Voice command creation device and computer-readable storage medium
Patent Information
- Application Number
- CN202480089255.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-15
- Publication Date
- 2026-10-09
Smart Images

Figure CN122893154A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to a voice command generation device and a computer-readable storage medium. Background Technology
[0002] Previously, voice command devices existed that were operated using human voice. These devices stored the correspondence between commands called voice commands and mechanical actions, causing the machine to execute the actions spoken by the user. Examples of voice command devices include automobiles and mobile phones. Voice command devices also exist in industrial machinery in factories (e.g., Patent Document 1).
[0003] Existing technical documents
[0004] Patent documents
[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-42420 Summary of the Invention
[0006] The problem that the invention aims to solve
[0007] The voice command device stores the correspondence between voice commands and actions. It also has voice recognition capabilities; when it receives a voice command that closely resembles a registered voice command, it performs the action accordingly.
[0008] Each machine's actions are predetermined. A voice command generation device maps these actions to voice commands. As more voice commands are registered, the voice content becomes repetitive. Changing the voice content avoids repetition, but storing this content becomes a burden for the user.
[0009] The goal is to create voice commands on-site that avoid repetitive speech content.
[0010] Methods for solving problems
[0011] As one aspect of this disclosure, a voice command generation apparatus includes: a voice designation receiving unit that receives a voice designation for operating industrial machinery; an action designation receiving unit that receives a designation for an action of the industrial machinery; a state designation receiving unit that receives a designation for a mechanical state of the industrial machinery; and a command generation unit that generates a voice command that associates the voice designation, the action designation, and the mechanical state. Attached Figure Description
[0012] Figure 1 This is a schematic diagram illustrating the relationship between the voice command generation device and the voice command device.
[0013] Figure 2 This is a block diagram of a voice command generation device.
[0014] Figure 3 This represents an example of a voice command that associates speech content with action content in relation to a machine's state.
[0015] Figure 4 This represents an example of a voice command that associates speech content with action content in relation to a machine's state.
[0016] Figure 5 This represents an example of a voice command that associates speech content with mechanical state and action content.
[0017] Figure 6 This is a flowchart illustrating the operation of the voice command generation device.
[0018] Figure 7 This is an example of a diagram showing a specified screen representing voice content, action content, and mechanical state.
[0019] Figure 8 This is a hardware structure diagram of a voice command generation device. Detailed Implementation
[0020] The following is related to the appendix. Figure 1 The embodiments of this disclosure will be described below. Furthermore, in the following description, structures having the same or similar functions will be labeled with the same reference numerals. Also, repeated descriptions of these structures will sometimes be omitted.
[0021] In this application, "based on XX" means "at least based on XX," but also includes cases where it is based on other elements besides XX. Furthermore, "based on XX" is not limited to the direct use of XX, but also includes cases based on information obtained through calculations or processing of XX. "XX" can be any element (e.g., any information).
[0022] The voice command generation device 100 can be installed, for example, on a numerical control device, a personal computer set up alongside the numerical control device, a personal computer connected to the numerical control device via a wired / wireless network, a unit computer, a fog computer, a cloud server, or other computer.
[0023] Figure 1 This diagram illustrates the relationship between the voice command generation device 100 and the voice command device. The voice command device in this embodiment is industrial machinery in a factory, such as machine tools and numerical control devices. The voice command device receives voice commands generated by the voice command generation device 100, recognizes the voice, and executes actions associated with the voice content. The voice command device includes not only the main body of the industrial machinery but also a remote control for operating the industrial machinery, a suspended control panel, and a personal computer arranged alongside the industrial machinery.
[0024] The voice command generation device 100 generates voice commands used in the voice command system. A voice command is a command that associates voice content with action content for operating industrial machinery. The action content of the industrial machinery varies from machine to machine.
[0025] Figure 2 This is a block diagram of a voice command generation device 100. The voice command generation device 100 includes a voice designation receiving unit 1, an action designation receiving unit 2, a status designation receiving unit 3, and a command generation unit 4.
[0026] The voice specification receiving unit 1 accepts the specification of voice content. The voice content can be specified by voice or text.
[0027] The motion specification receiving unit 2 accepts the motion specifications of the industrial machinery. The motion specifications can be entered by the user via text input or selected via tags. In the tag format, a list of motion specifications is displayed, and the user's selection is accepted. A list of motion specifications for the industrial machinery is provided in advance by the manufacturer.
[0028] Furthermore, at timed intervals when the user specifies voice content, prompting action content associated with similar voice content, or action content containing phrases similar to the specified voice content, can serve as alternatives for industrial machinery operations. The operation overview of industrial machinery contains numerous operations. Choosing the desired action from a large number of options is burdensome for the user. By prompting alternative action content based on the specified voice content, this burden can be reduced.
[0029] The status designation receiving unit 3 accepts the designation of the machine status of the industrial machinery. The machine status can be entered by the user via text input or selected via tags. The machine status includes machine mode, signal status, processing status, parameter status, and operating status. In the tag format, a list of machine statuses is displayed, allowing the user to select. A list of machine statuses for the industrial machinery is provided in advance by the manufacturer.
[0030] The actions and states of industrial machinery are related. That is, the selected action determines the selectable state of the machinery. Conversely, the selected state of the machinery determines the selectable actions.
[0031] That is, the state designation receiving unit 3 restricts the selection range of the mechanical state according to the selected action content, and the action designation receiving unit 2 restricts the selection range of the action content according to the selected mechanical state.
[0032] Command Production Department 4 associates voice content, action content, and machine status to create voice commands. In this association process, voice content and action content can be associated with machine status, or vice versa.
[0033] The data can be in the form of a table, or it can be linked by IDs as in non-SQL. The following description uses examples of tables.
[0034] Figure 3 as well as Figure 4 This is an example of a voice command that associates voice content with action content in relation to a mechanical state.
[0035] exist Figure 3 In the example, the mechanical state "handwheel mode" is associated with voice content such as "X (aikesi)," "Y (wai)," "Z (zei)," "10x," and "100x." Furthermore, each voice content is associated with action content such as "switch to X-axis," "switch to Y-axis," "switch to Z-axis," "switch axis magnification to 10x," and "switch axis magnification to 100x."
[0036] exist Figure 4 In the example, the "edit mode" of the mechanical state is associated with the voice content "X (aikesi)," "Y (wai)," "Z (zei)," "10," "100," etc. Furthermore, each voice content is associated with the action content "to program input field X," "to program input field Y," "to program input field Z," "to program input field 10," "to program input field 100," etc.
[0037] Figure 5 This is an example of a voice command that associates voice content with machine state and action content.
[0038] exist Figure 5 In the code, the voice content "X (aikesi)" is associated with "handwheel mode" and "switch to X-axis", "edit mode" and "input X to program", "other modes" and "no action". That is, if the mechanical state when "aikesi" is spoken is "handwheel mode", the action "switch to X-axis" is executed; if the mechanical state is "edit mode", the action "input X to program" is executed; if the mechanical state is "other modes", "no action" is executed (i.e., no action is performed).
[0039] If so Figure 5 By associating voice content and action content with the corresponding mechanical state, it is possible to switch between effective voice content or action content based on the mechanical state.
[0040] Reference Figure 6 Explain the operation of the voice command generation device 100.
[0041] When the user is instructed to start making a voice command, the receiving screen is displayed (step S1), and the user's voice content, action content, and mechanical status are specified (step S2).
[0042] Figure 7 This is an example of a specified screen. The "X-axis" is specified in the specified screen for voice content. "Switch to X-axis signal" is specified in the specified screen for motion content. "Handwheel mode" is specified in the specified screen for mechanical status.
[0043] exist Figure 7 In the designated screen, text input is performed on the specified content, but the action content and machine status can also be displayed as labels, and selections can be accepted.
[0044] It can also display a list of voice content. The displayed voice content includes voice content previously registered by other users, voice content previously registered on other industrial machinery, etc. Users can refer to the registered voice content.
[0045] Command creation unit 4 associates mechanical information, action content, and voice content to create voice commands (step S3). In the association process, voice content and action content can be associated with mechanical state, or action content can be associated with mechanical state.
[0046] As explained above, the voice command generation apparatus 100 of this embodiment associates voice commands with mechanical states. Therefore, even with the same voice content, different mechanical states will associate it with different actions.
[0047] exist Figure 5 In the example, even with the same voice content "X (aikesi)," if the mechanical state is "handwheel mode," the action content is "switch to X-axis," and if the mechanical state is "edit mode," the action content is "input X to the program." Similarly, even with the same voice content "Y (wai)," if the mechanical state is "handwheel mode," the action content becomes "switch to Y-axis," and if the mechanical state is "edit mode," the action content becomes "input Y to the program."
[0048] In this way, by creating voice commands that associate speech content with mechanical states, it becomes possible to associate a large amount of speech content with a small amount of action content. Because the amount of speech content is reduced, the user's workload is lessened.
[0049] Furthermore, the amount of voice content that should be recognized by the voice command device (industrial machinery) is reduced. This improves the recognition rate and response speed of voice commands.
[0050] The hardware structure of the voice command generation device 100 using the present disclosure will be described below. Figure 8 This is a hardware structure diagram of the voice command generation device 100. (For example...) Figure 8 As shown, the voice command production device 100 includes a CPU 111 for overall control of the voice command production device 100, a ROM 112 for recording programs and data, and a RAM 113 for temporarily expanding data. The CPU 111 reads the system program recorded in the ROM 112 via the bus and determines the compatibility between the program block and the tool.
[0051] The non-volatile memory 114 is backed up, for example by a battery (not shown), and retains its storage state even when the power to the voice command generation device 100 is disconnected. Various data, such as programs read from the external device 120 via interfaces 115, 118, and 119, and operation inputs input via the input device 20, are stored in the non-volatile memory 114. The non-volatile memory 114 may also store programs and data used to execute the voice command generation device 100 of this embodiment.
[0052] Interface 115 is used to connect the voice command generation device 100 to an external device 120 such as an adapter. Programs and various parameters are read from the external device 120.
[0053] Interface 118 is used to connect the voice command generation device 100 to a display device 30 such as a liquid crystal display. The display device 30 displays data read from the memory, data obtained as a result of executing programs, etc.
[0054] Interface 119 is used to connect the voice command generation device 100 to input devices 20 such as keyboards and indicator devices. Input devices 20 transmit instructions and data based on operator operations to CPU 111 via interface 119.
[0055] This disclosure has been described in detail, but it is not limited to the various embodiments described above. Various additions, substitutions, modifications, and partial deletions can be made to these embodiments without departing from the spirit of this disclosure, or without departing from the spirit of this disclosure derived from the content described in the patent protection scope and its equivalents. Furthermore, these embodiments can also be implemented in combination. For example, in the embodiments described above, the order of each action and the order of each process are shown as an example, but are not limited thereto.
[0056] The following are notes regarding embodiments of this disclosure.
[0057] (Postscript 1)
[0058] The voice command generation device (100) includes: a voice designation receiving unit (1) that receives the designation of voice content for operating industrial machinery; an action designation receiving unit (2) that receives the designation of action content of the industrial machinery; a status designation receiving unit (3) that receives the designation of the mechanical status of the industrial machinery; and a command generation unit (4) that generates a voice command that associates the voice content, action content, and mechanical status.
[0059] (Postscript 2)
[0060] The action designation receiving unit (2) provides a list of the action content of the industrial machinery and accepts selections from the user.
[0061] (Note 3)
[0062] The status designation receiving unit (3) prompts the user with a list of the mechanical status of the industrial machinery and accepts the user's selection.
[0063] (Postscript 4)
[0064] The state designation receiving unit (3) restricts the selection range of the mechanical state according to the selected action content, and the action designation receiving unit (2) restricts the selection range of the action according to the selected mechanical state.
[0065] (Note 5)
[0066] The mechanical state includes at least one of the following: industrial machinery mode, signal state, processing state, parameter state, and operation state.
[0067] (Note 6)
[0068] The voice designation receiving unit (1) accepts the designation of voice content for operating industrial machinery, and the action designation receiving unit (2) prompts action content associated with voice commands similar to the designated voice content from the voice content that has been registered as voice commands, as alternative selections.
[0069] (Note 7)
[0070] The computer-readable storage medium (112, 113, 114) stores commands that cause one or more processors (111) to perform the following processes: accepting a specification of voice content for operating industrial machinery; accepting a specification of action content of the industrial machinery; accepting a specification of the mechanical state of the industrial machinery; and generating a voice command that associates the voice content, action content, and mechanical state.
[0071] Explanation of reference numerals in the attached figures
[0072] 100 Voice Command Creation Device
[0073] 1 Voice designated receiving unit
[0074] 2 Action Designation Receiving Unit
[0075] 3-State Designated Receiving Department
[0076] 4. Command Production Department
[0077] 111 CPU
[0078] 112 ROM
[0079] 113 RAM
[0080] 114 non-volatile memory.
Claims
1. A voice command generation device, characterized in that, have: The voice designation receiving unit accepts the designation of voice content for operating industrial machinery; The action designation receiving unit receives the designation of the action content of the industrial machinery; The status designation receiving unit accepts the designation of the mechanical status of the industrial machinery; The command production department creates voice commands that associate the voice content, action content, and mechanical state.
2. The voice command generation device according to claim 1, characterized in that, The action specification receives a list of the actions of the industrial machinery and accepts selections from the user.
3. The voice command generation device according to claim 1, characterized in that, The status specification receiving unit displays a list of the mechanical status of the industrial machinery to the user and accepts selections from the user.
4. The voice command generation device according to claim 1, characterized in that, The state designation receiving unit limits the range of mechanical states to be selected based on the chosen action content. The action designator restricts the range of action selection based on the selected mechanical state.
5. The voice command generation device according to claim 1, characterized in that, The mechanical state includes at least one of the following: industrial machinery mode, signal state, processing state, parameter state, and operation state.
6. The voice command generation device according to claim 1, characterized in that, The voice designation receiving unit accepts the designation of voice content for operating industrial machinery. The action designation receiving unit prompts for action content associated with a voice command that is similar to the designated voice content from the voice content that has been registered as a voice command, and uses this as a candidate for selection.
7. A computer-readable storage medium, characterized in that, The storage medium stores commands that perform the following processes: Accepts the specified voice content for operating industrial machinery; Accept the specified actions of the industrial machinery; Accept the specification of the mechanical state of the industrial machinery; Create voice commands that associate the spoken content, the action content, and the mechanical state.
Citation Information
Patent Citations
Control device of machine tool
JP2020042420A