0040] 5.2 Action

[0041] 5.3 Action / Effect

[0042] 6. Others

[0043] Below, embodiments of the present disclosure are described in detail with reference to the accompanying drawings. The embodiments described below illustrate several examples of the present disclosure and do not limit the content of the present disclosure. In addition, the structures and actions described in each embodiment are not necessarily all required structures and actions of the present disclosure. In addition, the same reference numerals are given to the same structural elements, and repeated descriptions are omitted.

[0044] 1. Explanation of terms

[0045] The terms used in this specification are defined as follows.

[0046] “Standardized software” is application software that performs at least one of the tasks of managing, monitoring, and analyzing a specific device according to predefined functions and display specifications.

[0047] A "web application" is software that can be used on the internet using a web browser. Web applications can be used on various devices, such as personal computers, smartphones, and tablets, without installing the application software, as long as they are connected to the internet.

[0048] The "standard operation screen" is a pre-designed standard user interface (UI) in application software.

[0049] The “interactive operation screen” is an operation screen in which a user asks questions and issues commands using natural language, and the application software responds to the questions and commands from the user.

[0050] Unstructured data is data that lacks regularity and continuity and is not easily managed using conventional databases and tables. Examples of unstructured data include text documents, images, and audio files.

[0051] "Operation data" is the operational information generated by the laser device.

[0052] "Professional Information Processors" are chat agents with highly specialized knowledge in a specific field. Unlike general chat agents, these agents can accurately handle conversations using terms and concepts related to that field.

[0053] A "query" is a question or instruction received by the system from the user. It is a natural language instruction string that specifies the desired information and the format in which it is provided, or specifies an operation desired by the laser device. An example of a query might be "Report detailed operational diagnostics of laser 65400011 in a standard format."

[0054] A query response is a natural language response from the system in response to a specific query. Depending on the content, a query response may include not only text strings but also graphics, images, and more.

[0055] The Large Language Model Processor (LLM) performs natural language processing based on AI (Artificial Intelligence) models trained using large amounts of text data. The LLM can understand and execute complex language tasks.

[0056] "Prompt words" are natural language text instructions or questions sent to the LLM. Based on the prompt words, the LLM understands what to respond to (answer) or what task to perform.

[0057] The "Query Input Processor (QIP)" analyzes the user's request (query) and executes a process of replacing the query with input prompt words suitable for the LLM.

[0058] The "Response Output Processor (ROP)" executes processing for composing the content returned as a reply response to the LLM into a format and content that conforms to the content specified by the user.

[0059] The Agent Action Processor (AAP) performs the following processing: it analyzes the output of the LLM, obtains the information required to form an appropriate response from an external information source, and forms an appropriate response that matches the user's query.

[0060] 2. Comparative Example

[0061] 2.1 Laser device

[0062] 2.1.1 Structure

[0063] Figure 1 1 is a diagram illustrating the structure of an exemplary laser device 10. Laser device 10 is a discharge-excited gas laser device and includes an oscillator (OSC) 20, an amplifier (AMP) 50, a monitor module 70, and a laser processor 80. The processor disclosed herein is a processing device comprising a storage device storing a control program and a CPU that executes the control program. The processor is specifically configured or programmed to perform various processes.

[0064] The OSC 20 includes a narrowbanding module (LNM) 22 , a cavity 24 , an output coupler (OC) 26 , a pulsed power module (PPM) 28 , and a charger 32 .

[0065] The LNM 22 includes prisms 36 and 38, a grating 42, and a rotation stage 44 for rotating the prism 38. The LNM 22 rotates the prism 38 to change the incident angle with respect to the grating 42, thereby controlling the center wavelength of the pulsed laser light.

[0066] The cavity 24 includes a pair of discharge electrodes 46 and 47, and two windows 48 and 49 through which the laser light passes. Excimer laser gas is introduced into the cavity 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).

[0067] OC26 is a partial reflection mirror that reflects part of the pulsed laser light and transmits the other part.

[0068] The LNM 22 and the OC 26 together constitute an optical resonator, and the cavity 24 is arranged on the optical path of the optical resonator.

[0069] AMP 50 includes a rear mirror (RM) 52 , a cavity 54 , an output coupler (OC) 56 , a pulsed power module (PPM) 58 , and a charger 62 .

[0070] RM52 is a partial reflector that reflects part of the pulsed laser and transmits the other part. The reflectivity of RM52 can be 80% to 90%.

[0071] The cavity 54 includes a pair of discharge electrodes 64 and 65 and two windows 66 and 67 for transmitting laser light. Excimer laser gas is introduced into the cavity 54.

[0072] OC56 is a partial reflector that reflects a portion of the pulsed laser and transmits it. The reflectivity of OC56 can be 10% to 30%.

[0073] RM52 and OC56 together form an optical resonator, and cavity 54 is arranged on the optical path of the optical resonator. The optical resonator may be a Fabry-Perot type optical resonator.

[0074] Monitor module 70 includes beam splitters 72 and 74, a spectrum detector 76 for measuring the wavelength and spectral line width of the pulsed laser light, and a photosensor 78 for detecting the pulse energy of the pulsed laser light. Spectrum detector 76 may be an etalon spectrometer, and photosensor 78 may be a photodiode.

[0075] 2.1.2 Action

[0076] Laser processor 80 receives target central wavelength λt and target pulse energy Et from an external device such as an exposure device (not shown). Laser processor 80 then sets charging voltages V1 and V2 of charger 32 and charger 62 to obtain pulsed laser light of target pulse energy Et.

[0077] A first charging capacitor (not shown) in the PPM 28 is charged at a charging voltage V1, and a second charging capacitor (not shown) in the PPM 58 is charged at a charging voltage V2.

[0078] Upon receiving a light emission trigger Trt from an external device such as an exposure device, the laser processor 80 transmits a light emission trigger Tr1 to the switch 33 within the PPM 28. When the switch 33 is actuated, the charge stored in the first charging capacitor is converted within the PPM 28 into a high-voltage pulse corresponding to the charging voltage V1, which is then applied between the discharge electrodes 46 and 47 within the cavity 24.

[0079] As a result, discharge occurs between discharge electrodes 46 and 47 within cavity 24, exciting the laser gas. Then, the optical resonator formed by OC 26 and LNM 22 generates narrowband seed light with an ultraviolet wavelength of 150 nm to 380 nm, which is then output from OSC 20. The wavelength of the seed light can be the oscillation wavelength of an ArF excimer laser or a KrF excimer laser.

[0080] Furthermore, upon receiving the emission trigger Trt, the laser processor 80 sends the emission trigger Tr2 to the switch 59 of the PPM 58 , so that discharge occurs between the discharge electrodes 64 and 65 when the seed light output from the OSC 20 enters the discharge space of the cavity 54 of the AMP 50 .

[0081] 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 cavity 54 .

[0082] As a result, discharge occurs between discharge electrodes 64 and 65 in cavity 54, exciting the laser gas. At this point, seed light output from OSC 20 passes through RM 52 and enters the discharge space in cavity 54. The incident seed light is amplified by the optical resonator formed by RM 52 and OC 56 and output from AMP 50.

[0083] The pulsed laser light output from AMP 50 enters monitor module 70. Part of the pulsed laser light entering monitor module 70 is reflected by beam splitter 72, and part of it is reflected by beam splitter 74 and enters spectrum detector 76. The pulsed laser light that has passed through beam splitter 74 enters optical sensor 78.

[0084] 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.

[0085] The laser processor 80 can control the rotating stage 44 in the LNM 22 so that the central wavelength measured by the spectrum detector 76 becomes the target central wavelength λt. The rotating stage 44 can be a rotating stage including a piezoelectric element.

[0086] The laser processor 80 can 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.

[0087] 2.2 Laser Management System

[0088] 2.2.1 Structure

[0089] Figure 2 This diagram shows the structure of a comparative example laser management system 100. The comparative example disclosed herein is a method known only to the applicant and is not a publicly known example acknowledged by the applicant. The laser management system 100 performs at least one of management, monitoring, and analysis of the laser device 10.

[0090] The laser management system 100 includes a laser device 10 , a work data server 104 , a laser management server 110 , and a terminal 150 .

[0091] The operation data server 104 is a data server that stores the operation data of the laser device 10 .

[0092] The terminal 150 is, for example, a personal computer, a smartphone, or a tablet.

[0093] The laser management server 110 includes a standard software processor (SSP) 128 storing the standard software 122 .

[0094] The SSP 128 obtains the operating data of the laser device 10 from the operating data server 104 via the network.

[0095] The standardization software 122 is provided in the form of a web application that operates via a network.

[0096] The standardization operation screen 124 of the standardization software 122 is displayed on the terminal 150 and is generated in a manner that allows user operation.

[0097] 2.2.2 Action

[0098] The laser device 10 transmits the operation data to the operation data server 104 , and the operation data server 104 accumulates the operation data.

[0099] The laser management server 110 receives a request for browsing predetermined information from the user through the standard operation screen 124 .

[0100] The calibration software 122 of the laser management server 110 uses the stored operation data to perform analysis of a specific laser device 10. The calibration software 122 provides the user with at least one of the predetermined functions of management, monitoring, and analysis of the laser device 10.

[0101] The calibration software 122 of the laser management server 110 displays the requested information and the like on the calibration operation screen 124 .

[0102] The user browses information on the setting operation screen 124 .

[0103] Different standardized software 122 or standardized operation screens 124 are provided according to the needs of different users such as field service engineers (FSE), device owners, and researchers.

[0104] 2.2.3 Topics

[0105] When controlling the laser device 10, such as by changing parameters, the FSE accesses the operating data server 104, which stores the operating data of the laser device 10, via the standardized operation screen 124 and queries the operating data within the operating data server 104. The FSE then determines control values ​​for parameter changes to the laser device 10, among other things. At this point, the FSE estimates the number of pulses, or its evolution over time (laser performance), as future laser characteristics, as well as future laser performance after the parameter changes. Examples of laser characteristics include the pulse energy, central wavelength, spectral linewidth, cavity pressure, applied voltage between electrodes, and the number of pulses used by various components of the pulsed laser output from the laser device 10. Laser performance can include indicators related to the performance of the laser device 10.

[0106] However, even for an experienced FSE, it is difficult to estimate the future laser performance of the laser device 10 .

[0107] Furthermore, if there is a discrepancy in the information acquired by the FSE, the control signal of the laser device 10 may deviate and become unstable.

[0108] 3. Implementation Method 1

[0109] 3.1 Structure

[0110] Figure 3 : is a diagram showing a laser management system 100A according to the first embodiment. Figure 3 The structure shown is Figure 2 The differences are explained.

[0111] Comparing laser management system 100A and laser management system 100, differences exist in the configuration within laser management server 110A, the connection between laser management server 110A, document server 106, and AI prediction processing device 108, and the transmission of control signals such as parameter changes from laser management server 110A to laser device 10. Furthermore, the term "management" in this disclosure encompasses the concept of "control."

[0112] 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 behavior processor (AAP) 136, an equipment agent processor (EAP) 138 and an equipment control processor (ECP) 140.

[0113] SRP130, QIP132, LLM134, AAP136, EAP138, and ECP140 can be application software or hardware such as a CPU. The various application software can also be installed as a single processor.

[0114] Input and output by the user are performed on the interactive operation screen 126 of the terminal 150 via the SRP 130 .

[0115] The SRP 130 performs input and output on the interactive operation screen 126 of the terminal 150 .

[0116] The ECP 140 is capable of communicating with the laser device 10 .

[0117] The document server 106 stores unstructured data such as manuals and maintenance reports of the laser device 10. The document server 106 includes a laser device technical document database (Database: DB).

[0118] 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 .

[0119] The life prediction model may be, for example, a learned model generated using the machine learning method described in Patent Document 3. The machine learning method described in Patent Document 3 generates a learning model for predicting the life of consumables in laser device 10. The machine learning method includes the following steps: obtaining first life-related information, which includes data on parameters related to the life of the consumables, corresponding to different numbers of oscillation pulses from the time the consumables are used until they are replaced; dividing the first life-related information into multiple levels representing the degree of degradation of the consumables based on the number of oscillation pulses, and generating training data that associates the first life-related information with the levels representing the degree of degradation; performing machine learning using the training data to generate a learning model that predicts the degree of degradation of the consumables based on the data on the life-related parameters; and storing the generated learning model. For each consumable scheduled for replacement in laser device 10, the corresponding life prediction model is used based on the life-related information of the consumables, thereby enabling the AI ​​prediction processing device 108 to predict the life of each consumable scheduled for replacement.

[0120] The learning model is, for example, a neural network model, and is actually a program that causes a computer to execute a process of predicting the degree of degradation of consumables of the laser device 10 .

[0121] The AI ​​prediction processing device 108 can predict the life of each consumable scheduled to be replaced in the laser device 10 by using a corresponding life prediction model based on the life-related information of the consumable.

[0122] The laser performance prediction model is a learned model that can predict the future transition of the laser performance of the laser device 10 corresponding to the number of pulses or date and time in any component replacement scenario.

[0123] At least one of the work data server 104 and the document server 106 may also be installed inside the laser management server 110A.

[0124] The terminal 150 may be connected to the laser management server 110A via a network, or may be connected via a wired or wireless connection.

[0125] The interactive operation screen 126 of the terminal 150 may also be displayed on the monitor screen of the laser management server 110A.

[0126] Other structures can be Figure 2 same.

[0127] 3.2 Action

[0128] 3.2.1 Action flow of laser management system

[0129] Figure 4 This is a diagram showing the operation flow of the laser management system 100A according to the first embodiment. Figure 4 The operation flow of the laser management system 100A will be described.

[0130] SRP 130 receives query W0 from terminal 150 .

[0131] The QIP 132 decomposes the query W0 received from the SRP 130 to generate a first query item W1 requiring external information and a second query item W2 requiring no external information.

[0132] Figure 5 FIG is a diagram showing an example of query items generated based on a user's query. Figure 5 The figure shows an example of generating the first query item W1 and the second query item W2 when the query W0 is "Change the target value of the cavity gas pressure in order to extend the cavity life of the OSC of laser 65400011 by 2 Bpls." Note that "Laser 65400011" is the name that identifies the model of the laser.

[0133] In this case, QIP 132 decomposes the received query W0 into six query items. Query item 1 is "Information about the model of laser 65400011," query item 2 is "Information about changes in cavity gas pressure of laser 65400011," query item 3 is "Determination of cavity gas pressure change based on the information," query item 4 is "Analysis of operating data of laser 65400011," query item 5 is "Prediction of performance when the target gas pressure value is changed," and query item 6 is "Determination of the target gas pressure value based on the information."

[0134] Of these six inquiry items, item numbers 1, 2, 4, and 5 are difficult to answer appropriately using only LLM 134 and require external information to obtain an appropriate answer. Therefore, they are classified as first inquiry item W1. Item numbers 3 and 6 do not require external information to answer and are classified as second inquiry item W2.

[0135] In this case, external information refers to information stored in at least one of the work data server 104, the document server 106, and the AI ​​prediction processing device 108. The criterion for determining whether an inquiry item requires external information is, for example, whether LLM 134 can generate a highly accurate response independently. For inquiry items classified as the first inquiry item W1, it is difficult for LLM 134 to generate a highly accurate response independently. For inquiry items classified as the second inquiry item W2, LLM 134 can generate a highly accurate response independently. A highly accurate response is one that is based on facts and has few misidentifications or errors.

[0136] In addition, depending on the content of the inquiry W0 received from the SRP 130 , only one of the first inquiry item W1 and the second inquiry item W2 may be generated.

[0137] The QIP 132 sends the second query item W2 to the EAP 138 .

[0138] The QIP 132 transmits the first query item W1 to the AAP 136. The first query item W1 may also be transmitted to the EAP 138 because it is used to confirm external information.

[0139] AAP 136 receives the first query item W1 from QIP 132 and assigns the corresponding external information processing program to the first query item W1. The external information processing program obtains the required information from the external device (at least one of the work data server 104, document server 106, and AI prediction processing device 108), analyzes the obtained information, and summarizes the results.

[0140] For example, for Figure 5 For the first query item W1 of item number 2, AAP 136 obtains the manual of laser 65400011 from the document server 106, analyzes it, and summarizes the results. Figure 5 For the first query item W1 of item number 4, AAP136 obtains the applied voltage (HV) between the discharge electrodes 46 and 47 in the cavity 24 of the OSC20 of the laser 65400011, the gas pressure in the cavity 24 of the OSC20, and the total number of device shots from the work data server 104, analyzes them, and summarizes the results. Figure 5 In the first inquiry item W1 of item number 5, AAP136 obtains the working data of the laser 65400011 from the working data server 104, and sends the obtained working data to the AI ​​prediction processing device 108. The laser performance prediction model of the AI ​​prediction processing device 108 obtains the prediction results of the laser performance such as the applied voltage (HV) or gas pressure between the discharge electrodes 46 and 47 in the cavity 24 of the OSC20 when the target value of the gas pressure in the cavity of the OSC20 is changed based on the working data, analyzes the obtained results, and summarizes the results.

[0141] The AAP 136 executes all assigned external information processing programs. The AAP 136 performs external information composition processing to aggregate all information and generates the first agent response W3. At this time, the AAP 136 can also perform processing while communicating with the LLM 134 as needed.

[0142] AAP 136 sends the first agent response W3 to EAP 138 .

[0143] The EAP 138 receives the second inquiry item W2 from the QIP 132 and the first agent response W3 from the AAP 136 .

[0144] EAP 138 may also receive the first agent response W3 from AAP 136 and confirm whether it contains the required information.

[0145] EAP138 generates the first inquiry item prompt word W4 related to the response to the second inquiry item W2. Figure 5 The first inquiry item prompt word W4 related to the second inquiry item W2 of item number 3 includes, for example, the manual of the laser device 10 and the prompt word "information on a method for changing the target value of the cavity gas pressure of the OSC of the laser 65400011".

[0146] The LLM 134 receives the first inquiry item presentation word W4 from the EAP 138 and generates a first inquiry item response W5 as a response to the first inquiry item presentation word W4. Figure 5 The first inquiry item response W5 of the first inquiry item prompt word W4 of the second inquiry item W2 of item number 3 is, for example, "a method for changing a target value of the gas pressure of the cavity of the OSC of the laser 65400011".

[0147] Based on the first query item response W5 and the first agent response W3, the EAP 138 generates a first control signal W6 for the laser device 10. The first control signal W6 is, for example, a control signal that means "change the target value of the OSC cavity gas pressure from P1 to P2."

[0148] The EAP 138 transmits the generated first control signal W6 to the ECP 140 .

[0149] 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 .

[0150] 3.2.2 Laser device control process

[0151] Figure 6 This is a flowchart showing an example of controlling the laser device 10 by the laser management server 110A according to the first embodiment. Figure 6 The method of steps S1 to S7 shown is an example of the “laser management method” in the present disclosure.

[0152] In step S1, SRP 130 receives a query W0 from the outside. Step S1 is an example of "first step" in the present disclosure.

[0153] In step S2, the QIP 132 decomposes the query W0 to generate a first query item W1 requiring external information and a second query item W2 requiring no external information. Step S2 is an example of the "second step" in the present disclosure.

[0154] In step S3, AAP 136 receives the first query W1 from QIP 132, obtains required information from unstructured data and structured data, and generates a first agent response W3 as a response to the first query W1. The unstructured data includes the manual and maintenance report of the laser device 10, and the structured data includes at least one of the following: operating data of the laser device 10, a lifespan prediction result of consumables of the laser device 10 based on a lifespan prediction model, and a laser performance prediction result of the laser device 10 based on a laser performance prediction model. Step S3 is an example of the "third step" in the present disclosure.

[0155] In step S4, the EAP 138 receives the second query item W2 from the QIP 132 and the first agent response W3 from the AAP 136, and generates a first query item prompt word W4 related to the second query item W2. Step S4 is an example of the "fourth step" in the present disclosure.

[0156] In step S5 , the LLM 134 receives the first inquiry item presentation word W4 from the EAP 138 and generates a first inquiry item response W5 as a response to the first inquiry item presentation word W4 . Step S5 is an example of the “fifth step” in the present disclosure.

[0157] 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 "step 6" in the present disclosure.

[0158] 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 the present disclosure.

[0159] 3.3 Function / Effect

[0160] According to the laser management system 100A, the laser performance prediction model can be used to predict the future laser performance change of the laser device 10. Therefore, the FSE can easily estimate the future laser performance of the laser device 10.

[0161] In the laser management system 100A, the QIP 132 decomposes the query W0 into a first query item W1 requiring external information and a second query item W2 not requiring external information. Then, in the laser management system 100A, the AAP 136 obtains the required external information, and the EAP 138 generates a first control signal W6 for the laser device 10 based on the obtained external information. Consequently, the laser management system 100A can stably obtain valid information and maintain stable control of the laser device 10.

[0162] 4. Modification of Implementation 1

[0163] 4.1 Structure

[0164] Figure 7 : is a diagram showing the structure of a laser management system 100B according to a modified example of the first embodiment. Figure 7 The structure shown is Figure 3 The differences are explained.

[0165] When comparing the laser management system 100A and the laser management system 100B, the differences are that the QIP 132 communicates with the LLM 134, the AAP 136 communicates with the LLM 134, and the EAP 138 communicates with the SRP 130. Other structures can be Figure 3 The structure of the laser management system 100A shown is the same.

[0166] 4.2 Action

[0167] Figure 8 : is a diagram showing the operation flow of the laser management system 100B. Figure 8 The operation flow of the laser management system 100B shown in FIG. Figure 4 The differences are explained.

[0168] When performing language processing in generating the first inquiry item W1 and the second inquiry item W2, the QIP 132 may generate a sorting prompt word W7. For example, the sorting prompt word W7 may be "decompose the inquiry and divide it into items."

[0169] LLM134 can receive the sorting prompt word W7 from QIP132 and generate a sorting response W8 as a response to the sorting prompt word W7. The sorting response W8 is, for example, Figure 5 The query items after such item division are shown.

[0170] QIP 132 may receive a sort response W8 from LLM 134 .

[0171] AAP 136 may also generate unstructured data prompt words W9 when acquiring unstructured data and generating the first agent response W3. Unstructured data prompt words W9 may include, for example, external information from the manual of laser device 10 and prompt words such as "a section describing how to change the target value of the gas pressure in the OSC cavity of laser device 65400011."

[0172] LLM 134 may also receive unstructured data prompt word W9 from AAP 136 and generate unstructured data response W10 as a response to unstructured data prompt word W9. Unstructured data response W10 may include, for example, "The method for changing the target value of the cavity gas pressure of the OSC of laser 65400011 is described on page AA, line BB, to page CC, line DD."

[0173] The AAP 136 may also receive the unstructured data response W10 from the LLM 134. The AAP 136 generates the first agent response W3 by analyzing the unstructured data response W10 received from the LLM 134. In this case, the AAP 136 dispatches an appropriate external information processing program and generates the first agent response W3 based on the result.

[0174] The EAP 138 may also transmit the first control signal W6 to the SRP 130 .

[0175] 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 .

[0176] EAP138 may also transmit the first agent response W3 or the first query item response W5 to SRP130. EAP138 may also 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 SRP130. EAP138 may also combine the first agent response W3 (generated by AAP136) and the first query item response W5 (generated by LLM134) to generate a query response. SRP130 may also transmit at least one of the first agent response W3, the first query item response W5, and the query response received from EAP138 to terminal150. At least one of the first agent response W3, the first query item response W5, and the query response may also be displayed on the interactive operation screen 126 of terminal150.

[0177] The interactive operation screen 126 of the terminal 150 may also display messages for the user. The message may include suggestions related to at least one of the first control signal W6, the first agent response W3, the first query item response W5, and the query response. Furthermore, the suggestions may include diagrams, charts, and 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 purpose of the query W0 is at least one of the functions of management, monitoring, and analysis.

[0178] Other actions can be combined with Figure 4 same.

[0179] 4.3 Action / Effect

[0180] The laser management system 100B has the same effects as the laser management system 100A.

[0181] According to the laser management system 100B, the language processing function is further improved in the QIP 132 and the AAP 136 as compared to the laser management system 100A.

[0182] 5. Implementation Method 2

[0183] 5.1 Structure

[0184] The structure of the laser management system according to the second embodiment may be the same as that of the laser management system 100B.

[0185] 5.2 Action

[0186] Figure 9 This is a flowchart showing an example of controlling the laser device 10 by the laser management server according to the second embodiment. Figure 9 , for Figure 6 The differences are explained. Figure 9 In the embodiment, steps S8 to S12 are added after step S7.

[0187] After a predetermined time has passed since step S7, in step S8, the AAP 136 acquires the operating data of the laser device 10 after the first control signal W6 is transmitted. The operating data of the laser device 10 is stored in the operating data server 104. Step S8 is an example of the "eighth step" in the present disclosure.

[0188] In step S9, the AAP 136 generates a second agent response to the first query item W1. Step S9 is an example of "step 9" in this disclosure. The AAP 136 may also analyze the operating data of the laser device 10 to generate a second agent response to the first query item W1. Furthermore, the second agent response may differ from the first agent response W3.

[0189] In step S10, EAP 138 receives the second agent response from AAP 136 and determines whether 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 "step 10" in this disclosure.

[0190] 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 "eleventh step" in the present disclosure.

[0191] In step S12, the ECP 140 receives the second control signal from the EAP 138 and transmits the second control signal to the laser device 10. Step S12 is an example of "step 12" in the present disclosure.

[0192] The control process of steps S8 to S12 can be repeated multiple times.

[0193] Other steps can be Figure 6 same.

[0194] 5.3 Action / Effect

[0195] The laser management system according to the second embodiment has the same effects as those of the laser management system 100A and the laser management system 100B.

[0196] The laser management system of the second embodiment obtains the operation data of the laser device 10 after the first control signal W6 is transmitted and generates the second control signal as needed, thereby further stabilizing the control of the laser device 10 .

[0197] 6. Others

[0198] The above description is not limiting but merely illustrative. Therefore, those skilled in the art will appreciate that modifications can be made to the embodiments of the present disclosure without departing from the scope of the claims. Furthermore, those skilled in the art will appreciate that the embodiments of the present disclosure can be used in combination.

[0199] Unless otherwise expressly stated, the terms used in this specification and claims as a whole should be interpreted as “non-limiting” terms. For example, terms such as “including”, “having”, “having”, and “having” should be interpreted as “not excluding the presence of structural elements other than the structural elements described”. In addition, the modifier “one” should be interpreted as meaning “at least one” or “one or more”. In addition, terms such as “at least one of A, B, and C” should be interpreted as “A”, “B”, “C”, “A+B”, “A+C”, “B+C”, or “A+B+C”. It should be interpreted as further including combinations of these and parts other than “A”, “B”, and “C”.

Claims

1. A laser management server, which is a laser management server for a laser device, having: a transceiver processor that receives inquiries from the outside; a query input processor that receives the query from the transceiver processor, decomposes 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 behavior processor receiving the first inquiry item from the inquiry input processor, acquiring required information from unstructured data and structured data, and generating a first agent response as a response to the first inquiry item, wherein the unstructured data includes a manual and a maintenance report of the laser device, and the structured data includes at least one of operating data of the laser device, a predicted result of the life of consumables of the laser device based on a life prediction model, and a predicted result of laser performance of the laser device based on a laser performance prediction model; a device agent processor receiving the second inquiry item from the inquiry input processor and the first agent response from the agent behavior processor, and generating an inquiry item prompt word related to the second inquiry item; as well as a large-scale language model processor that receives the query item prompt word from the device agent processor and generates a query item response as a response to the query item prompt word; The device agent processor receives the query item 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 item response. The laser management server further includes a device control processor, which receives the first control signal from the device agent processor and sends the first control signal to the laser device.

2. The laser management server according to claim 1, wherein: The agent behavior processor obtains the operating data of the laser device after the first control signal is sent, and generates a second agent response as a response to the first inquiry item. The device agent processor receives the second agent response from the agent behavior processor, and determines 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 receives the second control signal from the device agent processor and sends the second control signal to the laser device.

3. The laser management server according to claim 1, wherein: The query input processor generates a sorting prompt word when performing language processing in generating the first query item and the second query item. The large-scale language model processor receives the sorting prompt word from the query input processor, generates a sorting response as a response to the sorting prompt word, The query input processor receives the sorted response from the large-scale language model processor.

4. The laser management server according to claim 1, wherein: When the agent behavior processor obtains the unstructured data and generates the first agent response, it generates an unstructured data prompt word. The large-scale language model processor receives the unstructured data prompt word from the agent behavior processor and generates an unstructured data response as a response to the unstructured data prompt word; The agent behavior processor receives an unstructured data response from the large-scale language model processor.

5. The laser management server according to claim 4, wherein: The unstructured data prompt word includes the unstructured data.

6. The laser management server according to claim 1, wherein: The device agent processor sends the first control signal to the transceiver processor.

7. The laser management server according to claim 1, wherein: The transceiver processor receives the first control signal from the device agent processor and transmits the first control signal to the outside.

8. The laser management server according to claim 1, wherein: The transceiver processor receives the inquiry from a terminal connected via a network.

9. The laser management server according to claim 8, wherein: The inquiry is received from an interactive operation screen of the terminal.

10. The laser management server according to claim 9, wherein: The first control signal is displayed on the interactive operation screen of the terminal.

11. A laser management method for a laser device, comprising the following steps: In step 1, the transceiver processor receives an inquiry from the outside; In step 2, the query input processor decomposes the query to generate a first query item requiring external information and a second query item not requiring external information; In step 3, the agent behavior processor receives the first inquiry item from the inquiry input processor, obtains required information from unstructured data and structured data, and generates a first agent response as a response to the first inquiry item, wherein the unstructured data includes a manual and a maintenance report of the laser device, and the structured data includes at least one of operating data of the laser device, a predicted result of the life of consumables of the laser device based on a life prediction model, and a predicted result of laser performance of the laser device based on a laser performance prediction model. In step 4, the device agent processor receives the second inquiry item from the inquiry input processor and the first agent response from the agent behavior processor, and generates an inquiry item prompt word related to the second inquiry item; In step 5, the large-scale language model processor receives the query item prompt word from the device agent processor and generates a query item response as a response to the query item prompt word; In step 6, the device agent processor receives the query item 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 item response; and In step 7, the device control processor receives the first control signal from the device agent processor and sends the first control signal to the laser device.

12. The laser management method according to claim 11, wherein: The laser management method further comprises the following steps: In step 8, the agent behavior processor obtains the operating data of the laser device after sending the first control signal; In step 9, the agent behavior processor generates a second agent response as a response to the first query item; In step 10, the device agent processor receives the second agent response from the agent behavior processor, and determines whether the first control signal needs to be changed based on the second agent response. In step 11, if it is determined in step 10 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; as well as In step 12, the device control processor receives the second control signal from the device agent processor and sends the second control signal to the laser device.

13. The laser management method according to claim 11, wherein: The laser management method comprises the following steps: In the second step, the query input processor generates a sorting prompt word when performing language processing in generating the first query item and the second query item. The large-scale language model processor receives the sorting prompt word from the query input processor, generates a sorting response as a response to the sorting prompt word, The query input processor receives the sorted response from the large-scale language model processor.

14. The laser management method according to claim 11, wherein: The laser management method comprises the following steps: In the third step, when the agent behavior processor obtains the unstructured data and generates the agent response, an unstructured data prompt word is generated. The large-scale language model processor receives the unstructured data prompt word from the agent behavior processor, and generates an unstructured data response as a response to the unstructured data prompt word; The agent behavior processor receives an unstructured data response from the large-scale language model processor.

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

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

17. The laser management method according to claim 11, wherein: The laser management method comprises the following steps: In the sixth step, the transceiver processor receives the first control signal from the device agent processor and transmits the first control signal to the outside.

18. The laser management method according to claim 11, wherein: The first step comprises the following steps: The transceiver processor receives the inquiry from a terminal connected via a network.

19. The laser management method according to claim 18, wherein: The inquiry is received from an interactive operation screen of the terminal.

20. The laser management method according to claim 19, wherein: The first control signal is displayed on the interactive operation screen of the terminal.

Images