[go: up one dir, main page]

WO2021221372A1 - Dispositif électronique de fourniture d'informations associées au défaut de produit et son procédé d'exploitation - Google Patents

Dispositif électronique de fourniture d'informations associées au défaut de produit et son procédé d'exploitation Download PDF

Info

Publication number
WO2021221372A1
WO2021221372A1 PCT/KR2021/004929 KR2021004929W WO2021221372A1 WO 2021221372 A1 WO2021221372 A1 WO 2021221372A1 KR 2021004929 W KR2021004929 W KR 2021004929W WO 2021221372 A1 WO2021221372 A1 WO 2021221372A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
electronic device
product
defective
machine learning
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/KR2021/004929
Other languages
English (en)
Korean (ko)
Inventor
이정구
이승호
김병규
박상완
박정은
이대희
이상현
이정헌
이지우
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.)
Samsung Electronics Co Ltd
Original Assignee
Samsung Electronics Co Ltd
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 Samsung Electronics Co Ltd filed Critical Samsung Electronics Co Ltd
Publication of WO2021221372A1 publication Critical patent/WO2021221372A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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—Programme-control systems
    • G05B19/02—Programme-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]
    • G05B19/41875—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 quality surveillance of production
    • 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—Programme-control systems
    • G05B19/02—Programme-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]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06Q10/00—Administration; Management
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • 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
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • Various embodiments of the present disclosure relate to an electronic device for providing information related to a defect of a product, and an operating method thereof.
  • a test is conducted to determine whether the materials included in the manufactured product are of good quality. During the test, the disassembly and assembly of the product is repeated several times to determine which of the materials included in the product is good or defective.
  • disassembly and assembly of products may be repeatedly performed at each facility. Since testing of materials included in products is performed by technicians, the number of times that disassembly and assembly of products performed during testing are performed may be determined according to the skill of the technicians. Accordingly, when the skill level of the technicians is relatively low, the number of times of disassembling and assembling the product performed during testing may be relatively increased. In addition, as the process conditions (eg, temperature, humidity, etc.) of the product are different for each facility where the product test is performed, the defects of the materials included in the product are different, so disassembly of the product to find the defective material And the number of times the assembly is performed may be relatively large.
  • process conditions eg, temperature, humidity, etc.
  • an electronic device and an operating method thereof accumulate process information related to a plurality of materials included in a product and material information indicating defective materials, and generate models or statistical data based on the accumulated information.
  • the electronic device and the method of operation thereof select a suitable method for providing information related to the defect of the material (eg, a model or statistical method) and providing information related to material defects in a selected suitable method, it is possible to reduce the number of disassembly and assembly of the product.
  • an electronic device includes a display, a camera circuit, and at least one processor, wherein the at least one processor uses the camera circuit to photograph an object including a plurality of materials, Obtaining first information about a product associated with the photographed object, receiving a plurality of parameters specifying a plurality of process steps for producing the product as input values, and receiving at least one defect corresponding to the plurality of parameters Acquire a model for providing material and defective probability, identify the number of training data used for learning of the model, and based on the identified number of training data, either the model or statistical analysis method
  • An electronic device configured to make a selection and provide second information associated with a defect identified based on the selected result and a plurality of first parameters currently associated with the product and the first information may be provided.
  • a method of operating an electronic device using the camera circuit, photographing an object including a plurality of materials, obtaining first information about a product associated with the photographed object; , receiving a plurality of parameters specifying a plurality of process steps for producing the product as input values, and obtaining a model for providing at least one defective material and defective probability corresponding to the plurality of parameters; Identifying the number of training data used for learning the model, selecting any one of the model or statistical analysis method based on the identified number of training data, and the selected result and the current product
  • a method of operation may be provided, comprising providing second information associated with a defect identified based on a plurality of associated first parameters and the first information.
  • an electronic device includes at least one processor, wherein the at least one processor includes a plurality of process information related to a product from a plurality of external electronic devices, and a plurality of defective materials related to the product. information is obtained, and the plurality of process information includes information on a plurality of parameters related to the process of the product, and the defective material information relates to a defective material included in the product corresponding to the plurality of parameters.
  • a machine related to the product generating a learning model receives a plurality of parameters specifying a plurality of process processes as input values, and is implemented to provide at least one defective material and a defective probability corresponding to the plurality of parameters, , an electronic device configured to provide the machine learning model corresponding to the product to the first external electronic device based on receiving identification information related to the product from the first external electronic device.
  • the means for solving the problem are not limited to the above-mentioned solutions, and the not mentioned solutions are to those of ordinary skill in the art to which the present invention belongs from the present specification and the accompanying drawings. can be clearly understood.
  • an electronic device and an operating method thereof provide disassembly and assembly of a product by providing information related to a defect of a material based on information of a machine learning model generated based on accumulated information or a statistical method By reducing the number of times this is performed, time or cost required for testing can be reduced.
  • an electronic device and an operating method thereof provide information related to the defect of a material in a method selected according to the reliability of the accumulated information (eg, whether a rare defect), so that the disassembly and assembly of the product is performed. By reducing the number of times, the time or cost required for testing can be reduced.
  • FIG. 1 is a block diagram of an electronic device in a network environment, according to various embodiments of the present disclosure
  • FIG. 2 is a view for explaining a process of identifying a plurality of materials included in a product and a defective material among a plurality of materials included in the product according to various embodiments of the present disclosure
  • FIG. 3 is a diagram for describing an example of facilities, servers, and electronic devices according to various embodiments of the present disclosure
  • FIG. 4 is a diagram for describing an example of components included in a first server, a second server, and an electronic device according to various embodiments of the present disclosure
  • FIG. 5 is a view for explaining an example of process information and defective material information according to various embodiments of the present disclosure
  • FIG. 6 is a diagram for explaining an example of facility information and defective facility information according to various embodiments of the present disclosure
  • FIG. 7 is a flowchart illustrating an example of an operation of an electronic device according to various embodiments of the present disclosure
  • FIG. 8 is a diagram for describing an example of an operation of an electronic device according to various embodiments of the present disclosure.
  • FIG. 9 is a flowchart illustrating another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • FIG. 10 is a diagram for describing another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • FIG. 11 is a diagram for describing an example of an operation of determining whether an electronic device has a rare defect, according to various embodiments of the present disclosure
  • FIG. 12 is a flowchart illustrating an example of operations of a first server, a second server, and an electronic device according to various embodiments of the present disclosure
  • FIG. 13 is a diagram for describing an example of operations of facilities, a first server, a second server, and an electronic device according to various embodiments of the present disclosure
  • FIG. 14 is a diagram for explaining an operation for generating a machine learning model of a second server according to various embodiments of the present disclosure
  • 15 is a flowchart illustrating another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • 16A is a diagram for explaining an example of an operation of providing information related to a defect based on at least one model of an electronic device according to various embodiments of the present disclosure
  • 16B is a diagram for explaining another example of an operation of providing information related to a defect based on at least one model of an electronic device according to various embodiments of the present disclosure
  • 17 is a diagram for explaining an example of an operation of providing information related to a defect based on a statistical analysis method of an electronic device according to various embodiments of the present disclosure
  • FIG. 18 is a flowchart illustrating another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • 19 is a diagram for describing an example of an interface displayed by an electronic device, according to various embodiments of the present disclosure.
  • FIG. 20 is a diagram for describing another example of an interface displayed by an electronic device, according to various embodiments of the present disclosure.
  • 21 is a flowchart illustrating another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • FIG. 22 is a diagram for describing an example of a graphic object for indicating a material of an electronic device and an operation of displaying a defective probability in a form associated with the graphic object according to various embodiments of the present disclosure
  • FIG. 23 is a diagram for explaining another example of a graphic object for indicating a material of an electronic device and an operation of displaying a defective probability in a form associated with the graphic object according to various embodiments of the present disclosure
  • the method for inferring or predicting information related to the defect for each material included in the product is a defect using process information and defective material information to be described later.
  • An artificial intelligence model (hereinafter, a machine learning model) may be used to provide information related to .
  • Processors of the servers for generating a machine learning model to be described later may convert the process information and defective material information into a form suitable for use as an input of an artificial intelligence model by performing a pre-processing process.
  • AI models can be acquired through learning.
  • acquired through learning means that the basic artificial intelligence model is learned using a plurality of learning data by a learning algorithm, whereby a predefined action rule or artificial intelligence model set to perform a desired characteristic (or purpose) is acquired means to be
  • the artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and a neural network operation is performed through an operation between an operation result of a previous layer and a plurality of weight values.
  • Inferential prediction is a technology for logically reasoning and predicting information by judging information, and uses knowledge/probability-based reasoning, optimization prediction, preference-based planning, recommendation, etc. includes
  • FIG. 1 is a block diagram of an electronic device 101 in a network environment 100 according to various embodiments.
  • an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or a second network 199 . It may communicate with the electronic device 104 or the server 108 through (eg, a long-distance wireless communication network). According to an embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 .
  • a first network 198 eg, a short-range wireless communication network
  • a second network 199 e.g., a second network 199
  • the electronic device 101 may communicate with the electronic device 104 through the server 108 .
  • the electronic device 101 includes a processor 120 , a memory 130 , an input device 150 , a sound output device 155 , a display device 160 , an audio module 170 , and a sensor module ( 176 , interface 177 , haptic module 179 , camera module 180 , power management module 188 , battery 189 , communication module 190 , subscriber identification module 196 , or antenna module 197 . ) may be included. In some embodiments, at least one of these components (eg, the display device 160 or the camera module 180 ) may be omitted or one or more other components may be added to the electronic device 101 . In some embodiments, some of these components may be implemented as one integrated circuit. For example, the sensor module 176 (eg, a fingerprint sensor, an iris sensor, or an illuminance sensor) may be implemented while being embedded in the display device 160 (eg, a display).
  • the sensor module 176 eg, a fingerprint sensor, an iris sensor, or an illuminance sensor
  • the processor 120 for example, executes software (eg, a program 140) to execute at least one other component (eg, a hardware or software component) of the electronic device 101 connected to the processor 120 . It can control and perform various data processing or operations. According to one embodiment, as at least part of data processing or operation, the processor 120 converts commands or data received from other components (eg, the sensor module 176 or the communication module 190 ) to the volatile memory 132 . may be loaded into the volatile memory 132 , process commands or data stored in the volatile memory 132 , and store the resulting data in the non-volatile memory 134 .
  • software eg, a program 140
  • the processor 120 converts commands or data received from other components (eg, the sensor module 176 or the communication module 190 ) to the volatile memory 132 .
  • the volatile memory 132 may be loaded into the volatile memory 132 , process commands or data stored in the volatile memory 132 , and store the resulting data in the non-volatile memory 134 .
  • the processor 120 includes a main processor 121 (eg, a central processing unit or an application processor), and a secondary processor 123 (eg, a graphics processing unit, an image signal processor) that can be operated independently or in conjunction with the main processor 121 . , a sensor hub processor, or a communication processor). Additionally or alternatively, the auxiliary processor 123 may be configured to use less power than the main processor 121 or to be specialized for a designated function. The auxiliary processor 123 may be implemented separately from or as a part of the main processor 121 .
  • a main processor 121 eg, a central processing unit or an application processor
  • a secondary processor 123 eg, a graphics processing unit, an image signal processor
  • the auxiliary processor 123 may be configured to use less power than the main processor 121 or to be specialized for a designated function.
  • the auxiliary processor 123 may be implemented separately from or as a part of the main processor 121 .
  • the auxiliary processor 123 may be, for example, on behalf of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or when the main processor 121 is active (eg, executing an application). ), together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display device 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states.
  • the coprocessor 123 eg, an image signal processor or a communication processor
  • may be implemented as part of another functionally related component eg, the camera module 180 or the communication module 190. have.
  • the memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176 ) of the electronic device 101 .
  • the data may include, for example, input data or output data for software (eg, the program 140 ) and instructions related thereto.
  • the memory 130 may include a volatile memory 132 or a non-volatile memory 134 .
  • the program 140 may be stored as software in the memory 130 , and may include, for example, an operating system 142 , middleware 144 , or an application 146 .
  • the input device 150 may receive a command or data to be used by a component (eg, the processor 120 ) of the electronic device 101 from the outside (eg, a user) of the electronic device 101 .
  • the input device 150 may include, for example, a microphone, a mouse, a keyboard, or a digital pen (eg, a stylus pen).
  • the sound output device 155 may output a sound signal to the outside of the electronic device 101 .
  • the sound output device 155 may include, for example, a speaker or a receiver.
  • the speaker can be used for general purposes such as multimedia playback or recording playback, and the receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from or as part of the speaker.
  • the display device 160 may visually provide information to the outside (eg, a user) of the electronic device 101 .
  • the display device 160 may include, for example, a display, a hologram device, or a projector and a control circuit for controlling the corresponding device.
  • the display device 160 may include a touch circuitry configured to sense a touch or a sensor circuit (eg, a pressure sensor) configured to measure the intensity of a force generated by the touch. have.
  • the audio module 170 may convert a sound into an electric signal or, conversely, convert an electric signal into a sound. According to an embodiment, the audio module 170 acquires a sound through the input device 150 , or an external electronic device (eg, a sound output device 155 ) connected directly or wirelessly with the electronic device 101 . The sound may be output through the electronic device 102 (eg, a speaker or headphones).
  • an external electronic device eg, a sound output device 155
  • the sound may be output through the electronic device 102 (eg, a speaker or headphones).
  • the sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, user state), and generates an electrical signal or data value corresponding to the sensed state. can do.
  • the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, a humidity sensor, or an illuminance sensor.
  • the interface 177 may support one or more designated protocols that may be used for the electronic device 101 to directly or wirelessly connect with an external electronic device (eg, the electronic device 102 ).
  • the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.
  • HDMI high definition multimedia interface
  • USB universal serial bus
  • SD card interface Secure Digital Card
  • the connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the electronic device 102 ).
  • the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).
  • the haptic module 179 may convert an electrical signal into a mechanical stimulus (eg, vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic sense.
  • the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.
  • the camera module 180 may capture still images and moving images. According to an embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.
  • the power management module 188 may manage power supplied to the electronic device 101 .
  • the power management module 188 may be implemented as, for example, at least a part of a power management integrated circuit (PMIC).
  • PMIC power management integrated circuit
  • the battery 189 may supply power to at least one component of the electronic device 101 .
  • battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.
  • the communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). It can support establishment and communication through the established communication channel.
  • the communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication.
  • the communication module 190 is a wireless communication module 192 (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (eg, : It may include a local area network (LAN) communication module, or a power line communication module).
  • a wireless communication module 192 eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module
  • GNSS global navigation satellite system
  • wired communication module 194 eg, : It may include a local area network (LAN) communication module, or a power line communication module.
  • a corresponding communication module is a first network 198 (eg, a short-range communication network such as Bluetooth, WiFi direct, or IrDA (infrared data association)) or a second network 199 (eg, a cellular network, the Internet, or It may communicate with an external electronic device via a computer network (eg, a telecommunication network such as a LAN or WAN).
  • a computer network eg, a telecommunication network such as a LAN or WAN.
  • These various types of communication modules may be integrated into one component (eg, a single chip) or may be implemented as a plurality of components (eg, multiple chips) separate from each other.
  • the wireless communication module 192 uses the subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199 .
  • the electronic device 101 may be identified and authenticated.
  • the antenna module 197 may transmit or receive a signal or power to the outside (eg, an external electronic device).
  • the antenna module may include one antenna including a conductor formed on a substrate (eg, a PCB) or a radiator formed of a conductive pattern.
  • the antenna module 197 may include a plurality of antennas. In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is connected from the plurality of antennas by, for example, the communication module 190 . can be selected. A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna.
  • other components eg, RFIC
  • other than the radiator may be additionally formed as a part of the antenna module 197 .
  • peripheral devices eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)
  • GPIO general purpose input and output
  • SPI serial peripheral interface
  • MIPI mobile industry processor interface
  • the command or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199 .
  • Each of the electronic devices 102 and 104 may be the same or a different type of the electronic device 101 .
  • all or part of the operations performed by the electronic device 101 may be executed by one or more of the external electronic devices 102 , 104 , or 108 .
  • the electronic device 101 may perform the function or service itself instead of executing the function or service itself.
  • one or more external electronic devices may be requested to perform at least a part of the function or the service.
  • the one or more external electronic devices that have received the request may execute at least a part of the requested function or service, or an additional function or service related to the request, and transmit a result of the execution to the electronic device 101 .
  • the electronic device 101 may process the result as it is or additionally and provide it as at least a part of a response to the request.
  • cloud computing, distributed computing, or client-server computing technology may be used.
  • the electronic device may have various types of devices.
  • the electronic device may include, for example, a portable communication device (eg, a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance device.
  • a portable communication device eg, a smart phone
  • a computer device e.g., a smart phone
  • a portable multimedia device e.g., a portable medical device
  • a camera e.g., a portable medical device
  • a camera e.g., a portable medical device
  • a camera e.g., a portable medical device
  • a wearable device e.g., a smart bracelet
  • a home appliance device e.g., a home appliance
  • first”, “second”, or “first” or “second” may simply be used to distinguish the component from other components in question, and may refer to components in other aspects (e.g., importance or order) is not limited. It is said that one (eg, first) component is “coupled” or “connected” to another (eg, second) component, with or without the terms “functionally” or “communicatively”. When referenced, it means that one component can be connected to the other component directly (eg by wire), wirelessly, or through a third component.
  • module may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as, for example, logic, logic block, component, or circuit.
  • a module may be an integrally formed part or a minimum unit or a part of the part that performs one or more functions.
  • the module may be implemented in the form of an application-specific integrated circuit (ASIC).
  • ASIC application-specific integrated circuit
  • Various embodiments of the present document include one or more instructions stored in a storage medium (eg, internal memory 136 or external memory 138) readable by a machine (eg, electronic device 101).
  • a machine eg, electronic device 101
  • the processor eg, the processor 120
  • the device eg, the electronic device 101
  • the one or more instructions may include code generated by a compiler or code executable by an interpreter.
  • the device-readable storage medium may be provided in the form of a non-transitory storage medium.
  • 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (eg, electromagnetic wave), and this term is used in cases where data is semi-permanently stored in the storage medium and It does not distinguish between temporary storage cases.
  • a signal eg, electromagnetic wave
  • the method according to various embodiments disclosed in this document may be provided in a computer program product (computer program product).
  • Computer program products may be traded between sellers and buyers as commodities.
  • the computer program product is distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)), or through an application store (eg Play StoreTM) or on two user devices (eg, It can be distributed (eg downloaded or uploaded) directly, online between smartphones (eg: smartphones).
  • a part of the computer program product may be temporarily stored or temporarily created in a machine-readable storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server.
  • each component eg, a module or a program of the above-described components may include a singular or a plurality of entities.
  • one or more components or operations among the above-described corresponding components may be omitted, or one or more other components or operations may be added.
  • a plurality of components eg, a module or a program
  • the integrated component may perform one or more functions of each component of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. .
  • operations performed by a module, program, or other component are executed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations are executed in a different order, or omitted. or one or more other operations may be added.
  • FIG. 2 is a view for explaining a process of identifying a plurality of materials included in a product and a defective material among a plurality of materials included in the product according to various embodiments of the present disclosure
  • various types of processes related to various types of products 201 may be performed in various facilities.
  • the various types of processes are to identify a process for producing the product 201, and information related to the defect of the product 201 (eg, information on defective materials among materials included in the product 201). tests may be included.
  • the product 201 may include a plurality of materials (or parts) (eg, A1 202 , A2 203 , A3 204 ) as shown in FIG. 2 .
  • the product 201 includes a plurality of materials 202, 203, and 204, such as a camera module, an interposer printed circuit board (PCB), a wireless charging coil, a SUB PCB, an antenna module, a display, and a surface mounted device (SMD).
  • the SMD may include RLC components including resistors, inductors, and capacitors, and various integrated circuit (IC) components.
  • the product 201 may include components constituting the electronic device illustrated in FIG. 1 as a plurality of materials 202 , 203 , and 204 .
  • a test (eg, 210 to 212 ) may be performed in a facility to identify a defective material among a plurality of materials 202 , 203 , and 204 included in the product 201 .
  • the technician may disassemble the product 201 into a plurality of materials as shown in FIG. 2 and reassemble by replacing at least one material among the plurality of materials with another material of the same type (210). ).
  • the technician disassembles the electronic device into a first material 202 , a second material 203 , and a third material 204 , and replaces the first material with a fourth material (not shown) of the same type, , the replaced fourth material, the second material, and the third material may be reassembled into the product 201 .
  • the technician tests whether the reassembled product 201 is driven normally, and repeats the disassembly and reassembly process described above if the product 201 is identified as defective 211 because the product 201 is not driven normally. can do.
  • the technician may identify 212 the material before replacement as a defective material.
  • the test as described above may include a swap test.
  • information about the replaced material may be stored and/or managed.
  • various pieces of information related to the product 201 on which the test has been performed eg, information about the product 201 , information related to the process of the product 201
  • information on a material identified as defective may be stored.
  • Each piece of information is inputted into one device (eg, personal terminal, PC, etc.) being used by the technician, and the input information is stored in one device and transferred from the device to another device (eg, server), or a measurement device (eg, sensors, simulation devices, etc.) can be automatically stored and managed.
  • various information generated by processes and/or tests in various facilities may be provided to servers (eg, the first server 302 ).
  • Servers eg, a first server 302 and a second server 303 to be described later
  • process the various information into training data and perform machine learning based on the training data and the machine learning engine to create a machine learning model.
  • generated, and the generated machine learning model may be provided to the electronic device.
  • the electronic device 301 may provide information related to defects of products based on the machine learning model (eg, information indicating a defect probability of materials included in the products).
  • FIG. 3 is a diagram for describing an example of facilities, servers, and electronic devices according to various embodiments of the present disclosure; According to various embodiments, not limited to that shown in FIG. 3 , and/or more facilities than the facilities 310 , 311 , 312 , servers 302 , 303 and electronic device 301 shown in FIG. 3 . Alternatively, devices may be implemented, or some of the illustrated facilities 310 , 311 , 312 , servers 302 , 303 and electronic device 301 may not be implemented. For example, according to various embodiments, the second server 303 may not be implemented, and the operation of the second server 303 may be performed in the first server 302 .
  • information related to the obtained product may be transmitted to the first server 302 .
  • various processes for producing a product and/or devices for collecting information related to a test for identifying whether a product is defective eg, a sensor module, a simulation
  • a PC running a program, etc. A PC running a program, etc.
  • devices for storing eg, a PC, a personal terminal used by a technician
  • Devices that store information related to various processes and/or tests related to products provided in the facilities 310 , 311 , and 312 may transmit the information to the first server 302 in real time or periodically.
  • the information collected and transmitted may include process information including a plurality of parameters specifying the process process of the product and defective material information including information on at least one defective material corresponding to the plurality of parameters.
  • process information including a plurality of parameters specifying the process process of the product and defective material information including information on at least one defective material corresponding to the plurality of parameters.
  • a plurality of parameters may be measured and/or entered (eg entered by a technician) to represent a process process for producing a product, such that they may be stored and/or managed, which may be identified during testing of the product.
  • Information on defective materials may be stored and/or managed.
  • a plurality of parameters and defective material information included in the process information will be described later with reference to FIG. 5 .
  • Identification information for specifying (or identifying) a facility may be further added to the collected and transmitted information (eg, process information and defective material information). Accordingly, the process information and defective material information accumulated in the first server 302 may be managed for each facility.
  • environments in which products are produced or tested for products are different for each facility 310 , 311 , and 312 . Accordingly, information related to processes and/or tests may be generated in different environments. In other words, information related to various processes for producing a product and/or product testing obtained for each facility may be different from each other. For example, when products of the same model are tested in different facilities, it may be identified that different defective materials are included in products of the same model based on different parameters related to the process.
  • the first server 302 may store and/or manage raw data of training data for generating a model. For example, the first server 302 transmits process information including a plurality of parameters specifying a plurality of process processes and defective material information indicating defective materials as a result of a product test to different facilities 310 , 311 , and 312 . ) can be received and accumulated. In addition, the first server 302 may process process information and defective material information in a related form. The process information and the defective material information will be further described later with reference to FIG. 5 .
  • the first server 302 may store and/or manage machine learning models for providing information related to defects of materials included in a product.
  • the information related to the failure of the materials may include information indicating the probability of failure of at least some of the plurality of materials included in the product.
  • the first server 302 manages the information (eg, process information and defective material information) accumulated in the first server 302 in an associated form, and manages the information managed in the associated form in the second server 303 . ) can be transmitted.
  • the first server 302 may receive and store machine learning models generated based on the transmitted information from the second server 303 , and provide the stored machine learning models to the electronic device 301 .
  • the first server 302 accumulates only information received from a plurality of facilities, and the machine learning model generated by the second server 303 is transmitted from the second server 303 to the electronic device. It can be passed directly to 301 .
  • the machine learning models may be implemented and/or trained based on machine learning engines and training data to provide information related to the failure of the materials in response to input information.
  • machine learning models are based on a plurality of parameters (eg, product specification values, product process environment values (temperature, humidity, etc.)) related to the product process included in the process information. It may be implemented and/or learned to provide a probability of failure of at least some of the plurality of materials. Learning of the machine learning model will be described later with reference to FIGS. 12 to 14 .
  • the first server 302 accumulates process information and defective material information transmitted from a plurality of different facilities 310 , 311 , 312 as raw data for generating a machine learning model, and the accumulated information
  • a machine learning model for providing defect prediction information generated based on the above, processes and/or tests on products can be performed in facilities at a uniform level between facilities.
  • a machine learning model is generated based on different information generated as processes and/or tests are performed in different environments configured in each facility, so that the first server 302 can provide materials for various process environments. It is possible to provide information related to a star defect to the electronic device 301 .
  • the second server 303 will be described.
  • the second server 303 may generate machine learning models for providing bad prediction information.
  • the second server 303 may generate a machine learning model for providing defect prediction information based on the process information and defective material information accumulated in the first server 302 and at least one machine learning algorithm.
  • the at least one machine learning algorithm may include a support vector machine (SVM), a random forest (RF), a gradient boosting classification (GBC), a light gradient boosting machine (LGBM), and an ENSEMBLE.
  • the electronic device 301 may be used by users who perform processes and/or tests on products in a facility.
  • the electronic device 301 may provide defect prediction information about a product.
  • the electronic device 301 receives a machine learning model stored and/or managed in the first server 302 , and based on the received machine learning model and information about the product (eg, process information), a product It is possible to provide (eg, display on a display or output information about defective materials through a speaker) to provide predictive failure information (eg, failure probability information for each material) related to the materials included in the .
  • the electronic device 301 may provide feedback and/or provide product-related information (eg, information on defective materials among materials included in the product). For example, the electronic device 301 establishes a communication connection with a server (eg, the first server 302 or the second server 303 ) to directly transmit information or within a facility where the electronic device 301 is located. Information may be transmitted to the server through devices capable of communicating with the provided server. The information fed back to the first server 302 may be used for retraining of the machine learning model in the first server 302 and/or the second server 303.
  • product-related information eg, information on defective materials among materials included in the product.
  • the electronic device 301 establishes a communication connection with a server (eg, the first server 302 or the second server 303 ) to directly transmit information or within a facility where the electronic device 301 is located. Information may be transmitted to the server through devices capable of communicating with the provided server. The information fed back to the first server 302 may be used for retraining of the machine learning model in the
  • the electronic The device 301 may include various types of devices such as a personal terminal used by a technician in a facility, a device installed in the facility (eg, a simulation device, a process device, a facility management server, a communication interface device provided throughout the facility).
  • a personal terminal used by a technician in a facility
  • a device installed in the facility eg, a simulation device, a process device, a facility management server, a communication interface device provided throughout the facility.
  • the electronic device 301 transmits information with external electronic devices (eg, servers and devices located in facilities such as personal terminals and process devices) based on various types of wireless communication methods. and/or receive, for example, the electronic device 301 transmits and transmits information to and from the external electronic devices based on a telecommunication network (eg, a local access network (LAN) and a wide access network (WAN)). / or receive. As another example, the electronic device 301 may transmit and/or receive information with the external electronic devices based on an IoT wireless network (eg, an ultra-delay sensor device network). As another example, the electronic device 301 may transmit and/or receive information with the external electronic devices based on a mobile network (eg, a 5G network). Without being limited thereto, the electronic device 301 may transmit and/or receive information to and/or from external electronic devices using the communication module 190 of the electronic device 101 as described above, and thus a redundant description will be omitted. do.
  • a telecommunication network eg, a local
  • first server 302 the second server 303 , and the electronic device 301 according to various embodiments will be described.
  • the first server 302 , the second server 303 , and the electronic device 301 may have more or more components than the illustrated components.
  • the enemy may be implemented with at least one component.
  • the first server 302 , the second server 303 , and the electronic device 301 include components (eg, the processor 120 , communication module 190, etc.) may be included.
  • the processor eg, the processor 120
  • the processor may be controlled to perform an operation related to the corresponding unit.
  • 5 is a view for explaining an example of process information and defective material information according to various embodiments of the present disclosure
  • 6 is a diagram for explaining an example of facility information and defective facility information according to various embodiments of the present disclosure.
  • the first server 302 will be described.
  • the first server 302 includes a processor 420 including a data collection unit 421 and a data processing unit 422 , a first database 423 and a second database 424 . may include.
  • the processor 420 eg, the data collection unit 421 of the first server 302 receives from various facilities (eg, devices within the facilities 310 , 311 , 312 ). Process information and/or defective material information can be received and managed as raw data.
  • the processor 420 (eg, the data processing unit 422 ) of the first server 302 manages a plurality of accumulated process information and/or a plurality of defective material information in a form related to each other. can do.
  • the operation of managing the plurality of process information and the plurality of defective material information of the first server 302 in an associated form will be further described later with reference to FIGS. 12 to 14 .
  • the first database 423 of the first server 302 may store various types of information received from various facilities (eg, devices within the facilities).
  • the first database 423 may include process information 610 and defective material information 620 as shown in FIG. 5 .
  • the process information 610 may represent various information related to a process of a product.
  • the process information 610 may include product-related identification information (eg, PN data 601 ) and a plurality of parameters (eg, 602 ) specifying a product-related process process.
  • the meaning of specifying the process process may mean having a value for identifying various elements related to the process process.
  • the plurality of parameters are various factors related to the process process, including whether the product passes or not (P/F information), a specification value identified during testing, a step of a process for producing the product (eg, an aging step), and the product It may include the conditions of the process to produce it (eg temperature, humidity, etc.).
  • identification information on the product, information on the process step, and information on process conditions may be measured and/or inputted.
  • the information on the process step and the information on the process conditions are parameterized and managed so as to indicate each process step and process condition, and process information including a plurality of parameters from the facilities to the first server 302 ( 610) may be transmitted.
  • the defective material information 620 includes product-related identification information, information on a plurality of materials included in the product (eg, information for identifying materials), and defective materials among a plurality of materials. It may include information 611 about the Information on a plurality of materials included in the defective material information 620 includes information for identifying assembly materials such as speakers, displays, antennas, and connectors and information for identifying circuit components in the printed circuit board (eg, RLC). devices, integrated circuit components). Information on defective materials among a plurality of materials included in the defective material information 620 may be generated during a test performed to identify whether a product is defective (or broken) in facilities. For example, , during the tests performed to identify whether the product is defective (or defective), defective material is identified (e.g. mechanically or by a technician) based on the disassembly and/or reassembly of the materials, and accordingly Electronic information (eg, defective material information 620 ) may be generated to indicate the identified defective material.
  • Electronic information eg, defective material information 620
  • the process information 610 and the defective material information 620 may be related to each other based on common information of the process information 610 and the defective material information 620 , respectively.
  • the process information and the defective material information may be related to each other based on an identification number (eg, PN) for a product.
  • PN an identification number
  • the identification information on the product included in the first process information is the first identification information (eg, PN#1)
  • the first defective material information including the first identification information (eg, PN#1) is It may be associated with the first process information.
  • process information is used as input data and defective material information is used as output data, so that machine learning can be performed, which will be described later with reference to FIGS. 12 to 14 .
  • the first database may store facility information related to a facility and facility information indicating a defective facility among facilities disposed in the facility as shown in FIG. 6 .
  • the facility information may include information for identifying the facility as various parameters related to the facility (eg, #1 to #5), facility error information indicating whether the facilities in the facility have errors, and values for various environments within the facility. have.
  • the defective facility information may include information for identifying facilities (eg, #1 to #5) and information for identifying defective facilities within the facility (eg, A1 to A4). Accordingly, information for indicating faulty (or defective) facilities among facilities included in the facilities may be provided.
  • the machine learning models described herein configure the facility in response to a plurality of parameters related to the facility, as well as information related to the failure of the facilities included in the product in response to a plurality of parameters related to the process of the product. It may be implemented to provide information related to the failure of the equipment.
  • the second database 424 of the first server 302 may store a plurality of machine learning models received from the second server 303 .
  • the plurality of machine learning models stored in the second database 424 may be classified and stored based on product identification information (eg, PN).
  • product identification information eg, PN
  • the first server 302 provides information about the product received from the electronic device 301 (eg, first information to be described later) to the product.
  • Identification information eg, PN
  • the first server 302 may identify at least one machine learning model corresponding to the identified identification information among the plurality of machine learning models, and transmit the identified at least one machine learning model to the electronic device 301 .
  • the second server 303 may include a processor 410 including a data processing unit 411 and a machine learning unit 412 .
  • the processor 410 (eg, the data processing unit 411 ) of the second server 303 may provide a plurality of process information and a plurality of material information to be used for learning based on a machine learning algorithm. can be processed
  • the processor 410 of the second server 303 may process process information and material information to have a specific data format required for learning based on a machine learning algorithm for learning. The processing operation of the process information and the material information of the second server 303 will be described later with reference to FIGS. 12 to 14 .
  • the processor (eg, the machine learning unit 412 ) of the second server 303 performs machine learning based on a plurality of process information and a plurality of material information received from the first server 301 .
  • the processor 410 of the second server 303 performs learning based on the training data and the machine learning engines stored in the second server 303, and generates at least one machine learning model as a result of the learning performance.
  • the machine learning models are based on a plurality of parameters (eg, product specification value, product process environment value (temperature, humidity, etc.)) related to the process of the product included in the process information. may be implemented and/or learned to provide a probability of failure of at least some of the materials.
  • the machine learning model learning operation of the second server 303 will be further described later with reference to FIGS. 12 to 14 .
  • the operations of the second server 303 may be performed by the first server 302 .
  • units implemented in the second server 303 eg, the machine learning unit 411
  • the first server 302 may be implemented in the first server 302 .
  • the electronic device 301 is a processor 430 including a data processing unit 431 , a machine learning unit 432 , a failure prediction information providing unit 433 , and/or a modeling unit 434 .
  • a camera circuit 436 a communication circuit 437 , a display 438 , a third database 439 , and a fourth database 440 may be included.
  • the processor eg, the data processing unit 431 and the machine learning unit 432 of the electronic device 301 , like the processor of the second server 303 , provides process information and defective materials. Information can be processed into training data, and a machine learning model can be created based on the training data. Also, the processor of the electronic device 301 may update the already acquired machine learning model based on currently received process information and defective material information.
  • the processor 430 eg, the failure prediction information providing unit 433 ) of the electronic device 301 identifies whether there is sparse defective data in training data for learning a machine learning model, and Depending on whether data is available, information related to material defects may be provided based on a machine learning model or a statistical algorithm.
  • the existence of the sparse defective data may be defined as the number of data indicating defective materials in the training data. An operation of determining whether a rare defect is present will be described later with reference to FIG. 11 .
  • the processor 430 eg, the modeling unit 434 of the electronic device 301 may process and display a product and information related to defects of materials included in the product as a graphic object.
  • the display operation of the graphic object of the electronic device 301 will be described later with reference to FIGS. 21 to 23 .
  • the electronic device 301 photographs the object using the camera circuit 436 , and Information about the object (eg, product information) can be obtained.
  • the electronic device 301 may receive a machine learning model and training data (eg, a plurality of process information and a plurality of defective material information) by using the communication circuit 437 .
  • a machine learning model and training data eg, a plurality of process information and a plurality of defective material information
  • the electronic device 301 may control the display 438 to display information about a photographed object and information related to a defect.
  • the third database 439 of the electronic device 301 may store a plurality of process information and a plurality of defective material information received from the first server 302 .
  • the fourth database 440 of the electronic device 301 may store at least one machine learning model received from the second server 303 .
  • components implemented in the above-described devices are not limited to the description and may be implemented in other devices.
  • the machine learning unit 411 of the second server 303 may be implemented in the first server 302 . Accordingly, operations performed in one device may be implemented to be performed in another device.
  • processor 430 is an example of the processor 120 described above with reference to FIG. 1 , in the following description, for convenience of description, reference numerals in the drawings are referred to as 120 instead of 430 .
  • the electronic device 301 acquires information (eg, product information) corresponding to the photographed object 201 , and based on the obtained information, a defect (eg, object) associated with the object 201 . It is possible to provide information about the probability that the materials included in (201) are defective).
  • FIG. 7 is a flowchart 700 for explaining an example of an operation of the electronic device 301 according to various embodiments of the present disclosure. According to various embodiments, the operations illustrated in FIG. 7 are not limited to the illustrated order and may be performed in various orders. In addition, according to various embodiments, more operations than those illustrated in FIG. 7 or at least one fewer operations may be performed. Hereinafter, FIG. 7 will be described with reference to FIG. 8 .
  • FIG. 8 is a diagram for describing an example of an operation of the electronic device 301 according to various embodiments of the present disclosure.
  • the electronic device 301 may photograph an object in operation 701 .
  • a technician who performs and/or manages a process and/or test on a product in a facility may photograph the object 201 using the electronic device 301 as shown in FIG. 8 .
  • the electronic device 301 may acquire first information corresponding to the photographed object in operation 702 .
  • the first information may include information related to a product corresponding to the photographed object 201 .
  • the first information includes identification information indicating a product corresponding to the photographed object 201, product-related specification information, product-related process equipment information, product-related model name information, or product-related process step information.
  • the product information may include a specification for a product to be photographed (eg, a mobile device), a product model name, and identification information (eg, PN information).
  • product information includes process equipment information about the manufacturing process at the time of occurrence of a defect, test type (eg, manufacturing process step), test item (eg, detailed measurement item), test measurement value, and test limitation (eg Max/Min value). ) and measurement data (eg, test report) such as test results (eg, PASS/FAIL information).
  • test type e.g, manufacturing process step
  • test item e.g, detailed measurement item
  • test limitation eg Max/Min value
  • measurement data eg, test report
  • test results eg, PASS/FAIL information
  • the electronic device 101 identifies process information related to the current product from the first information, and inputs the identified process information as input data to the machine learning model to obtain defect information related to materials included in the product. can do.
  • the first information may include information related to a relatively small amount of product compared to the above-described process information.
  • the first information may include relatively simple content information related to the product compared to the process information.
  • the first information may not include information on materials included in the product.
  • the electronic device 101 receives process information related to a product corresponding to the first information stored in the facility in which the electronic device 101 is currently located and information on materials included in the product, and receives the received process information and Information on materials may be used as input data to a machine learning model to obtain defect information related to materials included in a product.
  • the electronic device 301 performs the object 201 based on a specific code (eg, 801 ) for providing information embodied in the object 201 . It is possible to obtain first information corresponding to . For example, as shown in FIG. 8 , the electronic device 301 captures and recognizes a QR code 801 displayed on a display device (eg, a display) of a product or attached to the product, thereby capturing the first information. can be obtained In other words, the QR code 801 may be implemented to provide the first information to the product.
  • a specific code eg, 801
  • a QR code 801 for providing first information related to the product may be generated and attached to the product, or the product may be set to display the QR code.
  • the QR code 801 may be encoded in a specific data format to provide the first information as shown in [Table 1] below. It is not limited to the above description, and in addition to the QR code, a code for providing various types of first information such as a barcode that can be encoded to provide information may be implemented.
  • the electronic device 301 identifies the appearance of the object 201 from the photographed image of the object 201 , and the identified object 201 . It is possible to obtain information corresponding to the appearance of
  • the electronic device 301 transmits information indicating the appearance of the identified object 201 to the server, and receives first information corresponding to the appearance of the identified object 201 retrieved from the server from the server.
  • the electronic device 301 may acquire the first information in a method other than the method of photographing, without being limited to the above description.
  • the first information may be provided to the electronic device 301 through proximity communication between the object 201 and the electronic device 301 .
  • an NFC tag implemented to provide the first information to the object 201 is implemented, and the electronic device 301 may receive the first information through NFC communication by approaching the object 201 .
  • the electronic device 301 may display an interface through which information about a product may be input, and may acquire first information from the user of the electronic device 301 on the interface.
  • the electronic device 301 has a text field for receiving information input, or a drop-down form, a tree form, and a check box form for receiving a selection of information. The same interface may be displayed, and first information may be input through the displayed interface.
  • the electronic device 301 performs at least one piece of information about a defect associated with the photographed object 201 based on the first information in operation 703 .
  • can provide At least one piece of information about the defect associated with the photographed object 201 may include a defect probability for each material included in the object 201 as shown in 802 of FIG. 8 .
  • the electronic device 301 may provide information of a machine learning model corresponding to an identification number for a product included in the first information, process information and defective material information accumulated in a server corresponding to the first information, and statistical analysis. Based on the method, it is possible to identify the defective probability of at least some of the plurality of materials included in the object 201 . An operation of identifying the defective probability for each material of the electronic device 301 will be described later with reference to FIGS. 15 to 17 .
  • the electronic device may provide information related to the product defect based on a machine learning model or a statistical method according to the reliability of the machine learning model for providing the product defect related information. For example, the electronic device may determine the reliability of the machine learning model based on the scarcity of defective materials included in training data learned when the machine learning model is generated.
  • FIG. 9 is a flowchart 900 for explaining another example of an operation of an electronic device according to various embodiments of the present disclosure. According to various embodiments, the operations illustrated in FIG. 9 are not limited to the illustrated order and may be performed in various orders. In addition, according to various embodiments, more operations than those illustrated in FIG. 9 or at least one fewer operations may be performed. Hereinafter, FIG. 9 will be described with reference to FIGS. 10 to 11 .
  • 10 is a diagram for describing another example of an operation of an electronic device according to various embodiments of the present disclosure
  • 11 is a diagram for describing an example of an operation of determining whether an electronic device has a rare defect, according to various embodiments of the present disclosure
  • the electronic device 301 (eg, the at least one processor 120 ) photographs the object 201 including a plurality of materials in operation 901 , and the photographed object 201 in operation 902 . It is possible to obtain first information about the related product. For example, as illustrated in 1001 of FIG. 10 , the electronic device 301 may photograph an object 201 including a code implemented to provide product-related information. Operations 901 to 902 of the electronic device may be performed in the same manner as operations 701 to 702 of the above-described electronic device, and thus redundant descriptions will be omitted.
  • the electronic device 301 may acquire a machine learning model corresponding to the first information in operation 903 .
  • the electronic device 301 receives a plurality of parameters specifying a plurality of process processes for producing a product as input values, and provides at least one defective material and a defective probability corresponding to the plurality of parameters.
  • a machine learning model can be obtained for
  • the electronic device 301 may acquire a machine learning model implemented to provide information related to defects of a plurality of materials included in a specific product corresponding to the photographed object 201 . An operation of providing a defective material and a defective probability using a machine learning model will be described later with reference to FIG. 16 .
  • the electronic device 301 may receive a machine learning model from a server.
  • the electronic device 301 (eg, at least one processor 120 ) is a server (eg, a first server 302 or a second server 303 (not shown)) as shown in 1002 of FIG. 10 . ) to the first information 1010 and/or to transmit identification information (eg, PN) for the product included in the first information 1010, and to a server (eg, the first server 302 or the second server 303) )), the machine learning model 1013 corresponding to the first information 1010 and/or identification information (eg, PN) among a plurality of models stored in the server may be received from the server.
  • a server eg, a first server 302 or a second server 303 (not shown)
  • identification information eg, PN
  • the electronic device 301 may include at least one of a plurality of models stored in a server (eg, the first server 302 or the second server 303 ) corresponding to identification information on a product included in the first information.
  • a server eg, the first server 302 or the second server 303
  • the server identifies at least one machine learning model corresponding to the received first information 1010 and/or identification information (eg, PN) among the plurality of machine learning models, and the identified at least one machine learning model
  • the model may be transmitted to the electronic device 301 .
  • the electronic device 301 may generate a machine learning model without being limited to the above description.
  • the electronic device 301 (eg, at least one processor 120 ) transmits first information to the first server 302 as shown in 1002 of FIG. 10 , and the first server 302 . It is possible to receive a plurality of process information and a plurality of defective material information accumulated in the , and process the received information (eg, a plurality of process information and a plurality of defective material information) into training data.
  • the electronic device 301 may generate machine learning models by performing learning based on the processed training data and the machine learning algorithm (or engine).
  • the electronic device 301 (eg, at least one processor 120 ) is configured to receive a plurality of machines of various types from a server (eg, the first server 302 or the second server 303 ). Learning models are received and stored in advance, and when the first information is obtained, a machine learning model corresponding to the first information among a plurality of machine learning models may be identified.
  • the electronic device 301 may periodically and/or generate a plurality of machine learning models related to various types of products from a server (eg, the first server 302 or the second server 303) when a specific event occurs. It may be received and stored.
  • the electronic device 301 When the first information is obtained by photographing the object 201 , the electronic device 301 identifies a machine learning model corresponding to the first information (eg, PN) from among a plurality of pre-stored machine learning models, and then An operation (eg, operation 903 to operation 905) may be performed.
  • a machine learning model corresponding to the first information eg, PN
  • An operation eg, operation 903 to operation 905
  • the electronic device 301 eg, the at least one processor 120 identifies a specific machine learning model with high reliability from among at least one machine learning model corresponding to the first information, Subsequent operations (eg, operations 904 to 906) may be performed based on a specific machine learning model.
  • the electronic device 301 may identify the number of training data used for learning the machine learning model in operation 904 .
  • the electronic device 301 may perform a sparse failure prediction operation of the machine learning model, and may select whether to perform an operation based on the machine learning model according to the result.
  • the electronic device 301 determines the reliability of the machine learning model based on the number of identified training data, and when the reliability of the machine learning model is greater than or equal to a preset value (high reliability), an operation based on the machine learning model is performed. and, when the reliability of the machine learning model is less than a preset value (low reliability), an operation based on a statistical analysis method may be performed.
  • the electronic device 301 eg, at least one processor 120 based on training data (eg, a plurality of process information and a plurality of defective material information) for generating a machine learning model. can identify the number of defective materials.
  • training data eg, a plurality of process information and a plurality of defective material information
  • the electronic device 301 (eg, at least one processor 120 ) includes a plurality of process information 1011 used to learn the machine learning model 1013 as shown in 1002 of FIG. 10 . and a plurality of defective material information 1012 may be received from the first server 302 . As shown in 1003 of FIG. 10 , the electronic device 301 determines that the machine learning model 1013 is defective from training data (eg, a plurality of process information 1011 and a plurality of defective material information 1012 ). It is possible to identify the number of materials (1031). As shown in 1101 of FIG.
  • the electronic device 301 provides a plurality of material information (eg, a plurality of process information 1011 and a plurality of defective material information 1012) included in the training data 1012 , and information 1105 indicating defective materials may be identified from the plurality of pieces of defective material information 1012 to identify the number of defective materials (or the number of defective materials for each material).
  • the number of defective materials (or the number of defective materials per material) may be the number of defective materials identified from a plurality of material information regardless of the type of materials.
  • the electronic device 301 (eg, at least one processor 120 ) requests the server for the number of defective materials included in training data related to the machine learning model, and the number of defective materials from the server. information can be received.
  • the electronic device 301 may identify the number of defective materials from the received information on the machine learning model.
  • the electronic device 301 performs an operation based on a machine learning model or a statistical analysis method based on the number of training data identified in operation 905 .
  • the electronic device 301 may compare the number of identified defective materials with a pre-stored threshold in order to determine the appropriateness of using the machine learning model.
  • the electronic device 301 evaluates the reliability of the machine learning model by comparing the number of identified defective materials and a threshold (eg, about 100 to 1,000) (eg, high reliability if the number is greater than or equal to the threshold, If the number is less than the threshold, the reliability is low).
  • the threshold value may be a value preset for each machine learning model (eg, automatically or by a user setting) and stored in advance in the electronic device 301 .
  • the electronic device 301 receives information about a value (eg, set by the administrator of the first server 302 ) preset in the server (eg, the first server 302 ) from the server, and the value It is also possible to set a threshold value based on the information on In addition, the threshold value may be set for each type of machine learning engine used to obtain the machine learning model.
  • a value eg, set by the administrator of the first server 302
  • the server eg, the first server 302
  • the threshold value may be set for each type of machine learning engine used to obtain the machine learning model.
  • the electronic device 301 may compare the total number of defective materials with a threshold value. For example, the electronic device 301 (eg, at least one processor 120 ) identifies the number of defective materials for each type of material as shown in 1102 of FIG. 11 , and as shown in 1103 of FIG. As shown, the total number of defective materials (eg X pieces) can be identified, and the total number (eg X pieces) can be compared with a threshold value.
  • the electronic device 301 eg, at least one processor 120 identifies the number of defective materials for each type of material as shown in 1102 of FIG. 11 , and as shown in 1103 of FIG. As shown, the total number of defective materials (eg X pieces) can be identified, and the total number (eg X pieces) can be compared with a threshold value.
  • the electronic device 301 identifies the number of defective materials for each type as shown in 1102 of FIG. 11 , and determines the number of defective materials for each type. You can compare the number of materials and the threshold. The electronic device 301 determines when a type having the number of defective materials (or the number of defective materials 1110 for each material) greater than or equal to a threshold is identified (or is identified by more than a preset value) based on a machine learning model When an operation is selected and a type having the number of defective materials less than the threshold (or the number of defective materials 1110 per material) is identified (or is identified as much as more than a preset value) in a statistical analysis method based actions can be performed.
  • the electronic device 301 may compare the number of defective materials received from the server with a threshold value.
  • the electronic device 301 (eg, the at least one processor 120 ) performs machine learning evaluated by itself in the server instead of the operation of the electronic device 301 identifying the number of training data.
  • Information indicating reliability of the model may be received. Accordingly, the electronic device 301 may perform an operation based on the machine learning model when the reliability is greater than or equal to the threshold, and may perform an operation based on a statistical analysis method when the reliability is less than the threshold.
  • the electronic device 301 (eg, the at least one processor 120 ) performs the selected result and a plurality of first parameters currently associated with the product in operation 906 as shown in 1005 of FIG. 10 .
  • Second information related to the identified defect and the first information may be provided based on the .
  • the electronic device 301 results in the product-related information 1051 and information ( 1052) may be displayed.
  • the product-related information 1051 may be obtained based on the first information 1010 .
  • the electronic device 301 when an operation based on the machine learning model is selected, receives first information (Identifies the process information 1041 including parameters related to the process related to the product from 1010, and based on the parameters included in the identified process information 1041 and the machine learning model, associated with the defect of the material included in the product.
  • the second information eg, material defect probability
  • the electronic device 301 uses the process information 1041 identified from the first information 1010 as input data of the machine learning model, and outputs data from the machine learning model, the second information associated with the defect of the material (eg, of the material). defective probability) 1042 .
  • the electronic device 301 transmits first information and/or product identification information (eg, PN) to devices (eg, devices accumulating process information) provided in the facility, and is provided in the facility It is also possible to receive information related to the currently photographed product accumulated in real time from the devices.
  • the received information related to the currently photographed product accumulated in real time may include related process information 1041 and/or information (not shown) on materials included in the product.
  • the electronic device 301 when an operation based on a statistical analysis method is selected, the electronic device 301 provides a plurality of process information corresponding to the first information accumulated in the first server 302 and a plurality of defective materials. By analyzing the information in a statistical way, it is possible to provide second information related to the defect (eg, the material defect probability). Each operation will be described later with reference to FIGS. 15 to 17 .
  • the electronic device 301 determines the reliability of the machine learning model based on the scarcity of defective material information included in the training data for learning the machine learning model (eg, the number of defective materials and a threshold value). compare) and display information related to material defects in a method (machine learning model or statistical method) selected based on the determined reliability, thereby providing more accurate defect-related information for the currently photographed product. .
  • the electronic device 301 may appropriately use the statistical analysis method.
  • the first server 302 receives and accumulates process information and/or defective material information from different facilities and/or electronic devices 301 , and accumulates the accumulated process information and/or defective material information. Information can be processed into training data.
  • the second server 303 may generate a machine learning model based on the training data received from the first server 302 .
  • the electronic device 301 may receive a machine learning model from a server (the first server 302 or the second server 303 ).
  • FIG. 12 is a flowchart 1200 for explaining an example of operations of the first server 302 , the second server 303 , and the electronic device 301 according to various embodiments of the present disclosure.
  • the operations illustrated in FIG. 12 are not limited to the illustrated order and may be performed in various orders. Also, according to various embodiments, more operations than the operations illustrated in FIG. 12 or at least one fewer operations may be performed.
  • FIG. 12 will be described with reference to FIGS. 13 to 14 .
  • 13 is a diagram for describing an example of operations of facilities, the first server 302 , the second server 303 , and the electronic device 301 according to various embodiments of the present disclosure.
  • 14 is a diagram for explaining an operation for generating a machine learning model of the second server 303 according to various embodiments.
  • the first server 302 may accumulate process information and defective material information in operation 1201 .
  • the first server 302 may receive process information and defective material information from each of a plurality of facilities as shown in FIG. 13 .
  • the process information and defective material information may include information for identifying facilities. Accordingly, the first server 302 may classify and store process information and defective material information for each facility based on the information for identifying the facilities.
  • the processor (eg, the data processing unit 422) of the first server 302 manages the accumulated process information and defective material information in a mutually related form as shown in FIG. 14 (FIG. 14 of 1401) can be done.
  • the electronic device compares identification information (eg, PN) for a product included in the process information and identification information (eg, PN) for a product included in the defective material information, and has identification information corresponding to each other.
  • Identification information and defective material information can be stored in a form related to each other.
  • the first server 302 associates the first process information and the first defective material information in response to the first identification information (eg, PN#1) corresponding to the product, and the second identification information (eg, PN) By associating the second process information and the second defective material information in response to #2), and by associating the third process information and the third material information in response to the third identification information (eg, PN#3), the raw data It can be processed into two-dimensional information 1410 .
  • the information 1410 processed in the two-dimensional form may indicate defective (or repaired) materials in response to a plurality of parameters related to a process with respect to a product for a specific identification number.
  • the information managed in the associated form indicates that the product of the first identification number includes the first material and the second material as defective materials when the specification is the first value and the temperature is the second value.
  • the first server 302 may transmit process information and defective material information to the second server 303 in operation 1202 as shown in FIG. 13 .
  • the first server 302 may perform subsequent operations (eg, operations 1203 to 1204 ) of the second server 303 in the first server 302 without performing operation 1202 .
  • the following operation for generating the machine learning model of the second server 303 may be performed by the first server 302 .
  • the second server 303 may process process information and defective material information related to each other in order to perform machine learning in operation 1203 .
  • the second server 303 (eg, the data processing unit 411 ) transmits the managed process information and the defective material information in an associated form received from the first server 302 received for learning. , can be converted into information in the same format (data wrangling). For example, the second server 303 receives the process information and the defective material information as shown in 1401 of FIG. 14 , and converts the process information and the defective material information in two dimensions as shown in 1402 of FIG. 14 . It can be processed into information 1410 in the form.
  • the process information and the defective material information before being processed for machine learning may have different formats.
  • the process information before processing is data in the form of text generated based on one equipment (eg, simulation measurement equipment), and the defective material information before processing is based on other equipment (eg, high-performance analysis platform (eg, brightics)).
  • the second server 303 may convert the processing information and the defective material information into the same format that can be analyzed by the machine learning engine.
  • the second server 303 may identify process information and material information corresponding to a product corresponding to a specific identification number from the information 1410 processed in a two-dimensional form.
  • the second server 303 converts information processed in a two-dimensional form into a pivot table form 1411 (data reshaping) to identify process information and material information corresponding to a specific product.
  • the second server 303 may identify information indicating only process information and material information corresponding to a product having a first identification number from information processed in a two-dimensional form.
  • the processed information on which at least one of data wrangling and data reshaping is performed may be defined as training data.
  • the processor eg, the machine learning unit 412 of the second server 303 , based on the process information processed in operation 1204 , the material information, and the at least one machine learning engine, It is possible to obtain a machine learning model 1406 of The at least one machine learning engine (or algorithm) 1405 may include a support vector machine (SVM), random forest (RF), gradient boosting classification (GBC), light gradient boosting machine (LGBM), and ENSEMBLE. .
  • SVM support vector machine
  • RF random forest
  • GBC gradient boosting classification
  • LGBM light gradient boosting machine
  • ENSEMBLE ENSEMBLE
  • the second server 303 uses a plurality of process information as input data (or input vector) and a plurality of material information as output data (or output vector) to at least one machine learning algorithm 1405 .
  • at least one machine learning model (or an answer vector) may be obtained. That is, machine learning may be performed based on information on defective materials corresponding to values of a plurality of parameters. As defective materials are learned in response to specific parameters, as a result, a machine learning model 1406 that is a kind of matrix for providing the probability of failure of materials in response to a parameter related to the process of the current product may be obtained.
  • the learning may be performed by a method of assigning a score or probability). Sequentially, as learning proceeds based on material information corresponding to the remaining process information, weights are assigned to each material included in the product, so that the machine is a kind of matrix for providing the probability of failure of materials in response to process-related parameters.
  • a learning model 1406 may be obtained.
  • At least one machine learning model may be implemented to provide information on defective materials in response to process information.
  • the at least one machine learning model may be implemented to provide a probability of being defective for each material in response to an input of a plurality of parameters included in the process information.
  • the second server 303 may identify defective material information that does not include information on defective materials from the training data, and exclude the identified defective material information from the training data. Instead, the second server 303 may include defective material information, which does not include information on defective materials, in the test data in operation 1205, which will be described later. For example, the second server 303 may evaluate the machine learning model using a plurality of process information and a plurality of material information as test data in order to test the reliability of the machine learning model that has been trained. According to various embodiments, the second server 303 may store the reliability of the at least one machine learning model obtained in operation 1205 . For example, the second server 303 may measure the reliability of the machine learning model by using at least a portion of the training data as test data.
  • the second server 303 may transmit the at least one machine learning model obtained in operation 1206 and the reliability measured for the at least one machine learning model to the first server 302 .
  • the first server 302 stores the at least one machine learning model and the confidence associated with the at least one machine learning model in operation 1207 , and stores the at least one machine learning model and the at least one machine learning model in operation 1208 .
  • Reliability associated with the machine learning model may be provided to the electronic device 301 . Accordingly, the at least one machine learning model and reliability may be provided to the electronic device 301 periodically or in response to the occurrence of an event.
  • the second server 303 may provide the electronic device 301 with the generated at least one machine learning model and the reliability associated with the at least one machine learning model as in operation 1209 . may be
  • the electronic device 301 may acquire and store at least one machine learning model in operation 1210 .
  • the electronic device 301 may transmit process information and material information to the first server 302 when acquiring process information and material information in operation 1211 .
  • the electronic device 301 may transmit process information and/or material information acquired in real time while performing a process related to a current product to the first server 302 .
  • the electronic device 301 receives the information on the defective material identified through the interface when the defective material is identified and sends the information to the first server 302 . can be transmitted
  • the first server 302 may update the process information and the defective material information in operation 1212 and cause at least one machine learning model to be updated.
  • various process information and various defective material information are obtained from various facilities, and a machine learning model is generated based on the obtained various process information and defective material information, thereby providing more accurate information related to product defects.
  • a machine learning model can be created to provide.
  • FIG. 15 is a flowchart 1500 for explaining another example of an operation of the electronic device 301 according to various embodiments of the present disclosure.
  • the operations illustrated in FIG. 15 are not limited to the illustrated order and may be performed in various orders. Also, according to various embodiments, more operations than the operations illustrated in FIG. 15 or at least one fewer operations may be performed.
  • FIG. 15 will be described with reference to FIGS. 16 to 17 .
  • 16A is a diagram for explaining an example of an operation of providing information related to a defect based on at least one machine learning model of the electronic device 301 according to various embodiments of the present disclosure.
  • 16B is a diagram for explaining another example of an operation of providing information related to a defect based on at least one machine learning model of the electronic device 301 according to various embodiments of the present disclosure.
  • 17 is a diagram for explaining an example of an operation of providing information related to a defect based on a statistical analysis method of the electronic device 301 according to various embodiments of the present disclosure.
  • the electronic device 301 may acquire first information about a product associated with the photographed object in operation 1501 .
  • Operations 1501 of the electronic device 301 may be performed in the same manner as operations 701 to 702 of the electronic device 301 described above, and thus a redundant description will be omitted.
  • the electronic device 301 determines, in operation 1502 , of defective materials based on training data for learning a machine learning model corresponding to the first information. You can compare counts and thresholds associated with machine learning models. Operations 1502 of the electronic device 301 may be performed like operations 904 to 905 of the electronic device 301 , and thus a redundant description will be omitted.
  • the electronic device 301 determines in operation 1503 that the number of defectives is greater than a threshold value, or in operation 1503 when the number of defectives is greater than the threshold value.
  • an operation of providing information related to a failure based on the machine learning model (operations 1505 to 1507) may be performed.
  • the electronic device 301 acquires at least one piece of first process information and at least one piece of first material information corresponding to the first information in operation 1505 .
  • the electronic device 301 may acquire product-related information (eg, process information and information on materials included in the product) corresponding to the currently photographed object in real time.
  • the acquisition of information in real time means acquiring related information (eg, process information and defective material information) in response to acquiring the first information as the electronic device 301 captures the current object.
  • the electronic device 301 may identify process information from the obtained first information.
  • the electronic device 301 may include a plurality of process information for various types of products and a plurality of material information for products stored in the electronic device 301 in a facility in which the electronic device 301 is currently located. At least one piece of first process information and at least one piece of first defective material information corresponding to the first information about the currently photographed product may be identified. Also, for example, the electronic device 301 may request and receive at least one piece of first process information and at least one piece of first defective material information corresponding to the first information from other devices in the facility.
  • the electronic device 301 may process at least one piece of first process information and at least one piece of first defective material information in operation 1506 .
  • the electronic device 301 obtains first process information corresponding to the currently photographed product (eg, corresponding to the PN of the product) and at least one piece of first defective material information ( 1603), and the obtained first process information and at least one piece of first defective material information may be converted into information of the same format (data wrangling) (1604).
  • the electronic device may reshape the information processed in the two-dimensional form into the form of a pivot table ( 1605 ).
  • Operation 1604 data wrangling operation of the electronic device and operation 1605 (reshaping operation) of the electronic device may be performed in the same manner as operations 1402 and 1403 of the second server 303, and thus redundant descriptions will be omitted.
  • the electronic device 301 may perform an operation of allocating dummy data 1610 to the information converted into a pivot table ( 1606 ).
  • Data for using the machine learning model may be insufficient in the product-related information (the at least one first process information and the at least one first defective material information) received by the electronic device 301 . Accordingly, as shown in FIG. 16B , in order to use the machine learning model, the electronic device 301 may add as much dummy data 1610 as the insufficient number of data to the information converted in the form of a pivot table.
  • the electronic device 301 (eg, at least one processor 120 ) responds to the first information based on at least one piece of first process information and at least one piece of first material information. You can also update your machine learning model.
  • the electronic device 301 may previously receive and store a plurality of machine learning models from the first server 302 .
  • the electronic device 301 may periodically receive a plurality of machine learning models from the first server 302 .
  • the electronic device 301 may receive a plurality of machine learning models from other nearby electronic devices (terminals of other technicians).
  • the electronic device 301 may receive a plurality of machine learning models stored in various devices provided in a facility.
  • the electronic device 301 identifies at least one machine learning model corresponding to the currently acquired first information among the plurality of machine learning models, and receives the at least one first machine learning model in real time from the identified at least one machine learning model.
  • Process information and at least one piece of first defective material information may be processed, and the machine learning model may be updated based on the processed information.
  • the electronic device 301 may update at least one machine learning model corresponding to the first information by using the information processed as in operation 1203 of the second server 303 as training data.
  • the updated at least one machine learning model may provide different (eg, more accurate) failure information from failure information corresponding to a specific parameter before the update.
  • the electronic device 301 receives raw data (eg, a plurality of process information and a plurality of material information accumulated in the first server 302) from the first server 302, It can also be machined and created machine learning models.
  • the operation of generating the machine learning model of the electronic device may be performed in the same manner as operations 1203 to 1205 of the second server 303 described above, and thus a redundant description will be omitted.
  • the electronic device 301 (eg, the at least one processor 120 ) performs at least one of the processed at least one first process information and the processed at least one second defective material information in operation 1507 . And based on the machine learning model, it is possible to identify the probability of failure for a plurality of materials.
  • the electronic device 301 eg, the at least one processor 120 .
  • the electronic device 301 performs a plurality of parameters included in the currently received at least one first process information and the machine learning model as shown in FIG. 16A . Based on this, it is possible to identify the probability of failure for each of a plurality of materials included in the product corresponding to the photographed object. That is, as shown in FIG.
  • the electronic device 301 sets a plurality of parameters 1601 (eg, specification information and environment information) included in at least one piece of first process information currently received in real time to at least one It is provided as an input value of the machine learning model 1406, and based on the provision, as an output value of at least one machine learning model 1406, it is possible to identify the defective probability 1602 for each of a plurality of materials included in the product. .
  • parameters 1601 eg, specification information and environment information
  • the electronic device 301 (eg, the at least one processor 120 ) provides at least one piece of first process information processed and at least one piece of first defective material information processed as shown in FIG. 16B .
  • the machine learning model (1607) As an input value of the machine learning model (1607), as an output value of the machine learning model, as an output value of at least one machine learning model (1406), a defective probability is identified for each of a plurality of materials included in the product (1608) can
  • an operation of providing information related to a defect based on a statistical analysis method may be performed.
  • the electronic device 301 may identify a failure probability for each of a plurality of materials based on an algorithm in operation 1508 .
  • the electronic device 301 receives a plurality of process information and a plurality of material information accumulated in the first server 302 corresponding to the first information from the first server 302 , and statistics the received information. It is possible to identify the probability of failure for each material by analyzing it in a systematic way.
  • defective probability per material defective number per material/total number of defective materials
  • the electronic device 301 calculates a defect probability for each material for each parameter based on a plurality of received process information and a plurality of material information, and , it is possible to calculate the defective probability for each material by reflecting the calculated probability in the process information corresponding to the current product received in real time.
  • the electronic device 301 calculates a defect probability for each material for each parameter included in the received process information, and reflects it in process information corresponding to the current product.
  • the probability of failure can be calculated.
  • the electronic device 301 may calculate the number of defectives for each material for each parameter.
  • the electronic device 301 may calculate the failure probability for each material by reflecting the failure probability for each material for each parameter in the first parameters included in the currently received process information.
  • the electronic device 301 identifies a degree of association with a material defect for each parameter included in the process information, and according to the identified degree of association, The probability of failure for each material can be statistically analyzed. For example, the electronic device 301 may identify the number of defective materials for each parameter, and may assign weights to each parameter when calculating a probability based on the identified number of materials. For example, when the number of defective materials corresponding to the parameter is large, a relatively higher weight may be given. Accordingly, the electronic device 301 may further add (eg, multiply, add) a weight when calculating the probability based on the number of defective materials.
  • the electronic device 301 eg, the at least one processor 120 ) displays the defective probability of at least some of the plurality of materials based on the defective probability of each of the plurality of materials in operation 1509 . can do.
  • the electronic device 301 eg, the at least one processor 120 identifies a probability of failure for each of a plurality of materials, identification information on materials having a failure probability greater than or equal to a threshold value, and a list of the materials. It can indicate the probability that it is defective.
  • the electronic device 301 eg, the at least one processor 120
  • the electronic device 301 has a predetermined number of defective probabilities in descending order from the material having the highest defective probability based on the defective probabilities for each of the plurality of materials. It is possible to identify as many materials as possible, and display information about the identified materials and the probability that the materials are defective.
  • the electronic device 301 may provide information related to the identified defect based on a machine learning model or provide information related to the identified defect based on statistical analysis according to a user's selection.
  • FIG. 18 is a flowchart 1800 for explaining another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • the operations illustrated in FIG. 18 are not limited to the illustrated order and may be performed in various orders.
  • more operations than those illustrated in FIG. 18 or at least one fewer operations may be performed.
  • FIG. 18 will be described with reference to FIGS. 19 to 20 .
  • 19 is a diagram for describing an example of an interface displayed by an electronic device, according to various embodiments of the present disclosure.
  • 20 is a diagram for describing another example of an interface displayed by an electronic device, according to various embodiments of the present disclosure;
  • the electronic device 301 may acquire first information about a product associated with the photographed object in operation 1801 .
  • Operations 1801 of the electronic device 301 may be performed in the same manner as operations 901 to 902 of the electronic device 301 described above, and thus a redundant description will be omitted.
  • the electronic device 301 receives the selection of the unified indication in operation 1802 , information and statistical information associated with the identified defect based on the machine learning model
  • An operation eg, operations 1803 to 1805 of providing information related to the identified defect based on the analysis method may be performed.
  • the integrated indication may be defined as an operation of displaying information associated with a defect identified based on both a machine learning model and a statistical analysis method.
  • the electronic device 301 may set an integrated display according to a user's setting and perform an integrated display operation.
  • the electronic device 301 displays a specific element (eg, an icon) on an interface (eg, the interface of FIG. 19 or the interface of FIG. 20 ), and when the element is selected, a machine learning model and a statistical analysis method An operation of displaying information related to the identified defect based on all may be performed on the interface.
  • the electronic device 301 may store an application or program implemented to perform an operation for providing information on defective materials.
  • the electronic device 301 may display a specific element (eg, an icon) for setting whether to display the integrated display on the execution screen of the application.
  • the electronic device 301 may automatically perform an integrated display setting and perform an integrated display operation. For example, when the number of defective materials is included in a specified range based on training data for learning the machine learning model, the electronic device 301 identifies defects based on both the machine learning model and the statistical analysis method. It is possible to perform an operation of displaying information related to the .
  • the electronic device 301 (eg, the at least one processor 120 ) performs second information on the probability of failure of at least some of the plurality of materials based on the process information and the machine learning model in operation 1803 .
  • the electronic device 301 may set at least one of a plurality of materials included in a product based on a machine learning model corresponding to the first information and at least one piece of first process information currently received in response to the first information. Some defective probabilities can be identified.
  • Operations 1803 of the electronic device 301 may be performed in the same manner as operations 1505 to 1506 of the above-described electronic device 301 , and thus a redundant description will be omitted.
  • the electronic device 301 determines the probability of failure of at least some of the plurality of materials based on process information, material information, and an algorithm in operation 1804 .
  • 3 information can be identified.
  • the electronic device 301 receives a plurality of process information and a plurality of material information corresponding to the first information from the first server 302, and statistically calculates the number of defects for each material from the plurality of material information. , it is possible to identify the defective probability of at least some of the plurality of materials. Since operation 1804 of the electronic device 301 may be performed like operation 1508 of the above-described electronic device 301, a redundant description will be omitted.
  • the electronic device 301 may display a user interface including the first information, the second information, and the third information in operation 1805 .
  • the electronic device 301 determines a defect probability 1901 for each of a plurality of materials identified based on a machine learning model and a plurality of materials identified based on a statistical analysis method.
  • An interface containing a star failure probability 1902 may be displayed.
  • Various product information eg, SPEC information, PN information, process line information, process information, time information, or product model information
  • SPEC information e.g, SPEC information, PN information, process line information, process information, time information, or product model information
  • the electronic device 301 may provide a probability of failure 1901 for each of a plurality of materials identified based on a machine learning model and a probability of failure 1902 for each of a plurality of materials identified based on a statistical analysis method. ), a visual effect may be applied to the information about the probability of failure displayed based on the number of training data. For example, when the number of defective materials identified from the training data is equal to or greater than a threshold, the electronic device 301 may more visually highlight (eg, increase the size, color, /Brightness/Saturation, etc.) can be set differently. Conversely, when the number of defective materials identified from the training data is less than the threshold, the electronic device 301 may more visually highlight the displayed failure probability based on a statistical analysis method.
  • the electronic device 301 eg, the at least one processor 120
  • the machine learning model learning is selected in operation 1806
  • an operation eg, operations 1807 to 1808
  • the electronic device 301 performs second information on the probability of failure of at least some of the plurality of materials based on the process information and the machine learning model in operation 1807 . may be identified, and a user interface including the first information and the second information may be displayed in operation 1808 .
  • the electronic device 301 displays some of the defective probabilities for each material identified based on the machine learning model 2001, or When the algorithm is selected, an interface including a part 2001 among the defective probabilities of a plurality of materials identified based on a statistical analysis method may be displayed. Some of the displayed materials 2001 may be materials identified as having the highest probability of failure.
  • the interface may include information (2002, 2003, 2004, 2005, 2006) about the product based on the first information (1010).
  • the electronic device 301 (eg, the at least one processor 120 ) performs a statistical analysis method when an integrated indication is not selected in operation 1802 and machine learning model learning is not selected in operation 1806 .
  • An operation (eg, operations 1809 to 1810) of providing only information related to the identified defect based on the .
  • the electronic device 301 determines the probability of failure of at least some of the plurality of materials based on process information, material information, and an algorithm in operation 1809 .
  • 3 information may be identified, and a user interface including the first information and the third information may be displayed in operation 1810 .
  • a graphic object for representing the material and a defect probability may be displayed in a form associated with the graphic object.
  • FIG. 21 is a flowchart 2000 illustrating another example of an operation of an electronic device according to various embodiments of the present disclosure.
  • the operations illustrated in FIG. 21 are not limited to the illustrated order and may be performed in various orders.
  • more operations than the operations illustrated in FIG. 21 or at least one fewer operations may be performed.
  • FIG. 21 will be described with reference to FIGS. 22 to 23 .
  • 22 is a diagram for describing an example of a graphic object for indicating a material of an electronic device and an operation of displaying a defective probability in a form associated with the graphic object according to various embodiments of the present disclosure
  • 23 is a diagram for explaining another example of a graphic object for indicating a material of an electronic device and an operation of displaying a defective probability in a form associated with the graphic object according to various embodiments of the present disclosure
  • the electronic device 301 may photograph an object in operation 2101 .
  • the electronic device 301 may photograph an object for a process and/or a test in a facility. Since operation 2101 of the electronic device 301 may be performed like operation 701 and operation 901 described above, a redundant description will be omitted.
  • the electronic device 301 acquires first information about a product related to the photographed object in operation 2102 , and corresponds to the first information in operation 2103 .
  • machine learning models can be obtained.
  • the electronic device 301 may obtain first information indicating information related to a product corresponding to the photographed object, and obtain a machine learning model corresponding to the first information. Since operations 2102 to 2103 of the electronic device 301 may be performed in the same manner as operations 902 to 903 of the electronic device 301 described above, redundant descriptions will be omitted.
  • the electronic device 301 selects one of an operation based on a machine learning model or an operation based on a statistical analysis method in operation 2104 , and in operation 2105 .
  • Second information associated with the identified defect may be identified based on the selected result and the plurality of first parameters currently associated with the product.
  • the electronic device 301 identifies the defective probability of some of the plurality of materials included in the product based on the process information and the machine learning model currently received in response to the first information, or a statistical analysis method Based on the , it is possible to identify the defective probability of some of the plurality of materials included in the product. Since operations 2104 to 2105 of the electronic device 301 may be performed in the same manner as operations 1505 to 1509 of the electronic device 301 described above, redundant descriptions will be omitted.
  • the electronic device 301 displays objects for representing materials in operation 2106 , and displays the first information and the second information in a form associated with the object. can be displayed For example, as shown in FIG. 22 , the electronic device 301 displays an object (eg, 2201 ) indicating a plurality of materials included in the photographed object 201 , and a defective probability (eg, 2202) for each object. can be displayed.
  • an object eg, 2201
  • a defective probability eg, 2202
  • the at least one electronic device 301 is configured to provide a material-related defect probability, augmented reality, virtual reality, or Mixed reality can be implemented.
  • the electronic device 301 for providing the above-described failure probability may be a glass device 2301 that can be worn by a user.
  • the glass device 2301 recognizes a user's gaze and displays an image so that an object 2302 related to a plurality of materials included in a product corresponding to the object 201 recognized by the user is recognized on the real object, Information 2303 on the defect probability may be displayed around the object.
  • a glass device 2301 is provided separately from the electronic device 301 , and the electronic device 301 configures the object 2302 so that the glass device 2301 displays the object 2302 and information 2303 on the defect probability. and information for displaying information 2303 on the defect probability may be transmitted to the glass device 2301 .
  • an electronic device eg, the electronic device 301 of FIG. 4
  • a display eg, the display 438 of FIG. 4
  • a camera circuit eg, the camera circuit 436 of FIG. 4
  • at least one processor eg, the processor 120 of FIG. 1
  • the at least one processor uses the camera circuit to use a plurality of materials (eg, the plurality of materials ( 202, 203, and 204)), obtain first information about a product (eg, product 201 of FIG. 2 ) associated with the photographed object, and produce the product.
  • a machine learning model for receiving a plurality of parameters specifying process processes as input values and providing at least one defective material and a defective probability corresponding to the plurality of parameters (eg, the machine learning model 1013 of FIG. 10 ) to obtain, identify the number of training data used for learning of the machine learning model, and select any one of the machine learning model or statistical analysis method based on the identified number of training data, and the selected
  • An electronic device configured to provide the first information and second information associated with an identified defect based on a result and a plurality of first parameters currently associated with the product may be provided.
  • the training data used for learning the machine learning model may include information indicating whether or not the product has passed a test related to the object, a result of the test of the at least one product, and a condition of a process.
  • An electronic device comprising process information including the plurality of parameters indicating at least one piece of information related to, and information on defective materials for at least one material included in the product corresponding to the plurality of parameters may be provided.
  • the electronic device may be provided, in which the plurality of parameters (eg, the specification value of FIG. 5 ) include parameters indicating conditions of a process for producing the product.
  • the plurality of parameters eg, the specification value of FIG. 5
  • the plurality of parameters include parameters indicating conditions of a process for producing the product.
  • the at least one processor identifies the number of defective materials (eg, 1102 and 1103 in FIG. 11 ) included in the training data, and compares the number of defective materials with a threshold value.
  • a set electronic device may be provided.
  • the at least one processor is configured to process at least one piece of first process information including the plurality of first parameters currently associated with the product and at least one defective material corresponding to the plurality of first parameters. If at least one piece of first material information including information indicating the An electronic device configured to identify and provide a probability that at least some of the plurality of materials are defective as the second information based on the probability of failure for each of the identified plurality of materials may be provided.
  • an electronic device may be provided, wherein at least some of the plurality of materials have a failure probability equal to or greater than a preset value.
  • an electronic device configured to acquire the machine learning model identified as having high reliability among a plurality of machine learning models may be provided.
  • the at least one processor updates the machine learning model based on the at least one first process information and the at least one first material information, and the updated machine learning model and the plurality of An electronic device configured to identify a probability of being defective for each of a plurality of materials based on the first parameter may be provided.
  • the defective materials included in the training data are statistically analyzed, and based on the statistical analysis result, the plurality of pieces of information as the second information
  • An electronic device configured to provide a probability that at least some of the materials are defective may be provided.
  • the at least one processor (eg, the processor 120 of FIG. 1 ) is configured to obtain the first information from image information obtained based on photographing the object using the camera circuit.
  • the electronic device may be set, and the first information may include at least one of identification information on the product or process-related information on the product.
  • the at least one processor displays the object for the plurality of materials (eg, the object 2201 of FIG. 23 ), and displays the object in a form associated with the displayed object for the plurality of materials.
  • An electronic device configured to display at least one piece of information related to at least some of a plurality of materials may be provided.
  • a method of operating an electronic device eg, the electronic device 301 of FIG. 4
  • photographing an object including a plurality of materials using the camera circuit Acquiring first information about a product associated with , receiving a plurality of parameters specifying a plurality of process steps for producing the product as input values, and receiving at least one defective material and a defect corresponding to the plurality of parameters obtaining a machine learning model for providing a probability, identifying the number of training data used for learning the machine learning model, based on the identified number of training data, the machine learning model or statistical analysis selecting any one of the methods, and providing the first information and second information associated with an identified defect based on the selected result and a plurality of first parameters currently associated with the product.
  • a machine learning model for providing a probability
  • the training data used for learning the machine learning model may include information indicating whether or not the product has passed a test related to the object, a result of the test of the at least one product, and a condition of a process.
  • Process information including the plurality of parameters indicating at least one piece of information related to, and information on defective materials for at least one material included in the product corresponding to the plurality of parameters, an operation method comprising: may be provided.
  • the plurality of parameters may include a parameter indicating whether the product passes or not and a parameter indicating conditions of a process for producing the product, an operating method may be provided.
  • an operation method may be provided, further comprising: identifying the number of defective materials included in the training data, and comparing the number of defective materials with a threshold value.
  • At least one of at least one first process information including the plurality of first parameters currently associated with the product and information indicative of at least one defective material corresponding to the plurality of first parameters. Acquiring one piece of first material information, when the number of defective materials is equal to or greater than a threshold, identifying a probability of failure for each of a plurality of materials based on the machine learning model and the plurality of first parameters; and providing, as the second information, a probability that at least some of the plurality of materials are defective, based on the probability of failure for each of the identified plurality of materials.
  • an operating method may be provided.
  • an operating method configured to acquire the machine learning model identified as having high reliability among a plurality of machine learning models may be provided.
  • updating the machine learning model based on the at least one first process information and the at least one first material information, and the updated machine learning model and the plurality of first parameters An operating method may be provided, further comprising identifying a probability of being defective for each of a plurality of materials based on the .
  • an electronic device eg, the second server 303 of FIG. 4
  • includes at least one processor eg, the processor 410 of FIG. 4
  • the at least one processor includes a plurality of A plurality of process information related to a product and a plurality of pieces of defective material information related to the product are obtained from external electronic devices, and the plurality of process information includes information on a plurality of parameters related to the process of the product.
  • the defective material information includes information on defective materials included in the product corresponding to the plurality of parameters, and the plurality of process information and the plurality of defective materials obtained to perform machine learning information is processed into training data, and based on the training data and the machine learning engine, a machine learning model related to the product is generated, and the generated machine learning model includes a plurality of parameters specifying a plurality of process processes as input values is provided, and is implemented to provide at least one defective material and a defective probability corresponding to the plurality of parameters, and based on receiving identification information related to the product from a first external electronic device, the product corresponding to the product An electronic device configured to provide a machine learning model to the first external electronic device may be provided.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Manufacturing & Machinery (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Automation & Control Theory (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • General Factory Administration (AREA)

Abstract

Selon divers modes de réalisation, il peut y avoir un dispositif électronique comportant un affichage, un circuit de caméra, et au moins un processeur, lesdits processeurs étant configurés pour photographier un objet comprenant une pluralité de matériaux, à l'aide du circuit de caméra, pour obtenir des premières informations concernant un produit associé à l'objet photographié, doté, en tant que valeurs d'entrée, d'une pluralité de paramètres spécifiant une pluralité de processus servant à générer le produit pour obtenir un modèle destiné à fournir une probabilité de défaut et au moins un matériau de défaut correspondant à la pluralité de paramètres, pour identifier le nombre d'éléments de données de formation utilisées pour former le modèle, pour sélectionner l'un quelconque du modèle ou d'un procédé d'analyse statistique, sur la base du nombre identifié d'éléments de données de formation, et pour fournir les premières informations et les secondes informations associées à un défaut identifié sur la base d'une pluralité de premiers paramètres actuellement associés au produit et d'un résultat de la sélection. Divers autres modes de réalisation sont possibles. Pendant ce temps, une opération consistant à fournir les secondes informations associées à un défaut du dispositif électronique peut être effectuée à l'aide d'un modèle d'apprentissage automatique.
PCT/KR2021/004929 2020-04-28 2021-04-20 Dispositif électronique de fourniture d'informations associées au défaut de produit et son procédé d'exploitation Ceased WO2021221372A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020200051846A KR20210133090A (ko) 2020-04-28 2020-04-28 제품의 불량과 연관된 정보를 제공하기 위한 전자 장치 및 그 동작 방법
KR10-2020-0051846 2020-04-28

Publications (1)

Publication Number Publication Date
WO2021221372A1 true WO2021221372A1 (fr) 2021-11-04

Family

ID=78373631

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/004929 Ceased WO2021221372A1 (fr) 2020-04-28 2021-04-20 Dispositif électronique de fourniture d'informations associées au défaut de produit et son procédé d'exploitation

Country Status (2)

Country Link
KR (1) KR20210133090A (fr)
WO (1) WO2021221372A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781934A (zh) * 2022-06-17 2022-07-22 希望知舟技术(深圳)有限公司 工单分配方法及相关装置
CN116167313A (zh) * 2023-02-22 2023-05-26 深圳市摩尔芯创科技有限公司 一种用于集成电路设计的训练数据生成方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150018681A (ko) * 2013-08-08 2015-02-24 국립대학법인 울산과학기술대학교 산학협력단 생산 공정에서 데이터마이닝을 이용하여 제품 상태를 예측하는 장치 및 방법
KR101863196B1 (ko) * 2017-07-24 2018-06-01 한국생산기술연구원 딥러닝 기반 표면 결함 검출장치 및 방법
US20180373233A1 (en) * 2017-06-27 2018-12-27 Fanuc Corporation Failure predicting apparatus and machine learning device
KR20190081708A (ko) * 2017-12-29 2019-07-09 주식회사 비스텔 뉴럴 네트워크 모델 기반의 웨이퍼 불량 패턴 인식 방법 및 이를 위한 컴퓨터 프로그램
KR20190143192A (ko) * 2018-06-20 2019-12-30 에임시스템 주식회사 기계 학습 기반의 자동 결함 분류 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150018681A (ko) * 2013-08-08 2015-02-24 국립대학법인 울산과학기술대학교 산학협력단 생산 공정에서 데이터마이닝을 이용하여 제품 상태를 예측하는 장치 및 방법
US20180373233A1 (en) * 2017-06-27 2018-12-27 Fanuc Corporation Failure predicting apparatus and machine learning device
KR101863196B1 (ko) * 2017-07-24 2018-06-01 한국생산기술연구원 딥러닝 기반 표면 결함 검출장치 및 방법
KR20190081708A (ko) * 2017-12-29 2019-07-09 주식회사 비스텔 뉴럴 네트워크 모델 기반의 웨이퍼 불량 패턴 인식 방법 및 이를 위한 컴퓨터 프로그램
KR20190143192A (ko) * 2018-06-20 2019-12-30 에임시스템 주식회사 기계 학습 기반의 자동 결함 분류 방법

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781934A (zh) * 2022-06-17 2022-07-22 希望知舟技术(深圳)有限公司 工单分配方法及相关装置
CN114781934B (zh) * 2022-06-17 2022-09-20 希望知舟技术(深圳)有限公司 工单分配方法及相关装置
CN116167313A (zh) * 2023-02-22 2023-05-26 深圳市摩尔芯创科技有限公司 一种用于集成电路设计的训练数据生成方法和系统
CN116167313B (zh) * 2023-02-22 2023-09-12 深圳市摩尔芯创科技有限公司 一种用于集成电路设计的训练数据生成方法和系统

Also Published As

Publication number Publication date
KR20210133090A (ko) 2021-11-05

Similar Documents

Publication Publication Date Title
WO2021025350A1 (fr) Dispositif électronique gérant une pluralité d'agents intelligents et son procédé de fonctionnement
WO2021091171A1 (fr) Dispositif électronique et procédé de commande de celui-ci, et support d'informations
WO2020159147A1 (fr) Dispositif électronique et procédé de commande d'objet graphique du dispositif électronique
WO2020159200A1 (fr) Procédé de fourniture de données associées à des données originales et dispositif électronique et support de stockage associés
WO2019039868A1 (fr) Dispositif électronique d'affichage d'application et son procédé de fonctionnement
WO2022019682A1 (fr) Système et procédé de calcul de frontière
WO2020130301A1 (fr) Dispositif électronique permettant de suivre l'activité d'un utilisateur et son procédé de fonctionnement
WO2021221372A1 (fr) Dispositif électronique de fourniture d'informations associées au défaut de produit et son procédé d'exploitation
WO2020180034A1 (fr) Procédé et dispositif pour fournir des informations basées sur une sélection par un utilisateur
WO2021158040A1 (fr) Dispositif électronique fournissant un énoncé correspondant au contexte d'une conversation, et procédé d'utilisation associé
WO2020167006A1 (fr) Procédé de fourniture de service de reconnaissance vocale et dispositif électronique associé
WO2020138957A1 (fr) Procédé de recommandation dynamique de catalogue et dispositif électronique associé
WO2020171584A1 (fr) Dispositif électronique destiné à afficher un écran d'exécution d'application et procédé de commande associé
WO2021230485A1 (fr) Procédé et appareil de fourniture d'image
WO2020159318A1 (fr) Dispositif électronique pour l'affichage d'au moins un élément graphique et procédé de commande associé
WO2020153598A1 (fr) Procédé d'analyse de prévision de données et dispositif électronique l'utilisant
WO2022131739A1 (fr) Procédé de traitement d'image et dispositif électronique le prenant en charge
WO2021085855A1 (fr) Procédé et appareil pour prendre en charge un agent vocal dans lequel participent une pluralité d'utilisateurs
WO2019240434A1 (fr) Dispositif électronique et procédé de commande correspondant
WO2023132459A1 (fr) Dispositif électronique permettant d'afficher un objet de réalité augmentée et procédé associé
WO2022203374A1 (fr) Procédé pour fournir un service d'assistant vocal, et dispositif électronique pour le prendre en charge
WO2021091347A1 (fr) Dispositif électronique permettant de recommander un cadeau et son procédé de fonctionnement
WO2021086130A1 (fr) Dispositif électronique de traitement d'un énoncé d'utilisateur et son procédé d'opération
WO2025159265A1 (fr) Dispositif électronique, serveur et procédé de fonctionnement associé pour une expérience contrôlée
WO2020145536A1 (fr) Procédé d'identification de dispositif externe par enregistrement de caractéristiques d'un signal em et dispositif électronique mettant en œuvre ledit procédé

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: 21796246

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21796246

Country of ref document: EP

Kind code of ref document: A1