WO2024014251A1 - 情報処理方法、情報処理システム及びコンピュータプログラム - Google Patents

情報処理方法、情報処理システム及びコンピュータプログラム Download PDF

Info

Publication number
WO2024014251A1
WO2024014251A1 PCT/JP2023/023072 JP2023023072W WO2024014251A1 WO 2024014251 A1 WO2024014251 A1 WO 2024014251A1 JP 2023023072 W JP2023023072 W JP 2023023072W WO 2024014251 A1 WO2024014251 A1 WO 2024014251A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
integrated
information processing
intermediate representation
machine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2023/023072
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
淳 田村
剛 守屋
勇樹 片岡
暁 今倉
鉄也 櫻井
保徳 二村
秀彩 叶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tokyo Electron Ltd
University of Tsukuba NUC
Original Assignee
Tokyo Electron Ltd
University of Tsukuba NUC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tokyo Electron Ltd, University of Tsukuba NUC filed Critical Tokyo Electron Ltd
Priority to KR1020257004004A priority Critical patent/KR20250040000A/ko
Priority to CN202380052362.2A priority patent/CN119631092A/zh
Priority to JP2024533609A priority patent/JPWO2024014251A1/ja
Publication of WO2024014251A1 publication Critical patent/WO2024014251A1/ja
Priority to US19/016,213 priority patent/US20250147498A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41845—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by system universality, reconfigurability, modularity
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/45—Nc applications
    • G05B2219/45031—Manufacturing semiconductor wafers

Definitions

  • the present invention relates to an information processing method, an information processing system, and a computer program.
  • the present disclosure aims to provide an information processing method, an information processing system, and a computer program that can collect data from multiple devices in a concealed state called intermediate representation, and perform machine difference correction and construction of a prediction model.
  • a first intermediate representation obtained by applying an intermediate representation conversion function to first data individually used in a plurality of devices is obtained from each device, and a first intermediate representation is obtained from each device.
  • a second intermediate representation obtained by applying the intermediate representation conversion function to commonly used second data is obtained from each device, and the integrated representation conversion function is applied to each of the second intermediate representations obtained from each device.
  • the parameters of the integrated representation transformation function are adjusted so as to minimize the difference between the integrated representations obtained by Based on this, a computer executes a process of deriving a machine difference correction function for correcting machine differences between the plurality of devices.
  • data can be collected from multiple devices in a concealed state called intermediate representation, and machine difference correction and prediction models can be constructed.
  • FIG. 1 is a schematic diagram showing a configuration example of an information processing system according to an embodiment.
  • FIG. 2 is a block diagram showing the internal configuration of an operating institution server.
  • FIG. 2 is a block diagram showing the internal configuration of an analysis engine server. It is an explanatory diagram explaining an outline of processing in a training phase.
  • 3 is a flowchart illustrating a process execution procedure in a training phase.
  • 3 is a flowchart illustrating a process execution procedure in an operation phase.
  • 7 is a flowchart showing the procedure of processing executed by the analysis engine server according to the second embodiment.
  • FIG. 1 is a schematic diagram showing a configuration example of an information processing system according to an embodiment.
  • the information processing system according to the embodiment includes a plurality of operation agency servers 100-1, 100-2, ..., 100-n installed in a plurality of device operation agencies MF1, MF2, ..., MFn, respectively, and an analysis agency AF. and an analysis engine server 200 installed at. n is an integer of 2 or more.
  • the operating agency servers 100-1, 100-2, . . . , 100-n and the analysis agency server 200 are each communicably connected via a communication network NW.
  • the operating institution server 100-1 is a server device installed in the device operating institution MF1.
  • the device operating organization MF1 operates the device 120-1. In the example of FIG. 1, only one device 120-1 is shown for the sake of simplicity, but the number of devices operated by the device operating organization MF1 may be two or more.
  • An example of the equipment operating organization MF1 is a semiconductor manufacturing manufacturer, and an example of the equipment 120-1 is a semiconductor manufacturing equipment.
  • the operating institution server 100-1 holds data (first data) used individually by the device 120-1 and data (second data) commonly used by the plurality of device operating institutions MF1 to MFn.
  • first data used individually by the device 120-1
  • second data commonly used by the plurality of device operating institutions MF1 to MFn.
  • data used individually by the device 120-1 will also be referred to as raw data
  • data commonly used by each institution will also be referred to as anchor data.
  • Raw data may contain confidential information that cannot be provided to other institutions.
  • the equipment 120-1 of the equipment operating organization MF1 is a semiconductor manufacturing equipment
  • the raw data includes at least one of substrate measurement result data before substrate processing, time series data during substrate processing, and substrate measurement result data after substrate processing. Including one.
  • the operating agency server 100-1 cannot provide raw data to the analysis agency server 200 from the viewpoint of information anonymity. Therefore, when providing raw data to the analysis agency server 200, the operating agency server 100-1 converts the raw data into an intermediate representation using the intermediate representation conversion function F 1 unique to its own server, and The expression is provided to the analysis engine server 200.
  • the operating agency server 100-1 converts the anchor data into an intermediate representation using the same intermediate representation conversion function F1 , and uses the intermediate representation of the converted anchor data together with the intermediate representation of the raw data after the conversion to the analysis agency server 100-1. 200.
  • the intermediate representation of raw data will also be referred to as raw data intermediate representation
  • the intermediate representation of anchor data will also be referred to as anchor data intermediate representation.
  • the operating institution server 100-i (i is an integer from 2 to n) holds raw data used individually by the devices 120-i and anchor data commonly used by each institution. Further, the operating agency server 100-i converts the raw data and anchor data into intermediate representations using respective intermediate representation conversion functions F i and provides the intermediate representations to the analysis agency server 200.
  • the analysis engine server 200 is a server device provided in the analysis engine AF.
  • the analysis engine server 200 acquires the raw data intermediate representation and the anchor data intermediate representation from each operation engine server 100-1, 100-2, . . . , 100-n.
  • the analysis engine server 200 generates an instrument difference correction function and a prediction model based on the raw data intermediate representation obtained from each operation engine server 100-1, 100-2, . . . , 100-n.
  • the mechanical difference correction function is a function for correcting the mechanical differences of each device 120-1, 120-2, . . . , 120-n, and can be derived based on the raw data intermediate representation.
  • the prediction model is a model that outputs estimated values of response data in each device 120-1, 120-2, ..., 120-n when raw data is input, and is based on machine difference correction functions and raw data intermediate representations. It is possible to derive
  • the analysis engine server 200 provides the generated machine difference correction function and prediction model to each operation engine server 100-1, 100-2, . . . , 100-n.
  • FIG. 2 is a block diagram showing the internal configuration of the operating institution server 100.
  • the operating institution server 100 is a dedicated or general-purpose server, and includes a control section 101, a storage section 102, a connection section 103, a communication section 104, an operation section 105, a display section 106, and the like.
  • the control unit 101 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.
  • the ROM included in the control unit 101 stores control programs and the like that control the operations of each hardware unit included in the operating institution server 100.
  • the CPU in the control unit 101 reads and executes the control program stored in the ROM and various computer programs stored in the storage unit 102, and controls the operation of each hardware part, thereby controlling the entire apparatus according to the present disclosure.
  • the server is made to function as the operating institution server 100.
  • the RAM included in the control unit 101 temporarily stores data used during execution of calculations.
  • control unit 101 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 101 is not limited to the above.
  • the control unit 101 includes one or more control circuits or arithmetic operations including, for example, a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, a volatile or nonvolatile memory, etc. It may also be a circuit.
  • the control unit 101 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given until a measurement end instruction is given, and a counter that counts the number of measurements.
  • the storage unit 102 includes storage devices such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), and an EEPROM (Electronically Erasable Programmable Read Only Memory).
  • the storage unit 102 stores various computer programs executed by the control unit 101 and various data used by the control unit 101.
  • the connection unit 103 includes a connection interface for connecting the device 120-1 (or 120-2 to 120-n).
  • the connection interface may be a wired interface or a wireless interface.
  • the operating agency server 100 acquires raw data from the device 120-1 connected to the connection unit 103.
  • the communication unit 104 includes a communication interface for transmitting and receiving various data to and from external devices including the analysis engine server 200.
  • a communication interface included in the communication unit 104 for example, a communication interface compliant with a communication standard such as LAN (Local Area Network) can be used.
  • LAN Local Area Network
  • the operation unit 105 includes operation devices such as a touch panel, a keyboard, and switches, and accepts various operations and settings by a user and the like.
  • the control unit 101 performs appropriate control based on various types of operation information given from the operation unit 105, and stores setting information in the storage unit 102 as necessary.
  • the display unit 106 includes a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence), and displays information to be notified to the user in accordance with instructions from the control unit 101.
  • a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence)
  • the operating institution server 100 in this embodiment may be a single server, or may be a server system composed of multiple servers, peripheral devices, and the like. Furthermore, the operating institution server 100 may be a virtual machine or may be a cloud. Furthermore, the operating institution server 100 may be provided in each device 120-1, 120-2, . . . , 120-n.
  • FIG. 3 is a block diagram showing the internal configuration of the analysis engine server 200.
  • the analysis engine server 200 is a dedicated or general-purpose server, and includes a control section 201, a storage section 202, a communication section 203, an operation section 204, a display section 205, and the like.
  • the control unit 201 includes a CPU, ROM, RAM, etc.
  • the ROM included in the control unit 201 stores control programs and the like that control the operations of each hardware unit included in the analysis engine server 200.
  • the CPU in the control unit 201 reads and executes the control program stored in the ROM and various computer programs stored in the storage unit 202, and controls the operation of each hardware part, thereby controlling the entire apparatus according to the present disclosure.
  • the analysis engine server 200 is made to function as an analysis engine server 200.
  • the RAM included in the control unit 201 temporarily stores data used during execution of calculations.
  • control unit 201 has a configuration including a CPU, a ROM, and a RAM, but the configuration of the control unit 201 is not limited to the above.
  • the control unit 201 may be one or more control circuits or arithmetic circuits including, for example, a GPU, an FPGA, a DSP, a quantum processor, a volatile or nonvolatile memory, or the like.
  • the control unit 201 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given until a measurement end instruction is given, and a counter that counts the number of measurements.
  • the storage unit 202 includes a storage device such as an HDD, SSD, or EEPROM.
  • the storage unit 202 stores various computer programs executed by the control unit 201 and various data used by the control unit 201.
  • the computer program stored in the storage unit 202 includes a model generation program PG (program product )including. Further, the data stored in the storage unit 202 includes data (parameters) of the machine difference correction function, intermediate representation conversion function, integrated representation conversion function, and prediction model generated by the model generation program PG. Furthermore, the storage unit 202 stores data (intermediate representations of explanatory variables, objective variables, intermediate representations of anchor data, etc.) transmitted from the operating institution server 100.
  • PG program product
  • the computer program stored in the storage unit 202 is provided by a non-temporary recording medium RM2 that readably records the computer program.
  • the recording medium RM2 is a portable memory such as a CD-ROM, a USB memory, an SD (Secure Digital) card, a micro SD card, or a Compact Flash (registered trademark).
  • the control unit 201 reads various computer programs from the recording medium RM2 using a reading device (not shown), and stores the read various computer programs in the storage unit 202. Further, the computer program stored in the storage unit 202 may be provided through communication. In this case, the control unit 201 may acquire the computer program through communication via the communication unit 203 and store the acquired computer program in the storage unit 202.
  • the communication unit 203 includes a communication interface for transmitting and receiving various data to and from external devices including the operating institution server 100.
  • a communication interface for example, a communication interface compliant with a communication standard such as LAN can be used.
  • the communication unit 203 transmits the data to the destination external device, and when receiving data transmitted from the external device, outputs the received data to the control unit 201. do.
  • the operation unit 204 includes operation devices such as a touch panel, a keyboard, and switches, and accepts various operations and settings from a user and the like.
  • the control unit 201 performs appropriate control based on various types of operation information given from the operation unit 204, and stores setting information in the storage unit 202 as necessary.
  • the display unit 205 includes a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence), and displays information to be notified to the user etc. in accordance with instructions from the control unit 201.
  • a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence), and displays information to be notified to the user etc. in accordance with instructions from the control unit 201.
  • analysis engine server 200 in this embodiment may be a single server, or may be a server system composed of multiple servers, peripheral devices, and the like. Furthermore, the analysis engine server 200 may be a virtual machine or a cloud.
  • the information processing system creates an machine difference correction function and a prediction model in a training phase before the start of operation, and generates response data using the prediction model in the operation phase after the start of operation. Make an estimate.
  • FIG. 4 is an explanatory diagram illustrating an overview of processing in the training phase.
  • the number of equipment operating organizations is two, and the equipment operating organization MF1 is referred to as "equipment operating organization 1" and the equipment operating organization MF2 is referred to as “equipment operating organization 2.”
  • the device 120-1 is operating in the device operating organization MF1
  • raw data is obtained from the device 120-1.
  • the raw data includes explanatory variables and objective variables.
  • the explanatory variables include cumulative usage time, power supply voltage, temperature, pressure, etc.
  • the objective variables include the degree of component wear.
  • the explanatory variable obtained by the device operating organization MF1 is expressed as X1
  • the objective variable is expressed as Y1 .
  • Raw data including the explanatory variable X 1 and the objective variable Y 1 are collected at any time during the training phase and are stored in the storage unit 102 of the operating agency server 100-1.
  • raw data (explanatory variable X 2 and objective variable Y 2 ) obtained during operation of device 120-2 is accumulated in storage unit 102 of operating agency server 100-2.
  • the anchor data X anc in the figure is anchor data common to the device operating organizations MF1 and MF2.
  • the anchor data X anc has the same number of dimensions as the explanatory variables, and is generated by the device operating organizations MF1 and MF2 using the same random number seed so as to have at least about 1000 records.
  • Intermediate representation conversion functions F 1 and F 2 are provided in the operating agency servers 100-1 and 100-2, respectively.
  • the intermediate representation conversion functions F 1 and F 2 are functions prepared separately in the operating agency servers 100-1 and 100-2, and, for example, principal component conversion functions in principal component analysis can be used.
  • the operating agency servers 100-1 and 100-2 convert them into intermediate representations using intermediate representation conversion functions F 1 and F 2 , respectively.
  • the explanatory variables of the raw data are converted into intermediate representations, but the target variables are not converted into intermediate representations.
  • intermediate representations obtained by applying the intermediate representation conversion function F 1 to the explanatory variable X 1 and the anchor data X anc are expressed as X 1 _tilde and X 1 anc _tilde, respectively.
  • intermediate representations obtained by applying the intermediate representation conversion function F 2 to the explanatory variable X 2 and the anchor data X anc are respectively written as X 2 _tilde and X 2 anc _tilde.
  • ..._tilde in the specification represents a character with a tilde.
  • the analysis agency server 200 receives the intermediate representation X 1 _tilde of the explanatory variable X 1 , the objective variable Y 1 , and the intermediate representation X 1 anc _tilde of the anchor data to be memorized. Similarly, the analysis agency server 200 receives the intermediate representation X 2 _tilde of the explanatory variable X 2 , the objective variable Y 2 , and the intermediate representation X 2 anc _tilde of the anchor data X anc transmitted from the operation agency server 100-2, The information is stored in the storage unit 202.
  • the analysis agency server 200 is provided with integrated expression conversion functions G 1 and G 2 for each device operating agency.
  • Integrated representation conversion functions G 1 and G 2 are integrated representation conversion functions for intermediate representations X 1 anc _tilde and X 2 anc _tilde of anchor data This is a function generated by applying G 1 and G 2 and adjusting the parameters of each integrated expression conversion function G 1 and G 2 so as to minimize the difference between the obtained integrated expressions.
  • the analysis engine server 200 converts the intermediate representation X 1 _tilde of the explanatory variable and the intermediate representation X 1 anc _tilde of the anchor data into an integrated representation, respectively, using the integrated representation conversion function G 1 for the device operating organization MF1.
  • the integrated expressions after conversion are written as X 1 _hat and X 1 unc _hat, respectively.
  • the analysis engine server 200 also converts the intermediate representation X 2 _tilde of the explanatory variable and the intermediate representation X 2 anc _tilde of the anchor data into an integrated representation, respectively, using the integrated representation conversion function G 2 for the device operating organization MF2.
  • the integrated expressions after conversion are written as X 2 _hat and X 2 unc _hat, respectively.
  • the integrated representation is also called a DC (Data Collaboration) representation.
  • ...-hat in the specification represents a character with a hat.
  • the analysis engine server 200 By converting the data into an integrated representation in the analysis agency server 200, it is possible to integrate the data used individually by each device operating agency as one data. However, if there is a difference between the devices (in this example, between the devices 120-1 and 120-2), there is a possibility that analysis performance will be degraded by integrating the data with the difference. Therefore, the analysis engine server 200 according to the present embodiment corrects the machine difference between the machines by using the integrated expressions X 1 _hat and X 2_hat of the raw data (explanatory variables) generated by each machine operating institution. Derive the machine difference correction function.
  • the analysis engine server 200 sets a problem of classifying the original engine from the integrated data, and derives a correction function by finding the machine difference correction value that makes classification difficult. Assuming that the explanatory variables of the raw data have a multivariate normal distribution, the difference in variance and covariance is corrected using a rotation matrix (including scale), and the difference in means is corrected using a shift.
  • the classification problem can be expressed as shown in Equation 1.
  • the equipment operating organization MF1 is the reference organization
  • the equipment operating organization MF2 is the target organization for machine difference correction.
  • the matrices X, F, and G in Equation 1 represent explanatory variables, intermediate representation conversion functions, and integrated representation conversion functions of raw data in each institution, respectively, and the subscript represents the institution number.
  • the matrices D and S in Equation 1 are a rotation matrix and a shift matrix, respectively, and are applied to the raw data of the device operating organization MF2 to correct the shift machine difference and the variance-covariance machine difference.
  • W is a classifier.
  • the analysis engine server 200 calculates the classification error by solving a classification problem using the integrated data of the equipment operating organization MF1 as a positive example and the integrated data of the equipment operating organization MF2 that has been corrected for machine differences as a negative example.
  • the analysis engine server 200 estimates the machine difference by optimizing the matrices D and S that give the maximum classification error using the quasi-Newton method or the like.
  • the rotation matrix D can be expressed as a linear combination of s rotation matrices, and the coefficient matrix ⁇ i for the rotation matrix D i is the variance-covariance of the i-th explanatory variable.
  • the shift matrix S can be expressed as a linear combination of s diagonal matrices whose diagonal elements are orthogonal basis vectors, and the shift matrix S for which the coefficient ⁇ i for the diagonal matrix S i is included in the i-th explanatory variable There will be machine differences.
  • Equation 3 ⁇ i and ⁇ i can be taken out of the intermediate representation as shown in Equation 3, so the machine difference correction function can be generated by the analysis engine AF without sharing the raw data. Furthermore, by applying a correction function to the intermediate representation and converting it into integrated data, integrated analysis that removes the influence of machine differences becomes possible.
  • the analysis engine server 200 can generate training data that is a set of a device-independent explanatory variable X_hat and a corresponding objective variable Y by applying the machine difference correction function and integrating the data.
  • the analysis engine server 200 uses training data including the explanatory variable X_hat and the objective variable Y to generate a prediction model that predicts the objective variable Y (response data) from the explanatory variable X.
  • the analysis engine server 200 can generate a prediction model using a known method such as linear regression. Alternatively, the analysis engine server 200 may generate the predictive model using other machine learning algorithms such as support vector machines, random forests, neural networks, etc.
  • FIG. 5 is a flowchart showing the procedure for executing processing in the training phase.
  • the control unit 101 of the operating institution server 100 generates common anchor data for each device operating institution MF1 to MFn, and stores the generated anchor data in the storage unit 102 (step S101).
  • the control unit 101 can generate common anchor data for each of the equipment operating organizations MF1 to MFn by using the same random number seed for each of the equipment operating organizations MF1 to MFn.
  • the control unit 101 stores raw data (explanatory variables and objective variables) obtained during the operation of the device in the storage unit 102 (step S102), and generates an intermediate representation conversion function based on the anchor data and explanatory variables (step S103). ).
  • the control unit 101 may generate, for example, a principal component conversion function in principal component analysis as the intermediate representation conversion function.
  • the control unit 101 generates intermediate representations of explanatory variables and anchor data (step S104), and sends the training data (intermediate representations of explanatory variables and objective variables) and intermediate representations of anchor data from the communication unit 104 to the analysis engine server 200. Transmit (step S105).
  • the control unit 201 of the analysis engine server 200 receives the training data and the intermediate representation of the anchor data through the communication unit 203, and stores these data in the storage unit 202 (step S106).
  • the analysis engine server 200 collects training data until the collection period elapses or until the number of collected data exceeds a predetermined number.
  • the control unit 201 generates an integrated representation conversion function based on the intermediate representation of the anchor data (step S107).
  • the control unit 201 applies the integrated representation conversion function for each institution to the anchor data intermediate representation of each device operating institution MF1 to MFn, and converts the integrated expression conversion function for each institution so as to minimize the difference between the obtained integrated expressions. By adjusting the parameters of , it is possible to generate an integrated representation conversion function for each institution.
  • the control unit 201 generates a machine difference correction function from the intermediate representation of the explanatory variables included in the training data (step S108).
  • the control unit 201 can derive the machine difference correction function using the intermediate representation of the explanatory variables, as shown in Equation 3.
  • the control unit 201 converts the intermediate representation of the explanatory variables included in the training data into an integrated representation by applying the integrated representation conversion function and the machine difference correction function (step S109).
  • the control unit 201 generates a predictive model using the converted integrated expression (explanatory variable) and the target variable included in the training data (step S110). For example, linear regression can be used to generate the predictive model, and other machine learning algorithms may also be used.
  • the control unit 201 transmits the generated integrated representation conversion function, machine difference correction function, and prediction model to each operating agency server 100 through the communication unit 203 (step S111).
  • the control unit 101 of the operating institution server 100 receives the integrated expression function, the machine difference correction function, and the prediction model transmitted from the analysis institution server 200, and stores them in the storage unit 102 (step S112).
  • FIG. 6 is a flowchart showing the processing execution procedure in the operation phase.
  • the control unit 101 of the operating agency server 100 acquires data (explanatory variables and objective variables) obtained during operation of the device (step S121).
  • the control unit 101 sequentially applies a machine difference correction function, an intermediate representation conversion function, and an integrated representation conversion function to the explanatory variables included in the acquired data to perform machine difference correction, conversion to an intermediate representation, and conversion to an integrated representation. Execute (steps S122 to S124).
  • the control unit 101 estimates the response data of the device by inputting the integrated expression obtained in step S124 into the prediction model (step S125).
  • the control unit 101 causes the display unit 106 to display the estimated response data.
  • the control unit 101 may output the estimated response data to the communication unit 104 and transmit it to a user terminal (not shown) through the communication unit 104.
  • an integrated representation conversion function is generated using an intermediate representation of anchor data that is commonly used by a plurality of devices.
  • a machine difference correction function and a device Generate a predictive model that estimates the response data for .
  • machine difference correction functions and prediction models can be corrected, so improvements can be expected in terms of quality control.
  • Embodiment 2 In Embodiment 2, updating of a prediction model will be described.
  • FIG. 7 is a flowchart showing the procedure of processing executed by the analysis engine server 200 according to the second embodiment.
  • the control unit 201 of the analysis agency server 200 obtains actual measured values (objective variables) and intermediate expressions (explanatory variables) obtained during device operation at each device operating facility MF1 to MFn (step S201).
  • the acquired actual measurement value and intermediate expression are stored in the storage unit 202 as a set.
  • the control unit 201 determines whether it is necessary to update the prediction model (step S202).
  • the control unit 201 calculates the degree of deviation between the obtained measured value (objective variable) and the response data (predicted value) obtained by inputting the obtained intermediate expression (explanatory variable) into the prediction model, and calculates the calculated degree of deviation. is equal to or greater than the threshold, it may be determined that the prediction model is updated. If it is determined that the update is not necessary (S202: NO), the control unit 201 ends the processing according to this flowchart.
  • control unit 201 corrects the intermediate expression (explanatory variable) stored in the storage unit 202 using the machine difference correction function (step S203), and uses the machine difference corrected intermediate expression.
  • the expression is converted into an integrated expression using an integrated expression conversion function (step S204).
  • the control unit 201 reconstructs the prediction model using the set of the explanatory variable converted into the integrated expression and the corresponding actual measurement value (objective variable) (step S205).
  • a known method such as linear regression is used to reconstruct the prediction model.
  • other machine learning algorithms such as support vector machines, random forests, neural networks, etc. may be used to reconstruct the predictive model.
  • Embodiment 2 when there is a discrepancy between the actual measured value of each device and the predicted value by the predictive model, the predictive model can be reconstructed.
  • a semiconductor manufacturing manufacturer is cited as an example of the equipment operating organizations MF1 to MFn
  • a semiconductor manufacturing equipment is cited as an example of the equipment 120-1 to 120-n, but the equipment operating organizations are not limited to these.
  • MF1 to MFn may be medical institutions or financial institutions
  • devices 120-1 to 120-n may be medical equipment or terminals used in these institutions.
  • Operation agency server 101 Control unit 102 Storage unit 103 Connection unit 104 Communication unit 105 Operation unit 106 Display unit 200 Analysis agency server 201 Control unit 202 Storage unit 203 Communication unit 204 Operation unit 205 Display unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Automation & Control Theory (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2023/023072 2022-07-14 2023-06-22 情報処理方法、情報処理システム及びコンピュータプログラム Ceased WO2024014251A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020257004004A KR20250040000A (ko) 2022-07-14 2023-06-22 정보 처리 방법, 정보 처리 시스템 및 기록 매체
CN202380052362.2A CN119631092A (zh) 2022-07-14 2023-06-22 信息处理方法、信息处理系统以及计算机程序
JP2024533609A JPWO2024014251A1 (https=) 2022-07-14 2023-06-22
US19/016,213 US20250147498A1 (en) 2022-07-14 2025-01-10 Information processing method, information processing system, and recording medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022-113348 2022-07-14
JP2022113348 2022-07-14

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US19/016,213 Continuation US20250147498A1 (en) 2022-07-14 2025-01-10 Information processing method, information processing system, and recording medium

Publications (1)

Publication Number Publication Date
WO2024014251A1 true WO2024014251A1 (ja) 2024-01-18

Family

ID=89536450

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/023072 Ceased WO2024014251A1 (ja) 2022-07-14 2023-06-22 情報処理方法、情報処理システム及びコンピュータプログラム

Country Status (6)

Country Link
US (1) US20250147498A1 (https=)
JP (1) JPWO2024014251A1 (https=)
KR (1) KR20250040000A (https=)
CN (1) CN119631092A (https=)
TW (1) TW202403649A (https=)
WO (1) WO2024014251A1 (https=)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009135704A (ja) * 2007-11-29 2009-06-18 Ricoh Co Ltd 画像処理装置
JP2009295658A (ja) * 2008-06-03 2009-12-17 Renesas Technology Corp 半導体製造装置の校正方法、ならびに半導体装置の製造システムおよび製造方法
JP2012026989A (ja) * 2010-07-28 2012-02-09 Hitachi High-Technologies Corp 電子顕微鏡を用いたパターン寸法計測方法、パターン寸法計測システム並びに電子顕微鏡装置の経時変化のモニタ方法
CN112285521B (zh) * 2019-12-27 2021-07-27 电子科技大学 一种自校正的igbt健康监测方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7137943B2 (ja) 2018-03-20 2022-09-15 株式会社日立ハイテク 探索装置、探索方法及びプラズマ処理装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009135704A (ja) * 2007-11-29 2009-06-18 Ricoh Co Ltd 画像処理装置
JP2009295658A (ja) * 2008-06-03 2009-12-17 Renesas Technology Corp 半導体製造装置の校正方法、ならびに半導体装置の製造システムおよび製造方法
JP2012026989A (ja) * 2010-07-28 2012-02-09 Hitachi High-Technologies Corp 電子顕微鏡を用いたパターン寸法計測方法、パターン寸法計測システム並びに電子顕微鏡装置の経時変化のモニタ方法
CN112285521B (zh) * 2019-12-27 2021-07-27 电子科技大学 一种自校正的igbt健康监测方法

Also Published As

Publication number Publication date
KR20250040000A (ko) 2025-03-21
JPWO2024014251A1 (https=) 2024-01-18
US20250147498A1 (en) 2025-05-08
TW202403649A (zh) 2024-01-16
CN119631092A (zh) 2025-03-14

Similar Documents

Publication Publication Date Title
JP6574527B2 (ja) 時系列データ特徴量抽出装置、時系列データ特徴量抽出方法及び時系列データ特徴量抽出プログラム
KR102225370B1 (ko) 학습을 통한 파라미터 개선 기반의 예측 시스템 및 방법
JP7279445B2 (ja) 予測方法、予測プログラムおよび情報処理装置
EP3195068B1 (en) Bias estimation apparatus and method and failure diagnosis apparatus and method
KR102723956B1 (ko) 고도로 공선적인 응답 공간에서의 처방적 분석
Li et al. An adaptive importance sampling algorithm for Bayesian inversion with multimodal distributions
WO2019163866A1 (ja) 量子回路学習装置、量子回路学習方法、コンピュータプログラム、及び記録媒体
JP2022543266A (ja) 回帰モデルを使用する化学生成物の生成方法
WO2020066725A1 (ja) データ処理装置、データ処理方法、及びプログラム
WO2020003624A1 (ja) 消費電力推定装置
JP7135025B2 (ja) 情報処理装置、情報処理方法およびプログラム
CN112771355B (zh) 仪器间变化校正方法和系统
JP6086875B2 (ja) 発電量予測装置および発電量予測方法
Jia et al. Self-tuning final product quality control of batch processes using kernel latent variable model
WO2024014251A1 (ja) 情報処理方法、情報処理システム及びコンピュータプログラム
JP7335414B1 (ja) 学習装置、学習方法及び学習プログラム
JP6374371B2 (ja) 電力系統監視装置および電力系統監視方法
JPWO2016203757A1 (ja) 制御装置、それを使用する情報処理装置、制御方法、並びにコンピュータ・プログラム
JP5076031B2 (ja) 製品寿命分析装置及び製品寿命分析方法
US20210382460A1 (en) Production Information Generation System, Production Information Generation Device, and Production Information Generation Method
CN119998739A (zh) 信息处理方法、计算机程序以及信息处理装置
JP2019008534A (ja) 制御装置
JP2022131657A (ja) 環境因子設定装置、環境試験装置、プログラム及び環境因子設定方法
US20250271823A1 (en) Information processing device, information processing method, and computer program product
JP2007304767A (ja) 制御システムおよび制御方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23839426

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024533609

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 202380052362.2

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 20257004004

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020257004004

Country of ref document: KR

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 202380052362.2

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 1020257004004

Country of ref document: KR

122 Ep: pct application non-entry in european phase

Ref document number: 23839426

Country of ref document: EP

Kind code of ref document: A1