sewing machine

Abstract

In a sewing machine that can be operated by voice commands, the goal is to achieve both safety and ease of operation through voice control. [Solution] The sewing machine 1, which forms a stitch in fabric by moving a needle 5 up and down, has a microphone 16 that collects sound emitted by the user, and a control unit 20 configured to process the sound collected by the microphone 16 to recognize voice commands for operating the sewing machine 1 emitted by the user and to execute the recognized voice commands. The control unit 20 has a wake word mode and a two-factor authentication mode that execute voice commands on the condition that a predetermined sound is emitted by the user, as well as a direct command mode that executes voice commands without requiring such conditions, and is configured to switch the voice command mode at least according to the operating status of the sewing machine 1.

Description

Technical Field

[0001] The present invention relates to a sewing machine that forms stitches on cloth by moving a needle up and down.

Background Art

[0002] In recent years, various devices that can perform so-called voice operations, which recognize voice commands (voice commands) issued by a user and execute these voice commands, have been developed. Even in the field of sewing machines, technologies for performing various operations based on voice commands from a user have been developed.

[0003] For example, Patent Document 1 describes a sewing machine capable of setting operations and sewing operations by voice. In this Patent Document 1, examples of setting operations by voice include "motor speed 3", "feed amount 4", "straight stitch", etc., and an example of a sewing operation by voice is "start".

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In voice operations performed by voice commands as described above, while an improvement in the operability of the device can be expected, there is a concern about the risk of misrecognition of voice commands. For example, if a voice command is misrecognized, an operation unintended by the user may be performed, which may impair safety. In this regard, in the technology described in Patent Document 1, after recognizing a voice command, the recognition result is displayed on a display (for example, "start" is displayed), and the sewing machine is operated on the condition that a voice of approval (OK) from the user for this is recognized. Therefore, it can be said that the risk of misrecognition of voice commands can be reduced.

[0006] As described above, the method of using user approval in addition to voice commands will be referred to as "two-factor authentication" below. While this two-factor authentication is effective in ensuring security, it impairs the usability of the device because it requires additional user approval. Therefore, applying two-factor authentication to all voice commands is considered undesirable from a usability standpoint.

[0007] Therefore, it can be said that in conventional voice control systems, there is a trade-off between safety and usability. Thus, it would be ideal to achieve voice control that balances both safety and usability.

[0008] This invention was made to solve the above-mentioned problems, and aims to achieve both safety and ease of operation in voice-controlled sewing machines. [Means for solving the problem]

[0009] To achieve the above objective, the present invention provides a sewing machine that forms a stitch in a cloth by moving a needle up and down, comprising: a microphone that collects sound emitted by a user; and a control unit configured to process the sound collected by the microphone to recognize voice commands for operating the sewing machine emitted by the user and to execute the recognized voice commands, wherein the control unit has a first mode that executes voice commands on the condition that a predetermined sound is emitted or a predetermined operation is performed by the user, and a second mode that executes voice commands without requiring any conditions, and is configured to switch between the first mode and the second mode at least according to the operating status of the sewing machine.

[0010] In this configuration, the present invention uses multiple modes (first and second modes) for recognizing and executing voice commands when operating a sewing machine by voice, and automatically switches between these modes depending on the operating status of the sewing machine. The first mode executes voice commands only when a predetermined voice is uttered or a predetermined operation is performed by the user, thus ensuring safety in voice operation. In contrast, the second mode executes voice commands without requiring such conditions, thus ensuring operability in voice operation. Therefore, in this embodiment, by appropriately switching between the first and second modes, it is possible to achieve both safety and operability in voice operation.

[0011] In the present invention, preferably, the predetermined voice is a predetermined wake word other than a voice command, uttered by the user before and / or after the recognition of a voice command. This first mode, which uses such a wake word, prevents voice commands from being activated at times unintended by the user, thereby ensuring security.

[0012] In the present invention, preferably, the sewing machine has a command notification unit for notifying the user of recognized voice commands, and the first mode is a mode in which a voice command is executed on the condition that the user has emitted a predetermined voice for approval or has performed a predetermined operation in response to the notification content of the command notification unit. With the present invention configured in this way, it is possible to prevent voice operations from being performed at times unintended by the user, and to prevent voice operations (content) from being performed unintended by the user, thereby effectively ensuring safety.

[0013] In the present invention, preferably, the control unit is configured to set a second mode when the sewing machine is in sewing operation, and to set a first mode when the sewing machine is not in sewing operation. With the present invention configured in this way, during sewing operations where operability is prioritized, a second mode is set that immediately executes operations in response to voice commands, thereby ensuring the operability of the sewing machine. In addition, during non-sewing operations where safety is prioritized, a first mode is set that requires predetermined voice commands or operations in addition to voice commands, thereby ensuring the safety of the sewing machine.

[0014] In the present invention, preferably, the sewing machine has a command notification unit for notifying the user of recognized voice commands, the predetermined voice is a predetermined wake word other than a voice command, and the first mode includes a first first mode which executes a voice command recognized thereafter on the condition that the user has issued a predetermined wake word, and a second first mode which executes a voice command on the condition that the user has issued a predetermined voice for approval of the notification content of the command notification unit or that a predetermined operation has been performed after the voice command has been recognized, and the control unit is configured to set the first first mode when the predetermined wake word is recognized first, and to set the second first mode when a voice command is recognized first. With the present invention configured in this way, it is possible to appropriately switch between a first first mode and a second first mode based on the voice emitted by the user.

[0015] In the present invention, preferably, the sewing machine has a command notification unit for notifying the user of recognized voice commands, the predetermined voice is a predetermined wake word other than a voice command, and the first mode includes a first first mode which executes the voice command recognized after the system recognizes that the user has issued a predetermined wake word before and / or after the voice command has been recognized, and a second first mode which executes the voice command after the system recognizes that the user has issued a predetermined voice for approval of the notification content of the command notification unit or that a predetermined operation has been performed, and the control unit is configured to set the first first mode when a voice command for setting the sewing machine is recognized, and to set the second first mode when a voice command for operating the sewing machine is recognized. In this configuration, the present invention uses two modes with different levels of safety (a first first mode and a second first mode) as the first mode. Specifically, the first first mode, which requires a wake word from the user in addition to voice commands, has a lower level of safety than the second first mode, which requires user approval in addition to voice commands. In other words, the second first mode has a higher level of safety than the first first mode. With this invention, the first first mode can be accurately set in situations where the safety requirements are relatively low, such as when setting up a sewing machine, and the second first mode can be accurately set in situations where the safety requirements are relatively high, such as when operating a sewing machine.

[0016] In the present invention, preferably, the sewing machine has a timer unit that measures the time between the recognition of a voice command and the recognition of a predetermined voice or operation uttered by the user before and / or after the recognition of the voice command, and the control unit is configured in the first mode to terminate the voice recognition process without performing any actions if the time measured by the timer unit exceeds a predetermined time. According to the present invention configured in this way, in the first mode, if a predetermined voice or predetermined operation is not recognized even after a predetermined time has elapsed, the voice recognition process can be terminated promptly.

[0017] Preferably, the present invention includes a time limit notification unit that notifies the time measured by the timer unit and / or that the speech recognition process has ended when the time measured by the timer unit exceeds a predetermined time. According to the present invention configured in this way, the user can be accurately made aware of the time elapsed since the first action (voice or operation) and that the measured time has exceeded a predetermined time and the voice recognition process has ended.

[0018] In the present invention, preferably, the sewing machine further has a mode notification unit configured to notify the user of mode information, and the control unit controls the mode notification unit so as to notify the user of the switching between the first mode and the second mode, and / or notify the user of the currently set mode among the first mode and the second mode. According to the present invention configured as described above, it is possible to accurately let the user grasp the mode switching and the current mode.

[0019] In the present invention, preferably, the sewing machine has an instruction notification unit for notifying the user of the recognized voice instruction, a predetermined voice is a predetermined wake word other than the voice instruction, and the first mode is recognition of the emission of the predetermined wake word by the user, and recognition of the emission of a predetermined voice for approval from the user or the performance of a predetermined operation with respect to the notification content of the instruction notification unit, as conditions, a mode for executing the voice instruction. According to such a first mode, it is possible to more effectively ensure the safety in voice operation.

Effects of the Invention

[0020] According to the present invention, in a sewing machine operable by voice instruction, it is possible to achieve both the safety and the operability in voice operation.

Brief Description of the Drawings

[0021] [Figure 1] It is a perspective view showing the appearance of a sewing machine according to an embodiment of the present invention. [Figure 2] It is a block diagram showing the electrical configuration of a sewing machine according to an embodiment of the present invention. [Figure 3] It is an explanatory diagram of the flow of voice operation in the wake word mode according to an embodiment of the present invention. [Figure 4] It is an explanatory diagram of the flow of voice operation in the two-step authentication mode according to an embodiment of the present invention. [Figure 5]This diagram illustrates the flow of voice operation in direct command mode according to an embodiment of the present invention. [Figure 6] This is a flowchart showing the voice control processing according to an embodiment of the present invention. [Modes for carrying out the invention]

[0022] A sewing machine according to an embodiment of the present invention will be described below with reference to the attached drawings.

[0023] <Device configuration> First, the overall configuration of the sewing machine according to this embodiment will be described with reference to Figure 1. Figure 1 is a perspective view showing the external appearance of the sewing machine according to this embodiment.

[0024] As shown in Figure 1, the sewing machine 1 mainly consists of a base portion 2 that is placed on a table or the like, a roughly L-shaped arm portion 3 extending from the base portion 2, and a sewing portion 4 provided at one end of the arm portion 3. The sewing portion 4 has a needle 5 for forming a stitch in the fabric, a needle plate 6 that covers the area around where the needle 5 descends, and a presser foot 7 for holding the fabric between the needle plate 6 and the presser foot. The sewing machine 1 also has a drive motor 11, a feed motor 12, and an amplitude motor 13 for performing various operations of the sewing machine 1.

[0025] Sewing machine 1 sews fabric by intertwining an upper thread (not shown) and a lower thread (not shown) to form a stitch. In this case, the upper thread is supplied from a spool (not shown) and inserted through the needle 5, the lower thread is wound onto a bobbin (not shown) and stored, the bobbin is stored in a hook (not shown), and the hook is stored inside sewing machine 1. Inside sewing machine 1, the rotational force of the drive motor 11 is transmitted by the action of a drive mechanism (not shown) to the up-and-down movement of the needle 5, the rotational movement of the hook, and the fabric feeding mechanism (not shown), etc.

[0026] In more detail, in sewing machine 1, the needle 5, through which the upper thread has been inserted, penetrates the fabric and approaches the bobbin. Then, the bobbin mechanism causes the upper and lower threads to intertwine, and after this, the needle 5 rises and exits the fabric, forming a stitch on the fabric. The fabric is then fed forward by the fabric feeding mechanism by a predetermined amount, and the next stitch is formed in the same procedure as above, so that a continuous linear sewing pattern with stitches formed at predetermined intervals is applied to the fabric (normal sewing).

[0027] Furthermore, as shown in the enlarged view below Figure 1, the sewing machine 1 can perform zigzag stitching on the fabric C (which is fed as shown by arrow A2) by combining the action of a needle oscillation mechanism (not shown) that oscillates the needle 5 from side to side (arrow A1) and an amplitude motor 13. In this zigzag stitching, the feed pitch P and zigzag width W are set in advance, and the sewing machine 1 drives each motor based on these set values ​​to form stitches S according to the set values.

[0028] Furthermore, as shown in Figure 1, the sewing machine 1 includes an operation button 15 operated by the user, a microphone 16 for collecting voices emitted by the user, a display unit 17 such as an LCD (Liquid Crystal Display) for displaying various information, a speaker 18 for outputting voices and the like to the user, and a lighting unit 19 composed of LEDs (Light Emitting Diodes). The display unit 17 may be configured as a touch panel that can be operated by the user. The operation button 15 is a manual operation unit for starting and stopping the sewing machine 1. The lighting unit 19 can light up, turn off, blink, and change the color of the light it emits. For example, the lighting unit 19 is a microphone indicator. The display unit 17, speaker 18, and lighting unit 19 correspond to examples of the "command notification unit," "time limit notification unit," and "mode notification unit" in the present invention.

[0029] Next, the electrical configuration of the sewing machine 1 according to this embodiment will be described with reference to Figure 2. Figure 2 is a block diagram showing the electrical configuration of the sewing machine 1 according to this embodiment.

[0030] As shown in Figure 2, the sewing machine 1 has a control unit 20 that performs various controls on the sewing machine 1. The control unit 20 is composed of a computer that includes one or more processors (typically CPUs) and memory such as ROM or RAM that stores various programs (including basic control programs such as an OS and application programs launched on the OS to realize specific functions) and various data that are interpreted and executed on the processor.

[0031] Specifically, the control unit 20 receives an operation signal indicating the user's operation of the operation button 15 and an audio signal corresponding to the voice collected by the microphone 16. If the display unit 17 is configured as a touch panel, the control unit 20 also receives an operation signal corresponding to the user's touch operation. Based on these input signals, the control unit 20 controls the drive motor 11, feed motor 12, amplitude motor 13, display unit 17, speaker 18, and lighting unit 19 by outputting control signals to them. Details of the control performed by the control unit 20 in this embodiment will be described later.

[0032] <Control according to this embodiment> Next, the control performed by the control unit 20 in this embodiment will be described in detail.

[0033] In this embodiment, the control unit 20 processes the audio signal corresponding to the sound collected by the microphone 16 to recognize voice commands for operating the sewing machine 1 issued by the user, and executes the recognized voice commands (voice operation). In particular, in this embodiment, the control unit 20 has multiple modes (hereinafter referred to as "voice command modes") for recognizing and executing voice commands when performing voice operation, and automatically switches between these multiple voice command modes according to the operating status of the sewing machine 1. In this way, safety and ease of operation in voice operation are achieved.

[0034] Specifically, the control unit 20, as the above voice command mode, (1) A wake word mode in which a voice command is executed on the condition that a predetermined wake word has been uttered by the user before the voice command is recognized, (2) A two-factor authentication mode in which, after recognizing a voice command, the voice command is executed on the condition that the system recognizes that the user has uttered a predetermined voice to authorize the execution of the voice command, (3) A direct command mode that does not require the above conditions and executes the voice command immediately after recognition, It has three modes.

[0035] More specifically, in wake word mode, voice commands recognized after the user utters a wake word are executed only if the wake word is spoken, thereby preventing voice operation from occurring at unintended times. The wake word is a pre-set arbitrary word (equivalent to a password-like keyword), such as a greeting word like "Hello," "Hi," or "Hey," or a nickname for the device.

[0036] On the other hand, in two-factor authentication mode, recognized voice commands are notified to the user, and the voice command is executed only after the user approves the notification. This prevents voice operations from being performed at unintended times or with unintended voice operations (content). In this two-factor authentication mode, the user approves the execution of the voice command by uttering words such as "OK," "Yes," or "GO."

[0037] In this embodiment, when the sewing machine 1 is in sewing operation (i.e., when the needle 5 is being driven up and down by the drive motor 11), the control unit 20 sets the direct command mode to prioritize the operability of the sewing machine 1. Conversely, when the sewing machine 1 is not in sewing operation, the control unit 20 sets the wake word mode or the two-factor authentication mode to prioritize the safety of the sewing machine 1. Furthermore, when the sewing machine 1 is not in sewing operation, the control unit 20 sets the wake word mode if the wake word is recognized first, and sets the two-factor authentication mode if a voice command is recognized first.

[0038] Furthermore, the wake word mode and two-factor authentication mode correspond to the "first mode" in this invention, and the direct command mode corresponds to the "second mode" in this invention. In addition, the wake word mode and two-factor authentication mode correspond to the "first first mode" and the "second first mode" in this invention, respectively.

[0039] (Voice control flow in each mode) Next, with reference to Figures 3 to 5, the flow of voice operation in each voice command mode in this embodiment will be described in detail.

[0040] Figure 3 is an explanatory diagram of the flow of voice operation in wake word mode according to this embodiment. First, in wake word mode, when the sewing machine 1 is in voice recognition state and the user utters a predetermined wake word, the control unit 20 of the sewing machine 1 recognizes the wake word by processing the sound collected by the microphone 16. At this time, the control unit 20 performs control to respond to the recognized wake word, for example, by changing the color of the illuminated unit 19 (red to green, etc.), displaying the text "Wake word received" on the display unit 17, outputting a reply voice ("OK" or "Yes," etc.) from the speaker 18, or outputting a beep sound from the speaker 18.

[0041] The sewing machine 1 then enters a state where it can receive voice commands from the user. When the user issues a voice command within a predetermined reception time, the control unit 20 recognizes the voice command by processing the voice signal corresponding to the voice collected by the microphone 16. At this time, the control unit 20 responds to the recognized voice command by displaying the content corresponding to the voice command on the display unit 17 or outputting sound from the speaker 18. After this, the control unit 20 executes the recognized voice command. On the other hand, if the user does not issue a voice command within the predetermined reception time, the control unit 20 terminates the voice recognition process without executing anything. The control unit 20 functions as the "timer unit" in this invention.

[0042] Here, the wake word mode is typically used to perform various settings (setting changes) within the sewing machine 1 using voice commands, without involving the movement of the sewing machine 1. In this case, when the control unit 20 responds to a recognized voice command, it may, for example, display text such as "Settings changed" on the display unit 17, or output this voice from the speaker 18. In one example, the wake word mode is used when setting the feed pitch P and zigzag width W applied to zigzag stitching (see Figure 1). In another example, the wake word mode is used when switching between normal mode for normal stitching and embroidery mode for embroidery stitching (in this mode, an embroidery unit including an embroidery hoop is attached to the sewing machine 1), or when recalling or selecting various patterns and designs used in embroidery mode.

[0043] Next, Figure 4 is an explanatory diagram of the flow of voice operation in the two-factor authentication mode according to this embodiment. First, in the two-factor authentication mode, when the sewing machine 1 is in a voice recognition state and the user issues a voice command, the control unit 20 of the sewing machine 1 recognizes the voice command by processing the voice signal corresponding to the voice collected by the microphone 16. At this time, in order to respond to the recognized voice command, the control unit 20 displays the content of the voice command on the display unit 17 or outputs the voice from the speaker 18.

[0044] Then, the sewing machine 1 enters a state where it is ready to receive an approval command from the user. When the user issues an approval command (such as "OK," "Yes," or "GO") within a predetermined acceptance time, the control unit 20 recognizes the approval command by processing the audio signal corresponding to the voice collected by the microphone 16. At this time, the control unit 20 performs controls to respond to the recognized approval command, such as changing the color of the light unit 19 (red to green, etc.), displaying the text "Approval received" on the display unit 17, outputting a reply (such as "OK" or "Yes") from the speaker 18, or outputting a beep from the speaker 18. After this, the control unit 20 executes the previously recognized audio command. On the other hand, if the user does not issue an approval command within the predetermined acceptance time, the control unit 20 terminates the audio recognition process without executing anything.

[0045] Here, the two-factor authentication mode is typically used to operate the sewing machine 1 by voice command. In this case, when the control unit 20 responds to the recognized voice command, it may, for example, display the text "Operating" on the display unit 17 or output this voice from the speaker 18. In one example, the two-factor authentication mode is used to start the sewing machine 1 or to move the embroidery hoop of the embroidery unit to the embroidery area or home position.

[0046] Next, Figure 5 is an explanatory diagram of the flow of voice operation in direct command mode according to this embodiment. First, in direct command mode, when the sewing machine 1 is in voice recognition state and the user issues a voice command, the control unit 20 of the sewing machine 1 recognizes the voice command by processing the voice signal corresponding to the voice collected by the microphone 16. At this time, in order to respond to the recognized voice command, the control unit 20 displays the content of the voice command on the display unit 17 or outputs the voice from the speaker 18. Then, the control unit 20 immediately executes the recognized voice command.

[0047] Here, the direct command mode is used, for example, to stop the sewing machine 1, change the sewing direction of the sewing machine 1 (for example, to change the sewing direction backward in order to perform a reverse stitch), or change the operating speed of the sewing machine 1.

[0048] In the example described above, sewing machine 1 responded (recognition response) to the recognized wake word, voice command, and approval command, but such recognition responses may be omitted as appropriate. However, recognition responses to voice commands in two-factor authentication mode (e.g., text display or voice output such as "I will operate") are required. This is because in two-factor authentication mode, a recognition response that notifies the voice command is necessary to obtain user approval for the recognized voice command.

[0049] (flowchart) Next, with reference to Figure 6, a flowchart illustrating the voice control processing according to this embodiment will be described. This flowchart is repeatedly executed at predetermined intervals by the control unit 20 of the sewing machine 1. Specifically, the processor within the control unit 20 reads a program stored in memory and executes the program, thereby realizing the processing and control related to this flowchart.

[0050] First, in step S11, the control unit 20 determines whether or not the drive motor 11 is moving. Here, the control unit 20 determines whether or not the needle 5 is being driven up and down by the drive motor 11, that is, whether or not the sewing machine 1 is in the process of sewing.

[0051] If, as a result of step S11, the control unit 20 determines that the drive motor 11 is moving (step S11: Yes), that is, if the sewing machine 1 is in sewing operation, it proceeds to step S12. In step S12, the control unit 20 sets the voice command mode to direct command mode and enters a voice recognition state (standby state) that accepts voice signals from the microphone 16. In this case, the control unit 20 may inform the user that the voice command mode has been switched to direct command mode, and / or that the currently set voice command mode is direct command mode, by changing the color of the illuminated unit 19, displaying text on the display unit 17, or outputting sound from the speaker 18.

[0052] The control unit 20 then proceeds to step S13 and determines whether or not a voice command from the user has been recognized based on the voice signal corresponding to the sound picked up by the microphone 16. If the control unit 20 determines that the voice command has been recognized (step S13: Yes), it proceeds to step S14 and executes the voice command. On the other hand, if the control unit 20 does not determine that the voice command has been recognized (step S13: No), it returns to step S13. In this case, the control unit 20 repeats the determination in step S13 until a voice command is recognized.

[0053] On the other hand, if the control unit 20 does not determine in step S11 that the drive motor 11 is moving (step S11: No), that is, if the sewing machine 1 is not in sewing operation, it proceeds to step S15. In step S15, the control unit 20 enters a voice recognition state (standby state) where it receives voice signals from the microphone 16. Then, the control unit 20 proceeds to step S16 and determines whether or not a voice command from the user has been recognized based on the voice signal corresponding to the voice collected by the microphone 16.

[0054] If, as a result of step S16, the control unit 20 determines that the voice command has been recognized (step S16: Yes), it proceeds to step S17. In step S17, the control unit 20 sets the voice command mode to two-factor authentication mode. In this case, the control unit 20 responds to the recognized voice command by displaying the content of the voice command on the display unit 17 or outputting an audio signal from the speaker 18 in order to obtain user approval for the voice command. The control unit 20 may also notify the user that the voice command mode has been switched to two-factor authentication mode, and / or that the currently set voice command mode is two-factor authentication mode, by changing the color of the illuminated unit 19, displaying text on the display unit 17, or outputting an audio signal from the speaker 18.

[0055] Then, the control unit 20 proceeds to step S18 and determines whether or not an approval command from the user has been recognized based on the audio signal corresponding to the voice collected by the microphone 16. If the control unit 20 determines that an approval command has been recognized (step S18: Yes), it proceeds to step S19 and executes the audio command recognized in step S16.

[0056] In response, if the control unit 20 does not determine that the approval command has been recognized (step S18: No), it proceeds to step S20 and determines whether a predetermined reception time has elapsed since the voice command was recognized in step S16. As a result, if the control unit 20 determines that the reception time has elapsed (step S20: Yes), it returns to step S16 and attempts to recognize the voice command or wake word again. If it does not determine that the reception time has elapsed (step S20: No), it returns to step S18 and waits for the user's approval command to be recognized.

[0057] The control unit 20 may also inform the user of the elapsed time until the above-mentioned reception time is reached, that is, the elapsed time since the voice command was recognized in step S16. In one example, the control unit 20 displays a numerical countdown on the display unit 17. In another example, the control unit 20 flashes the indicator light 19 while the time until the reception time is reached, gradually increasing the flashing cycle as time progresses, and switching the indicator light 19 from flashing to on or off when the reception time is reached. Furthermore, instead of informing the user of the elapsed time since the voice command was recognized, or in addition to informing the user of the elapsed time, the control unit 20 may also inform the user that the elapsed time has exceeded the reception time and the voice recognition process has ended.

[0058] On the other hand, if the control unit 20 does not determine in step S16 that a voice command has been recognized (step S16: No), it proceeds to step S21. In step S21, the control unit 20 determines whether or not a wake word from the user has been recognized based on the voice signal corresponding to the voice collected by the microphone 16. If the control unit 20 does not determine that a wake word has been recognized (step S21: No), it returns to step S16. In this case, the control unit 20 repeats the determinations in steps S16 and S21 until a voice command or wake word is recognized.

[0059] In response, if the control unit 20 determines that the wake word has been recognized (step S21: Yes), it proceeds to step S22. In step S22, the control unit 20 sets the voice command mode to wake word mode. In this case, the control unit 20 may inform the user that the voice command mode has been switched to wake word mode, and / or that the currently set voice command mode is wake word mode, by changing the color of the illuminated unit 19, displaying text on the display unit 17, or outputting sound from the speaker 18.

[0060] Then, the control unit 20 proceeds to step S23 and determines whether or not a voice command from the user has been recognized based on the voice signal corresponding to the voice collected by the microphone 16. If the control unit 20 determines that a voice command has been recognized (step S23: Yes), it proceeds to step S24 and executes the voice command.

[0061] In response, if the control unit 20 does not determine that the voice command has been recognized (step S23: No), it proceeds to step S25 and determines whether a predetermined reception time has elapsed since the wake word was recognized in step S21. If the control unit 20 determines that the reception time has elapsed (step S25: Yes), it returns to step S16 and attempts to recognize the voice command and wake word again. If it does not determine that the reception time has elapsed (step S25: No), it returns to step S23 and waits for the voice command from the user to be recognized.

[0062] The control unit 20 may also inform the user of the elapsed time until the above-mentioned reception time is reached, that is, the elapsed time since the wake word was recognized in step S21. In one example, the control unit 20 displays a numerical countdown on the display unit 17. In another example, the control unit 20 flashes the light unit 19 while the time until the reception time is reached, gradually increasing the flashing cycle as time progresses, and switching the light unit 19 from flashing to on or off when the reception time is reached. Furthermore, instead of informing the user of the elapsed time since the wake word was recognized, or in addition to informing the user of the elapsed time, the control unit 20 may also inform the user that the elapsed time has exceeded the reception time and the voice recognition process has ended.

[0063] <Mechanism and Effects> Next, the operation and effects of the sewing machine 1 according to this embodiment will be described.

[0064] In this embodiment, the sewing machine 1, which forms a stitch in the fabric by moving the needle 5 up and down, includes a microphone 16 that collects sounds emitted by the user, and a control unit 20 configured to process the sounds collected by the microphone 16 to recognize voice commands for operating the sewing machine 1 emitted by the user and to execute the recognized voice commands. The control unit 20 has a wake word mode and a two-factor authentication mode that execute voice commands on the condition that a predetermined sound is emitted by the user, as well as a direct command mode that executes voice commands without requiring such conditions, and is configured to switch the voice command mode at least according to the operating status of the sewing machine 1.

[0065] According to this embodiment, when performing voice operation, multiple voice command modes are used to recognize and execute voice commands, and these multiple voice command modes are automatically switched according to the operating status of the sewing machine 1. In particular, in this embodiment, the multiple voice command modes include a direct command mode that ensures operability, and a wake word mode and a two-factor authentication mode that ensure security. Therefore, according to this embodiment, it is possible to achieve both security and operability in voice operation.

[0066] Furthermore, according to this embodiment, the predetermined voice is a predetermined wake word other than a voice command, uttered by the user before the voice command is recognized. In other words, the control unit 20 uses a wake word mode in which it executes a voice command when it recognizes that the predetermined wake word has been uttered by the user. This prevents voice operations from being performed at times unintended by the user, thereby ensuring safety.

[0067] Furthermore, according to this embodiment, the sewing machine 1 is equipped with a display unit 17, a speaker 18, and a lighting unit 19 for notifying the user of recognized voice commands. The two-factor authentication mode is a mode in which a voice command is executed only when it is recognized that the user has emitted a predetermined voice for approval in response to the notification. With such a two-factor authentication mode, it is possible to prevent voice operations from being performed at times unintended by the user, and to prevent voice operations (content) from being performed unintended by the user, thereby effectively ensuring security.

[0068] Furthermore, according to this embodiment, the control unit 20 sets the direct command mode when the sewing machine 1 is performing a sewing operation, and sets the wake word mode or two-factor authentication mode when the sewing machine 1 is not performing a sewing operation. As a result, during sewing operations where operability is prioritized, the direct command mode, which immediately executes voice commands, is set, thereby ensuring the operability of the sewing machine 1. In addition, during non-sewing operations where safety is prioritized, the wake word mode or two-factor authentication mode, which requires a wake word or approval in addition to voice commands, is set, thereby ensuring the safety of the sewing machine 1.

[0069] Furthermore, according to this embodiment, the control unit 20 is configured to set the wake word mode if the wake word is recognized first, and to set the two-factor authentication mode if the voice command is recognized first. This allows for appropriate switching between the wake word mode and the two-factor authentication mode based on the voice command emitted by the user.

[0070] Furthermore, according to this embodiment, the control unit 20 measures the time between the recognition of the wake word uttered by the user and the recognition of the subsequent voice command, and the time between the recognition of the voice command and the recognition of the subsequent voice for user approval. If these measured times exceed the acceptance time, the control unit 20 terminates the voice recognition process without performing any actions. This allows the voice recognition process to be terminated quickly in wake word mode and two-factor authentication mode if the predetermined voice is not recognized even after the acceptance time has elapsed. Moreover, according to this embodiment, the measured time and / or the fact that the measured time has exceeded the acceptance time and the voice recognition process has been terminated is indicated by the display unit 17, speaker 18, and lighting unit 19. This allows the user to accurately recognize the time elapsed since the first voice was uttered and that the measured time has exceeded the acceptance time and the voice recognition process has been terminated.

[0071] Furthermore, according to this embodiment, the control unit 20 controls the display unit 17, speaker 18, and lighting unit 19 to notify the user of the change in voice command mode and / or the currently set voice command mode. This allows the user to accurately understand the change in voice command mode and the current voice command mode.

[0072] <Variation> Next, modifications of the above-described embodiment will be explained. The following modifications can be implemented by combining them as appropriate.

[0073] (Variation 1) In the embodiment described above, the wake word mode executed the voice command when the wake word was recognized before the voice command was recognized, that is, when the voice command was recognized after the wake word was recognized. In another example, the wake word mode may be configured to execute the voice command when the wake word was recognized after the voice command was recognized, that is, when the voice command was recognized before the wake word was recognized. In yet another example, the wake word mode may be configured to execute the operation corresponding to the voice command when the wake word was recognized both before and after the voice command was recognized.

[0074] (Modification 2) In the embodiment described above, the two-factor authentication mode performed the operation corresponding to the voice command when it recognized that the user had emitted a predetermined voice message to authorize the execution of the operation corresponding to the voice command. In another example, the two-factor authentication mode may be configured to perform the operation corresponding to the voice command when it recognizes that the user has performed a predetermined operation (e.g., a touch panel operation or a hand gesture operation) to authorize the execution of the operation corresponding to the voice command.

[0075] (Variation 3) In the embodiment described above, the control unit 20 set the wake word mode if the wake word was recognized before the voice command was recognized, and set the two-factor authentication mode if the voice command was recognized before the wake word was recognized. In this embodiment, the wake word mode and the two-factor authentication mode were switched based on the voice emitted by the user. In another example, the control unit 20 may set the wake word mode if a voice command for setting the sewing machine 1 is recognized, and set the two-factor authentication mode if a voice command for operating the sewing machine 1 is recognized.

[0076] Here, wake word mode, which requires a wake word from the user in addition to voice commands, can be said to have a lower level of security than two-factor authentication mode, which requires user approval in addition to voice commands. In other words, two-factor authentication mode can be said to have a higher level of security than wake word mode. Therefore, as shown in the other examples above, wake word mode can be appropriately set in situations where the security requirements are relatively low, such as when setting up sewing machine 1, and two-factor authentication mode can be appropriately set in situations where the security requirements are relatively high, such as when sewing machine 1 is operated.

[0077] (Modification 4) In the embodiments described above, the wake word mode and the two-factor authentication mode were used as the first mode in the present invention. In other examples, a mode combining the wake word mode and the two-factor authentication mode may be used as the first mode. Specifically, as the first mode, a mode may be used in which a voice command is executed on the condition that the user has uttered a predetermined wake word and that the user has uttered a predetermined voice for approval (or that a predetermined operation has been performed) in response to the notification content corresponding to the voice command. For example, in this mode, the control unit 20 executes the voice command when the wake word → voice command → approval command is recognized in that order, or executes the voice command when the voice command → approval command → wake word is recognized in that order. Such other examples can more effectively ensure security in voice operation.

[0078] (Variation 5) In the embodiments described above, the microphone 16, display unit 17, speaker 18, lighting unit 19, and control unit 20 of the present invention were provided on the sewing machine body. In other examples, some or all of these components (microphone 16, display unit 17, speaker 18, lighting unit 19, and control unit 20) may be separate from the sewing machine. Specifically, the present invention may be a voice-operable sewing machine equipped with a wired or wirelessly connected smartphone, tablet, or smart speaker, where the microphone of the smartphone is used as microphone 16, the speaker of the smartphone is used as speaker 18, the screen of the smartphone is used as display unit 17 and lighting unit 19, and the control device of the smartphone is used as at least a part of the control unit 20 (mainly the voice recognition execution unit, etc.). For example, in this example, since existing smartphones, tablets, or smart speakers can be used, the sewing machine body does not necessarily need to have a microphone, speaker, display unit, etc., thus providing a simple and inexpensive voice-operable sewing machine. [Explanation of Symbols]

[0079] 1 Sewing machine 2 Base section 3. Arm section 4 Sewing section 5 needles 6 Needle Plate 7. Press down 11 Drive motor 12 Feed motor 13 Amplitude motor 15 Operation buttons 16 Mike 17 Display section 18 speakers 19 Lighting part 20 Control Unit

Claims

1. A sewing machine that forms stitches in fabric by moving the needle up and down, A microphone that collects voices emitted by the user, A control unit is configured to process the sound collected by the microphone to recognize voice commands for operating the sewing machine issued by the user, and to execute the recognized voice commands. It has, The control unit, It has a first mode that executes the voice command on the condition that a predetermined sound is uttered or a predetermined operation is performed by the user, It has a second mode that executes the voice command without requiring the aforementioned conditions, The first mode and the second mode are switched depending on the operating status of the sewing machine. A sewing machine characterized by being configured in such a way.

2. The sewing machine according to claim 1, wherein the predetermined voice is a predetermined wake word other than the voice command, uttered by the user before and / or after the recognition of the voice command.

3. The sewing machine has a command notification unit for notifying the user of the recognized voice command, The sewing machine according to claim 1, wherein the first mode is a mode in which the voice command is executed on the condition that the user has emitted a predetermined voice for approval or has performed a predetermined operation in response to the content of the command notification unit's notification.

4. The sewing machine according to claim 1, wherein the control unit is configured to set the second mode when the sewing machine is in sewing operation, and to set the first mode when the sewing machine is not in sewing operation.

5. The sewing machine has a command notification unit for notifying the user of the recognized voice command, The aforementioned predetermined voice is a predetermined wake word other than the aforementioned voice command. The first mode includes a first mode which executes the voice command recognized thereafter, on the condition that the user has uttered the predetermined wake word, and a second first mode which executes the voice command on the condition that, after the voice command has been recognized, the user has uttered a predetermined voice for approval or performed a predetermined operation in response to the notification content of the command notification unit. The control unit is configured to set the first mode if the predetermined wake word is recognized first, and to set the second mode if the voice command is recognized first. The sewing machine according to claim 1.

6. The sewing machine has a command notification unit for notifying the user of the recognized voice command, The aforementioned predetermined voice is a predetermined wake word other than the aforementioned voice command. The first mode includes a first mode which executes the voice command after recognition, on the condition that the user has uttered a predetermined wake word before and / or after the voice command has been recognized, and a second first mode which executes the voice command after recognition, on the condition that the user has uttered a predetermined voice for approval or performed a predetermined operation in response to the notification content of the command notification unit. The control unit is configured to set the first mode when the voice command for setting the sewing machine is recognized, and to set the second mode when the voice command for operating the sewing machine is recognized. The sewing machine according to claim 1.

7. The sewing machine has a timer unit that measures the time between the recognition of the voice command and the recognition of a predetermined voice or operation uttered by the user before and / or after the recognition of the voice command. The control unit is configured to terminate the speech recognition process without performing any actions if the time measured by the timer unit exceeds a predetermined time in the first mode. The sewing machine according to claim 1.

8. The sewing machine according to claim 7, further comprising a time limit notification unit that notifies that the time measured by the timer unit and / or that the time measured by the timer unit exceeds the predetermined time, thereby ending the voice recognition process.

9. The sewing machine further includes a mode notification unit configured to notify the user of mode information. The control unit is configured to control the mode notification unit so as to notify the user of the switching between the first mode and the second mode, and / or to notify the user of the currently set mode among the first mode and the second mode. The sewing machine according to claim 1.

10. The sewing machine has a command notification unit for notifying the user of the recognized voice command, The aforementioned predetermined voice is a predetermined wake word other than the aforementioned voice command. The sewing machine according to claim 1, wherein the first mode is a mode in which the voice command is executed on the condition that the user has issued a predetermined wake word, and that the user has issued a predetermined voice for approval or performed a predetermined operation in response to the content of the command notification unit.

Images