User assistance device

Abstract

In order to enable easy verification and correction of a processing program regardless of the experience or knowledge of an operator, the present invention enables the creation of a prompt for generating, using a generative AI device, a highly accurate summary of a processing program or a selected range.　This user assistance device performs a user assistance function of displaying a processing program for an industrial machine, and comprises: a processing program acquisition unit that acquires a processing program; an instruction information acquisition unit that acquires instruction information including an instruction included in the processing program and instruction format information; a prompt creation unit that, on the basis of the processing program and the instruction information, creates a prompt for instructing a generative AI device to generate a summary of the processing program; and a presentation unit that presents, to a user, the summary of the processing program generated by the generative AI device on the basis of the created prompt.

Description

Assistive devices

[0001] SUMMARY The present disclosure relates to a user assistive device that creates prompts for generating summaries for machining programs.

[0002] Commands for movement, cutting, etc., to industrial machinery are sometimes given by a text-format machining program. Such machining programs are generally automatically generated by a tool called CAM (Computer Aided Manufacturing). When adjusting the program, the machining program may be directly checked, verified, and corrected. In this regard, a technology has been proposed for optimizing NC command codes included in the generated machining program to speed up the operation of the machine tool. For example, see Patent Document 1.

[0003] Japanese Patent Application Laid-Open No. 2021-068180

[0004] Operators who have few opportunities to directly check and modify machining programs spend a lot of time understanding how the machining programs operate. This poses a problem of time-consuming verification of machining programs. Furthermore, when modifying a machining program, identifying the areas to be modified can take time, making the modification difficult. Another method for summarizing natural language is to use a generative AI device such as a large-scale language model (LLM). However, because machining programs are not natural language, it is difficult for a generative AI device to understand the NC command codes contained in the machining program, making it impossible to accurately summarize the program.

[0005] Therefore, it is desirable to create prompts using a generating AI device to generate a highly accurate summary of a processing program or a selected range so that the processing program can be easily verified and modified regardless of the operator's experience or knowledge.

[0006] One aspect of the user assistance device of the present disclosure is a user assistance function that displays a machining program for an industrial machine, and includes a machining program acquisition unit that acquires the machining program, an instruction information acquisition unit that acquires instruction information including instructions and instruction format information contained in the machining program, a prompt creation unit that creates a prompt to instruct a generation AI device to create a summary of the machining program based on the machining program and the instruction information, and a presentation unit that presents to the user a summary of the machining program generated by the generation AI device based on the created prompt.

[0007] 16 is a diagram showing an example of a functional block configuration of a user assistance system according to a first embodiment. FIG. 17 is a diagram showing an example of a machining program. FIG. 18 is a diagram showing an example of command information included in the machining program of FIG. 2. FIG. 19 is a diagram showing an example of a prompt created by a prompt creation unit. FIG. 20 is a diagram showing an example of a summary of the contents of a machining program generated by a generation AI device based on the prompt of FIG. 4. FIG. 21 is a flowchart illustrating user assistance processing of a user assistance device. FIG. 19 is a diagram showing an example of a prompt including an instruction to highlight a variable parameter. FIG. 21 is a diagram showing an example of a summary generated by the prompt of FIG. 7 in which a variable parameter is highlighted. FIG. 22 is a diagram showing an example of a prompt including an instruction to highlight a variable parameter and an instruction to add an identifier for the line number and / or an argument. FIG. 23 is a diagram showing an example of a summary generated by the prompt of FIG. 9 in which a variable parameter is highlighted and an identifier is added. FIG. 24 is a diagram showing an example of a functional block configuration of a user assistance system according to a second embodiment. FIG. 25 is a diagram showing an example of a prompt created by a prompt creation unit. FIG. 26 is a diagram showing an example of a summary of the contents of a machining program generated by a generation AI device based on the prompt of FIG. 16. 23 is a diagram showing an example of a prompt generated by a prompt creation unit. FIG. 24 is a diagram showing an example of a summary of the contents of a machining program generated by a generation AI device based on the prompt of FIG. 18. FIG. 25 is a flowchart explaining the user assistance processing of a user assistance device. FIG. 26 is a diagram showing an example of a functional block configuration of a user assistance system according to a fourth embodiment. FIG. 27 is a diagram showing an example of a machining program. FIG. 28 is a diagram showing an example of a summary generated by a generation AI device for the machining program of FIG. 22. FIG. 29 is a diagram showing an example of a summary in which variable parameters have been changed in the summary of FIG. 23. FIG. 29 is a diagram showing an example of a machining program generated by a program generation unit based on the summary of FIG. 24. FIG. 29 is a flowchart explaining the user assistance processing of a user assistance device 10C.FIG. 10 is a diagram showing an example of a functional block configuration of a user assistance system according to a fifth embodiment. FIG. 11 is a diagram showing an example of a processing program. FIG. 12 is a diagram showing an example of a summary when summary conditions for confirming laser processing conditions are acquired. FIG. 13 is a diagram showing an example of a processing program. FIG. 14 is a diagram showing an example of a summary when summary conditions for confirming assist gas output conditions are acquired. FIG. 15 is a diagram showing an example of a processing program. FIG. 16 is a diagram showing an example of a summary when summary conditions for confirming the flow of laser processing are acquired. FIG. 17 is a flowchart illustrating user assistance processing of a user assistance device.

[0008] First Embodiment A user assistance system according to a first embodiment will be described in detail below with reference to the accompanying drawings. FIG. 1 is a diagram illustrating an example of a functional block configuration of the user assistance system according to the first embodiment. Here, a laser processing machine is used as an example of industrial machinery. The present invention is also applicable to various other industrial machinery, such as machine tools, industrial robots, service robots, forging machines, and injection molding machines. In the case of an industrial robot, the processing program is a robot program. As shown in FIG. 1 , the user assistance system 1 includes a user assistance device 10 and a generating AI device 20. The user assistance device 10 and the generating AI device 20 may be connected to each other and communicate via a network (not shown), such as a local area network (LAN) or the Internet. In this case, the user assistance device 10 and the generating AI device 20 include a communication unit (not shown) for communicating with each other via such a connection. The user assistance device 10 and the generating AI device 20 may also be directly connected to each other via a connection interface (not shown).

[0009] <Generation AI Device 20> The generation AI device 20 is, for example, a computer or web server known to those skilled in the art. The generation AI device 20 accepts prompts, which are text data such as questions or requests, and inputs them into a trained language model (for example, a large-scale language model (LLM) such as ChatGPT (registered trademark)). The generation AI device 20 generates response sentences to the prompts or sentences in accordance with requests (for example, a summary sentence based on a summary request and original text, or an example sentence based on an example request). The generation AI device 20 transmits the generated sentence data to the user assistance device 10. Note that the trained language model (for example, a large-scale language model) may be, for example, a learning model trained using a large amount of data on the web as training data, and in particular, the learning model may be a learning model provided from an external source. Furthermore, the trained language model may be a training model that has undergone additional training related to specialized fields such as processing programs, for example, training by prompts and / or fine tuning, transfer learning, etc., on the provided training model.

[0010] <User assistance device 10> The user assistance device 10 is, for example, a known information processing device (computer) and includes, as shown in Fig. 1, a machining program acquisition unit 110, a command information acquisition unit 120, a prompt creation unit 130, and a presentation unit 140. The user assistance device 10 includes a processing unit (not shown) such as a CPU to realize the operations of the functional blocks in Fig. 1. The user assistance device 10 also includes a main storage device (not shown) such as a ROM (Read Only Memory) or HDD (Hard Disk Drive) that stores various control programs, and a RAM (Random Access Memory) for storing data temporarily required for the processing unit to execute a program.

[0011] In the user assistance device 10, the processing unit reads the OS and application software from the auxiliary storage device, and executes calculations based on the OS and application software while loading the OS and application software into the main storage device. Based on the results of this calculation, the user assistance device 10 controls each piece of hardware. This allows the processing of the functional blocks in Figure 1 to be realized. In other words, the user assistance device 10 can be realized by the cooperation of hardware and software.

[0012] The processing program acquisition unit 110 acquires a processing program, for example, from a laser processing machine (not shown) or a numerical control device that controls the laser processing machine. Specifically, the processing program acquisition unit 110 acquires a processing program such as that shown in Fig. 2 from the laser processing machine (not shown) based on a user's input operation received via an input device (not shown) such as a keyboard or a touch panel included in the user assistance device 10.

[0013] The command information acquisition unit 120 acquires command information including commands and command format information included in the machining program. Specifically, the command information acquisition unit 120 analyzes, for example, each block of the machining program in FIG. 2 to acquire, as command information, commands (e.g., G-codes, M-codes, etc.) included in the machining program and command format information (e.g., a format indicating parameters such as coordinate values ​​for each G-code). FIG. 3 is a diagram showing an example of command information included in the machining program in FIG. 2. Note that, since the commands and command format information vary depending on the manufacturer of the laser processing machine (not shown), a database related to commands and command format information may be prepared in advance for each manufacturer on a network (not shown). In this case, the command information acquisition unit 120 may analyze each block of the machining program to acquire, as command information, the commands and command format information included in the machining program from the database for each manufacturer.

[0014] The prompt creation unit 130 creates a prompt that instructs the generation AI device 20 to generate a summary of the processing program based on the processing program and command information. Specifically, the prompt creation unit 130 creates a prompt that summarizes the contents of the processing program based on the processing program of FIG. 2 and the command information of FIG. 3, as shown in FIG. 4, in response to a user instruction received, for example, via an input device (not shown) of the user assistance device 10. In the prompt shown in FIG. 4, the first line contains a command statement that instructs the user to summarize the contents of the processing program: "Please summarize the contents of the processing program based on the following assumptions." The second line of the prompt stores the processing program to be summarized. The third line of the prompt stores command information as assumptions. Note that in the prompt of FIG. 4, the processing program and command information are surrounded by a solid-line rectangle, but the solid-line rectangle may be omitted. The prompt creation unit 130 then outputs the created prompt to the generation AI device 20.

[0015] The AI ​​generation device 20 inputs the received prompt into a trained language model and generates a summary explaining the contents of the machining program. FIG. 5 is a diagram showing an example of a summary of the contents of the machining program generated by the AI ​​generation device 20 based on the prompt in FIG. 4. That is, the first line of the summary in FIG. 5 explains the first line of the machining program in FIG. 2 as "switch to nozzle A." The second line of the summary explains the second line of the machining program in FIG. 2 as "after outputting assist gas output at 0.1 MPa nitrogen for 1 second." The third and fourth lines of the summary explain the third line of the machining program in FIG. 2 as "perform piercing for 5 seconds while incrementing the frequency command from 3000 W, 100 Hz, 10% in steps to 100 Hz and the duty command by 10%, every 0.5 seconds." Lines 5 to 6 of the summary explain lines 4 to 7 of the processing program in Figure 2 as follows: "Then, processing is performed into a rectangular shape of 100 mm in length and 100 mm in width at a continuous output of 3000 W." The generating AI device 20 transmits the summary in Figure 5 to the user assistance device 10.

[0016] The presentation unit 140 presents the user with a summary of the processing program generated by the generation AI device 20 based on the created prompt. Specifically, the presentation unit 140 receives, for example, the summary shown in FIG. 5 from the generation AI device 20 and displays the received summary on a display device (not shown) such as a liquid crystal display included in the user assistance device 10. This allows the user to easily verify and modify the processing program regardless of their experience or knowledge.

[0017] <User Assistance Processing of User Assistance Device 10> Next, the flow of the user assistance processing of the user assistance device 10 will be described with reference to Fig. 6. Fig. 6 is a flowchart illustrating the user assistance processing of the user assistance device 10. The flow shown here is executed every time the user assistance device 10 receives an input instruction for an editing program from the user. Note that the user assistance device 10 may also execute the flow of Fig. 6 when, in addition to receiving an input instruction for an editing program from the user, the selection of part of an editing program is received, a button for instructing a summary is pressed, or one editing program is selected from multiple editing programs.

[0018] In step S11, when the machining program acquisition unit 110 receives an input instruction for a machining program from the user via an input device (not shown) of the user assistance device 10, it acquires the machining program from a laser processing machine or a numerical control device (not shown).

[0019] In step S12, the command information acquisition unit 120 acquires command information including commands and command format information included in the machining program acquired in step S11.

[0020] In step S13, the prompt creation unit 130 creates a prompt that instructs the generation AI device 20 to generate a summary of the machining program based on the machining program acquired in step S11 and the command information acquired in step S12.

[0021] In step S14, the prompt creation unit 130 outputs the prompt created in step S13 to the generation AI device 20.

[0022] In step S15, the presentation unit 140 receives a summary of the processing program from the generation AI device 20.

[0023] In step S16, the presentation unit 140 presents the summary received in step S15 by displaying it on the display device (not shown) of the user assistance device 10.

[0024] As described above, the user assistance device 10 according to the first embodiment can create prompts for generating a highly accurate summary of a machining program using the AI ​​generation device 20, so that the machining program can be easily verified and modified without relying on the operator's experience or knowledge. Furthermore, when verifying and modifying a machining program for industrial machinery, the user can verify and modify the program without relying on the operator's experience or knowledge, thereby reducing the time required for verification and modification. The first embodiment has been described above.

[0025] <Variation of the First Embodiment> In the first embodiment described above, the prompt creation unit 130 creates a prompt that instructs the generation AI device 20 to generate a summary of the processing program based on the processing program and command information, and the presentation unit 140 displays the summary generated by the generation AI device 20 on a display device (not shown) of the user assistance device 10. However, this is not limited to this. For example, the prompt creation unit 130 may create a prompt that includes an instruction to highlight a variable parameter based on the command format information of the command information, or an instruction to add an identifier of the line number and / or argument in the processing program to the variable parameter. The presentation unit 140 may highlight the variable parameter in the summary generated by the generation AI device 20. Note that the identifier may be a range of characters, such as a certain number of characters in the processing program, in addition to the line number and / or argument.

[0026] FIG. 7 is a diagram illustrating an example of a prompt including an instruction to highlight variable parameters. As shown in FIG. 7 , the prompt creation unit 130 creates a prompt with a statement in the first line, similar to the prompt in FIG. 4 , that instructs the user to summarize the contents of the machining program: “Based on the following assumptions, summarize the contents of the machining program and output the summary by enclosing the variable parameters in square brackets [ ], as in the output example.” The statement “Enclose the variable parameters in square brackets [ ], as in the output example” is an instruction to highlight the variable parameters. FIG. 8 is a diagram illustrating an example of a summary generated by the prompt in FIG. 7 , in which the variable parameters are highlighted. As shown in FIG. 8 , the presentation unit 140 may highlight the variable parameters enclosed in brackets in bold on the display device (not shown) of the user assistance device 10. Although the presentation unit 140 highlights the variable parameters in bold in FIG. 8 , they may also be highlighted in a color such as red.

[0027] FIG. 9 illustrates an example of a prompt including an instruction to highlight variable parameters and an instruction to add line numbers and / or argument identifiers. As shown in FIG. 9 , the prompt creation unit 130 creates a prompt with a statement in the first line that instructs the user to summarize the contents of a machining program: "Based on the following assumptions, summarize the contents of the machining program, enclose the variable parameter portion in square brackets [ ], and enclose the line numbers and arguments in the program in parentheses ( ) as in the output example." The statement "Enclose the variable parameter portion in square brackets [ ], and enclose the line numbers and arguments in the program in parentheses ( ) as in the output example" is an instruction to highlight variable parameters and also an instruction to add identifiers to the variable parameters. FIG. 10 illustrates an example of a summary generated by the prompt in FIG. 9 , in which variable parameters are highlighted and identifiers are added. As shown in FIG. 10 , the presentation unit 140 highlights the variable parameters in bold, adds line numbers and argument identifiers, and displays the summary on the display device (not shown) of the user assistance device 10. Although the presentation unit 140 highlights the variable parameters in bold in FIG. 10, they may be highlighted in colored text such as red.

[0028] Second Embodiment Next, the second embodiment will be described. As described above, in the first embodiment, the user assistance device 10 acquires a processing program and instruction information for the processing program, and creates a prompt that instructs the generation AI device 20 to create a summary of the processing program based on the acquired processing program and instruction information. In contrast, in the second embodiment, the user assistance device 10A acquires the processing program and instruction information for the processing program, as well as prerequisites for executing the processing program, and creates a prompt that instructs the generation AI device 20 to create a summary of the processing program based on the processing program, instruction information, and prerequisites. This differs from the first embodiment in that the user assistance device 10A can thereby create a prompt for generating a highly accurate summary of the processing program or a selected range using the generation AI device 20, so that the processing program can be easily verified and modified regardless of the operator's experience or knowledge. The second embodiment will be described below.

[0029] FIG. 11 is a diagram showing an example of a functional block configuration of a user assistance system according to the second embodiment. Elements having the same functions as those of the user assistance system 1 in FIG. 1 are designated by the same reference numerals, and detailed descriptions thereof are omitted. As shown in FIG. 11 , the user assistance system 1 includes a user assistance device 10A and a generation AI device 20. The user assistance device 10A and the generation AI device 20 are connected to each other via a network (not shown), such as a LAN or the Internet, and communicate with each other. In this case, the user assistance device 10A and the generation AI device 20 are equipped with a communication unit (not shown) for communicating with each other via such a connection. The user assistance device 10A and the generation AI device 20 may also be directly connected to each other via a connection interface (not shown). The generation AI device 20 has the same functions as the generation AI device 20 of the first embodiment.

[0030] The user assistance device 10A is, for example, a known information processing device (computer) similar to the user assistance device 10 of the first embodiment, and as shown in Fig. 11, includes a machining program acquisition unit 110, a command information acquisition unit 120, a prompt creation unit 130a, a presentation unit 140, and a prerequisite acquisition unit 150. The user assistance device 10A includes a processing unit (not shown) such as a CPU to realize the operation of the functional blocks in Fig. 11. The user assistance device 10A also includes a secondary storage device (not shown) such as a ROM or HDD that stores various control programs, and a main storage device (not shown) such as a RAM for storing data temporarily required for the processing unit to execute the programs.

[0031] In the user assistance device 10A, the arithmetic processing unit loads the OS and application software from the auxiliary storage device, and executes arithmetic processing based on the OS and application software while loading the loaded OS and application software into the main storage device. Based on the results of this calculation, the user assistance device 10A controls each piece of hardware. This allows the processing represented by the functional blocks in FIG. 11 to be realized. In other words, the user assistance device 10A can be realized by the cooperation of hardware and software. The machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 have the same functions as the machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 of the first embodiment.

[0032] The precondition acquisition unit 150 acquires preconditions for executing a machining program. Specifically, the precondition acquisition unit 150 acquires, as preconditions, setting information (default values) related to at least one of a machining program or command information that is not set in the machining program or command information but is preset in a laser processing machine (not shown). For example, the setting information (default values) preset in the laser processing machine (not shown) may be a machining speed of "6000 mm / min" or an assist gas pressure of "0.5 MPa."

[0033] The prompt creation unit 130a creates a prompt that instructs the generation AI device 20 to generate a summary of the machining program based on the machining program, command information, and prerequisites. Specifically, the prompt creation unit 130a creates a prompt that summarizes the contents of the machining program based on, for example, the machining program shown in FIG. 2 and the command information shown in FIG. 3 received by the user via the input device (not shown) of the user assistance device 10, and the prerequisites. FIG. 12 is a diagram showing an example of a prompt created by the prompt creation unit 130a. As in the case of FIG. 4, lines 1 to 3 of the prompt shown in FIG. 12 store a command statement instructing the generation of a summary of the contents of the machining program, the machining program to be summarized, and command information. Line 4 of the prompt shown in FIG. 12 stores prerequisites for the setting information (default values) preset in the laser processing machine (not shown). Note that in the prompt shown in FIG. 12, the machining program, command information, and prerequisites are surrounded by a solid-line rectangle, but the solid-line rectangle may be omitted. The prompt creation unit 130a then outputs the created prompt to the generation AI device 20.

[0034] Fig. 13 is a diagram showing an example of a summary of the contents of a machining program generated by the generation AI device 20 based on the prompt in Fig. 12. In the summary shown in Fig. 13, compared to the summary in Fig. 5, a description of the machining speed is added in the fifth line.

[0035] <User Assistance Processing of User Assistance Device 10A> Next, the flow of the user assistance processing of the user assistance device 10A will be described with reference to Figure 14. Figure 14 is a flowchart illustrating the user assistance processing of the user assistance device 10A. The flow shown here is executed each time the user assistance device 10A receives an input instruction for a processing program from the user. Note that the processing of steps S21, S22, and S25 to S27 is similar to the processing of steps S11, S12, and S14 to S16 in Figure 6, and therefore will not be described again.

[0036] In step S23, the precondition acquisition unit 150 acquires preconditions (setting information) that are set in advance in the laser processing machine (not shown) when the processing program is executed.

[0037] In step S24, the prompt creation unit 130 creates a prompt that instructs the generation AI device 20 to generate a summary of the machining program based on the machining program acquired in step S21, the command information acquired in step S22, and the prerequisites acquired in step S23.

[0038] As described above, the user assistance device 10A according to the second embodiment can create prompts for generating a highly accurate summary of a machining program or a selected area using the AI ​​generation device 20, allowing the user to easily verify and modify the machining program without relying on the operator's experience or knowledge. Furthermore, when verifying and modifying a machining program for industrial machinery, the user can verify and modify the program without relying on the operator's experience or knowledge, thereby reducing the time required for verification and modification. The second embodiment has been described above.

[0039] <Third Embodiment> Next, the third embodiment will be described. As described above, in the first embodiment, the user assistance device 10 acquired a processing program and instruction information for the processing program, and based on the acquired processing program and instruction information, created a prompt that instructs the generation AI device 20 to summarize the processing program. In the second embodiment, the user assistance device 10A acquired the processing program and instruction information for the processing program, as well as prerequisites for executing the processing program, and created a prompt that instructs the generation AI device 20 to summarize the processing program based on the processing program, instruction information, and prerequisites. In contrast, in the third embodiment, when a range of the processing program to be summarized is specified based on a user's input instruction, the user assistance device 10B acquires, as prerequisites, modal information set and retained by a processing program executed before the specified range of the processing program. This differs from the first and second embodiments in that the user assistance device 10B thereby can create a prompt for generating a highly accurate summary of the processing program or a selected range using the generation AI device 20, allowing the operator to easily verify and modify the processing program regardless of their experience or knowledge. The third embodiment will now be described.

[0040] FIG. 15 is a diagram showing an example of a functional block configuration of a user assistance system according to the third embodiment. Elements having similar functions to those of the user assistance system 1 in FIG. 11 are designated by the same reference numerals, and detailed descriptions thereof are omitted. As shown in FIG. 15, the user assistance system 1 includes a user assistance device 10B and a generation AI device 20. The user assistance device 10B and the generation AI device 20 are connected to each other via a network (not shown), such as a LAN or the Internet, and communicate with each other. In this case, the user assistance device 10B and the generation AI device 20 are provided with a communication unit (not shown) for communicating with each other via such a connection. The user assistance device 10B and the generation AI device 20 may also be directly connected to each other via a connection interface (not shown). The generation AI device 20 has similar functions to the generation AI device 20 of the first embodiment.

[0041] The user assistance device 10B is, for example, a known information processing device (computer) similar to the user assistance device 10 of the first embodiment, and is configured to include a machining program acquisition unit 110, a command information acquisition unit 120, a prompt creation unit 130b, a presentation unit 140, and a prerequisite acquisition unit 150b, as shown in Fig. 15. The user assistance device 10B is equipped with a processing unit (not shown), such as a CPU, to realize the operations of the functional blocks in Fig. 15. The user assistance device 10B also includes an auxiliary storage device (not shown), such as a ROM or HDD, that stores various control programs, and a main storage device (not shown), such as a RAM, for storing data temporarily required for the processing unit to execute the programs.

[0042] In the user assistance device 10B, the arithmetic processing unit loads the OS and application software from the auxiliary storage device, and executes arithmetic processing based on the OS and application software while loading the loaded OS and application software into the main storage device. Based on the results of this calculation, the user assistance device 10B controls each piece of hardware. This allows the processing represented by the functional blocks in FIG. 15 to be realized. In other words, the user assistance device 10B can be realized by the cooperation of hardware and software. The machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 have the same functions as the machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 of the first embodiment.

[0043] For example, as shown in FIG. 16 , when a machining program in a range P1 indicated by a dashed rectangle is selected from among the machining programs in FIG. 16 by a user's input operation via an input device (not shown) of the user assist device 10B, the precondition acquisition unit 150b acquires, as preconditions, modal information set and held by a machining program in a range P2 indicated by a dashed-dotted rectangle that is executed before the machining program in the selected range P1. FIG. 17 is a diagram showing an example of modal information set and held by a machining program in a range P2 indicated by a dashed-dotted rectangle in FIG. 16 . The precondition acquisition unit 150b outputs the modal information in FIG. 17 as a precondition to the prompt creation unit 130b, which will be described later.

[0044] The prompt creation unit 130b creates a prompt that instructs the generation AI device 20 to generate a summary of the machining program based on the machining program and command information and preconditions for the range selected by the user via the input device (not shown) of the user assistance device 10. Specifically, the prompt creation unit 130b creates a prompt that summarizes the contents of the machining program for range P1 based on, for example, the machining program for range P1 selected by the user via the input device (not shown) of the user assistance device 10, the command information of FIG. 3, and the preconditions of FIG. 17. FIG. 18 is a diagram showing an example of a prompt generated by the prompt creation unit 130b. The prompt shown in FIG. 18 stores a statement commanding a summary of the contents of the machining program on the first line, and stores the machining program for range P1 to be summarized on the second line. The prompt shown in FIG. 18 also stores command information for the G code "G01" for range P1 on the third line, and stores the preconditions for the modal information of the machining program shown in FIG. 16 on the fourth line. 18, the machining program, command information, and prerequisites are enclosed in a solid-line rectangle, but the solid-line rectangle may be omitted. The prompt creation unit 130b then outputs the created prompt to the generation AI device 20.

[0045] Fig. 19 is a diagram showing an example of a summary of the contents of a machining program generated by the generation AI device 20 based on the prompt in Fig. 18. As shown in Fig. 19, a summary of the machining program for range P1 of the machining program in Fig. 16 is generated.

[0046] <User Assistance Processing of User Assistance Device 10B> Next, the flow of the user assistance processing of the user assistance device 10B will be described with reference to Figure 20. Figure 20 is a flowchart illustrating the user assistance processing of the user assistance device 10B. The flow shown here is executed each time the user assistance device 10B receives an instruction to select the range of a machining program from the user. Note that the processing of steps S31, S32, and S35 to S38 is similar to the processing of steps S21, S22, and S24 to S27 in Figure 14, and therefore will not be described again.

[0047] In step S33, the precondition acquisition unit 150b receives an instruction to select a machining program in the range P1 from among the machining programs, based on an instruction input by the user via an input device (not shown) of the user assistance device 10B.

[0048] In step S34, the precondition acquisition unit 150b acquires, as a precondition, modal information set and held by the machining program in the range P2 that is executed before the machining program in the range P1 selected in step S33.

[0049] As described above, the user assistance device 10B according to the third embodiment can create prompts for generating a highly accurate summary of a machining program or a selected area using the AI ​​generation device 20, allowing the operator to easily verify and modify the machining program without relying on their experience or knowledge. Furthermore, when verifying and modifying a machining program for industrial machinery, the user can verify and modify the program without relying on their experience or knowledge, thereby reducing the time required for verification and modification. The third embodiment has been described above.

[0050] <Fourth Embodiment> Next, the fourth embodiment will be described. As described above, in the first embodiment, the user assistance device 10 acquires a machining program and instruction information for the machining program, and generates a prompt instructing the AI ​​device 20 to generate a summary of the machining program based on the acquired machining program and instruction information. In the second embodiment, the user assistance device 10A acquires the machining program and instruction information for the machining program, as well as prerequisites for executing the machining program, and generates a prompt instructing the AI ​​device 20 to generate a summary of the machining program based on the machining program, instruction information, and prerequisites. In the third embodiment, when a range of the machining program to be summarized is specified based on a user's input instruction, the user assistance device 10B acquires, as prerequisites, modal information set and retained by a machining program executed before the specified range of the machining program. In contrast, in the fourth embodiment, the user assistance device 10C differs from the first to third embodiments in that, when a user specifies a variable parameter change instruction in the presented summary, the user assistance device 10C generates a machining program with the variable parameter changed. As a result, the user assistance device 10C can generate prompts for generating a highly accurate summary of the machining program or a selected area using the AI ​​generation device 20 so that the machining program can be easily verified and modified regardless of the operator's experience or knowledge. A fourth embodiment will now be described.

[0051] FIG. 21 is a diagram showing an example of a functional block configuration of a user assistance system according to the fourth embodiment. Elements having the same functions as those of the user assistance system 1 in FIG. 1 are designated by the same reference numerals, and detailed descriptions thereof are omitted. As shown in FIG. 21 , the user assistance system 1 includes a user assistance device 10C and a generation AI device 20. The user assistance device 10C and the generation AI device 20 are connected to each other via a network (not shown), such as a LAN or the Internet, and communicate with each other. In this case, the user assistance device 10C and the generation AI device 20 are equipped with a communication unit (not shown) for communicating with each other via such a connection. The user assistance device 10C and the generation AI device 20 may also be directly connected to each other via a connection interface (not shown). The generation AI device 20 has the same functions as the generation AI device 20 of the first embodiment.

[0052] The user assistance device 10C is, for example, a known information processing device (computer) or the like, similar to the user assistance device 10 of the first embodiment, and is configured to include a machining program acquisition unit 110, a command information acquisition unit 120, a prompt creation unit 130, a presentation unit 140, and a program generation unit 160, as shown in Fig. 21. The user assistance device 10C is equipped with a processing unit (not shown), such as a CPU, to realize the operations of the functional blocks in Fig. 21. The user assistance device 10C also includes an auxiliary storage device (not shown), such as a ROM or HDD, that stores various control programs, and a main storage device (not shown), such as a RAM, for storing data temporarily required for the processing unit to execute the programs.

[0053] In the user assistance device 10C, the arithmetic processing unit loads the OS and application software from the auxiliary storage device, and executes arithmetic processing based on the OS and application software while loading the loaded OS and application software into the main storage device. Based on the results of this calculation, the user assistance device 10C controls each piece of hardware. This allows the processing represented by the functional blocks in FIG. 21 to be realized. In other words, the user assistance device 10C can be realized by the cooperation of hardware and software. The machining program acquisition unit 110, the command information acquisition unit 120, the prompt creation unit 130, and the presentation unit 140 have the same functions as the machining program acquisition unit 110, the command information acquisition unit 120, the prompt creation unit 130, and the presentation unit 140 of the first embodiment.

[0054] For example, when the program generation unit 160 receives a user instruction to change a variable parameter highlighted by the presentation unit 140 via an input device (not shown) of the user assistance device 10C, the program generation unit 160 generates a machining program that reflects the change based on the change content and identifier of the received change instruction. Specifically, the presentation unit 140 receives, for example, a summary shown in FIG. 23 generated by the generation AI device 20 for the machining program shown in FIG. 22 from the generation AI device 20, and displays the summary display screen shown in FIG. 23 on the display device (not shown) of the user assistance device 10C. Based on a user input operation via the input device (not shown) of the user assistance device 10C, the program generation unit 160 receives an instruction to change the variable parameter "3000" corresponding to the identifier (S command on the second line) on the display screen of FIG. 23 to "4000" as shown in FIG. 24. In this case, the program generation unit 160 generates a machining program in which the power command is changed to "4000" as shown in FIG. 25. This allows users to easily modify machining programs regardless of their experience or knowledge.

[0055] <User assistance processing of user assistance device 10C> Next, the flow of the user assistance processing of the user assistance device 10C will be described with reference to Figure 26. Figure 26 is a flowchart illustrating the user assistance processing of the user assistance device 10C. The flow shown here is executed every time the user assistance device 10C receives an input instruction for a processing program from the user. Note that the processing from steps S41 to S46 is the same as the processing from steps S11 to S16 in Figure 6, and therefore a description thereof will be omitted.

[0056] In step S47, if the program generation unit 160 receives an instruction to change the variable parameters on the summary display screen presented in step S46 based on the user's input operation via the input device (not shown) of the user assistance device 10C, it generates a processing program with the variable parameters changed.

[0057] As described above, the user assistance device 10C according to the fourth embodiment can create prompts for generating a highly accurate summary of a machining program or a selected area using the AI ​​generation device 20, allowing the user to easily verify and modify the machining program regardless of the operator's experience or knowledge. Furthermore, when verifying and modifying a machining program for industrial machinery, the user can verify and modify the program without relying on the operator's experience or knowledge, thereby reducing the time required for verification and modification. Furthermore, the user assistance device 10C can change the machining program by making changes in the presented natural language summary, without directly modifying the machining program, allowing the user to easily modify the machining program regardless of their experience or knowledge. The fourth embodiment has been described above.

[0058] Fifth Embodiment Next, the fifth embodiment will be described. As described above, in the first embodiment, the user assistance device 10 acquires a processing program and instruction information for the processing program, and generates a prompt instructing the AI ​​device 20 to summarize the processing program based on the acquired processing program and instruction information. In the second embodiment, the user assistance device 10A acquires the processing program and instruction information for the processing program, as well as prerequisites for executing the processing program, and generates a prompt instructing the AI ​​device 20 to summarize the processing program based on the processing program, instruction information, and prerequisites. In the third embodiment, when a range of the processing program to be summarized is specified based on a user's input instruction, the user assistance device 10B acquires, as prerequisites, modal information set and retained by a processing program executed before the specified range of processing programs. In the fourth embodiment, when the user assistance device 10C receives a user instruction to change a variable parameter in the presented summary, it generates a processing program with the variable parameter changed. In contrast, in the fifth embodiment, the user assistance device 10D acquires summary conditions for summarizing the processing program and generates a prompt for summarizing the processing program based on the acquired summary conditions, which differs from the first to fourth embodiments. As a result, the user assistance device 10D can generate prompts for generating a highly accurate summary of the machining program or a selected area using the AI ​​generation device 20 so that the machining program can be easily verified and modified regardless of the operator's experience or knowledge. A fifth embodiment will now be described.

[0059] FIG. 27 is a diagram showing an example of a functional block configuration of a user assistance system according to the fifth embodiment. Elements having similar functions to those of the user assistance system 1 in FIG. 1 are designated by the same reference numerals, and detailed descriptions thereof are omitted. As shown in FIG. 27 , the user assistance system 1 includes a user assistance device 10D and a generation AI device 20. The user assistance device 10D and the generation AI device 20 are connected to each other via a network (not shown), such as a LAN or the Internet, and communicate with each other. In this case, the user assistance device 10D and the generation AI device 20 are equipped with a communication unit (not shown) for communicating with each other via such a connection. The user assistance device 10D and the generation AI device 20 may also be directly connected to each other via a connection interface (not shown). The generation AI device 20 has similar functions to the generation AI device 20 of the first embodiment.

[0060] The user assistance device 10D is, for example, a known information processing device (computer) similar to the user assistance device 10 of the first embodiment, and as shown in Fig. 27, is configured to include a processing program acquisition unit 110, a command information acquisition unit 120, a prompt creation unit 130d, a presentation unit 140, and a summary condition acquisition unit 170. The user assistance device 10D is equipped with a processing unit (not shown) such as a CPU to realize the operations of the functional blocks in Fig. 27. The user assistance device 10D also includes auxiliary storage devices (not shown) such as a ROM or HDD that store various control programs, and a main storage device (not shown) such as a RAM for storing data temporarily required for the processing unit to execute the programs.

[0061] In the user assistance device 10D, the arithmetic processing unit loads the OS and application software from the auxiliary storage device, and executes arithmetic processing based on the OS and application software while loading the loaded OS and application software into the main storage device. Based on the results of this calculation, the user assistance device 10D controls each piece of hardware. This allows the processing represented by the functional blocks in FIG. 27 to be realized. In other words, the user assistance device 10D can be realized by the cooperation of hardware and software. The machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 have the same functions as the machining program acquisition unit 110, the command information acquisition unit 120, and the presentation unit 140 of the first embodiment.

[0062] The summary condition acquisition unit 170 acquires summary conditions of the machining program based on a user's input operation via an input device (not shown) of the user assistance device 10D. Specifically, the summary condition acquisition unit 170 acquires summary conditions for checking laser machining conditions, assist gas output conditions, or the laser machining flow in the machining program acquired by the machining program acquisition unit 110, for example, based on a user's input operation via the input device (not shown) of the user assistance device 10D. That is, the summary condition acquisition unit 170 acquires "summarize to check laser machining conditions" as a summary condition for checking laser machining conditions based on a user's input operation via the input device (not shown) of the user assistance device 10D. Furthermore, the summary condition acquisition unit 170 acquires "summarize to check assist gas output conditions" as a summary condition for checking assist gas output conditions based on a user's input operation via the input device (not shown) of the user assistance device 10D. In addition, the summary condition acquisition unit 170 acquires "summarize the laser processing flow" as a summary condition for confirming the laser processing flow based on the user's input operation via the input device (not shown) of the user assistance device 10D.

[0063] The prompt creation unit 130d creates a prompt for summarizing the machining program based on the summarization conditions along with the machining program and command information, and outputs the created prompt to the generation AI device 20.

[0064] For example, if the processing program acquisition unit 110 acquires the processing program shown in FIG. 28 and the summary condition acquisition unit 170 acquires the summary condition "to provide a summary to confirm the laser processing conditions," the presentation unit 140 acquires the summary shown in FIG. 29 from the generation AI device 20 and displays it on the display device (not shown) of the user assistance device 10D. Also, if the processing program acquisition unit 110 acquires the processing program shown in FIG. 30 and the summary condition acquisition unit 170 acquires the summary condition "to provide a summary to confirm the assist gas output conditions," the presentation unit 140 acquires the summary shown in FIG. 31 from the generation AI device 20 and displays it on the display device (not shown) of the user assistance device 10D. Also, if the processing program acquisition unit 110 acquires the processing program shown in FIG. 32 and the summary condition acquisition unit 170 acquires the summary condition "to provide a summary of the laser processing flow," the presentation unit 140 acquires the summary shown in FIG. 33 from the generation AI device 20 and displays it on the display device (not shown) of the user assistance device 10D.

[0065] <User Assistance Processing of User Assistance Device 10D> Next, the flow of the user assistance processing of the user assistance device 10D will be described with reference to Figure 34. Figure 34 is a flowchart illustrating the user assistance processing of the user assistance device 10D. The flow shown here is executed each time the user assistance device 10D receives an instruction to select a range of a machining program from the user. Note that the processing of steps S51, S52, and S55 to S57 is similar to the processing of steps S11, S12, and S14 to S16 in Figure 6, and therefore will not be described again.

[0066] In step S53, the summary condition acquisition unit 170 acquires summary conditions for the machining program based on an input operation by the user via an input device (not shown) of the user assist device 10D.

[0067] In step S54, the prompt creation unit 130d creates a prompt that instructs the generation AI device 20 to generate a summary of the machining program based on the machining program acquired in step S51, the command information acquired in step S52, and the summary conditions acquired in step S53.

[0068] As described above, the user assistance device 10D according to the fifth embodiment can create prompts for generating a highly accurate summary of a machining program or a selected area using the AI ​​generation device 20, allowing the operator to easily verify and modify the machining program regardless of their experience or knowledge. Furthermore, when verifying and modifying a machining program for industrial machinery, the user can verify and modify the program without relying on their experience or knowledge, thereby reducing the time required for verification and modification. The fifth embodiment has been described above.

[0069] As described above in the first embodiment, the modified example of the first embodiment, and the second to fifth embodiments, the user assistance devices 10, 10A to 10D of the present disclosure can create prompts for generating a highly accurate summary of a processing program or a selected range using the generation AI device 20, so that the processing program can be easily verified and modified regardless of the operator's experience or knowledge.

[0070] <Modification 1> In the first embodiment, the modification of the first embodiment, and the second to fifth embodiments, the industrial machine is a laser processing machine, but is not limited to this. For example, the industrial machine may be a machine tool, an industrial robot, a service robot, a forging machine, an injection molding machine, or the like. For example, if the industrial machine is a machine tool, the summarization condition acquisition unit 170 may acquire summarization conditions such as "perform a summary to confirm cutting conditions," "perform a summary of the cutting flow," "perform a summary to confirm the cutting speed," "perform a summary to confirm the spindle rotation speed," and "perform a summary to confirm the machining shape."

[0071] <Modification 2> In the above-described embodiment, the generative AI device 20 uses a trained language model trained using a large amount of data on the web as training data, but this is not limited to this. For example, the trained language model of the generative AI device 20 may be a trained model that has undergone additional training, i.e., fine-tuning, in a specialized field such as a processing program.

[0072] <Variation 3> In the above-described embodiment, the user assistance devices 10, 10A to 10D create a prompt summarizing the machining program acquired from the industrial machine and present the summary generated by the generation AI device 20 based on the created prompt, but this is not limited to this. For example, the user assistance devices 10, 10A to 10D may create a prompt summarizing the simulation results of a simulation device that simulates the machining program as the simulation progresses, and present the summary generated by the generation AI device 20 based on the created prompt. This allows the user to easily verify and modify the machining program regardless of the operator's experience or knowledge.

[0073] Note that the functions of the user assistance devices 10, 10A to 10D in the first embodiment, the modified example of the first embodiment, and the second to fifth embodiments can be realized by hardware, software, or a combination of these. Here, "realized by software" means that the functions are realized by a computer reading and executing a program.

[0074] The program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs). The program may be provided to the computer by various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transient computer-readable media can provide the program to the computer via a wired communication path such as an electrical wire or optical fiber, or via a wireless communication path.

[0075] The step of executing the program recorded on the recording medium includes not only processes that are performed in chronological order, but also processes that are not necessarily performed in chronological order but are performed in parallel or individually. Also, the step of writing the program may be performed by cloud computing.

[0076] Although the present disclosure has been described in detail, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible in these embodiments without departing from the gist of the present disclosure or the spirit of the present disclosure derived from the content of the claims and their equivalents. These embodiments can also be implemented in combination. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical expressions are used in the description of the above-described embodiments.

[0077] The following supplementary notes are further disclosed regarding the above embodiments and variations. (Supplementary Note 1) A user assistance device (10) is a user assistance function that displays a machining program for an industrial machine, and includes a machining program acquisition unit (110) that acquires the machining program, a command information acquisition unit (120) that acquires command information including commands and command format information included in the machining program, a prompt creation unit (130) that creates a prompt that instructs a generation AI device (20) to create a summary of the machining program based on the machining program and the command information, and a presentation unit (140) that presents to the user a summary of the machining program generated by the generation AI device (20) based on the created prompt. (Supplementary Note 2) The user assistance device (10A) of Supplementary Note 1 includes a prerequisite acquisition unit (150) that acquires prerequisites for executing the machining program, and the prompt creation unit (130a) creates a prompt based on the prerequisites as well as the machining program and command information, and the presentation unit (140) presents a summary of the machining program generated by the generation AI device (20) based on the created prompt. (Supplementary Note 3) In the user assistance device (10A) of Supplementary Note 2, the prerequisite acquisition unit (150) acquires, as a prerequisite, setting information of an industrial machine related to at least one of a machining program or command information. (Supplementary Note 4) In the user assistance device (10B) of Supplementary Note 2, when a partial range of a machining program is specified, the prerequisite acquisition unit (150b) acquires, as a prerequisite, modal information set and held by a machining program executed before the specified range of the machining program. (Supplementary Note 5) In the user assistance device (10) of Supplementary Note 1, the prompt creation unit (130) creates a prompt including an instruction for adding an identifier to the variable parameter based on the command format information, and the presentation unit (140) highlights the variable parameter based on the identifier. (Supplementary Note 6) In the user assistance device (10) of Supplementary Note 5, the identifier is at least the number of lines and / or arguments of the machining program in which the variable parameter is set, or a range of characters in the machining program.(Supplementary Note 7) The user assistance device (10C) of Supplementary Note 5 includes a program generation unit (160) that, when receiving an instruction to change a variable parameter highlighted by the presentation unit (140), generates a machining program that reflects the change content based on the change content and identifier of the received change instruction. (Supplementary Note 8) The user assistance device (10D) of Supplementary Note 1 includes a summary condition acquisition unit (170) that acquires summary conditions for the machining program, and a prompt creation unit (130d) creates a prompt for summarizing the machining program based on the summary conditions.

[0078] 1 User assistance system 10, 10A, 10B, 10C, 10D User assistance device 110 Machining program acquisition unit 120 Command information acquisition unit 130, 130a, 130b, 130d Prompt creation unit 140 Presentation unit 150, 150b Prerequisite condition acquisition unit 160 Program generation unit 170 Summary condition acquisition unit 20 Generation AI device

Claims

1. A user assistance function for displaying a machining program of an industrial machine, comprising: a machining program acquisition unit that acquires a machining program; an instruction information acquisition unit that acquires instruction information including an instruction and instruction format information included in the machining program; a prompt creation unit that creates a prompt for instructing a generation AI device to generate a summary of the machining program based on the machining program and the instruction information; and a presentation unit that presents the summary of the machining program generated by the generation AI device to the user based on the created prompt.

2. The user assistance device according to claim 1, further comprising a prerequisite acquisition unit that acquires prerequisites for executing the machining program, wherein the prompt creation unit creates the prompt based on the machining program, the instruction information, and the prerequisites, and the presentation unit presents the summary of the machining program generated by the generation AI device based on the created prompt.

3. The user assistance device according to claim 2, wherein the prerequisite acquisition unit acquires, as the prerequisite, setting information of the industrial machine related to at least one of the machining program or the instruction information.

4. The user assistance device according to claim 2, wherein when a partial range of the machining program is specified, the prerequisite acquisition unit acquires, as the prerequisite, modal information set and held by the machining program executed before the machining program in the specified range.

5. The user assistance device according to claim 1, wherein the prompt creation unit creates the prompt including an instruction for adding an identifier to a variable parameter based on the instruction format information, and the presentation unit highlights the variable parameter based on the identifier.

6. The user assistance device according to claim 5, wherein the identifier is at least the line number and / or argument of the machining program in which the variable parameter is set, or the range of characters in the machining program.

7. The user assistance device according to claim 5, further comprising a program generation unit that generates a machining program in which the change content is reflected based on the change content of the received change instruction and the identifier when receiving a change instruction for the variable parameter highlighted by the prompting unit.

8. The user assistance device according to claim 1, further comprising a summary condition acquisition unit that acquires summary conditions of the machining program, wherein the prompt creation unit creates a prompt for summarizing the machining program based on the summary conditions.

Images