TW202001457A - Device and method for artificial intelligence controlling manufacturing apparatus - Google Patents
Device and method for artificial intelligence controlling manufacturing apparatus Download PDFInfo
- Publication number
- TW202001457A TW202001457A TW107121923A TW107121923A TW202001457A TW 202001457 A TW202001457 A TW 202001457A TW 107121923 A TW107121923 A TW 107121923A TW 107121923 A TW107121923 A TW 107121923A TW 202001457 A TW202001457 A TW 202001457A
- Authority
- TW
- Taiwan
- Prior art keywords
- image analysis
- process equipment
- artificial intelligence
- character recognition
- operation screen
- Prior art date
Links
Images
Abstract
Description
本發明是有關於一種製程設備之控制裝置與方法,且特別是有關於一種製程設備之人工智慧控制裝置與方法。The invention relates to a control device and method of process equipment, and in particular to an artificial intelligence control device and method of process equipment.
隨著半導體技術的發展,製程設備的操作也越趨複雜。在製程設備之操作過程中,操作人員必須相當熟悉使用者介面的流程,在操作畫面所顯示之資訊下,進行對應的操作。每一製程設備都需要有操作人員隨時待命進行監控,因此必須耗費大量人力來對製程設備進行操作。With the development of semiconductor technology, the operation of process equipment has become more and more complicated. During the operation of the process equipment, the operator must be very familiar with the flow of the user interface and perform the corresponding operation under the information displayed on the operation screen. Every process equipment needs an operator to stand by for monitoring at any time, so a lot of manpower must be spent to operate the process equipment.
此外,操作人員對於使用者介面所下的指令若有錯誤,不僅可能會嚴重損害到產品的良率,甚至會使製程設備發生故障。因此,如何讓製程設備之操作能夠有技術上的突破,一直是半導體產業不斷在努力的方向之一。In addition, if the operator makes mistakes on the instructions given by the user interface, it may not only seriously damage the yield of the product, but also cause the process equipment to malfunction. Therefore, how to make technological breakthroughs in the operation of process equipment has always been one of the efforts of the semiconductor industry.
本發明係有關於一種製程設備之人工智慧控制裝置與方法,其利用人工智慧之文字辨識程序及影像分析程序對使用者介面之操作畫面進行分析,以提供正確的控制指令給製程設備,有效提供產品的良率,避免製程設備故障,並增進製程效率。The invention relates to an artificial intelligence control device and method for a process equipment, which uses an artificial intelligence text recognition program and an image analysis program to analyze an operation screen of a user interface to provide correct control instructions to the process equipment, effectively providing Product yield, avoid process equipment failure, and improve process efficiency.
根據本發明之第一方面,提出一種製程設備之人工智慧控制裝置。該人工智慧控制裝置包括一通訊單元、一文字辨識單元、一影像分析單元及一指令提供單元。該通訊單元用以遠端連線至該製程設備,以接收一使用者介面之一操作畫面。該文字辨識單元係以一文字辨識程序(character recognition)辨識該操作畫面,以獲得一文字辨識結果。該影像分析單元係以一影像分析程序(image analyzing)分析該操作畫面,以獲得一影像分析結果。該指令提供單元用以根據該文字辨識結果或該影像分析結果,提供一控制指令,以對該製程設備或該使用者介面自動進行控制。According to the first aspect of the present invention, an artificial intelligence control device for process equipment is proposed. The artificial intelligence control device includes a communication unit, a text recognition unit, an image analysis unit and an instruction providing unit. The communication unit is used to remotely connect to the process equipment to receive an operation screen of a user interface. The character recognition unit recognizes the operation screen with a character recognition program (character recognition) to obtain a character recognition result. The image analysis unit analyzes the operation screen with an image analysis program (image analyzing) to obtain an image analysis result. The instruction providing unit is used for providing a control instruction based on the text recognition result or the image analysis result to automatically control the process equipment or the user interface.
根據本發明之第二方面,提出一種製程設備之人工智慧控制方法。人工智慧控制方法包括以下步驟。遠端連線至該製程設備,以接收一使用者介面之一操作畫面。以一文字辨識程序(character recognition)辨識該操作畫面,以獲得一文字辨識結果。以一影像分析程序(image analyzing)分析該操作畫面,以獲得一影像分析結果。根據該文字辨識結果或該影像分析結果,提供一控制指令,以對該製程設備或該使用者介面自動進行控制。According to the second aspect of the present invention, an artificial intelligence control method for process equipment is proposed. The artificial intelligence control method includes the following steps. Remotely connect to the process equipment to receive an operation screen of a user interface. A character recognition program (character recognition) is used to recognize the operation screen to obtain a character recognition result. An image analysis program (image analyzing) analyzes the operation screen to obtain an image analysis result. According to the text recognition result or the image analysis result, a control command is provided to automatically control the process equipment or the user interface.
為了對本發明之上述及其他方面有更佳的瞭解,下文特舉實施例,並配合所附圖式詳細說明如下:In order to have a better understanding of the above and other aspects of the present invention, the following examples are specifically described in conjunction with the accompanying drawings as follows:
請參照第1圖,其繪示根據一實施例之人工智慧控制裝置100的示意圖。人工智慧控制裝置100例如是一伺服器、一叢集計算系統(cluster computing system)、或一電腦。人工智慧控制裝置100用以對製程設備900、800進行操控。製程設備900具有一使用者介面(user interface)910。使用者介面910例如是一觸控螢幕。操作人員可以在使用者介面910所顯示之操作畫面F9上點選指令方塊,以對製程設備900下達控制指令CM9。在本實施例中,人工智慧控制裝置100能夠對操作畫面F9進行遠端分析,並依據分析結果直接下達控制指令CM9,而不需要操作人員的操作。Please refer to FIG. 1, which illustrates a schematic diagram of an artificial intelligence control device 100 according to an embodiment. The artificial intelligence control device 100 is, for example, a server, a cluster computing system (cluster computing system), or a computer. The artificial intelligence control device 100 is used to control the
請參照第1圖,人工智慧控制裝置100包括一通訊單元110、一文字辨識單元120、一影像分析單元130及一指令提供單元140。通訊單元110用以透過網路700遠端連線至製程設備900,例如是一無線通訊模組、或一有線網路模組。文字辨識單元120用以對文字進行辨識,影像分析單元130用以對影像進行分析,指令提供單元140用以提供製程設備900之控制指令。文字辨識單元120、影像分析單元130及指令提供單元140例如是一電路、一晶片、一電路板或儲存數組程式碼之儲存裝置。以下係搭配一流程圖詳細說明人工智慧控制裝置100之運作方式。Referring to FIG. 1, the artificial intelligence control device 100 includes a
請參照第2圖及第3圖,第2圖繪示根據一實施例之人工智慧控制方法的流程圖,第3圖繪示操作畫面F9之一示例圖。在步驟S110中,通訊單元110遠端連線至製程設備900,以接收操作畫面F9。在此步驟中,使用者介面910上之操作畫面F9係直接同步地傳輸至人工智慧控制裝置100。在一實施例中,通訊單元110可以每隔一預定時間(例如每秒鐘)接收操作畫面F9。或者,在另一實施例中,使用者介面910在操作畫面F9有更新時,才通知通訊單元110接收操作畫面F9。如第3圖所示,操作畫面F9上顯示操控按鈕B1、B2、文字C1及物件影像O1。Please refer to FIG. 2 and FIG. 3, FIG. 2 shows a flowchart of the artificial intelligence control method according to an embodiment, and FIG. 3 shows an example of the operation screen F9. In step S110, the
接著,在步驟S120中,文字辨識單元120以一文字辨識程序(character recognition)辨識操作畫面F9,以獲得一文字辨識結果CR。舉例來說,文字辨識結果CR例如是「Target Image」。由於操作畫面F9上所顯示之文字是由電腦軟體產生,因此文字辨識結果CR之準確度相當的高。在一實施例中,文字辨識單元120可以預存操作畫面F9可能出現之所有文字,再利用此些文字進行比對,即可精準地獲得文字辨識結果CR。Next, in step S120, the
然後,在步驟S130中,影像分析單元130以一影像分析程序(image analyzing)分析操作畫面F9,以獲得一影像分析結果IR。在一實施例中,影像分析程序可以分析出操作畫面F9上的物件影像、或者是操控按鈕B1、B2。影像分析程序更可針對物件影像分析物件影像之尺寸、物件影像之清晰度、物件影像之位置等資訊,例如是線路寬度、光罩圖案之清晰度等等。Then, in step S130, the
上述步驟S120及步驟S130之順序並不侷限於第2圖之示例。在一實施例中,亦可先執行步驟S130,再執行步驟S120。或者,再另一實施例中,亦可同時執行步驟S120及步驟S130。The order of the above steps S120 and S130 is not limited to the example of FIG. 2. In an embodiment, step S130 may be executed first, and then step S120 is executed. Alternatively, in still another embodiment, step S120 and step S130 may be performed simultaneously.
接著,在步驟S140中,指令提供單元140根據文字辨識結果CR或影像分析結果IR,提供控制指令CM9,以對製程設備900或使用者介面910自動進行控制。控制指令CM9例如是控制製程設備900去拍攝影像、卸載光罩、移動光罩等。或者,控制指令CM9例如是模擬使用者介面910被點選某一控制按鈕、或輸入某一字串。Next, in step S140, the command providing unit 140 provides a control command CM9 according to the character recognition result CR or the image analysis result IR to automatically control the
在步驟S140中,指令提供單元140可以僅根據文字辨識結果CR產生控制指令CM9,指令提供單元140亦可以僅根據影像分析結果IR產生控制指令CM9。In step S140, the command providing unit 140 may generate the control command CM9 based only on the character recognition result CR, and the command providing unit 140 may also generate the control command CM9 based only on the image analysis result IR.
步驟S140之進行方式可以透過物件導向程式設計(Object-oriented programming, OOP)的方式設計成有多種程式模組,以下舉例說明如下。Step S140 can be performed in a variety of programming modules through object-oriented programming (OOP). The following examples are described below.
請參照第4圖,其繪示步驟S140之一種實施態樣。在步驟S41中,判斷文字辨識結果CR為第一文字或第二文字。若文字辨識結果CR為第一文字,則進入步驟S42;若文字辨識結果CR為第二文字,則進入步驟S43。Please refer to FIG. 4, which illustrates an implementation aspect of step S140. In step S41, it is determined that the character recognition result CR is the first character or the second character. If the character recognition result CR is the first character, go to step S42; if the character recognition result CR is the second character, go to step S43.
在步驟S42中,執行程式模組OP42(示例於第5圖);在步驟S43中,執行程式模組OP43(示例於第6圖)。In step S42, the program module OP42 (exemplified in FIG. 5) is executed; in step S43, the program module OP43 (exemplified in FIG. 6) is executed.
請參照第5圖,其繪示程式模組OP42之實施態樣。在步驟S51中,判斷影像分析結果IR是否出現第一影像。若影像分析結果IR有出現第一影像,則進入步驟S52;若影像分析結果IR沒有出現第一影像,則進入步驟S53。Please refer to Figure 5, which shows the implementation of the program module OP42. In step S51, it is determined whether the first image appears in the image analysis result IR. If the first image appears in the image analysis result IR, go to step S52; if the first image does not appear in the image analysis result IR, go to step S53.
在步驟S52中,輸出第一控制指令;在步驟S53中,輸出第二控制指令。In step S52, a first control instruction is output; in step S53, a second control instruction is output.
請參照第6圖,其繪示程式模組OP43之實施態樣。在步驟S61中,判斷文字辨識結果CR為第三文字或第四文字。若文字辨識結果CR為第三文字,則進入步驟S62;若文字辨識結果CR為第四文字,則進入步驟S63。Please refer to Figure 6, which shows the implementation of the program module OP43. In step S61, it is determined that the character recognition result CR is the third character or the fourth character. If the character recognition result CR is the third character, go to step S62; if the character recognition result CR is the fourth character, go to step S63.
在步驟S62中,判斷影像分析結果IR之尺寸是否符合標準。若尺寸符合標準,則進入步驟S64;若尺寸不符合標準,則進入步驟S65。In step S62, it is determined whether the size of the image analysis result IR conforms to the standard. If the size meets the standard, proceed to step S64; if the size does not meet the standard, proceed to step S65.
在步驟S63中,輸出第三控制指令;在步驟S64中,輸出第四控制指令;在步驟S65中,輸出第五控制指令。In step S63, a third control instruction is output; in step S64, a fourth control instruction is output; in step S65, a fifth control instruction is output.
上述步驟S140之實施態樣僅為示例,並非用以侷限本發明之範圍。透過步驟S140所提供之各種程式模組,即可快速提供對應之控制指令CM9。控制指令CM9經由通訊單元110提供至製程設備900進行操作後,即可再一次進行上述步驟S110~S140,以自動執行後續動作。The implementation of the above step S140 is only an example and is not intended to limit the scope of the present invention. Through the various program modules provided in step S140, the corresponding control command CM9 can be quickly provided. After the control command CM9 is provided to the
舉例來說,請參照第3圖,物件影像O1例如是半導體的放大影像。透過文字辨識程序,得知操作畫面F9存在「Target Image」時,即可自動再利用影像分析程序分析物件影像O1是否清晰。判斷物件影像O1是否分析之方法例如是透過邊界偵測演算法(edge detection)之差分運算法。若物件影像O1不夠清晰,則輸出「調整焦距」之控制指令CM9。For example, referring to FIG. 3, the object image O1 is, for example, an enlarged image of a semiconductor. Through the text recognition program, when it is known that there is "Target Image" on the operation screen F9, the image analysis program can be automatically used to analyze whether the object image O1 is clear. The method for judging whether the object image O1 is analyzed is, for example, a differential operation method by an edge detection algorithm. If the object image O1 is not clear enough, the control command CM9 of "adjust focus" is output.
再舉一例來說,請參照第7圖,其繪示操作畫面F9之另一示例圖。物件影像O2例如是光罩的放大影像。利用影像分析程序分析出物件影像O2存在微粒P9後,自動判斷微粒P9是否位於影像視窗之邊緣。若微粒P9位於影像視窗之邊緣,則輸出「移動光罩載具」之控制指令CM9,以使微粒P9位於影像視窗之中央處。As another example, please refer to FIG. 7, which shows another example diagram of the operation screen F9. The object image O2 is, for example, an enlarged image of a mask. After analyzing the object image O2 with particles P9 by using the image analysis program, it automatically determines whether the particles P9 are located at the edge of the image window. If the particle P9 is located at the edge of the image window, the control command CM9 of "moving mask carrier" is output so that the particle P9 is located at the center of the image window.
再舉一例來說,請參照第8圖,其繪示操作畫面F9之另一示例圖。物件影像O3例如是線路的放大影像。利用影像分析程序分析線路之臨界尺寸(critical dimension)後,並輸出「上傳臨界尺寸至資料庫」之控制指令CM9。As another example, please refer to FIG. 8, which shows another example of the operation screen F9. The object image O3 is, for example, an enlarged image of the line. After analyzing the critical dimension of the line using the image analysis program, it outputs the control command CM9 of "upload critical dimension to the database".
透過上述實施例,製程設備之人工智慧控制裝置100與人工智慧控制方法利用人工智慧之文字辨識程序及影像分析程序對操作畫面F9進行分析,以提供正確的控制指令CM9給製程設備900,有效提供產品的良率,避免製程設備故障,並增進製程效率。Through the above embodiments, the artificial intelligence control device 100 and artificial intelligence control method of the process equipment use the character recognition program and the image analysis program of the artificial intelligence to analyze the operation screen F9 to provide the correct control command CM9 to the
此外,上述人工智慧控制裝置100係透過遠端控制進行操作,而能夠實現於多台製程設備,無需架設大量硬體即可實現。In addition, the above-mentioned artificial intelligence control device 100 is operated by remote control, and can be implemented in multiple process equipments, and can be realized without installing a large amount of hardware.
綜上所述,雖然本發明已以實施例揭露如上,然其並非用以限定本發明。本發明所屬技術領域中具有通常知識者,在不脫離本發明之精神和範圍內,當可作各種之更動與潤飾。因此,本發明之保護範圍當視後附之申請專利範圍所界定者為準。In summary, although the present invention has been disclosed as above with examples, it is not intended to limit the present invention. Those with ordinary knowledge in the technical field to which the present invention belongs can make various modifications and retouching without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be deemed as defined by the scope of the attached patent application.
100‧‧‧人工智慧控制裝置110‧‧‧通訊單元120‧‧‧文字辨識單元130‧‧‧影像分析單元140‧‧‧指令提供單元700‧‧‧網路800‧‧‧製程設備900‧‧‧製程設備910‧‧‧使用者介面B1、B2‧‧‧操控按鈕C1‧‧‧文字CM9‧‧‧控制指令CR‧‧‧文字辨識結果F9‧‧‧操作畫面IR‧‧‧影像分析結果S110、S120、S130、S140、S41、S42、S43、S51、S52、S53、S61、S62、S63、S64、S65‧‧‧步驟O1、O2、O3‧‧‧物件影像OP42、OP43‧‧‧程式模組P9‧‧‧微粒100‧‧‧Artificial
第1圖繪示根據一實施例之人工智慧控制裝置的示意圖。 第2圖繪示根據一實施例之人工智慧控制方法的流程圖。 第3圖繪示操作畫面之一示例圖。 第4圖繪示步驟S140之一種實施態樣。 第5圖繪示程式模組OP42之實施態樣。 第6圖繪示程式模組OP43之實施態樣。 第7圖繪示操作畫面之另一示例圖。 第8圖繪示操作畫面之另一示例圖。FIG. 1 is a schematic diagram of an artificial intelligence control device according to an embodiment. FIG. 2 is a flowchart of an artificial intelligence control method according to an embodiment. FIG. 3 shows an example of an operation screen. FIG. 4 shows an implementation aspect of step S140. Fig. 5 shows the implementation of the program module OP42. Fig. 6 shows the implementation of the program module OP43. FIG. 7 shows another example diagram of the operation screen. FIG. 8 shows another example diagram of the operation screen.
100‧‧‧人工智慧控制裝置 100‧‧‧Artificial intelligence control device
110‧‧‧通訊單元 110‧‧‧Communication unit
120‧‧‧文字辨識單元 120‧‧‧ character recognition unit
130‧‧‧影像分析單元 130‧‧‧Image Analysis Unit
140‧‧‧指令提供單元 140‧‧‧Command supply unit
700‧‧‧網路 700‧‧‧ Internet
800‧‧‧製程設備 800‧‧‧Process equipment
900‧‧‧製程設備 900‧‧‧Process equipment
910‧‧‧使用者介面 910‧‧‧User interface
CM9‧‧‧控制指令 CM9‧‧‧Control command
CR‧‧‧文字辨識結果 CR‧‧‧Text recognition result
F9‧‧‧操作畫面 F9‧‧‧Operation screen
IR‧‧‧影像分析結果 IR‧‧‧Image analysis results
Claims (12)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107121923A TWI818913B (en) | 2018-06-26 | 2018-06-26 | Device and method for artificial intelligence controlling manufacturing apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107121923A TWI818913B (en) | 2018-06-26 | 2018-06-26 | Device and method for artificial intelligence controlling manufacturing apparatus |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202001457A true TW202001457A (en) | 2020-01-01 |
TWI818913B TWI818913B (en) | 2023-10-21 |
Family
ID=69941991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107121923A TWI818913B (en) | 2018-06-26 | 2018-06-26 | Device and method for artificial intelligence controlling manufacturing apparatus |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI818913B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI739474B (en) * | 2020-06-11 | 2021-09-11 | 宏正自動科技股份有限公司 | Image processing device, image processing system and image processing method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7242988B1 (en) * | 1991-12-23 | 2007-07-10 | Linda Irene Hoffberg | Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore |
US7904187B2 (en) * | 1999-02-01 | 2011-03-08 | Hoffberg Steven M | Internet appliance system and method |
CN104395843B (en) * | 2012-06-19 | 2017-06-23 | 三菱电机株式会社 | Automatic operation system and operation automation method |
-
2018
- 2018-06-26 TW TW107121923A patent/TWI818913B/en active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI739474B (en) * | 2020-06-11 | 2021-09-11 | 宏正自動科技股份有限公司 | Image processing device, image processing system and image processing method |
Also Published As
Publication number | Publication date |
---|---|
TWI818913B (en) | 2023-10-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11948061B2 (en) | Deep auto-encoder for equipment health monitoring and fault detection in semiconductor and display process equipment tools | |
TWI693564B (en) | Automatic equipment management system and method thereof | |
US11887388B2 (en) | Object pose obtaining method, and electronic device | |
CN109407544B (en) | System module of simulation machine operation picture of non-invasive data extraction system | |
WO2023001063A1 (en) | Target detection method and apparatus, electronic device, and storage medium | |
JP2021108215A (en) | Method for recognizing image, device, electronic device, computer storage medium, and program | |
CN112233175B (en) | Chip positioning method and integrated positioning platform based on YOLOv3-tiny algorithm | |
CN111857470A (en) | Unattended control method and device for production equipment and controller | |
WO2018045774A1 (en) | Application control method and device | |
US20140214192A1 (en) | Apparatus For Design-Based Manufacturing Optimization In Semiconductor Fab | |
TWI818913B (en) | Device and method for artificial intelligence controlling manufacturing apparatus | |
JP2020030145A (en) | Inspection apparatus and inspection system | |
US20230419509A1 (en) | Production line monitoring method and monitoring system thereof | |
US20200066016A1 (en) | System For Editing Monitor Script In Screen Image And Method Thereof | |
US20160103445A1 (en) | Mobile connectivity and control of semiconductor manufacturing equipment | |
Wu et al. | Integrating computer vision and natural language instruction for collaborative robot human-robot interaction | |
US20210192779A1 (en) | Systems, Methods, and Media for Manufacturing Processes | |
US20170050319A1 (en) | Programmable Machine Vision Device | |
JP2023516776A (en) | Systems, methods and media for manufacturing processes | |
WO2021186462A1 (en) | System and method for factory automation and enhancing machine capabilities | |
Pan et al. | Research on functional test of mobile app based on robot | |
CN116051868B (en) | Interface element identification method for windows system | |
US11715300B1 (en) | Systems and methods for providing product assembly step recognition using augmented reality | |
US20240142932A1 (en) | Script creation method for robot process automation and electronic device using the same | |
TWI767590B (en) | Device and method for robotic process automation of multiple electronic computing devices |