Work support method and work support system

Abstract

To provide a work support method and work support system for enabling an operator to work in a working area to reliably recognize an unmanned carrier.SOLUTION: A work support method includes: collecting sound-recorded data in various environments in a working area 41; and constructing an acoustic model by machine learning by defining an acoustic feature quantity extracted from the sound-recorded data as learning data. When an operator wearing smart glasses 10 mounting an acoustic model is working in the working area 41, an unmanned carrier 90 travels in the working area 41 while issuing warning sound. The smart glasses 10 detect that the unmanned carrier 90 is issuing the warning sound by inputting the acoustic feature quantity extracted from the collected sound data to the acoustic model, so as to issue warning. The operator can reliably recognize the unmanned carrier 90 by the warning of the smart glasses 10 even when the operator is not aware of the warning sound issued by the unmanned carrier 90.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present invention relates to a method and system for supporting work performed by a worker in a work area where industrial equipment such as a substrate processing apparatus for performing predetermined processing on substrates is arranged and where automatic guided vehicles travel. Substrates to be processed by the substrate processing apparatus include, for example, semiconductor substrates, substrates for liquid crystal display devices, substrates for flat panel displays (FPDs), substrates for optical disks, substrates for magnetic disks, and substrates for solar cells. [Background technology]

[0002] Conventionally, in the manufacturing process of semiconductor devices, substrate processing apparatuses are used to perform various processes on substrates such as semiconductor substrates. Examples of substrate processing apparatuses include substrate cleaning apparatuses, heat treatment apparatuses, and inspection apparatuses. Typically, many substrate processing apparatuses are arranged in an orderly fashion in a large clean room. Maintenance is performed on these substrate processing apparatuses at appropriate intervals. Patent Document 1 describes arranging many substrate processing apparatuses at a relatively high density in a clean room and performing maintenance on the substrate processing apparatuses.

[0003] In a clean room where many substrate processing apparatuses are arranged, containers containing substrates are transported by automated guided vehicles (AGVs). Patent Document 2 describes that an automated guided vehicle carrying a container containing substrates automatically travels along a predetermined route within the clean room. The automated guided vehicle delivers unprocessed substrates to the substrate processing apparatus and retrieves processed substrates from the substrate processing apparatus. Workers who operate and maintain the substrate processing apparatus also work within the clean room. In other words, the workers work in an environment where automated guided vehicles are traveling within the clean room. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-4866 [Patent Document 2] Japanese Patent Publication No. 2020-189732 Summary of the Invention [Problem to be solved by the invention]

[0005] In addition to numerous substrate processing equipment, clean rooms are also home to tools and parts, creating a visually complex environment. As a result, workers working in clean rooms are visually fatigued and have difficulty noticing their surroundings and the movement of objects, which increases the risk of them being hit by an automated guided vehicle.

[0006] To avoid such dangers, automated guided vehicles emit a warning sound while traveling. However, the robots and pumps of the substrate processing equipment installed in the clean room also make noise, and if the automated guided vehicle continues to emit a warning sound in such a situation, workers concentrating on their work may become accustomed to the warning sound and may not notice the automated guided vehicle. Furthermore, if a worker is working very close to a robot or pump, the sound of the robot or pump itself may prevent the worker from hearing the warning sound in the first place.

[0007] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a work assistance method and a work assistance system that enable workers working in a work area to reliably recognize automatic guided vehicles. [Means for solving the problem]

[0008] In order to solve the above problems, a first aspect of the present invention provides a work support method for performing work in a work area where industrial equipment is arranged and where automatic guided vehicles travel, the method comprising: a model construction step of constructing an acoustic model that recognizes warning sounds emitted when the automatic guided vehicles move; a sound collection step of collecting sounds by the sound collection unit when a worker wearing a portable terminal equipped with a display unit, a communication unit, and a sound collection unit performs work in the work area; a determination step of determining whether the automatic guided vehicle is emitting a warning sound by inputting the sounds collected by the sound collection unit into the acoustic model; and a warning issuance step of the portable terminal issuing a warning when it is determined in the determination step that the automatic guided vehicle is emitting a warning sound. The model construction process includes a recording process of performing recording at each of a plurality of recording locations within the work area, with the automatic guided vehicle emitting a warning sound and with the automatic guided vehicle not emitting a warning sound; an analysis process of acquiring acoustic features from the sound recording data collected in the recording process; and a learning process of constructing the acoustic model by machine learning based on the labels assigned to the sound recording data collected in the recording process and the acoustic features. .

[0010] Also, 2 The embodiment is 1 In the task support method according to the aspect, the acoustic feature is a Mel-frequency cepstral coefficient, and in the determination step, Mel-frequency cepstral coefficients extracted from the sound collected by the sound collection unit are input to the acoustic model.

[0011] Also, 3 The embodiment of First or second In the work support method according to the aspect, when it is determined in the determination step that the automated guided vehicle is emitting a warning sound, the sound collection unit further includes a step of analyzing direction information of the warning sound, and in the alert issuing step, the mobile terminal issues the direction information along with the warning.

[0012] Also, 4 The aspects are as follows: 3 In the work support method according to any one of the above aspects, in the alert issuing step, the mobile terminal displays a warning screen and issues a warning sound.

[0013] Also, 5 The aspects are as follows: 4 In the work support method according to any one of the above aspects, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, and the mobile terminal is a smart glass.

[0014] Also, 6 The embodiment of Multiple A work support method for performing work in a work area where industrial equipment is arranged and where automatic guided vehicles travel, comprising: is determined in advance based on the processing schedules of the plurality of industrial machines a registration step of registering a travel route of the automated guided vehicle in the work area; and a display step of displaying the travel route on a portable terminal equipped with a display unit, a communication unit, and a sound collection unit when a worker wearing the portable terminal works in the work area. a warning generation step of the mobile terminal generating a warning when the worker approaches within a predetermined range from the travel route; Equipped with.

[0016] Also, 7 The embodiment of Sixth In the work support method according to the aspect, in the alert issuing step, the mobile terminal displays a warning screen and issues a warning sound.

[0017] Also, 8 The embodiment of 6th or 7th In the work support method according to the aspect, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, and the mobile terminal is a smart glass.

[0018] Also, 9 The aspect of the present invention is a work support system for performing work in a work area where industrial equipment is arranged and where an automated guided vehicle travels, the system comprising: a mobile terminal having a display unit, a communication unit, and a sound collection unit; a memory unit that stores an acoustic model that recognizes warning sounds emitted when the automated guided vehicle moves; a determination unit that determines whether the automated guided vehicle is emitting a warning sound by inputting sounds collected by the sound collection unit into the acoustic model when a worker wearing the mobile terminal performs work in the work area; and a warning issuance unit that issues a warning when the determination unit determines that the automated guided vehicle is emitting a warning sound. The acoustic model is constructed by machine learning based on acoustic features acquired from recording data collected by performing recordings at each of a plurality of recording locations within the work area, one with the automatic guided vehicle emitting a warning sound and one without the automatic guided vehicle emitting a warning sound, and labels assigned to the recording data. .

[0020] Also, 10 The embodiment is 9In the task assistance system according to the aspect, the acoustic feature is a Mel-frequency cepstral coefficient, and the determination unit inputs the Mel-frequency cepstral coefficient extracted from the sound collected by the sound collection unit into the acoustic model.

[0021] Also, 11 The embodiment of 9th or 10th In the work support system according to this aspect, when the judgment unit determines that the automated guided vehicle is emitting a warning sound, the sound collection unit analyzes the direction information of the warning sound, and the warning issuance unit issues the direction information along with the warning.

[0022] Also, 12 The embodiment of 9th to 11th In the work assistance system according to any one of the aspects, the warning issuing unit displays a warning screen and issues a warning sound.

[0023] Also, 13 The embodiment of 9th to 12th In the work assistance system according to any one of the aspects, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, and the mobile terminal is a pair of smart glasses.

[0024] Also, 14 The embodiment of Multiple A work support system for performing work in a work area where industrial equipment is arranged and where automatic guided vehicles travel, comprising: a mobile terminal having a display unit, a communication unit, and a sound collection unit; is determined in advance based on the processing schedules of the plurality of industrial machines a storage unit that stores a travel route of the automatic guided vehicle in the work area, and when a worker wearing the portable terminal works in the work area, the portable terminal displays the travel route. The system further includes a warning unit that issues a warning when the worker approaches within a predetermined range from the travel route. .

[0026] Also, 15 The embodiment of 14th In the work assistance system according to the aspect, the warning issuing unit displays a warning screen and issues a warning sound.

[0027] Also, 16 The embodiment of 14th or 15th In the work support system according to the aspect, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, and the mobile terminal is a smart glass. [Effects of the Invention]

[0028] 1st to 3rd 5 According to the work support method relating to the aspect, the sound collected by the sound collection unit is input into an acoustic model to determine whether the automated guided vehicle is emitting a warning sound, and when it is determined that a warning sound is being emitted, the mobile terminal issues a warning.Therefore, even if the worker is not aware of the warning sound emitted by the automated guided vehicle, the worker working in the work area can reliably recognize the automated guided vehicle due to the warning on the mobile terminal.

[0029] In particular, 3 According to the work support method of the aspect, the direction information of the warning sound is analyzed, and the mobile device issues the direction information along with the warning, so the worker can also recognize his or her positional relationship with the automatic guided vehicle.

[0030] No. 6 From 8 According to the work support method relating to the aspect, when a worker is working in a work area, the mobile device displays the travel route of the automated guided vehicle, so that the worker working in the work area can reliably recognize the automated guided vehicle.

[0031] No. 9 From 13 According to the work support system relating to the above aspect, the sound collected by the sound collection unit is input into an acoustic model to determine whether the automated guided vehicle is emitting a warning sound, and if it is determined that a warning sound is being emitted, a warning is issued.Therefore, even if the worker is not aware of the warning sound emitted by the automated guided vehicle, the worker working in the work area can reliably recognize the automated guided vehicle by the warning on the mobile terminal.

[0032] In particular, 11According to the work assistance system of the aspect (2), the direction information of the warning sound is analyzed and the direction information is issued together with the warning, so that the worker can also recognize the positional relationship with the automatic guided vehicle.

[0033] No. 14 From 16 According to the work support system relating to the above aspect, when a worker is working in a work area, the mobile device displays the travel route of the automated guided vehicle, so that the worker working in the work area can reliably recognize the automated guided vehicle. [Brief explanation of the drawings]

[0034] [Figure 1] 1 is a diagram showing a schematic configuration of a work support system according to the present invention; [Figure 2] FIG. 2 is a plan view showing an example of a layout of a plurality of substrate processing apparatuses. [Figure 3] FIG. 2 is a plan view of the substrate processing apparatus. [Figure 4] FIG. 2 is a diagram showing a schematic configuration of a processing unit. [Figure 5] FIG. 1 is a perspective view showing the appearance of smart glasses. [Figure 6] FIG. 2 is a block diagram showing functional configurations of a smart glass, a server, a work support terminal, and a control unit of a substrate processing apparatus. [Figure 7] 1 is a flowchart showing a procedure for constructing an acoustic model. [Figure 8] FIG. 1 is a diagram showing a schematic diagram of recording a sample sound in a work area. [Figure 9] FIG. 1 is a diagram illustrating model construction. [Figure 10] 10 is a flowchart showing the procedure for detecting warning sounds of an automated guided vehicle using smart glasses equipped with an acoustic model. [Figure 11] FIG. 10 is a diagram illustrating an example of detection of a warning sound from an automated guided vehicle. [Figure 12] FIG. 4 is a diagram illustrating an example of a warning message according to the first embodiment. [Figure 13]10 is a flowchart showing a procedure for displaying a travel route of an automated guided vehicle to call attention to the route. [Figure 14] FIG. 2 is a diagram showing an example of a travel route of an automated guided vehicle within a work area. [Figure 15] FIG. 10 is a diagram illustrating an example of a warning message according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0035] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Hereinafter, expressions indicating relative or absolute positional relationships (e.g., "in one direction," "along one direction," "parallel," "orthogonal," "center," "concentric," "coaxial," etc.) not only strictly represent the positional relationship but also represent a state of relative angular or distance displacement within a tolerance or a range that provides equivalent functionality, unless otherwise specified. Furthermore, expressions indicating an equal state (e.g., "identical," "equal," "homogeneous," etc.) not only represent a state of strict quantitative equality but also represent a state of difference that provides a tolerance or equivalent functionality, unless otherwise specified. Furthermore, expressions indicating a shape (e.g., "circular," "square," "cylindrical," etc.) not only represent a geometrically strict shape but also represent a shape within a range that provides equivalent functionality, such as irregularities or chamfers, unless otherwise specified. Furthermore, expressions such as "comprise," "comprise," "include," "have," etc., regarding components, are not exclusive expressions that exclude the presence of other components. Furthermore, the expression "at least one of A, B, and C" includes "A only," "B only," "C only," "any two of A, B, and C," and "all of A, B, and C."

[0036] First Embodiment FIG. 1 is a diagram showing a schematic configuration of a work support system according to the present invention. The work support system according to the present invention includes a plurality of substrate processing apparatuses 50, smart glasses 10, a server 70, and a work support terminal 80. The controllers of the smart glasses 10 and the substrate processing apparatuses 50 are connected to an information and communication network 5 (e.g., the Internet) via wireless communication. The work support terminal 80 and the server 70 are connected to the information and communication network 5 via a wired connection. Information can be transmitted and received between devices connected to the information and communication network 5; for example, information can be exchanged between the smart glasses 10 and the work support terminal 80. Note that whether each device is connected to the information and communication network 5 wirelessly or via a wired connection is not limited to the above example, and any appropriate form can be used (for example, the work support terminal 80 may be connected to the information and communication network 5 wirelessly).

[0037] 2 is a plan view showing an example of the layout of a plurality of substrate processing apparatuses 50. As shown in FIG. 2, the plurality of substrate processing apparatuses 50 are arranged in a regular pattern at regular intervals in a clean room 40. The clean room 40 is provided, for example, in a semiconductor device manufacturing factory, and is a room where a certain level of air cleanliness is ensured and the temperature and humidity are controlled. Workers perform operations and maintenance on the substrate processing apparatuses 50 in the clean room 40. That is, in the first embodiment, the inside of the clean room 40 in which the plurality of substrate processing apparatuses 50 are arranged is the work area.

[0038] An automated guided vehicle (AGV) 90 travels within the clean room 40, which is the work area. The automated guided vehicle 90 travels on the floor of the clean room 40 under the control of pre-programmed software. The automated guided vehicle 90 is guided, for example, by reading magnetic tape or markers provided on the floor of the clean room 40. The automated guided vehicle 90 travels according to route data provided by, for example, a host computer (not shown) that manages multiple substrate processing apparatuses 50. In other words, the automated guided vehicle 90 travels along a predetermined route that has been set in advance. Note that the automated guided vehicle 90 may also travel autonomously without being guided.

[0039] 3 is a plan view of the substrate processing apparatus 50. The substrate processing apparatus 50 is, for example, a single-wafer substrate cleaning apparatus that cleans substrates one by one. The substrate processing apparatus 50 includes an indexer 51, a plurality of processing units 52, a transfer robot 56, and a main transport robot 57.

[0040] A carrier C accommodating a plurality of substrates W is placed on the indexer 51. For example, three carriers C can be placed on the indexer 51. The automated guided vehicle 90 transports the carrier C accommodating a plurality of substrates W within the clean room 40 and hands it over to the indexer 51 of the substrate processing apparatus 50. More specifically, the automated guided vehicle 90 loads and transports the carrier C accommodating unprocessed substrates W, and hands it over to the indexer 51 of the substrate processing apparatus 50. The automated guided vehicle 90 also receives from the indexer 51 the carrier C accommodating substrates W that have been processed in the substrate processing apparatus 50 and transports it. The carrier C is, for example, a front opening unified pod (FOUP) that stores substrates W in an enclosed space.

[0041] The transfer robot 56 is configured to be capable of sliding movement, lifting and lowering movement, turning movement, and advancing and retreating movement of its hand along the arrangement direction of the plurality of carriers C. The transfer robot 56 removes unprocessed substrates W from the carriers C placed on the indexer 51. In addition, the transfer robot 56 stores processed substrates W into the carriers C placed on the indexer 51.

[0042] In the first embodiment, for example, three processing units 52 are stacked to form one stack. Then, for example, four stacks are arranged around the main transport robot 57 of the substrate processing apparatus 50. That is, one substrate processing apparatus 50 includes, for example, 12 (=3×4) processing units 52. Fig. 3 shows one stage of processing units 52 included in the same horizontal plane of the four stacks.

[0043] The main transport robot 57, which is disposed at the center of the four stacks, is configured to be capable of lifting and lowering, rotating, and moving its transport arm AM forward and backward. The main transport robot 57 can deliver substrates W to and from all 12 processing units 52. The main transport robot 57 receives unprocessed substrates W from the transfer robot 56 and transports them into any of the 12 processing units 52. The main transport robot 57 also removes processed substrates W from the processing units 52 and delivers them to the transfer robot 56.

[0044] The substrate processing apparatus 50 also includes a control unit 55. The control unit 55 is a general-purpose computer that controls the operations of the transfer robot 56, the main transport robot 57, and each of the processing units 52 provided within the apparatus. The control unit 55 has a touch panel serving as an input / output interface provided on a wall surface of the apparatus, and a communication unit that communicates with the outside of the apparatus. Note that, for convenience of illustration, the control unit 55 is shown in the indexer 51 in FIG. 3, but is not limited to this, and the control unit 55 may be provided at an appropriate position within the substrate processing apparatus 50.

[0045] FIG. 4 is a diagram showing a schematic configuration of the processing unit 52. The processing unit 52 includes a processing chamber 60, a spin holder 61, and a discharge nozzle 65. The processing chamber 60 is a hollow housing. The spin holder 61, the discharge nozzle 65, and the like are provided inside the processing chamber 60. The processing chamber 60 also has a loading / unloading port (not shown). The loading / unloading port is opened and closed by a shutter. With the loading / unloading port open, the main transport robot 57 loads and unloads the substrate W into and from the processing chamber 60. The loading / unloading port is closed during processing of the substrate W. The processing chamber 60 also has an air supply mechanism and an exhaust mechanism (not shown).

[0046] The rotation holder 61 includes a spin chuck 62 and a spin motor 63. The spin chuck 62 is a substrate holder that holds the substrate W in a horizontal position (a position in which the normal to the main surface of the substrate W is aligned vertically). The spin chuck 62 is, for example, a vacuum suction-type chuck. The spin chuck 62 has a disk shape with a diameter smaller than the diameter of the substrate W. The spin chuck 62 suction-holds the central portion of the lower surface of the substrate W. When the lower surface of the substrate W is suction-held by the spin chuck 62, the peripheral edge of the substrate W extends beyond the outer circumferential edge of the spin chuck 62. The spin chuck 62 may be another type of chuck, such as a clamping-type mechanical chuck.

[0047] The spin chuck 62 is connected to the spin motor 63 via a motor shaft. That is, the upper end of the motor shaft of the spin motor 63 is connected to the center of the lower surface of the spin chuck 62. When the spin motor 63 rotates the motor shaft while the substrate W is held by suction on the spin chuck 62, the substrate W and the spin chuck 62 rotate in a horizontal plane around a rotation axis along the vertical direction.

[0048] A cup 64 is provided to surround the periphery of the spin chuck 62. The cup 64 can be raised and lowered by a lifting mechanism (not shown). The cup 64 has a cylindrical shape, and the upper part of the cup 64 is inclined so that it approaches the spin chuck 62 as it goes up. However, the inner diameter of the upper end part of the cup 64 is larger than the diameter of the substrate W. During processing of the substrate W, the upper end of the cup 64 is higher than the height position of the substrate W held by the spin chuck 62. Therefore, liquid scattered by centrifugal force from the substrate W rotated by the spin motor 63 is received and recovered by the cup 64. The liquid recovered by the cup 64 is discharged from a drain pipe provided at the bottom of the cup 64. The cup 64 may have a multi-stage structure with multiple recovery ports provided for different purposes.

[0049] The discharge nozzle 65 discharges a processing liquid onto the substrate W held on the spin chuck 62. The processing liquid is a term that encompasses various chemical liquids and pure water. Examples of the chemical liquid include a liquid for etching or a liquid for removing particles. Specifically, an SC-1 liquid (a mixed solution of ammonium hydroxide, hydrogen peroxide, and pure water), an SC-2 liquid (a mixed solution of hydrochloric acid, hydrogen peroxide, and pure water), or hydrofluoric acid is used. The discharge nozzle 65 is moved by a drive mechanism (not shown) between a processing position above the spin chuck 62 and a standby position outside the cup 64. At the processing position, the discharge nozzle 65 discharges the chemical liquid onto the substrate W held on the spin chuck 62, thereby performing, for example, an etching process on the substrate W. Furthermore, the discharge nozzle 65 discharges pure water onto the substrate W, thereby performing a pure water rinse process on the substrate W.

[0050] A worker who performs operations or maintenance on the substrate processing apparatus 50 wears smart glasses 10. The smart glasses 10 are a type of wearable terminal that uses a head-mounted display (HMD). The smart glasses 10 are also devices that realize AR (Augmented Reality) or MR (Mixed Reality). For example, Microsoft's "HoloLens" (registered trademark) can be used as the smart glasses 10.

[0051] FIG. 5 is a perspective view showing the appearance of the smart glasses 10. The smart glasses 10 include a visor 11 and a headband 12. A worker wears the smart glasses 10 by placing the headband 12 on their head. The worker can adjust the length of the headband 12 to fit the size of their head. The headband 12 also includes a power button, a brightness button, a volume button, and the like.

[0052] The visor 11 includes various sensors and a display. The display is a see-through holographic lens. That is, the display can display a three-dimensional image in the worker's field of view using a hologram, and transmits light from real objects in the same way as regular eyeglass lenses. Therefore, a worker wearing the smart glasses 10 can view the displayed three-dimensional image while viewing real objects through the display.

[0053] The sensors of the visor 11 include, for example, multiple visible light cameras that mainly capture images in front of the visor 11, an infrared camera that tracks the worker's line of sight, a depth sensor that measures the distance to an object, and an inertial measurement sensor. The infrared camera tracks the line of sight by measuring the movement of the eyeballs of the person wearing the smart glasses 10. The depth sensor measures the distance to an object using, for example, the ToF (Time of Flight) method. The inertial measurement sensor is composed of an accelerometer, a gyroscope, a magnetometer, etc.

[0054] The smart glasses 10 also have a built-in computer equipped with a CPU, memory, etc. The smart glasses 10 are also provided with a wireless communication mechanism, and the computer in the smart glasses 10 connects to the information and communication network 5 using the wireless communication mechanism. The smart glasses 10 are also provided with a microphone array, a speaker, a battery, etc. The microphone array is a spatial arrangement of multiple microphones (for example, six microphones arranged at 60° intervals), and by analyzing the differences (time difference, phase difference, etc.) in the sounds measured by each microphone, the position and direction of the sound can be estimated.

[0055] 6 is a block diagram showing the functional configuration of the smart glasses 10, the server 70, the work support terminal 80, and the control unit 55 of the substrate processing apparatus 50. The smart glasses 10 include an imaging unit 21, a communication unit 22, a display unit 23, a sound collection unit 24, and a storage unit 25. The imaging unit 21 includes a visible light camera provided on the visor 11 described above. The imaging unit 21 includes, for example, four visible light cameras that capture images of the front and diagonally forward, and can capture images of the field of view of the worker wearing the smart glasses 10.

[0056] The communication unit 22 includes the wireless communication mechanism of the smart glasses 10 described above. The communication unit 22 transmits and receives data to and from the work support terminal 80 and the server 70 via the information and communication network 5. The communication unit 22 can also transmit and receive data directly to and from the control unit 55 of the substrate processing apparatus 50 if the distance is short. That is, the communication unit 22 can transmit data and commands to the control unit 55 of the substrate processing apparatus 50 directly or via the information and communication network 5.

[0057] The display unit 23 includes the display of the visor 11. The display unit 23 has a holographic processing device and displays a 3D image at a predetermined spatial position using hologram technology. Note that the 3D image displayed by the display unit 23 is not limited to a 3D shape, and may be a 2D image such as a document.

[0058] The sound collection unit 24 includes the microphone array described above. The sound collection unit 24 collects sounds around the smart glasses 10. Furthermore, the sound collection unit 24 can analyze and identify directional information of the generated sound, that is, the direction from which the sound is propagating, by analysis using the microphone array.

[0059] The storage unit 25 includes a memory and storage installed in the smart glasses 10. The memory and storage provided in the smart glasses 10 are, for example, a dynamic random access memory (DRAM) and a universal flash storage (UFS), respectively. The storage unit 25 stores applications and data used by the computer of the smart glasses 10.

[0060] The smart glasses 10 also include a determination unit 31 and a warning issuance unit 36. The determination unit 31 and the warning issuance unit 36 ​​are function processing units that are realized by the CPU of the smart glasses 10 executing a predetermined processing program. The processing contents of the determination unit 31 and the warning issuance unit 36 ​​will be described in further detail below.

[0061] The control unit 55 of the substrate processing apparatus 50 controls the operation of mechanisms provided in the processing unit 52, such as the discharge nozzle 65. The control unit 55 of the substrate processing apparatus 50 can communicate with the communication unit 22 of the smart glasses 10, and can also control the operation of various mechanisms provided in the processing unit 52 in accordance with operation instruction commands transmitted from the smart glasses 10.

[0062] The work support terminal 80 and the server 70 are installed, for example, in a factory of a vendor that manufactures and maintains the substrate processing apparatus 50. The work support terminal 80 and the server 70 are capable of communicating with the smart glasses 10 via the information and communication network 5. The work support terminal 80 and the server 70 are also capable of communicating with each other via the information and communication network 5.

[0063] The work support terminal 80 and the server 70 are general computer systems. That is, the work support terminal 80 and the server 70 are equipped with a CPU which is a circuit that performs various arithmetic processing, a ROM which is a read-only memory that stores basic programs, a RAM which is a readable and writable memory that stores various information, a storage unit (for example, a magnetic disk or SSD) that stores control software and data, and a communication unit that communicates with the information communication network 5.

[0064] The work support terminal 80 is a computer that, for example, allows a work supporter on the vendor side to support the work of a worker in the clean room 40. The work supporter can send various information from the work support terminal 80 to the smart glasses 10 worn by the worker in the clean room 40.

[0065] In the work support system according to the present invention, the server 70 is a computer that executes predetermined processes in response to requests from the smart glasses 10 and the work support terminal 80. The server 70 includes a memory unit 74 with a relatively large capacity. Large-sized data created by the smart glasses 10 and the work support terminal 80 may be stored in the memory unit 74.

[0066] Next, a work assistance method using the work assistance system having the above-described configuration will be described. In the first embodiment, an acoustic model for detecting warning sounds emitted by the automated guided vehicle 90 is constructed, and the acoustic model is installed in the smart glasses 10 to detect the warning sounds of the automated guided vehicle 90 within the work area. When traveling through the work area, the automated guided vehicle 90 emits a warning sound to avoid danger. The automated guided vehicle 90 travels through the work area while playing music, for example. The warning sound is not limited to music, and may be, for example, a voice or a beep. Typically, the volume of the warning sound emitted by the automated guided vehicle 90 is at least loud enough for a worker to hear in an environment where robots, pumps, etc. provided in the substrate processing apparatus 50 emit noise within the work area.

[0067] FIG. 7 is a flowchart showing the procedure for constructing an acoustic model. The construction of an acoustic model is a preparatory step for the work assistance method according to the present invention. First, sample sounds are recorded in the work area to collect recorded data (step S11). FIG. 8 is a diagram showing the recording of sample sounds in the work area. In the first embodiment, the work area 41 is located in a clean room 40. Within the work area 41, multiple substrate processing apparatuses 50 are arranged and automated guided vehicles 90 travel. In step S11, sample sounds are recorded within the work area 41 at multiple recording locations R1. The recording is performed using a predetermined recorder (e.g., an IC recorder).

[0068] Furthermore, at each of the multiple recording locations R1, recording is performed both when the automated guided vehicle 90 is emitting a warning sound within the work area 41 and when the automated guided vehicle 90 is not emitting a warning sound. Recording is performed at the multiple recording locations R1 not only when the automated guided vehicle 90 is emitting a warning sound, but also when the automated guided vehicle 90 is not emitting a warning sound in order to collect recording data in a wide variety of environments. In other words, by recording at different locations within the work area 41 both when a warning sound is being emitted and when it is not being emitted, it is possible to collect recording data in a variety of environments. By increasing the variety of recording data, it is possible to enrich the learning data for machine learning, which will be described later, and as a result, it is possible to improve the accuracy of the acoustic model that is constructed.

[0069] Next, a label is created for each of the collected multiple audio data (step S12). In this embodiment, a label is information indicating a correct answer given to each audio data. For example, a label "warning sound present" is created for audio data in a state where the automatic guided vehicle 90 is emitting an alarm sound. Also, a label "no alarm sound" is created for audio data in a state where the automatic guided vehicle 90 is not emitting an alarm sound. The labels may be created, for example, by the work assistance terminal 80 or the server 70. The created labels will become training data in subsequent machine learning.

[0070] Next, each of the collected multiple pieces of sound recording data is converted into Mel-Frequency Cepstrum Coefficients (MFCC) (step S13). MFCC is one type of acoustic feature. The collected sound recording data is a time-series signal, and it is inconvenient to input it directly into a model. Therefore, acoustic features, which are important information from the sound recording data, are extracted and applied to the model. In the first embodiment, MFCCs are used as acoustic features.

[0071] Conversion of recorded data, which is a time-series signal, into MFCCs is performed, for example, by the following process. First, a Fourier transform is performed on the recorded data, which is a time-series signal, to obtain a frequency spectrum. A Mel filter bank is applied to this frequency spectrum to obtain a Mel spectrum. A Mel spectrum is a spectrum in which the frequency axis is in the Mel scale. The Mel scale is a scale based on human hearing, which is sensitive to low-frequency sounds but insensitive to high-frequency sounds. MFCCs are then obtained by applying a discrete cosine transform to the Mel spectrum. MFCCs are acoustic features that take human hearing into account, and are therefore widely used in the field of speech recognition. The conversion process from recorded data to MFCCs can be performed, for example, by the work assistance terminal 80 or the server 70.

[0072] Next, an acoustic model is constructed by machine learning based on the obtained labels and MFCCs (step S14). FIG. 9 is a diagram schematically illustrating model construction. An acoustic model is constructed by machine learning using the MFCCs obtained by converting the audio data and the labels assigned to the audio data as training data. The labels are information indicating the correct answer given to the audio data and serve as training data for the machine learning. That is, in the first embodiment, supervised learning is performed in which example problems (MFCCs) and correct answers (labels) are paired. Also, in the first embodiment, audio data is collected in various environments to train the acoustic model and improve accuracy. Note that the machine learning may be performed, for example, on the work assistance terminal 80 or the server 70, or by another computer system. Also, some of the MFCCs and labels may be used as validation data and test data for the constructed acoustic model.

[0073] In the first embodiment, the acoustic model constructed by machine learning is installed in the smart glasses 10 (step S15). For example, the acoustic model constructed in the work support terminal 80 is stored in the storage unit 25 of the smart glasses 10. The acoustic model may be constructed in advance, for example, when the substrate processing apparatus 50 is installed in the clean room 40.

[0074] After constructing an acoustic model and loading it into the smart glasses 10, when a worker wearing the smart glasses 10 performs work at an appropriate timing in the work area 41, the smart glasses 10 detect the warning sound emitted by the automatic guided vehicle 90 while it is traveling. For example, when a worker wearing the smart glasses 10 performs maintenance on the substrate processing apparatus 50 in the work area 41 or operates the substrate processing apparatus 50, the warning sound of the automatic guided vehicle 90 is detected by the smart glasses 10 equipped with the acoustic model.

[0075] 10 is a flowchart showing the procedure for detecting warning sounds from an automated guided vehicle 90 using smart glasses 10 equipped with an acoustic model. First, when a worker wearing the smart glasses 10 is working in the work area 41, the sound collection unit 24 of the smart glasses 10 collects sounds within the work area 41 (step S21). Sounds generated within the work area 41 include operating sounds of the robots and pumps of the substrate processing apparatus 50, the voice of the worker, and warning sounds emitted when the automated guided vehicle 90 is traveling. The sound data collected by the sound collection unit 24 is a time-series signal whose intensity changes over time.

[0076] Next, the sound data collected by the smart glasses 10 is converted into Mel Frequency Cepstrum Coefficients (MFCCs) (step S22). As mentioned above, MFCCs are one type of acoustic feature, and are features that take into account human hearing in particular. The method of conversion to MFCCs is the same as step S13 in the acoustic model construction process (Fig. 7). That is, a Fourier transform is performed on the collected sound data to obtain a frequency spectrum, a Mel filter bank is applied to the frequency spectrum to obtain a Mel spectrum, and a discrete cosine transform is further applied to the Mel spectrum to obtain MFCCs.

[0077] Next, the determination unit 31 of the smart glasses 10 inputs the obtained MFCCs into the acoustic model installed in the smart glasses 10 (step S23). By inputting the MFCCs, which are acoustic features extracted from sound data collected within the work area 41, into the fully trained acoustic model, the acoustic model outputs whether or not the input data contains a warning sound from the automated guided vehicle 90. The determination unit 31 determines whether or not the automated guided vehicle 90 is emitting a warning sound within the work area 41 based on the output result of the acoustic model (step S24). That is, if the acoustic model outputs a result that the input data contains a warning sound, the determination unit 31 determines that the automated guided vehicle 90 is emitting a warning sound within the work area 41. On the other hand, if the acoustic model outputs a result that the input data does not contain a warning sound, the determination unit 31 determines that the automated guided vehicle 90 is not emitting a warning sound.

[0078] When the determination unit 31 determines that the automated guided vehicle 90 is emitting a warning sound within the work area 41, the sound collection unit 24 of the smart glasses 10 analyzes the direction information of the warning sound (step S25). The sound collection unit 24 includes a microphone array in which multiple microphones are spatially arranged, and can analyze the direction from which the warning sound is propagating.

[0079] Furthermore, the sound collection unit 24 detects whether the warning sound is gradually getting louder or quieter, and based on the result, the smart glasses 10 determine whether the automatic guided vehicle 90 is approaching or moving away. Specifically, if the warning sound collected by the sound collection unit 24 is gradually getting louder, the smart glasses 10 determine that the automatic guided vehicle 90 is approaching. Conversely, if the warning sound is gradually getting quieter, the smart glasses 10 determine that the automatic guided vehicle 90 is moving away.

[0080] FIG. 11 is a diagram schematically illustrating an example of detecting a warning sound from an automated guided vehicle 90. A worker wearing smart glasses 10 equipped with an acoustic model is working at position P1 within the work area 41. At that time, the automated guided vehicle 90 is traveling in the direction indicated by arrow AR11 in FIG. 11. The automated guided vehicle 90 emits a warning sound to avoid danger while traveling within the work area 41. The smart glasses 10 worn by the worker detect that the automated guided vehicle 90 is emitting a warning sound by inputting MFCCs extracted from collected sound data into the acoustic model. The smart glasses 10 also detect that the warning sound from the automated guided vehicle 90 is propagating from the front right of the worker and that the warning sound is gradually getting louder. As a result, the smart glasses 10 detect that the automated guided vehicle 90 is approaching from the front right of the worker.

[0081] Thereafter, the warning issuing unit 36 ​​of the smart glasses 10 issues a warning (step S26). Specifically, for example, the warning issuing unit 36 ​​displays a warning screen as a stereoscopic image on the display unit 23. FIG. 12 is a diagram showing an example of a warning screen displayed by the warning issuing unit 36. As shown in the figure, the warning screen displays a warning about the presence of the automatic guided vehicle 90 along with direction information of the automatic guided vehicle 90. The direction information includes information on the direction of the automatic guided vehicle 90 relative to the worker and whether the automatic guided vehicle 90 is approaching or receding. That is, in the example of FIG. 11, a warning message is displayed indicating that the automatic guided vehicle 90 is approaching from the front right. By displaying a warning screen including a message such as that shown in FIG. 12, the worker can recognize that the automatic guided vehicle 90 is approaching from the front right, and will pay attention to the automatic guided vehicle 90. As a result, the safety of the worker can be ensured. The warning issued by the warning issuing unit 36 ​​is not limited to a warning screen, but may instead or in addition be an audio warning, or may display a colored annotation in the direction in which the automated guided vehicle 90 is approaching.

[0082] In the first embodiment, an acoustic model for detecting warning sounds from the automated guided vehicle 90 is constructed in advance and installed in the smart glasses 10. When constructing the acoustic model, recordings are made in the work area 41 both when the automated guided vehicle 90 is emitting warning sounds and when it is not emitting warning sounds, to collect recording data in various environments, and MFCCs are extracted from the recording data as acoustic features to be used as learning data for machine learning. Because machine learning is performed based on a wealth of learning data, the accuracy of the acoustic model can be improved.

[0083] In the first embodiment, the MFCCs extracted from the sound collected by the smart glasses 10 worn by the worker performing the work are input into an acoustic model to determine whether the automated guided vehicle 90 is emitting a warning sound. If it is determined that the automated guided vehicle 90 is emitting a warning sound, the warning issuing unit 36 ​​of the smart glasses 10 issues a warning.

[0084] Originally, the reason why the automated guided vehicle 90 issues a warning sound is to alert nearby workers to the presence of the automated guided vehicle 90 and to avoid danger. However, if the automated guided vehicle 90 continues to issue a warning sound in an environment where the substrate processing apparatus 50 and the like also make noise, the workers who are concentrating on their work may become accustomed to the warning sound and fail to recognize the approach of the automated guided vehicle 90. In this embodiment, even if the workers have become accustomed to the warning sound issued by the automated guided vehicle 90, the smart glasses 10 issue a new warning, and this stimulus allows the workers to reliably recognize the presence of the automated guided vehicle 90.

[0085] Furthermore, in the first embodiment, when it is determined that the automated guided vehicle 90 is emitting a warning sound, the smart glasses 10 analyze the direction information of the warning sound. The direction information obtained as a result of the analysis is displayed on the warning screen. The direction information includes the direction of the automated guided vehicle 90 as seen from the worker and information on whether the automated guided vehicle 90 is approaching or moving away. This allows the worker to more accurately recognize their positional relationship with the automated guided vehicle 90.

[0086] Second Embodiment Next, a second embodiment of the present invention will be described. The configuration of the work support system in the second embodiment is the same as that in the first embodiment. While the first embodiment detects the warning sound of the automatic guided vehicle 90, the second embodiment displays the pre-registered travel route of the automatic guided vehicle 90 to alert the worker.

[0087] Fig. 13 is a flowchart showing a procedure for displaying the travel route of the automated guided vehicle 90 to call attention to the situation. The travel route of the automated guided vehicle 90 within the clean room 40, which is the work area 41, is determined in advance based on the processing schedules of the multiple substrate processing apparatuses 50 arranged within the clean room 40. Data on the travel route of the automated guided vehicle 90 within the work area 41 is registered in advance, for example, in the storage unit 74 of the server 70 (step S31). Fig. 14 is a diagram showing an example of the travel route of the automated guided vehicle 90 within the work area 41.

[0088] When a worker wearing the smart glasses 10 works in the work area 41, the display unit 23 of the smart glasses 10 displays the travel route of the automatic guided vehicle 90 (step S32). Specifically, for example, when a worker wearing the smart glasses 10 enters the work area 41, the smart glasses 10 read out the travel route of the automatic guided vehicle 90 registered in the memory unit 74 of the server 70, and the display unit 23 displays the travel route as a stereoscopic image as shown in FIG. 14. This allows the worker to recognize the travel route of the automatic guided vehicle 90 and to pay attention to the automatic guided vehicle 90. As a result, the safety of the worker can be ensured.

[0089] The smart glasses 10 monitor whether a worker is approaching the travel path of the automated guided vehicle 90 (step S33). Specifically, the smart glasses 10 determine whether the position of the worker wearing the smart glasses 10 is within a predetermined range from the travel path of the automated guided vehicle 90. One method for identifying the worker's position is, for example, to have the smart glasses 10 scan the work area 41 to create a spatial mesh, and then identify the worker's position by comparing the spatial mesh with a previously created spatial mesh. To create the spatial mesh, the worker wearing the smart glasses 10 simply turns on the scan mode. The created spatial mesh is represented by a large number of triangular meshes. Various shapes, including curved and flat surfaces, are represented by a set of many connected triangles. Complex shapes including uneven surfaces are represented by a high density of triangles, while flat shapes are represented by a relatively low density of triangles.

[0090] When the position of the worker identified by the comparison of the spatial meshes is within a predetermined range from the travel path of the automatic guided vehicle 90, the worker is too close to the travel path, and the warning unit 36 ​​of the smart glasses 10 issues a warning (step S34). Specifically, for example, the warning unit 36 ​​displays a warning screen as a three-dimensional image on the display unit 23. FIG. 15 is a diagram showing an example of the warning screen of the second embodiment displayed by the warning unit 36. As shown in the figure, the warning screen displays a warning message indicating that the worker is too close to the travel path of the automatic guided vehicle 90. By displaying the warning screen including the message as shown in FIG. 15, the worker can recognize that he or she is too close to the travel path of the automatic guided vehicle 90, and will pay attention to the automatic guided vehicle 90. As a result, the safety of the worker can be ensured. As in the first embodiment, the warning issued by the warning issuing unit 36 ​​is not limited to a warning screen, but may instead or in addition be an audio warning, or may display a colored annotation on the travel path of the automated guided vehicle 90.

[0091] In the second embodiment, when a worker wearing the smart glasses 10 works in the work area 41, the smart glasses 10 display the travel route of the pre-registered automatic guided vehicle 90. This allows the worker working in the work area 41 to recognize the automatic guided vehicle 90.

[0092] Furthermore, when a worker wearing the smart glasses 10 approaches within a predetermined range from the travel path of the automatic guided vehicle 90, the smart glasses 10 issue a warning. This allows the worker to reliably recognize that he or she is approaching too close to the travel path of the automatic guided vehicle 90.

[0093] <Modification> Although the embodiments of the present invention have been described above, various modifications can be made to the present invention without departing from the spirit and scope of the invention. For example, in the first embodiment, MFCCs are extracted from sound recording data as acoustic features and used as training data for machine learning. However, this is not limited to this. A frequency spectrum obtained by performing a Fourier transform on the sound recording data can also be used as the acoustic feature. In this case, in step S14, an acoustic model is constructed by machine learning using the frequency spectrum as training data, and in step S23, the frequency spectrum obtained from the collected sound data is input to the acoustic model. Alternatively, a Mel spectrum can be adopted as the acoustic feature by applying a Mel filter bank to the frequency spectrum. Alternatively, an acoustic model can be constructed using sound data, which is a time-series signal, as is, without extracting acoustic features.

[0094] Furthermore, in the first embodiment, the automated guided vehicle 90 approaches the worker, but even if the automated guided vehicle 90 moves away from the worker, the smart glasses 10 will issue a warning if they detect the warning sound of the automated guided vehicle 90. In other words, the smart glasses 10 will also issue a warning if they detect that the warning sound of the automated guided vehicle 90 is gradually getting quieter. In this way, the worker can reliably recognize the presence of the automated guided vehicle 90.

[0095] Furthermore, in the first embodiment, the direction information includes the direction of the automatic guided vehicle 90 relative to the worker and information on whether the automatic guided vehicle 90 is approaching or moving away, but in addition to this, information on the distance from the worker to the automatic guided vehicle 90 may be included. The distance from the worker to the automatic guided vehicle 90 can be calculated from the volume of the warning sound collected by the sound collection unit 24.

[0096] Furthermore, in the first embodiment, the constructed acoustic model is installed in the smart glasses 10, but this is not limited thereto, and the acoustic model may be stored in the server 70 or the work support terminal 80 and used by the smart glasses 10. Furthermore, in the second embodiment, data on the travel route of the automatic guided vehicle 90 may be registered directly in the smart glasses 10.

[0097] Moreover, both the first embodiment and the second embodiment may be implemented. That is, the smart glasses 10 may detect the warning sound of the automatic guided vehicle 90 while displaying the travel route of the automatic guided vehicle 90. In this way, the worker can more reliably recognize the automatic guided vehicle 90.

[0098] Furthermore, in each of the above embodiments, the worker uses smart glasses 10, but this is not limited thereto, and a portable terminal such as a tablet terminal or a smartphone may be used instead of the smart glasses 10. That is, any portable terminal equipped with a display unit, a communication unit, a sound collection unit, etc. is sufficient. However, since using a tablet terminal or the like would occupy the worker's hands while holding it, it is preferable to use a wearable terminal such as the smart glasses 10.

[0099] Furthermore, the substrate processing apparatus 50 installed in the normal area of ​​the clean room 40 is not limited to a substrate cleaning apparatus, but may be any apparatus that performs a predetermined process on a substrate, such as a heat treatment apparatus, an exposure apparatus, a coating and developing apparatus, a measuring apparatus, or an inspection apparatus. When the substrate processing apparatus 50 is a substrate cleaning apparatus, it may be a single-wafer type cleaning apparatus that cleans substrates one by one, or a batch type cleaning apparatus that cleans multiple substrates at once.

[0100] Furthermore, the work support technology according to the present invention is not limited to substrate processing equipment, but may be applied to any industrial equipment that performs any type of processing, such as a printing processing equipment, a film forming equipment, a medical equipment, and an appearance inspection equipment. [Explanation of symbols]

[0101] 5. Information and Communications Network 10. Smart Glasses 21 Imaging unit 22 Communications Department 23 Display section 24 Sound collection section 25,74 Storage part 31 Judgment section 36 Warning and Notification Department 40 Clean Room 41 Work Area 50 Substrate processing equipment 70 servers 80 Work support terminal 90 Automated Guided Vehicle W substrate

Claims

1. A work support method for performing work in a work area where industrial equipment is arranged and where automatic guided vehicles travel, comprising: a model construction step of constructing an acoustic model that recognizes a warning sound emitted when the automatic guided vehicle moves; a sound collection step in which the sound collection unit collects sound when a worker wearing a mobile terminal equipped with a display unit, a communication unit, and a sound collection unit works in the work area; a determination step of determining whether the automatic guided vehicle is emitting a warning sound by inputting the sound collected by the sound collection unit into the acoustic model; a warning issuing step of the mobile terminal issuing a warning when it is determined in the determination step that the automatic guided vehicle is issuing a warning sound; Equipped with The model building step includes: a recording step of recording in a state where the automatic guided vehicle is emitting a warning sound and a state where the automatic guided vehicle is not emitting a warning sound at each of a plurality of recording locations within the work area; an analysis step of acquiring acoustic features from the recording data collected in the recording step; a learning process for constructing the acoustic model by machine learning based on the labels assigned to the sound recording data collected in the sound recording process and the acoustic features; A work support method including:

2. 2. The work support method according to claim 1, the acoustic feature is a Mel-frequency cepstral coefficient, In the determining step, Mel-frequency cepstrum coefficients extracted from the sound collected by the sound collection unit are input to the acoustic model.

3. 2. The work support method according to claim 1, When it is determined in the determination step that the automatic guided vehicle is emitting a warning sound, the sound collection unit may analyze direction information of the warning sound, In the reporting step, the mobile terminal reports the direction information together with a warning.

4. 2. The work support method according to claim 1, In the alert issuing step, the mobile terminal displays a warning screen and issues a warning sound.

5. 5. The work support method according to claim 1, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, A work assistance method in which the mobile terminal is smart glasses.

6. A work support method for performing work in a work area where a plurality of industrial machines are arranged and where an automated guided vehicle travels, comprising: a registration step of registering a travel route of the automated guided vehicle in the work area, the travel route being determined in advance based on processing schedules of the plurality of industrial machines; a display step in which a portable terminal equipped with a display unit, a communication unit, and a sound collection unit is displayed on the portable terminal when a worker wearing the portable terminal works in the work area; a warning generation step of the mobile terminal generating a warning when the worker approaches within a predetermined range from the travel route; A work support method comprising:

7. 7. The work support method according to claim 6, In the alert issuing step, the mobile terminal displays a warning screen and issues a warning sound.

8. In the work support method according to claim 6 or claim 7, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, A work assistance method in which the mobile terminal is smart glasses.

9. A work support system for performing work in a work area where industrial equipment is arranged and where automatic guided vehicles travel, comprising: a mobile terminal including a display unit, a communication unit, and a sound collection unit; a storage unit that stores an acoustic model for recognizing a warning sound that is emitted when the automatic guided vehicle moves; a determination unit that determines whether the automated guided vehicle is emitting a warning sound by inputting sounds collected by the sound collection unit into the acoustic model when a worker wearing the portable terminal works in the work area; and a warning issuing unit that issues a warning when the determining unit determines that the automatic guided vehicle is issuing a warning sound; Equipped with The acoustic model is a work assistance system constructed by machine learning based on acoustic features obtained from recording data collected by performing recordings at each of a plurality of recording locations within the work area, one with the automated guided vehicle emitting a warning sound and one with the automated guided vehicle not emitting a warning sound, and labels assigned to the recording data.

10. 10. The work support system according to claim 9, the acoustic feature is a Mel-frequency cepstral coefficient, The determination unit inputs Mel-frequency cepstrum coefficients extracted from the sound collected by the sound collection unit into the acoustic model.

11. 10. The work support system according to claim 9, When the determination unit determines that the automatic guided vehicle is emitting a warning sound, the sound collection unit analyzes direction information of the warning sound, The work support system wherein the warning issuing unit issues the direction information together with the warning.

12. 10. The work support system according to claim 9, The warning issuing unit is a work support system that displays a warning screen and issues a warning sound.

13. The work support system according to any one of claims 9 to 12, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, The work support system, wherein the mobile terminal is a smart glass.

14. A work support system for performing work in a work area where a plurality of industrial machines are arranged and where automatic guided vehicles travel, comprising: a mobile terminal including a display unit, a communication unit, and a sound collection unit; a storage unit that stores a travel route of the automated guided vehicle in the work area that is determined in advance based on a processing schedule of the plurality of industrial machines; Equipped with When a worker wearing the mobile device works in the work area, the mobile device displays the travel route, The work support system further includes a warning issuing unit that issues a warning when the worker approaches within a predetermined range from the travel route.

15. The work support system according to claim 14, The warning issuing unit is a work support system that displays a warning screen and issues a warning sound.

16. In the work support system according to claim 14 or claim 15, the industrial equipment is a substrate processing apparatus that performs a predetermined process on a substrate, The work support system, wherein the mobile terminal is a smart glass.

Images