Program generation assistance device

Abstract

The system generates a NC program to achieve the desired actions of an industrial machine by generating a question to be input into the AI ​​generation device using the minimum labor required by the operator. The program generation assists in generating the numerical control program that enables the industrial machine to operate. This program generation assist includes: a machine information acquisition unit that acquires machine information related to the industrial machine; a question generation unit that acquires action information related to the desired actions of the industrial machine and combines it with the machine information acquired by the machine information acquisition unit to generate a question to be sent to the AI ​​generation device; a sending unit that sends the question generated by the question generation unit to the AI ​​generation device; a receiving unit that receives a first response result from the AI ​​generation device; and a prompting unit that prompts the first response result.

Description

Technical Field

[0001] This disclosure relates to a program generation auxiliary device for generating auxiliary numerical control programs. Background Technology

[0002] The technology of using numerical control programs (hereinafter also known as "NC programs") to make industrial machines move has become widespread.

[0003] NC programs have a unique syntax, which can be difficult for beginners to understand.

[0004] In this regard, a technique has been proposed to implement an operator interface for controlling the robot by using a programming language for describing robot operations and an intuitive, conversational environment for creating, editing, and executing programs. For example, see Patent Document 1.

[0005] Furthermore, it is thought that this problem can be solved by using technologies such as AI chatbots (hereinafter also referred to as "generated AI devices").

[0006] Specifically, the idea is that if we use questions (prompts) in the form of natural language to describe the actions of industrial machines and input them into an AI-generating device, we can easily create NC programs that implement those actions.

[0007] Existing technical documents

[0008] Patent documents

[0009] Patent Document 1: Japanese Patent Publication No. 4-507022 Summary of the Invention

[0010] The problem that the invention aims to solve

[0011] To achieve the desired actions of industrial machines, operators only need to input the minimum required questions into the AI ​​generator to obtain the NC program that will perform the action. However, in order for the AI ​​generator to correctly output the NC program used to achieve the desired actions and prevent the industrial machines from malfunctioning, it is necessary not only to input the action details into the AI ​​generator, but also to input machine information related to the industrial machine (such as machine name, current position of each axis, control mode, etc.).

[0012] Furthermore, a method was considered whereby operators input machine information from industrial machines in the form of questions from the AI-generating device, but this method would become a burden for the operators.

[0013] Therefore, it is hoped that by generating the minimum amount of labor required by the operator, inputting the question into the AI ​​generator, an NC program can be obtained to achieve the desired actions of the industrial machine.

[0014] Methods for solving problems

[0015] One aspect of the program generation assisting device disclosed herein is a program generation assisting device that assists in generating a numerical control program for operating an industrial machine. This program generation assisting device comprises: a machine information acquisition unit that acquires machine information related to the industrial machine; a question generation unit that acquires action information related to the desired action content of the industrial machine and combines it with the machine information acquired by the machine information acquisition unit to generate a question for a generation AI device; a sending unit that sends the question generated by the question generation unit to the generation AI device; a receiving unit that receives a first response result from the generation AI device; and a prompting unit that prompts the first response result. Attached Figure Description

[0016] Figure 1 This is a diagram illustrating an example of the functional block structure of the program generation auxiliary system of the first embodiment.

[0017] Figure 2 This is a diagram representing an example of a keyword list.

[0018] Figure 3A This is an example of a prototype of a question.

[0019] Figure 3B This is an example of a prototype of a question.

[0020] Figure 4 This is a diagram representing an example of a machine table.

[0021] Figure 5 This is a diagram representing an example of machine information.

[0022] Figure 6 This is a diagram representing an example of the generated question.

[0023] Figure 7 This is an example of a display screen showing the response result.

[0024] Figure 8 This is a flowchart illustrating the auxiliary processing of the program-generated auxiliary system.

[0025] Figure 9 This diagram illustrates an example of a program generation auxiliary system that includes two opposing twin-spindle lathes of different types configured within the same factory.

[0026] Figure 10 This diagram is an example of a prototype of a question in the case of a dual-spindle lathe.

[0027] Figure 11This is a diagram illustrating an example of machine information acquired by the machine information acquisition unit.

[0028] Figure 12 This is a diagram representing an example of the generated question.

[0029] Figure 13 This is a diagram illustrating an example of the functional block structure of the program generation auxiliary system according to the second embodiment.

[0030] Figure 14 This is an example of a display screen showing the response result.

[0031] Figure 15 This is a flowchart illustrating the auxiliary processing of the program-generated auxiliary system.

[0032] Figure 16 This is a diagram illustrating an example of machine information acquired by the machine information acquisition unit.

[0033] Figure 17 This is a diagram illustrating an example of the relationship between the machine coordinate system and the workpiece coordinate system.

[0034] Figure 18 This is a diagram representing an example of the generated question.

[0035] Figure 19A This is a flowchart illustrating the process of determining the radial retreat amount in the question generation part.

[0036] Figure 19B This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the XY plane in step S33.

[0037] Figure 19C This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the ZX plane in step S34.

[0038] Figure 19D This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the YZ plane in step S35.

[0039] Figure 20A This is a flowchart illustrating the process of determining the axial retreat amount in the question generation section.

[0040] Figure 20B This is an explanation Figure 20A The flowchart shows the detailed processing steps for determining the axial retraction amount in the XY plane in step S42.

[0041] Figure 20C This is an explanation Figure 20AThe flowchart shows the detailed processing steps for determining the axial retraction amount in the ZX plane in step S43.

[0042] Figure 20D This is an explanation Figure 20A The flowchart shows the detailed processing steps for determining the axial retraction amount in the YZ plane in step S44.

[0043] Figure 21 This is an example of a display screen showing the response result. Detailed Implementation

[0044] <First Implementation Method>

[0045] Hereinafter, the program generation assistance system of the first embodiment will be described in detail with reference to the accompanying drawings.

[0046] Figure 1 This diagram illustrates an example of the functional block structure of the program generation auxiliary system according to the first embodiment. Here, a vertical 3-axis machining center is used as an example of an industrial machine. Furthermore, the present invention can also be applied to various machines such as vertical 5-axis machining centers, industrial robots, service robots, forging machines, and injection molding machines. In the case of industrial robots, the NC program is a robot program.

[0047] like Figure 1 As shown, the program generation assistance system 1 has a program generation assistance device 10 and an AI generation device 20.

[0048] The program generation assist device 10 and the AI ​​generation device 20 can also communicate with each other via a network (not shown) such as a LAN (Local Area Network) or the Internet. In this case, the program generation assist device 10 and the AI ​​generation device 20 have a communication unit (not shown) for communicating with each other via this connection. Alternatively, the program generation assist device 10 and the AI ​​generation device 20 can also be directly connected to each other via a connection interface (not shown).

[0049] <Generated AI Device 20>

[0050] The AI ​​generation device 20 is, for example, a computer or web server known to those skilled in the art. The AI ​​generation device 20 receives questions, etc., as text data and inputs them into a learned language model (e.g., a large-scale language model (LLM) such as ChatGPT (registered trademark)). The AI ​​generation device 20 generates data for response sentences, such as an NC program for the question and a request sentence requesting additional information for generating the NC program. The AI ​​generation device 20 sends the generated response sentence data to the program generation assistance device 10.

[0051] Furthermore, a learned language model (e.g., a large-scale language model) can also be a learning model that has been trained using large amounts of data from the Web as training data, and in particular, the learning model can be a learning model provided externally. Additionally, a learned language model can also be a learning model that has undergone additional learning related to a specific domain, such as processing procedures, for example, learning and / or fine-tuning based on question sentences (hints), transfer learning, etc.

[0052] <Program Generation Auxiliary Device 10>

[0053] The program generation auxiliary device 10 is, for example, a known information processing device (computer), such as... Figure 1 As shown, it includes a control unit 11, an input unit 12, a storage unit 13, and a display unit 14. In addition, the control unit 11 includes a machine information acquisition unit 110, a question generation unit 111, a transmission unit 112, a receiving unit 113, a response result regeneration unit 114, and a prompting unit 115.

[0054] <Input Section 12>

[0055] The input unit 12 can be a keyboard, mouse, touch panel (displayed later on the front surface of the display unit 14), etc., and accepts input operations from the operator. Alternatively, the input unit 12 can be a microphone, etc., and can also accept the operator's voice as input. Or, the input unit 12 can be a digital camera, etc., and accept moving images containing the operator's movements and voice as input.

[0056] <Storage Department 13>

[0057] Storage unit 13 may be, for example, an SSD (Solid State Drive) or HDD (Hard Disk Drive), while storage control unit 11 executes the operating system and applications. Additionally, storage unit 13 stores a keyword table 131 related to keywords included in the operator's input received via input unit 12, prototype data 132 of preliminary question forms prepared in advance for each job content (question content) determined based on the keywords, and a machine table 133 containing machine information such as the current position of each industrial machine required to generate the question forms.

[0058] In the keyword table 131, the question generation unit 111, which will be described later, uses a known method to pre-correspond and store the keywords extracted from the content of the operator's input received by the input unit 12 with the work content of the vertical 3-axis machining center (not shown) of the industrial machine.

[0059] Figure 2 This is a diagram representing an example of keyword table 131.

[0060] The keyword table 131 has a storage area for "keywords" extracted from the input content of the operator received by the question generation unit 111 via the input unit 12, as described later, and "job content" determined based on the keywords.

[0061] In the keyword table 131, the storage area of ​​"keywords" stores, for example, a conditional expression for determining the work content stored in the storage area of ​​"work content" (described later) based on multiple keywords extracted from the operator's input content by the question generation unit 111 (described later).

[0062] The "Job Content" storage area in Keyword Table 131 stores job content such as "bring the tool closer to the workpiece", "remove the tool from the workpiece", "position the left spindle at 0°", and "position the right spindle at 0°".

[0063] In the prototype data 132, prototypes of question sentences prepared in advance for each job content (question content) determined by the question sentence generation unit 111 based on the input content of the operator are stored.

[0064] Figure 3A as well as Figure 3B This is an example of a prototype of a question. Figure 3A This represents the prototype of a question posed when separating a tool from a workpiece in a vertical 3-axis machining center. Figure 3B This represents the prototype of a question posed when separating a tool from a workpiece in a vertical 5-axis machining center.

[0065] In addition, Figure 3A and Figure 3BThe prototype of the question shown [ As will be described later, according to machine table 133, the values ​​in the machine information of the vertical 3-axis machining center (not shown) obtained by machine information acquisition unit 110 are stored.

[0066] in addition, Figure 3B The prototype of the question shown, with its [XY plane / ZX plane / YZ plane], [left / right side], and [positive / negative direction], represents the options for each industrial machine selected based on machine table 133.

[0067] In addition, the program generation assist device 10 stores the prototype of the question in the prototype data 132, but it can also generate the prototype of the question by learning the correspondence between keywords and task content in advance.

[0068] In Machine Table 133, for each industrial machine, the numerical values ​​stored in the prototype of the question and the information required for the selection of options are stored.

[0069] Figure 4 This is a diagram representing an example of machine table 133.

[0070] Machine Table 133 has a storage area for "Machine Type" which represents the types of industrial machines, and "Necessary Information" which is the information required for selecting the numerical values ​​or options stored in the prototype of the question for each industrial machine.

[0071] In the "Machine Type" storage area within Machine Table 133, for example, there are "Vertical 3-Axis Machining Center", "Horizontal 3-Axis Machining Center", "Vertical 5-Axis Machining Center", "Opposing Twin-Spindle Lathe", etc.

[0072] In the storage area of ​​"necessary information" in the machine table 133, the values ​​stored in the prototype of the question for each industrial machine, the "current position" and "backoff position" required for the selection of options, etc., are stored in the machine information obtained by the machine information acquisition unit 110 described later.

[0073] <Display Unit 14>

[0074] The display unit 14 is, for example, a liquid crystal display included in the program generation auxiliary device 10, which displays the generated NC program.

[0075] The control unit 11 includes a CPU, ROM, RAM, CMOS memory, etc., which are configured to communicate with each other via a bus, as is known to those skilled in the art.

[0076] The CPU is the processor that controls the program generation auxiliary device 10 as a whole. The CPU reads the system program and application program stored in ROM via the bus, and controls the entire program generation auxiliary device 10 according to the system program and application program. Thus, as... Figure 1 As shown, the control unit 11 is configured to perform the functions of the machine information acquisition unit 110, the question generation unit 111, the transmission unit 112, the receiving unit 113, the response result regeneration unit 114, and the prompting unit 115. Various data, such as temporary calculation data and display data, are stored in RAM. The CMOS memory is backed up by a battery (not shown) and is configured as a non-volatile memory that maintains its stored state even when the power supply to the numerical control device (not shown) is disconnected.

[0077] The machine information acquisition unit 110 acquires machine information related to the vertical 3-axis machining center (not shown), for example, from the vertical 3-axis machining center, the numerical control device (not shown) that controls the vertical 3-axis machining center, or a server (not shown) in the factory.

[0078] Figure 5 This is a diagram representing an example of machine information.

[0079] The machine information acquired by the machine information acquisition unit 110 includes acquisition information for "machine tool type," "axis structure," "machining type," and "control status," as well as information about their acquisition sources. Specifically, in "machine tool type," "vertical 3-axis machining center" is stored as "acquisition information," and the information obtained is stored as the "acquisition source" based on the machine's catalog data in a server (not shown) within the factory. Similarly, in "axis structure," "X / Y / Z 3-axis" is stored as "acquisition information," and the information obtained is stored as the "acquisition source" based on a backup taken when the machine starts up in the server (not shown) within the factory. Furthermore, in "machining type," "Z-axis drilling machining performed by a drilling tool" is stored as "acquisition information," and the information obtained is stored as the "acquisition source" based on the tool identification information and Z-axis drilling machining mode in the numerical control device (not shown). Additionally, in the "Control State", the "Instruction Mode: Increment (G91), Current Position: Z=-10.000, Position after Retreat: Z=100.000" is stored as "Acquired Information", and the numerical control device (not shown) is stored as "Acquired Source".

[0080] The question generation unit 111 acquires motion information related to the desired motion content of the vertical 3-axis machining center (not shown), and combines it with the machine information acquired by the machine information acquisition unit 110 to generate a question for the AI ​​generation device 20.

[0081] Specifically, for example, if an operator interrupts machining in a vertical 3-axis machining center due to unusual noises, the input unit 12 receives action information from the operator stating "I want to detach the cutting tool from the workpiece." The question generation unit 111 uses a known method to extract keywords such as "tool," "workpiece," and "detach" from the input of the action information. Based on the extracted keywords and the keyword table 131, the question generation unit 111 determines the operation content (question content) of "retracting the tool from the workpiece." Based on the determined operation content (question content), the question generation unit 111 obtains data from the prototype data 132. Figure 3A The prototype. The question generation unit 111 is based on... Figure 3A The prototype of the question and Figure 5 The machine information is used to generate a question (prompt).

[0082] Figure 6 This is a diagram representing an example of the generated question.

[0083] like Figure 6 As shown, in Figure 3A In the rudiments of the question, [ The part of ] is replaced with Figure 5 The values ​​of "current position" and "position after retreat" in the "control status" of the machine information.

[0084] Thus, the program generation auxiliary device 10 can generate a question input by the operator to the generation AI device 20 with the minimum required labor force, such as "wanting to detach the cutting tool from the workpiece".

[0085] The sending unit 112, such as a network interface, sends the question generated by the question generation unit 111 to the AI ​​generation device 20.

[0086] For example, the sending unit 112 will Figure 6 The question is sent to the AI ​​generation device 20, whereby the AI ​​generation device 20 generates a response to the question. Figure 6 The NC program's response to the question. However, in Figure 6 The current instruction pattern is not present in the question (e.g., Figure 5The AI ​​generation device 20 generates a message that cannot determine whether it is in absolute mode (G90) or incremental mode (G91) based on the "control state" information in the machine information. It then generates response results for the NC programs corresponding to G90 and G91 respectively as response candidates. Specifically, in absolute mode (G90), the AI ​​generation device 20 can reach the position after the instruction retreats, thus generating the NC program "G90 Z100.0". Similarly, in incremental mode (G91), the AI ​​generation device 20 can reach the position after the instruction retreats relative to the current position, thus generating the NC program "G91 Z110.0". Furthermore, the instruction value is calculated using "(position after retreat) - (current position)".

[0087] The receiving unit 113, for example, is a network interface, which receives the response result (first response result) of the NC program sent from the AI ​​generation device 20 in response to the question (prompt).

[0088] For example, as mentioned above, the AI ​​generation device 20 targets Figure 6 The system outputs a message indicating that it cannot determine whether the mode is absolute (G90) or incremental (G91), as well as the response results for the two NC program response candidates, "G90 Z100.0" and "G91 Z110.0". The receiving unit 113 receives the response results.

[0089] The response result regeneration unit 114 generates a response result (second response result) that supplements the response result (first response result) received by the receiving unit 113 with the machine information obtained by the machine information acquisition unit 110.

[0090] Specifically, the response result regeneration unit 114, for example, confirms the response result based on a message in the response result received by the receiving unit 113 that indicates it cannot be determined whether it is an absolute mode (G90) or an incremental mode (G91). Figure 5 Machine information. In Figure 5 In the machine information, the current instruction mode is incremental mode (G91), therefore the response result regeneration unit 114 determines that the NC program "G91Z110.0" is more suitable. The response result regeneration unit 114 adds priority "1" to the NC program "G91 Z110.0" and priority "2" to the NC program "G90 Z100.0", and generates a response result (second response result) that supplements the reason why the current instruction mode is incremental mode. The response result regeneration unit 114 outputs the generated response result to the prompt unit 115.

[0091] The prompting unit 115 displays the response result on the display unit 14 to provide a prompt.

[0092] Figure 7 This is an example of a screen displaying the response result. For example... Figure 7 As shown, the display screen on the display unit 14 displays priority order and supplementary information along with the two NC programs.

[0093] Then, when the operator selects "G91Z110.0" with priority "1" via the input unit 12, the program generation auxiliary device 10 outputs the selected NC program to the numerical control device (not shown). The numerical control device (not shown) is able to control the cutting tool to disengage from the workpiece in a vertical 3-axis machining center (not shown).

[0094] In this way, by displaying the priority of response results on the display unit 14, the operator can save time in studying the NC program.

[0095] In addition, the program generation assist device 10 (response result regeneration unit 114) displays the response result, which is supplemented with the machine information used, on the display unit 14 to provide a prompt, so that the operator can know on what basis the NC program of the response result was obtained and can perform illusion countermeasures.

[0096] <Assistive Processing of Program Generation Assist System 1>

[0097] Next, refer to Figure 8 This describes the process of generating auxiliary processing for auxiliary system 1.

[0098] Figure 8 This is a flowchart illustrating the auxiliary processing of the program generating auxiliary system 1.

[0099] In step S11, the machine information acquisition unit 110 acquires machine information related to the vertical 3-axis machining center (not shown) from the numerical control device (not shown), the server in the factory (not shown), etc.

[0100] In step S12, the question generation unit 111 determines the job content based on the input of the operator's action information via the input unit 12 and the machine information obtained in step S11, and obtains the prototype of the question from the prototype data 132 based on the determined job content.

[0101] In step S13, the question generation unit 111 generates a question based on the prototype of the question obtained in step S12 and the machine information obtained in step S11.

[0102] In step S14, the sending unit 112 sends the question generated in step S13 to the AI ​​generation device 20.

[0103] In step S15, the receiving unit 113 receives from the AI ​​generation device 20 the response result to the question sent in step S14.

[0104] In step S16, if the response result regeneration unit 114 receives a response result in step S15 containing multiple NC programs, it generates a supplementary response result by adding a priority order to the multiple NC programs based on the machine information obtained in step S11.

[0105] In step S17, the prompting unit 115 displays the response result generated in step S16 on the display unit 14 to provide a prompt.

[0106] As described above, the program generation assist device 10 of the first embodiment can generate a question input to the generation AI device 20 with the minimum labor required by the operator, and obtain an NC program to realize the desired action of the industrial machine.

[0107] In addition, by prompting the program generation assist device 10 to supplement the questions asked to the generation AI device 20 or the response results from the generation AI device 20 with information, the operator can easily confirm the appropriateness of the generated program and take countermeasures against illusions.

[0108] The first embodiment has been described above.

[0109] <Modifications of the First Embodiment>

[0110] In the first embodiment described above, the industrial machine is a vertical 3-axis machining center, but it is not limited to this. For example, the industrial machine could also be a opposed twin-spindle lathe.

[0111] Figure 9 This diagram illustrates an example of a program generation auxiliary system 1 that includes two opposing twin-spindle lathes of different types, configured within the same factory. Figure 9 In this system, the program generation auxiliary system 1, for example, integrates the program generation auxiliary device 10 and the AI ​​generation device 20 into a server, which is connected to the numerical control devices (not shown) of the opposed twin-spindle lathe A and the opposed twin-spindle lathe B. However, in Figure 9In the opposing twin-spindle lathes A and B, the M-codes for positioning the left spindle (or right spindle) at 0° are different. Specifically, for example, opposing twin-spindle lathe A uses M-code "M14" to position the left spindle AL at 0° in the NC program, and uses M-code "M15" to position the right spindle AR at 0°. On the other hand, opposing twin-spindle lathe B uses M-code "M14 P11" to position the left spindle BL at 0°, and uses M-code "M14 P12" to position the right spindle BR at 0°.

[0112] In such a case, when the question generation unit 111 receives motion information such as "I wish to position the left main axis at 0°" from the operator via the input unit 12, for example, it uses a known method to extract the keywords "left main axis," "0°," and "positioning" from the input content of the motion information. Based on the extracted keywords "left main axis," "0°," and "positioning" and the keyword table 131, the question generation unit 111 determines the operation content (question content) such as "position the left main axis at 0°." Based on the determined operation content (question content) and the machine table 133, the question generation unit 111 obtains the following from the prototype data 132: Figure 10 The prototype shown.

[0113] Question generation department 111 based on Figure 10 The prototype of the question and Figure 11 The machine information shown generates a question.

[0114] Figure 11 This is a diagram illustrating an example of machine information acquired by the machine information acquisition unit 110.

[0115] like Figure 11 As shown, the acquired machine information includes "machine tool type" and "identification ID," as well as information about their acquisition source. Specifically, in "machine tool type," "opposing twin-spindle lathe" is stored as "acquisition information," and the acquisition source is stored as data obtained from the machine's catalog data on a server (not shown) within the factory. Furthermore, in "identification ID," the unique ID "ABCD-1234-abcd-5678" of the opposing twin-spindle lathe B is stored as "acquisition information," and the acquisition source is stored as data obtained from a numerical control device (not shown).

[0116] Figure 12 This is a diagram representing an example of the generated question. For example... Figure 12 As shown, the generated question is in Figure 10 In the prototype of the question [ The part based on Figure 11The machine information's "Identification ID" was replaced with "Opposing Twin Spindle Lathe B".

[0117] The sending unit 112 will generate the question sentence from the question generation unit 111. Figure 12 The question is sent to the AI ​​generation device 20.

[0118] The receiving unit 113 receives the AI ​​generation device 20 sending the AI ​​generation device. Figure 12 The response result of the NC program "M14 P11" to the question.

[0119] Furthermore, since the response result regeneration unit 114 only has one NC program "M14 P11", it can output the response result to the prompt unit 115 without processing the response result.

[0120] The prompting unit 115 displays the response result on the display unit 14 to provide a prompt.

[0121] <Second Implementation Method>

[0122] Next, the second embodiment will be described. As described above, in the first embodiment, when the program generation assist device 10 receives a message from the generation AI device 20 indicating that the current instruction mode is unknown, and multiple NC program response candidates are provided as response results, it confirms the current instruction mode based on machine information. The program generation assist device 10 generates supplementary response results by adding a priority order to the multiple NC programs. In contrast, in the second embodiment, when the program generation assist device 10A receives a request from the generation AI device 20 for additional information related to the current instruction mode before receiving the response results of the NC programs, it determines based on machine information whether it can be provided as additional information. The difference from the first embodiment is that, if the program generation assist device 10A determines that it can be provided, it sends the additional information to the generation AI device 20.

[0123] Thus, the program generation assistance device 10A can generate the question input to the generation AI device 20 with the minimum labor required by the operator and obtain the NC program to realize the desired action of the industrial machine.

[0124] The second embodiment will be described below.

[0125] Figure 13 This is a diagram illustrating an example of the functional block structure of the program generation auxiliary system according to the second embodiment. Furthermore, regarding... Figure 1 Elements of the program generating auxiliary system 1 that have the same function are labeled with the same reference numerals, and detailed descriptions are omitted.

[0126] like Figure 13As shown, the program generation assistance system 1 has a program generation assistance device 10A and an AI generation device 20.

[0127] The program generation assist device 10A and the AI ​​generation device 20 communicate with each other via a network (not shown) such as a LAN or the Internet. In this case, the program generation assist device 10A and the AI ​​generation device 20 have a communication unit (not shown) for communicating with each other via this connection. Alternatively, the program generation assist device 10A and the AI ​​generation device 20 can also be directly connected to each other via a connection interface (not shown).

[0128] The AI ​​generation device 20 has the same functions as the AI ​​generation device 20 in the first embodiment.

[0129] The program generation assist device 10A, for example, is a known information processing device (computer), similar to the program generation assist device 10 of the first embodiment. Figure 13 As shown, it includes a control unit 11a, an input unit 12, a storage unit 13, and a display unit 14. In addition, the control unit 11a includes a machine information acquisition unit 110, a question generation unit 111, a transmission unit 112a, a receiving unit 113, a response result regeneration unit 114a, and a prompting unit 115.

[0130] The input unit 12, storage unit 13 and display unit 14 have the same functions as the input unit 12, storage unit 13 and display unit 14 in the first embodiment.

[0131] The keyword table 131, prototype data 132, and machine table 133 are the same as those in the first embodiment.

[0132] The control unit 11a includes a CPU, ROM, RAM, CMOS memory, etc., which are configured to communicate with each other via a bus, as is known to those skilled in the art.

[0133] The CPU is the processor that controls the program generation auxiliary device 10A as a whole. The CPU reads the system program and application program stored in ROM via the bus, and controls the program generation auxiliary device 10A as a whole according to the system program and application program. Thus, as... Figure 13 As shown, the control unit 11a is configured to perform the functions of the machine information acquisition unit 110, the question generation unit 111, the sending unit 112a, the receiving unit 113, the response result regeneration unit 114a, and the prompting unit 115.

[0134] The machine information acquisition unit 110, the question generation unit 111, the receiving unit 113, and the prompting unit 115 have the same functions as those of the machine information acquisition unit 110, the question generation unit 111, the receiving unit 113, and the prompting unit 115 in the first embodiment.

[0135] The response result regeneration unit 114a, similar to the first embodiment, generates information about the absence of a current instruction mode by... Figure 6 In the event that a question is sent to the AI ​​generation device 20 and additional information related to the current instruction mode is received from the AI ​​generation device 20 as a response result via the receiving unit 113, the request is processed according to... Figure 5 The machine information is used to determine whether additional information can be provided to the AI ​​generation device 20. The response result regeneration unit 114a then... Figure 5 Under the "control state" of the machine information, it can be confirmed that the current instruction mode is incremental mode (G91), and therefore it is determined that additional information can be provided. The response result regeneration unit 114a generates additional information indicating that the current instruction mode is incremental mode (G91).

[0136] Furthermore, the response result regeneration unit 114a can also display a query for the current instruction mode on the display unit 14 when there is no information related to the current instruction mode in the machine information, and accept the input of the current instruction mode from the operator through the input unit 12.

[0137] The sending unit 112a sends the additional information generated by the response result regeneration unit 114a to the AI ​​generation device 20.

[0138] The response result regeneration unit 114a receives the response result of the NC program “G91 Z110.0” from the AI ​​generation device 20 via the receiving unit 113.

[0139] In this way, the program generation auxiliary device 10A (response result regeneration unit 114a) can reduce the communication between the operator and the generation AI device 20 by responding to the request for additional information from the generation AI device 20.

[0140] Tips Department 115 will Figure 14 The response result is displayed on the display unit 14 to provide a prompt.

[0141] In this way, by providing supplementary responses with machine information and other details, operators can avoid spending time studying the NC program.

[0142] In addition, the prompting unit 115 displays the response results, including the machine information used, on the display unit 14 to provide a prompt, so that the operator can know the basis for obtaining the response results in the NC program and can take illusion countermeasures.

[0143] <Assistive Processing of Program Generation Assist System 1>

[0144] Next, refer to Figure 15 This describes the process of generating auxiliary processing for auxiliary system 1.

[0145] Figure 15 This is a flowchart illustrating the auxiliary processing of the program generating auxiliary system 1.

[0146] Furthermore, the processing of steps S21 to S25 and step S2C is... Figure 8 The processes of steps S11 to S15 and step S17 are the same, and the explanation is omitted.

[0147] In step S26, the response result regeneration unit 114a determines whether the response result received in step S25 is a request for additional information. If the received response result is a request for additional information, the process proceeds to step S27. On the other hand, if the received response result is not a request for additional information, the process proceeds to step S2C.

[0148] In step S27, the response result regeneration unit 114a determines whether additional information can be provided to the AI ​​generation device 20 based on the machine information. If additional information can be provided, the process proceeds to step S29. If additional information cannot be provided, the process proceeds to step S28.

[0149] In step S28, the response result regeneration unit 114a displays the query from the AI ​​generation device 20 on the display unit 14 and accepts the operator's input as a response to the query via the input unit 12.

[0150] In step S29, the response result regeneration unit 114a generates additional information based on machine information or the operator's input received in step S28.

[0151] In step S2A, the sending unit 112a sends the additional information generated in step S29 to the AI ​​generation device 20.

[0152] In step S2B, the response result regeneration unit 114a receives the response result based on the additional information via the receiving unit 113.

[0153] As described above, the program generation assist device 10A of the second embodiment can generate a question input to the generation AI device 20 with the minimum labor required by the operator, and obtain an NC program to realize the desired action of the industrial machine.

[0154] In addition, by prompting the AI ​​generation device 20 to provide information about what information has been added to the AI ​​generation device 20 or the response results from the AI ​​generation device 20, the operator can easily confirm the appropriateness of the generated program and take countermeasures against illusions.

[0155] The second embodiment has been described above.

[0156] <Modifications of the Second Embodiment>

[0157] In the second embodiment described above, the industrial machine is a vertical 3-axis machining center, but it is not limited to this. For example, the industrial machine could also be a vertical 5-axis machining center.

[0158] In this case, when the question generation unit 111 receives motion information such as "I want to detach the cutting tool from the workpiece" from the operator via the input unit 12, it uses a known method to extract the keywords "tool," "workpiece," and "detach" from the input content of the motion information. The question generation unit 111 then uses the extracted keywords "tool," "workpiece," and "detach" to... Figure 2 From keyword table 131, the task content (question content) such as "retracting the tool from the workpiece" is determined. Question generation unit 111, based on the determined task content (question content) and machine table 133, obtains from prototype data 132... Figure 3B The prototype of the question.

[0159] Question generation department 111 based on Figure 3B The prototype of the question and Figure 16 The machine information of the vertical 5-axis machining center (not shown) is used to generate a question.

[0160] Figure 16 This is a diagram illustrating an example of machine information acquired by the machine information acquisition unit 110.

[0161] like Figure 16 As shown, the acquired machine information includes "machine type," "control status," "machine settings," and "position of each axis," along with information about their acquisition source. Specifically, in "machine type," "vertical 5-axis machining center" is stored as "acquisition information," and the information obtained from the machine's catalog data on a server (not shown) within the factory is stored as the "acquisition source." Additionally, in "control status," "coordinate system: workpiece coordinate system (X...)" is stored as "acquisition information." W -Y W -Z WThe machine tool settings include: "Plane selection: XY plane, Tool axial offset: positive direction, Tool radial offset: right side, Tool travel direction: +X axis direction", which stores numerical control parameters (not shown) as the "acquisition source". Additionally, in "Machine Tool Settings", "Axial retraction amount: 10.000mm, Radial retraction amount: 0.400mm, Retraction speed: 1000mm / min" is stored as the "acquisition information", which also stores numerical control parameters (not shown) as the "acquisition source". Furthermore, in "Position of each axis", "X = 5.678mm, Y = 0.400mm, Z = -4.000mm, A = 0.0000deg, B = 45.0000deg" is stored as the "acquisition information", which also stores numerical control parameters (not shown) as the "acquisition source".

[0162] Figure 17 It represents the machine coordinate system (X). M -Y M -Z M ) and workpiece coordinate system (X) W -Y W -Z W A diagram illustrating an example of the relationship between the workpiece coordinate system (X) and the workpiece coordinate system (X). W -Y W -Z W ) is relative to the machine coordinate system (X) M -Y M -Z M The coordinate system has undergone parallel translation and / or rotation.

[0163] Figure 18 This is a diagram representing an example of the generated question. For example... Figure 18 As shown, the generated question is in Figure 3B In the prototype of the question [ ], partial replacement of options Figure 16 The values ​​and settings in the machine information, including "control status", "machine tool settings" and "position of each axis".

[0164] Furthermore, the question generation unit 111 generates... Figure 18 When presenting the question, multiple questions can also be combined. Figure 16 The machine information is used to supplement the question content. For example, the question generation unit 111 can also follow... Figures 19A to 19D The process shown determines the radial retraction amount, and follows... Figures 20A to 20D The process shown determines the axial retraction amount.

[0165] <Processing of radial retreat amount determination in question generation unit 111>

[0166] Figures 19A to 19DThis is a flowchart explaining the radial retreat amount determination process of the question generation unit 111.

[0167] In step S31, the question generation unit 111, according to... Figure 16 The machine information is transferred from the "control status" to the "+X axis direction" of the "tool's travel direction" to obtain the tool's travel direction vector V (= (1, 0, 0)). Furthermore, vector V is a normalized vector (length = 1 mm).

[0168] In step S32, the question generation unit 111, according to... Figure 16 The machine information is set from "Control Status" to "Plane Selection," determining whether it is an XY plane, ZX plane, or YZ plane. When the plane selection is XY plane, the process proceeds to step S33. Alternatively, when the plane selection is ZX plane, the process proceeds to step S34. When the plane selection is YZ plane, the process proceeds to step S35.

[0169] In step S33, the question generation unit 111 performs radial retreat amount determination processing in the XY plane to determine the radial retreat amount in the XY plane. Furthermore, the detailed process of the radial retreat amount determination processing in the XY plane will be described later.

[0170] In step S34, the question generation unit 111 performs a radial retraction amount determination process in the ZX plane to determine the radial retraction amount in the ZX plane. The detailed process for determining the radial retraction amount in the ZX plane will be described later.

[0171] In step S35, the question generation unit 111 performs radial retreat amount determination processing in the YZ plane to determine the radial retreat amount in the YZ plane. Furthermore, the detailed process of the radial retreat amount determination processing in the YZ plane will be described later.

[0172] Figure 19B This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the XY plane in step S33.

[0173] In step S331, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool radial offset" setting is to the left or right. If the "tool radial offset" setting is to the left, the process proceeds to step S332. On the other hand, if the "tool radial offset" setting is to the right, the process proceeds to step S333.

[0174] In step S332, the question generation unit 111 rotates the vector V around the Z-axis by +90° and calculates the vector W of the retreat direction.

[0175] In step S333, the question generation unit 111 rotates the vector V around the Z-axis by -90° and calculates the vector W of the retreat direction.

[0176] Figure 19C This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the ZX plane in step S34.

[0177] In step S341, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool radial offset" setting is left or right. If the "tool radial offset" setting is left, the process proceeds to step S342. On the other hand, if the "tool radial offset" setting is right, the process proceeds to step S343.

[0178] In step S342, the question generation unit 111 rotates the vector V around the Y-axis by +90° and calculates the vector W of the retreat direction.

[0179] In step S343, the question generation unit 111 rotates the vector V around the Y-axis by -90° and calculates the vector W of the retreat direction.

[0180] Figure 19D This is an explanation Figure 19A The flowchart shows the detailed processing steps for determining the radial retreat amount in the YZ plane in step S35.

[0181] In step S351, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool radial offset" setting is left or right. If the "tool radial offset" setting is left, the process proceeds to step S352. On the other hand, if the "tool radial offset" setting is right, the process proceeds to step S353.

[0182] In step S352, the question generation unit 111 rotates the vector V around the X-axis by +90° and calculates the vector W of the retreat direction.

[0183] In step S353, the question generation unit 111 rotates the vector V around the Z-axis by -90° and calculates the vector W of the retreat direction.

[0184] For example, in Figure 16 In the machine information, "Plane Selection" is "XY Plane" and "Tool Radial Offset" is "Right Side". Therefore, the question generation unit 111 performs radial backoff amount determination processing. Figure 19BIn step S333, the retreat direction vector W = (0, -1, 0) is calculated based on the vector V = (1, 0, 0). Since... Figure 16 The "radial retraction amount" in the machine information is "0.400mm", so the question generation unit 111 calculates the radial retraction vector as (0.000, -0.400, 0.000).

[0185] <Processing of determining the axial retreat amount of the question generation unit 111>

[0186] Figures 20A to 20D This is a flowchart explaining the process of determining the axial retreat amount of the question generation unit 111.

[0187] In step S41, the question generation unit 111, according to... Figure 16 The machine information is set from "Control Status" to "Plane Selection," determining whether it is an XY plane, ZX plane, or YZ plane. When the plane selection is XY plane, the process proceeds to step S42. When the plane selection is ZX plane, the process proceeds to step S43. When the plane selection is YZ plane, the process proceeds to step S44.

[0188] In step S42, the question generation unit 111 performs a retraction amount determination process for the axial direction in the XY plane, determining the retraction amount for the axial direction in the XY plane. The detailed process for determining the retraction amount for the axial direction in the XY plane will be described later.

[0189] In step S43, the question generation unit 111 performs a process to determine the axial retraction amount in the ZX plane, thereby determining the axial retraction amount in the ZX plane. The detailed process of the axial retraction amount determination process in the ZX plane will be described later.

[0190] In step S44, the question generation unit 111 performs a retraction amount determination process for the axial direction in the YZ plane, determining the axial retraction amount in the YZ plane. The detailed process for determining the axial retraction amount in the YZ plane will be described later.

[0191] Figure 20B This is an explanation Figure 20A The flowchart shows the detailed processing steps for determining the axial retraction amount in the XY plane in step S42.

[0192] In step S421, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool axis offset" setting is positive or negative. If the "tool axis offset" setting is positive, the process proceeds to step S422. Conversely, if the "tool axis offset" setting is negative, the process proceeds to step S423.

[0193] In step S422, the question generation unit 111 sets the vector W of the retreat direction to (0, 0, +1).

[0194] In step S423, the question generation unit 111 sets the vector W of the retreat direction to (0, 0, -1).

[0195] Figure 20C This is an explanation Figure 20A The flowchart shows the detailed processing steps for determining the axial retraction amount in the ZX plane in step S43.

[0196] In step S431, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool axis offset" setting is positive or negative. If the "tool axis offset" setting is positive, the process proceeds to step S432. On the other hand, if the "tool axis offset" setting is negative, the process proceeds to step S433.

[0197] In step S432, the question generation unit 111 sets the vector W of the retreat direction to (0, +1, 0).

[0198] In step S433, the question generation unit 111 sets the vector W of the retreat direction to (0, -1, 0).

[0199] Figure 20D This is an explanation Figure 20A The flowchart shows the detailed processing steps for determining the axial retraction amount in the YZ plane in step S44.

[0200] In step S441, the question generation unit 111, according to... Figure 16 The machine information's "control status" determines whether the "tool axis offset" setting is positive or negative. If the "tool axis offset" setting is positive, the process proceeds to step S442. Conversely, if the "tool axis offset" setting is negative, the process proceeds to step S443.

[0201] In step S442, the question generation unit 111 sets the vector W of the retreat direction to (+1, 0, 0).

[0202] In step S443, the question generation unit 111 sets the vector W of the retreat direction to (-1, 0, 0).

[0203] For example, in Figure 16 In the machine information, "Plane Selection" is "XY Plane" and "Tool Axis Offset" is "Positive Direction". Therefore, the question generation unit 111 performs axial retraction amount determination processing. Figure 20B In step S422, the retreat direction vector W is set to (0, 0, +1). Because... Figure 16 The machine information shows that the "axial retraction amount" is "10.000mm", so the question generation unit 111 calculates the axial retraction vector as (X = 0.000, Y = 0.000, Z = 10.000).

[0204] Then, the question generation unit 111 synthesizes the result with the radial retreat amount determination process, such as... Figure 18 As indicated by the question, the retreat vector is calculated as (0.000, -0.400, 10.000).

[0205] The sending unit 112a will generate the question sentence from the question generation unit 111. Figure 18 The question is sent to the AI ​​generation device 20.

[0206] Because in Figure 18 The question does not contain information related to the order of retreat, therefore the receiving unit 113 needs to receive additional information related to the order of retreat, whether it is from radial to axial or from axial to radial.

[0207] The response result regeneration unit 114a receives a request for additional information as the response result from the AI ​​generation device 20 via the receiving unit 113, and therefore... Figure 16 The machine information is used to determine whether additional information can be provided to the AI ​​generation device 20. The response result regeneration unit 114a, based on the information... Figure 16 If the machine information does not contain a retraction sequence (i.e., retraction from radial to axial or from axial to radial), it is determined that additional information cannot be provided. In this case, the response result regeneration unit 114a displays a query for the retraction sequence on the display unit 14, and generates additional information from the input unit 12 based on the operator's input related to the retraction sequence (e.g., from radial to axial).

[0208] The sending unit 112a sends the additional information generated by the response result regeneration unit 114a to the AI ​​generation device 20.

[0209] The response result regeneration unit 114a receives the NC program "G91 G01 Y-0.4 F1000 Z10.0" in the radial to axial sequence from the AI ​​generation device 20 as the response result via the receiving unit 113. Here, G01 indicates the cutting feed mode, and the value following F specifies the feed rate per minute (movement per minute (unit: mm / min)) during the cutting feed mode. In this NC program, the feed rate per minute is 1000 mm / min, which is equivalent to... Figure 18 The speed of retreat.

[0210] Furthermore, in place of the need for additional information, the response result regeneration unit 114a can receive messages from the AI ​​generation device 20 such as "It is impossible to determine whether the order is radial to axial or axial to radial", NC program "G91 G01 Y-0.4 F1000 Z10.0" in the case of radial to axial order, and NC program "G91 G01 Z10.0 F1000 Y-0.4" in the case of axial to radial order as response results.

[0211] In this case, the response result regeneration unit 114a can also confirm. Figure 16 Since there is no information related to the retraction order, the machine information is displayed on the display unit 14, and the operator receives input related to the retraction order (e.g., the order from radial to axial) via the input unit 12.

[0212] The response result regeneration unit 114a can also generate response results based on the operator's input, with priority order "1" added to the NC program in the radial to axial order and priority order "2" added to the NC program in the axial to radial order.

[0213] like Figure 21 As shown, the prompting unit 115 can also display a screen showing the two NC programs and their priority order on the display unit 14 to provide prompts.

[0214] As described above, as in the first embodiment, variations of the first embodiment, the second embodiment, and variations of the second embodiment, the program generation assist device 10, 10A of this disclosure can generate a query input to the AI ​​generation device with the minimum labor required by the operator, and obtain an NC program that realizes the desired action of the industrial machine.

[0215] <Variation Example 1>

[0216] In the first embodiment, variations of the first embodiment, the second embodiment, and variations of the second embodiment, the industrial machine is configured as a vertical three-axis machining center, a opposed twin-spindle lathe, or a vertical five-axis machining center, but is not limited to these. For example, the industrial machine may also be a machine tool, an industrial robot, a service robot, a forging machine, an injection molding machine, etc.

[0217] <Variation Example 2>

[0218] Furthermore, for example, in the first embodiment, variations of the first embodiment, the second embodiment, and variations of the second embodiment described above, the program generation assisting devices 10 and 10A are configured as devices different from the AI ​​generation device 20, but are not limited thereto. For example, the program generation assisting devices 10 and 10A may also include the AI ​​generation device 20. Alternatively, the program generation assisting devices 10 and 10A may also be included together with the AI ​​generation device 20 in a server.

[0219] <Variation Example 3>

[0220] Furthermore, for example, in the first embodiment, variations of the first embodiment, the second embodiment, and variations of the second embodiment described above, the program generation assisting devices 10 and 10A (response result regeneration units 114 and 114a) display response results (second response results) that add priority order or supplementary machine information to the response results (first response results) received from the AI ​​generation device 20, but are not limited to this. For example, the program generation assisting devices 10 and 10A may omit the function of the response result regeneration units 114 and 114a, and instead display the response results (first response results) received by the receiving unit 113 from the AI ​​generation device 20.

[0221] Furthermore, the functions included in the program generation auxiliary devices 10 and 10A in the variations of the first embodiment, the second embodiment, and the variations of the second embodiment can be implemented by hardware, software, or a combination thereof. Here, implementation by software means implementation by reading and executing the program by a computer.

[0222] Programs can be stored and provided 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., floppy disks, magnetic tapes, hard disks), optical-magnetic recording media (e.g., optical discs), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash memory ROMs, and RAM). Alternatively, programs can also be provided to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transient computer-readable media can provide programs to a computer via wired communication paths such as wires and optical fibers, or via wireless communication paths.

[0223] Furthermore, the steps of executing a program recorded on a recording medium naturally include processing performed sequentially in time, as well as processing performed in parallel or individually even if not necessarily in time sequence. Additionally, the steps describing the program can also be implemented via cloud computing.

[0224] 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 from the spirit of this disclosure derived from the content described in the claimed 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, and are not limited thereto. Similarly, the use of numerical values ​​or mathematical formulas in the description of the embodiments described above also applies.

[0225] The following notes are also disclosed regarding the above-described embodiments and variations.

[0226] (Note 1)

[0227] The program generation assist device 10 assists in generating a numerical control program that enables an industrial machine to operate. The program generation assist device includes: a machine information acquisition unit 110, which acquires machine information related to the industrial machine; a question generation unit 111, which acquires motion information related to the desired motion content of the industrial machine and combines it with the machine information acquired by the machine information acquisition unit 110 to generate a question for the generation AI device 20; a sending unit 112, which sends the question generated by the question generation unit 111 to the generation AI device 20; a receiving unit 113, which receives a first response result from the generation AI device 20; and a prompting unit 115, which prompts the first response result.

[0228] (Note 2)

[0229] In the program generation auxiliary devices 10 and 10A in Appendix 1, there are response result regeneration units 114 and 114a, which generate a second response result that supplements the first response result received by the receiving unit 113 with machine information obtained by the machine information acquisition unit 110, and the prompting unit 115 prompts the second response result generated by the response result regeneration units 114 and 114a.

[0230] (Note 3)

[0231] In the program generation auxiliary devices 10 and 10A in Appendix 2, when the receiving unit 113 receives two or more numerical control programs as first response results from the AI ​​generation device 20 for the question generated by the question generation unit 111, the response result regeneration unit 114 and 114a generate second response results that assign priority to the two or more numerical control programs based on the machine information of the industrial machine, and the prompting unit 115 prompts the second response results that have been assigned priority.

[0232] (Note 4)

[0233] In the program generation auxiliary device 10A described in Appendix 2 or Appendix 3, when the receiving unit 113 receives additional information from the generation AI device 20 in response to a question generated by the question generation unit 111, the response regeneration unit 114a determines whether it can be provided as additional information based on machine information. If it is determined that it can be provided, the additional information is sent to the generation AI device 20 via the sending unit 112a.

[0234] (Note 5)

[0235] In the program generation auxiliary device 10 or 10A described in Appendix 1 or Appendix 2, the prompting unit 115 prompts the machine information used when generating a question in the question generation unit 111.

[0236] (Note 6)

[0237] In the program generation auxiliary devices 10 and 10A in Appendix 2, the prompting unit 115 prompts the machine information supplemented by the response result regeneration units 114 and 114a.

[0238] (Note 7)

[0239] In the program generation auxiliary device 10 or 10A of Appendix 1 or Appendix 2, the machine information obtained by the machine information acquisition unit 110 includes at least one of the following: identification information of the industrial machine, type of industrial machine, structure of each axis constituting the industrial machine, position of each axis constituting the industrial machine, and control state of the industrial machine.

[0240] Symbol Explanation

[0241] 1. Program generation auxiliary system;

[0242] 10. 10A Program Generation Auxiliary Device;

[0243] 11, 11a Control Unit;

[0244] 110 Machine Information Acquisition Department;

[0245] 111 Question Generation Department;

[0246] 112, 112a Transmission Unit;

[0247] 113 Receiving Department;

[0248] 114, 114a Response Result Regeneration Unit;

[0249] 115 Reminder Department;

[0250] 12 Input Sections;

[0251] 13. Storage Unit;

[0252] 131 Keyword List;

[0253] 132 prototype data;

[0254] 133 machine table;

[0255] 14. Display Unit;

[0256] 20. Generate AI devices.

Claims

1. A program generation auxiliary device, which assists in generating numerical control programs to make industrial machines move, characterized in that, The program generation auxiliary device includes: The machine information acquisition unit acquires machine information related to the industrial machine. The question generation unit acquires motion information related to the desired motion content of the industrial machine and combines it with the machine information acquired by the machine information acquisition unit to generate a question for the AI ​​generation device. The sending unit sends the question generated by the question generation unit to the AI ​​generation device; The receiving unit receives a first response result from the AI ​​generating device; and The prompting section displays the result of the first response.

2. The program generation auxiliary device according to claim 1, characterized in that, The program generation assist device includes a response result regeneration unit that generates a second response result that supplements the first response result received by the receiving unit with the machine information obtained by the machine information acquisition unit. The prompting unit displays the second response result generated by the response result regeneration unit.

3. The program generation auxiliary device according to claim 2, characterized in that, When the receiving unit receives two or more numerical control programs as the first response results from the generating AI device in response to the question generated by the question generation unit, the response result regeneration unit generates a second response result that assigns a priority order to the two or more numerical control programs based on the machine information of the industrial machine. The prompting section indicates the second response result that has been assigned a priority order.

4. The program generation auxiliary device according to claim 2 or 3, characterized in that, When the receiving unit receives additional information from the generating AI device in response to the question generated by the question generation unit, the response result regeneration unit determines whether it can be provided as the additional information based on the machine information. If it is determined that it can be provided, the receiving unit sends the additional information to the generating AI device via the sending unit.

5. The program generation auxiliary device according to claim 1 or 2, characterized in that, The prompting section indicates the machine information used when generating the question in the question generation section.

6. The program generation auxiliary device according to claim 2, characterized in that, The prompting unit displays the machine information supplemented by the response result regeneration unit.

7. The program generation auxiliary device according to claim 1 or 2, characterized in that, The machine information obtained by the machine information acquisition unit includes at least one of the following: identification information of the industrial machine, type of the industrial machine, structure of each axis constituting the industrial machine, position of each axis constituting the industrial machine, and control state of the industrial machine.

Images