Semiconductor manufacturing equipment and support methods

Abstract

This technology provides support for communication among multiple workers operating semiconductor manufacturing equipment. [Solution] A semiconductor manufacturing apparatus in which work is performed by a first worker and a second worker, comprising: a recording unit that records the content spoken by the first worker; a text conversion unit that converts the recorded data into text; and a display control unit that displays the text data on a display device that can be viewed by the second worker.

Description

Technical Field

[0001] The present disclosure relates to a semiconductor manufacturing apparatus and a support method.

Background Art

[0002] For example, Patent Document 1 discloses a technique for appropriately supporting work when work is performed on inspection equipment, manufacturing equipment, etc.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present disclosure provides a technique for supporting communication among multiple workers who work on a semiconductor manufacturing apparatus.

Means for Solving the Problems

[0005] One aspect of the present disclosure is a semiconductor manufacturing apparatus in which work is performed by a first worker and a second worker, the apparatus including a recording unit that records the content spoken by the first worker, a text conversion unit that converts the recorded data into text, and a display control unit that causes the converted data to be displayed on a display device that can be viewed by the second worker.

Effects of the Invention

[0006] According to the present disclosure, it is possible to provide a technique for supporting communication among multiple workers who work on a semiconductor manufacturing apparatus.

Brief Description of the Drawings

[0007] [Figure 1] It is a diagram for explaining an example of the outline of the semiconductor manufacturing apparatus and the support method according to the present embodiment. [Figure 2] This is a diagram illustrating an example of a support system according to this embodiment. [Figure 3] This is a hardware configuration diagram of an example computer. [Figure 4] This is a functional block diagram of an example of a semiconductor manufacturing apparatus according to this embodiment. [Figure 5] This is a sequence diagram of an example of the processing of the semiconductor manufacturing apparatus according to this embodiment. [Figure 6] This is a diagram illustrating an example of a support system according to this embodiment. [Modes for carrying out the invention]

[0008] The following description of this embodiment will be given with reference to the drawings.

[0009] <Overview> Figure 1 is an example diagram illustrating the outline of a semiconductor manufacturing apparatus 10 and support method according to this embodiment. The semiconductor manufacturing apparatus 10 is an example of an apparatus in which work is performed by a first worker and a second worker. The semiconductor manufacturing apparatus 10 is an apparatus that performs processing such as film deposition, etching, or ashing, and processes a substrate such as a wafer W. The semiconductor manufacturing apparatus 10 is, for example, a substrate processing apparatus, a heat processing apparatus, or a film deposition apparatus.

[0010] One or more semiconductor manufacturing devices 10 are located within a cleanroom 2 where air cleanliness is ensured. Therefore, the first and second workers performing tasks on the semiconductor manufacturing devices 10 wear clean suits while working in the cleanroom 2. The first and second workers wear their clean suits so that they cover their ears as well. A clean suit is a full-body dust-free garment worn by workers when working in the cleanroom 2.

[0011] Furthermore, the cleanroom 2 is a noisy environment with high ambient noise levels. Consequently, the first and second workers performing tasks on the semiconductor manufacturing equipment 10 have difficulty hearing. As a result of these hearing difficulties, communication between the first and second workers in cleanroom 2 sometimes breaks down when they try to communicate verbally. Poor communication can lead to operational errors or accidents due to insufficient communication.

[0012] Therefore, in this embodiment, communication between a first worker and a second worker operating the semiconductor manufacturing apparatus 10 is supported as follows. Here, for example, an example of communication from the first worker to the second worker will be described.

[0013] The semiconductor manufacturing apparatus 10 is equipped with a microphone 12 and a display unit 14. The microphone 12 and the display unit 14 may be built into the semiconductor manufacturing apparatus 10 or be externally attached. The first worker speaks the content to be communicated to the second worker. The microphone 12 outputs the audio signal of the first worker's speech to the semiconductor manufacturing apparatus 10.

[0014] The semiconductor manufacturing apparatus 10 records the speech of the first worker, converts the recorded data into text as described below, and displays it on a display unit 14, which is an example of a display device that can be viewed by the second worker. The second worker can correctly recognize the content of the first worker's speech from the text displayed on the display unit 14. In this embodiment, communication between the first worker and the second worker is facilitated, and the occurrence of errors or accidents due to lack of communication can be reduced.

[0015] <System Configuration> FIG. 2 is a configuration diagram of an example of the support system 1 according to the present embodiment. The support system 1 in FIG. 2 includes a semiconductor manufacturing apparatus 10, a terminal device 20, and a wearable device 30. The terminal device 20 is an information processing terminal such as a PC (Personal Computer) or a smartphone possessed by the second operator. The wearable device 30 is an HMD (Head Mounted Display) or the like worn by the second operator.

[0016] The semiconductor manufacturing apparatus 10, the terminal device 20, and the wearable device 30 are connected so as to be capable of data communication via a network N such as the Internet or a LAN (Local Area Network).

[0017] The terminal device 20 has a display unit 22. Also, the wearable device 30 has a display unit 32. The display unit 14 of the semiconductor manufacturing apparatus 10, the display unit 22 of the terminal device 20, and the display unit 32 of the wearable device 30 are an example of a display device viewable by the second operator.

[0018] Note that the support system 1 shown in FIG. 1 is an example, and it is needless to say that there are various system configuration examples according to the application and purpose. The display device viewable by the second operator may be at least one of the display unit 14 of the semiconductor manufacturing apparatus 10, the display unit 22 of the terminal device 20, and the display unit 32 of the wearable device 30.

[0019] <Hardware Configuration> The terminal device 20 and the wearable device 30 in FIG. 2 may be realized by a computer having a hardware configuration as shown in FIG. 3, for example. Also, the device controller 16 of the semiconductor manufacturing apparatus 10 described later may be realized by a computer having a hardware configuration as shown in FIG. 3, for example. FIG. 3 is a hardware configuration diagram of an example of a computer 500.

[0020] The computer 500 in FIG. 3 includes an input device 501, an output device 502, an external I / F (interface) 503, a RAM (Random Access Memory) 504, a ROM (Read Only Memory) 505, a CPU (Central Processing Unit) 506, a communication I / F 507, and a HDD (Hard Disk Drive) 508, etc., and each is interconnected by a bus B. The input device 501 and the output device 502 may be in a form that is connected and used when necessary.

[0021] The input device 501 is a keyboard, a mouse, a touch panel, etc., and is used for an operator or the like to input an operation signal. The output device 502 is a display or the like, and displays the processing result by the computer 500. The communication I / F 507 is an interface for connecting the computer 500 to the network N shown in FIG. 2. The HDD 508 is an example of a non-volatile storage device that stores programs and data.

[0022] The external I / F 503 is an interface with an external device. The computer 500 can read a recording medium 503a such as an SD (Secure Digital) memory card via the external I / F 503. The external I / F 503 may be able to write to a recording medium 503a such as an SD memory card via the external I / F 503.

[0023] The ROM 505 is an example of a non-volatile semiconductor memory (storage device) in which programs and data are stored. The RAM 504 is an example of a volatile semiconductor memory (storage device) that temporarily holds programs and data. The CPU 506 is an arithmetic unit that realizes the control and functions of the entire computer 500 by reading programs and data from a storage device such as the ROM 505 or the HDD 508 onto the RAM 504 and executing processing.

[0024] The support system 1 according to the present embodiment realizes various functions shown in FIG. 4 by executing a program on the computer 500 shown in FIG. 2.

[0025] <Functional Configuration> Figure 4 is a functional block diagram of an example of a semiconductor manufacturing apparatus 10 according to this embodiment. The functional block diagram in Figure 4 omits the illustration of components that are not necessary for the explanation of this embodiment.

[0026] The semiconductor manufacturing apparatus 10 in Figure 4 includes a microphone 12, a display unit 14, an apparatus controller 16, an operation unit 17, and a communication unit 18. The apparatus controller 16 in Figure 4 implements a recording unit 50, a text conversion unit 52, a discrimination unit 54, a display control unit 56, and a supply unit 60 by executing a program for the apparatus controller 16.

[0027] The microphone 12 collects the speech of the first worker and outputs the audio signal of the first worker's speech to the device controller 16. For example, the microphone 12 should be positioned so as to be able to collect the content of conversations and vocalizations around the semiconductor manufacturing equipment 10 so as to be able to collect the speech of the first worker.

[0028] The recording unit 50 of the device controller 16 receives an audio signal from the microphone 12 and records the content spoken by the first worker.

[0029] The text conversion unit 52 performs the process of converting the recorded data into text. The text conversion unit 52 performs noise reduction and speech recognition of the recorded data using a mathematical model that has been trained by a machine learning algorithm to perform noise reduction or speech recognition. The machine learning algorithm is a description of the data processing method and parameter optimization method for training the mathematical model.

[0030] For example, in this embodiment, by supervising the model to learn the ambient noise generated in the cleanroom 2, a mathematical model (machine learning model) can be generated that effectively removes ambient noise generated in the cleanroom 2 from recorded data. Furthermore, in this embodiment, by supervising the model to learn the content spoken by workers in the cleanroom 2, a mathematical model can be generated that accurately performs speech recognition (including transcription) of the content spoken by a first worker in the cleanroom 2 from recorded data. Since the first worker speaking in the cleanroom 2 is almost exclusively a specialist in the semiconductor industry, the accuracy of speech recognition and transcription can be improved by supervising the model to learn, for example, nouns specific to the semiconductor industry.

[0031] For example, supervised learning that converts recorded data into text is performed using training data annotated with the elements listed in the table below. Elements that can be annotated include, for example, speech segments, speech content, speaker characteristics, frequency, emotion, and accent.

[0032] [Table 1] The purpose of detecting speech segments is to clarify the information about the start and end times of speech (the structure of the audio data). The purpose of detecting speech content is to transcribe the content of speech contained in the audio data sentence by sentence and to identify the language or dialect. The purpose of detecting speaker characteristics is to identify speakers or nouns specific to the semiconductor industry. The purpose of detecting frequency is to learn and predict frequently occurring words, as the users are limited to engineers in the semiconductor industry. The purpose of detecting accent is to improve the accuracy of word or word decomposition.

[0033] The discrimination unit 54 determines which semiconductor manufacturing equipment 10 the text data converted by the text conversion unit 52 was spoken to. Multiple semiconductor manufacturing equipment 10 may be arranged inside the cleanroom 2.

[0034] Determining which semiconductor manufacturing equipment 10 the spoken content is directed to can be done, for example, by including the unique name or identifier of the semiconductor manufacturing equipment 10 in the content spoken by the first worker. The discrimination unit 54 determines which semiconductor manufacturing equipment 10 the texted data is directed to based on the unique name or identifier of the semiconductor manufacturing equipment 10 included in the texted data. Alternatively, since each semiconductor manufacturing equipment 10 is equipped with a microphone 12, the discrimination unit 54 may determine that the spoken content of the first worker, picked up by its own microphone 12, is directed to that machine.

[0035] The display control unit 56 displays the data converted into text by the text conversion unit 52 on the display unit 14, which is viewable by the second operator. The display control unit 56 may also display on the display unit 14, which is viewable by the second operator, the content of the speech directed to the machine, which is determined by the discrimination unit 54 from the data converted into text by the text conversion unit 52.

[0036] In this embodiment, the content of the first worker's speech is transcribed and displayed as text on the display unit 14, so that even in a situation where it is difficult to hear sounds, such as inside the clean room 2, the second worker can correctly understand the content of the first worker's speech.

[0037] In Figure 4, the display device accessible to the second worker is shown as the display unit 14 of the semiconductor manufacturing apparatus 10, but it may also be the display unit 22 of the terminal device 20 or the display unit 32 of the wearable device 30.

[0038] The memory unit 58 stores the data converted into text by the text conversion unit 52. The memory unit 58 may also store the content of speech directed to the user, as determined by the discrimination unit 54, from the data converted into text by the text conversion unit 52. The memory unit 58 may be implemented by another device capable of communicating with the semiconductor manufacturing apparatus 10 or by cloud storage.

[0039] The providing unit 60 provides the text data stored in the storage unit 58 to the requester in accordance with the request for confirmation of the text data. Figure 4 shows an example where the requester is an operator who operated the operation unit 17 of the semiconductor manufacturing equipment 10, or an operator who operated a terminal device 20 or the like that can communicate data with the semiconductor manufacturing equipment 10.

[0040] The operation unit 17 receives a request from the operator to confirm the text data and notifies the supply unit 60 of the confirmation request. The supply unit 60 displays the text data stored in the storage unit 58 on the display unit 14 in accordance with the confirmation request notified by the operation unit 17.

[0041] The communication unit 18 receives a request for confirmation of text data from an operator operating a terminal device 20 or the like that can communicate with the semiconductor manufacturing equipment 10, and notifies the provision unit 60 of the confirmation request. The provision unit 60 transmits the text data stored in the storage unit 58 to the communication unit 18 in accordance with the confirmation request notified by the communication unit 18. The communication unit 18 transmits the text data to the terminal device 20 or the like that which made the confirmation request, and causes the text data stored in the storage unit 58 to be displayed on the display unit 22 of the terminal device 20.

[0042] In this embodiment, the content of the speech of the worker operating the semiconductor manufacturing equipment 10 can be reviewed later by storing the text data in the storage unit 58. Because the content of the speech of the worker operating the semiconductor manufacturing equipment 10 can be reviewed later in this embodiment, it is possible to visualize the work, which is expected to be effective in confirming the content of the work and in risk analysis when problems occur.

[0043] <Processing> In the following, an example is described in which the display device viewable by the second worker is the display unit 14 of the semiconductor manufacturing apparatus 10. Note that the display device viewable by the second worker may also be the display unit 22 of the terminal device 20 or the display unit 32 of the wearable device 30. The semiconductor manufacturing apparatus 10 according to this embodiment performs processing according to the processing procedure shown in Figure 5, for example. Figure 5 is a sequence diagram of an example of processing by the semiconductor manufacturing apparatus 10 according to this embodiment.

[0044] In step S10, the first worker operating the semiconductor manufacturing equipment 10 speaks a message to the second worker. The first worker operating the semiconductor manufacturing equipment 10 may include the unique name or identifier of the semiconductor manufacturing equipment 10 in the message they speak.

[0045] In step S12, the microphone 12 collects the speech of the first worker and outputs the audio signal of the first worker's speech to the device controller 16.

[0046] In step S14, the device controller 16 receives the audio signal of the first worker's speech from the microphone 12 and records the content of what the first worker said.

[0047] In step S16, the device controller 16 performs noise reduction on the recorded data using a mathematical model that has been trained by a machine learning algorithm to perform noise reduction processing.

[0048] In step S18, the device controller 16 uses a mathematical model trained on speech recognition processing by a machine learning algorithm to perform speech recognition on the recorded data and convert the content spoken by the first worker into text.

[0049] In step S20, the device controller 16 determines which semiconductor manufacturing device 10 the transcribed data (the transcribed content of the first operator's speech) was directed to.

[0050] In step S22, the device controller 16 displays the text data of the first worker's speech on the display unit 14, which is viewable by the second worker.

[0051] In step S24, the second worker can view the transcribed content of the first worker's speech displayed on the display unit 14 of the semiconductor manufacturing equipment 10. Therefore, even in a situation where it is difficult to hear sounds, such as inside the cleanroom 2, the second worker can accurately recognize the transcribed content of the first worker's speech in text form, like subtitles.

[0052] In this way, the second worker can correctly understand the content of the first worker's speech, and therefore, in this embodiment, it is effective in preventing accidents caused by a lack of communication between the first and second workers, such as electric shock accidents, contact accidents due to mechanical operation, or accidents caused by incorrect shaft-down.

[0053] <Other Embodiments> The above describes an example in which the content of the first worker's speech is converted into text and displayed on a display device accessible to the second worker, thereby enabling communication from the first worker to the second worker. In addition to converting the content of the first worker's speech into text and displaying it on a display device accessible to the second worker, the semiconductor manufacturing apparatus 10 according to this embodiment may also convert the content of the second worker's speech into text and display it on a display device accessible to the first worker. The semiconductor manufacturing apparatus 10 according to this embodiment may also enable bidirectional communication between the first worker and the second worker.

[0054] Furthermore, at least a portion of the processing performed by the device controller 16 of the semiconductor manufacturing apparatus 10 described above may be performed by an apparatus other than the semiconductor manufacturing apparatus 10. Figure 6 is a configuration diagram of an example of the support system 1 according to this embodiment. The support system 1 in Figure 6 has a plurality of semiconductor manufacturing apparatuses 10 and a support apparatus 100 located in a clean room 2. The plurality of semiconductor manufacturing apparatuses 10 and the support apparatus 100 are connected to each other via networks N1 and N2 such as the Internet or LAN, enabling data communication.

[0055] The support device 100 performs at least a portion of the processing performed by the device controller 16 of the semiconductor manufacturing equipment 10 described above. For example, the support device 100 receives voice data of speech uttered by workers from multiple semiconductor manufacturing equipment 10 in the cleanroom 2.

[0056] The support device 100 converts the received audio data into text using a mathematical model trained with a machine learning algorithm to perform noise reduction or speech recognition, and sends it back to the semiconductor manufacturing equipment 10 that the source of the audio data was identified by the discrimination unit 54.

[0057] The support system 1 in Figure 6 can receive audio data of speech uttered by workers from multiple semiconductor manufacturing equipment 10 within the cleanroom 2. Therefore, a mathematical model trained on the content of worker speech within the cleanroom 2 using a machine learning algorithm can be used for noise reduction processing or speech recognition processing.

[0058] A mathematical model trained using a machine learning algorithm on audio data collected within Cleanroom 2 can accurately remove noise from that audio data. Furthermore, a mathematical model trained using a machine learning algorithm on the content of worker speech within Cleanroom 2 can accurately recognize and transcribe the speech data spoken by workers within Cleanroom 2.

[0059] Although preferred embodiments of this embodiment have been described in detail above, this embodiment is not limited to the embodiments described above, and various modifications and substitutions can be made to the embodiments described above without departing from the scope of this embodiment.

[0060] It goes without saying that the support system 1 and semiconductor manufacturing apparatus 10 of this disclosure are not limited to the illustrated configuration, and there are various system configuration examples depending on the application and purpose. The semiconductor manufacturing apparatus 10 of this disclosure can be applied to any of the following: a single-wafer machine that processes substrates one by one, a batch machine that processes multiple substrates at once, and a semi-batch machine. [Explanation of Symbols]

[0061] 1. Support System 2. Cleanroom 10 Semiconductor manufacturing equipment 12 microphones 14, 22, 32 display section 16. Device Controller 20 Terminal devices 30 Wearable Devices 50 Recording Section 52 Text Conversion Section 54 Discrimination part 56 Display Control Unit 58 Memory section 60 Providing Department

Claims

1. A semiconductor manufacturing apparatus in which work is performed by a first worker and a second worker, A recording unit that records the content spoken by the first worker, A text conversion unit that converts the recorded data into text, A display control unit that displays the text data on a display device accessible to the second operator, Semiconductor manufacturing equipment having the following features.

2. The text conversion unit performs noise reduction and speech recognition on the recorded data using a mathematical model that has been trained by a machine learning algorithm to perform noise reduction or speech recognition. The semiconductor manufacturing apparatus according to claim 1.

3. A discrimination unit that determines which semiconductor manufacturing equipment the transcribed data was spoken to. The semiconductor manufacturing apparatus according to claim 1, further comprising the following:

4. The display control unit causes the converted text data to be displayed on the display unit of the semiconductor manufacturing apparatus, the display unit of the terminal device held by the second worker, or the display unit of the wearable device worn by the second worker. The semiconductor manufacturing apparatus according to claim 1.

5. A storage unit for storing the aforementioned text data, A providing unit provides the text data stored in the storage unit to the source requesting the confirmation of the text data, in accordance with the confirmation request for the text data. The semiconductor manufacturing apparatus according to claim 1, further comprising the following:

6. The aforementioned semiconductor manufacturing equipment is arranged in multiple locations within the cleanroom. A semiconductor manufacturing apparatus according to any one of claims 1 to 5.

7. A support method for a semiconductor manufacturing apparatus in which work is performed by a first worker and a second worker, the support method for the said work, Recording the content spoken by the first worker, The aforementioned recorded data is converted into text, The above-mentioned text data is displayed on a display device accessible to the second operator, A support method that has the following characteristics.

Images