Numerical control device, learning device, inference device, and operation screen display method for numerical control device

JPWO2024142401A5Active Publication Date: 2024-11-26MITSUBISHI ELECTRIC CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2023532569
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-12-28
Publication Date
2024-11-26
Estimated Expiration
2042-12-28

AI Technical Summary

Technical Problem

Conventional numerical control devices require users to search across multiple operation screens for desired information, complicating the user's operation when information is spread across multiple screens.

Method used

A numerical control device that utilizes a learning device to generate a trained model for inferring screen display data, combining information from multiple operation screens into a single new operation screen, using machine learning algorithms like reinforcement learning to optimize the display based on user interactions and machine tool states.

Benefits of technology

Improves user efficiency by reducing the number of operations, screen transitions, and operation time, allowing users to access multiple pieces of information on a single screen, thereby simplifying the user interface.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The numerical control device (1) includes a learning data acquisition unit that acquires learning data including operation log information that indicates user operations on an operation screen of the numerical control device (1) that controls a machine tool and information on the operation screen to be operated, and operating status information that indicates the state of the machine tool when the operation indicated by the operation log information was being performed, and a model generation unit that uses the learning data to generate, from the operation log information and the operating status information, a trained model for inferring screen display data for displaying a new operation screen that includes information desired by a user extracted from multiple existing operation screens.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] This disclosure relates to a numerical control device, a learning device, an inference device, and a method for displaying the operation screen of a numerical control device. [Background technology]

[0002] The operation screens of numerical control devices that control machine tools are used in a variety of situations. An operation screen that is easy to use is required depending on the situation in which it is used. For example, Patent Document 1 discloses a numerical control device that uses machine learning to rearrange the menus on the operation screen according to the operator. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Patent No. 6898479 [Overview of the project] [Problems that the invention aims to solve]

[0004] However, with the conventional technology described above, if the information the user is looking for is spread across multiple operation screens, the user still has to search for the information they are looking for across those multiple screens, which can make the user experience complicated.

[0005] This disclosure is made in view of the above, and aims to provide a numerical control device that can improve the user's work efficiency even when the information requested by the user in an existing operation screen is spread across multiple operation screens. [Means for solving the problem]

[0006] To solve the above-mentioned problems and achieve the objectives, the numerical control device according to this disclosure is characterized by comprising: a learning data acquisition unit that acquires learning data including operation log information indicating user operations on the operation screen of a numerical control device that controls a machine tool and information on the operation screen of the target of the operation, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; and a model generation unit that uses the learning data to generate a trained model for inferring screen display data for displaying a new operation screen that includes information extracted from multiple existing operation screens from the operation log information and operating state information. [Effects of the Invention]

[0007] The numerical control device described herein has the effect of providing a numerical control device that can improve the user's work efficiency even when the information requested by the user in an existing operation screen is spread across multiple operation screens. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows the functional configuration of the numerical control device according to Embodiment 1. [Figure 2] A diagram showing the detailed configuration of a learning device for a numerical control system of a machine tool. [Figure 3] Flowchart for the learning process of a learning device [Figure 4] Configuration diagram of an inference device for a numerical control system of a machine tool. [Figure 5] Flowchart for the inference process of the inference device [Figure 6] Diagram illustrating the effects of Embodiment 1 [Figure 7] This figure shows an example of a new operation screen displayed by the numerical control device according to Embodiment 3. [Figure 8] This figure shows the functional configuration of the numerical control device according to Embodiment 4. [Figure 9] This figure shows an example of how to share a trained model in Embodiment 5. [Figure 10]Figure for explaining the functions of the numerical control device according to Embodiment 6 [Figure 11] Figure showing an example of a new operation screen displayed by the numerical control device according to Embodiment 7 [Figure 12] Figure showing the functional configuration of the numerical control device according to Embodiment 11 [Figure 13] Figure showing dedicated hardware for realizing the functions of the numerical control device according to Embodiments 1 to 11 [Figure 14] Figure showing the configuration of the control circuit for realizing the functions of the numerical control device according to Embodiments 1 to 11

Embodiments for Carrying Out the Invention

[0009] Hereinafter, a numerical control device, a learning device, an inference device, and an operation screen display method of the numerical control device according to embodiments of the present disclosure will be described in detail based on the drawings.

[0010] Embodiment 1. FIG. 1 is a diagram showing the functional configuration of a numerical control device 1 according to Embodiment 1. The numerical control device 1 includes a control unit 11, an operation log acquisition unit 12, a data acquisition unit 13, a learning device 14, a learned model storage unit 15, an inference device 16, and an output unit 17. The numerical control device 1 is a device that controls a machine tool according to a machining program. The numerical control device 1 controls the movement of the machine tool by controlling a drive unit 2 provided in the machine tool. The drive unit 2 includes an amplifier, a motor, and the like. The numerical control device 1 can also control a peripheral device 3. Further, the numerical control device 1 can output an operation screen for operating the numerical control device 1 using a display device 4. In FIG. 1, the display device 4 is a device separate from the numerical control device 1, but the display device 4 may be built in the numerical control device 1. Also, in FIG. 1, the input device 5 is a device separate from the numerical control device 1, but the input device 5 may be built in the numerical control device 1.

[0011] The control unit 11 is connected to the drive unit 2 and peripheral devices 3, which are the controlled objects of the numerical control device 1. The control unit 11 has the function of controlling the amplifiers and motors provided in the drive unit 2 and the function of controlling the peripheral devices 3. It also acquires operating status information from the drive unit 2 and peripheral devices 3, respectively, indicating the operating status of each device, and outputs the acquired operating status information to the data acquisition unit 13. The operating status information can include, for example, operating modes such as machining, setup, and alarm occurrence, the status of PLC (Programmable Logic Controller) signals, and the status of the machining program for controlling the drive unit 2 of the machine tool. Furthermore, if the operating mode is alarm occurrence, the operating status information can also include the type of alarm and the content of the alarm.

[0012] The operation log acquisition unit 12 acquires operation log information indicating user operations on the operation screen of the numerical control device 1. The operation log information includes information about the operation screen being operated on. The operation screen information may include, for example, identification information for identifying the operation screen, hierarchical structure information indicating the relationship with other operation screens if the operation screen has a hierarchical structure, and screen display data for displaying the operation screen. The operation log acquisition unit 12 can acquire operation log information based on input information acquired from the input device 5. The input device 5 is, for example, a keyboard that accepts key input, a pointing device that accepts the specification of a coordinate position on the operation screen, or a microphone that accepts voice input. The pointing device is, for example, a mouse or a touch sensor. The touch sensor may be a touch panel in which the input device 5 and the display device 4 are integrated, or it may be a standalone touch pad.

[0013] The data acquisition unit 13 acquires various types of data used by the numerical control device 1. The data acquisition unit 13 can output the acquired data to the learning device 14 and the inference device 16, respectively. The data acquisition unit 13 can acquire operation log information from the operation log acquisition unit 12 and operation status information from the control unit 11.

[0014] The learning device 14 generates a trained model that uses machine learning to infer screen display data for displaying a new operation screen of the numerical control device 1. The learning device 14 stores the trained model, which is the result of the learning, in the trained model storage unit 15. The inference device 16 uses the trained model to infer screen display data for displaying a new operation screen and outputs the inference result, the screen display data, to the output unit 17.

[0015] The output unit 17 outputs a new operation screen using the display device 4 based on the screen display data output by the inference device 16. The screen display data may include at least one of the following pieces of information: the design of the new operation screen, the timing of information output, the method of information output, and operation guidance, which is information to support user operation. The design of the operation screen may include information such as the position on the screen where the information requested by the user is displayed and the size at which the information requested by the user is displayed. The timing of information output indicates the time when information is output to the user. The method of information output indicates whether or not there is highlighting, animation, or screen switching. Operation guidance is information to support user operation, such as supplementary information to the information output to the user and how to operate the screen. Since it is possible to display a new operation screen when new screen display data is generated, in the following description, generating new screen display data may be expressed as "generating a new operation screen." The timing at which the numerical control device 1 generates a new operation screen using the inference device 16 may be, for example, the timing when the operating mode of the machine tool changes, or the timing when the user performs an operation on the operation screen.

[0016] <Learning Phase> Figure 2 shows a detailed configuration of the learning device 14 related to the numerical control device 1 of a machine tool. The learning device 14 includes a learning data acquisition unit 141 and a model generation unit 142.

[0017] The training data acquisition unit 141 acquires operation log information and operating status information as training data.

[0018] The model generation unit 142 learns screen display data based on training data including operation log information and operating state information. That is, it generates a trained model that infers screen display data for displaying a new operation screen from the operation log information and operating state information of the numerical control device 1 of the machine tool. The "new operation screen" includes information extracted from multiple existing operation screens. Here, "information extracted from multiple existing operation screens" refers to information that is determined to be desired by the user based on the operation log information and operating state information, such as information displayed by the user in past operations in the operation log information. The phrase "information extracted from multiple existing operation screens" means that the extracted "information" is searched for among the information contained in multiple existing operation screens, and this includes not only cases where the extracted information was contained in multiple existing operation screens, but also cases where the extracted information was contained in one of the existing operation screens. Furthermore, the "new operation screen" includes information that contributes to improving the work efficiency of operations using the operation screen. "Information that contributes to improving work efficiency" includes information that reduces the burden on the user's operations. User operational burdens include, for example, the number of operations, the number of screen transitions, and the operation time. Information that reduces the user operational burden includes, for example, information extracted from existing operation screens, information that combines information extracted from existing operation screens, and operation guidance. Furthermore, "information that contributes to improving work efficiency" includes, for example, information that positively influences the operation results. Information that positively influences the operation results includes, for example, information that prevents user errors, such as operation guidance.

[0019] The learning algorithms used by the model generation unit 142 can be known algorithms such as supervised learning, unsupervised learning, and reinforcement learning. As an example, the case of applying reinforcement learning will be described. In reinforcement learning, an agent, which is an actor in a certain environment, observes the parameters of the environment indicating the current state and determines the action to be taken. The environment dynamically changes due to the agent's actions, and the agent is given a reward according to the change in the environment. The agent repeats this and learns the action policy that can obtain the most rewards through a series of actions. As typical methods of reinforcement learning, Q-learning and TD-learning are known. For example, in the case of Q-learning, the general update formula for the action value function Q(s,a) is represented by Equation (1).

[0020]

Equation

[0021] In Equation (1), s t represents the state of the environment at time t, and a t represents the action at time t. Due to the action a t , the state changes to s t+1 . r t+1 represents the reward obtained due to the change in that state, γ represents the discount rate, and α represents the learning coefficient. Note that γ is a value in the range of 0 < γ ≤ 1, and α is a value in the range of 0 < α ≤ 1. The operation log information becomes the action a t , the operation state information becomes the state s t , and the best action a t at the state s t at time t is learned.

[0022] The update formula, represented by equation (1), increases the action value Q of action a if the action value Q of action a with the highest Q value at time t+1 is greater than the action value Q of action a performed at time t, and decreases the action value Q if the opposite is true. In other words, it updates the action value function Q(s,a) so that the action value Q of action a at time t approaches the best action value at time t+1. As a result, the best action value in a given environment is sequentially propagated to the action values ​​in previous environments.

[0023] As described above, when a trained model is generated by reinforcement learning, the model generation unit 142 includes a reward calculation unit 143 and a function update unit 144, as shown in Figure 2.

[0024] The reward calculation unit 143 calculates the reward based on the operation log information and the operating status information. The reward calculation unit 143 calculates the reward r based on the reward criteria. The reward criteria include a reward increase criterion for increasing the reward r and a reward decrease criterion for decreasing the reward r. Here, it is preferable to increase or decrease the reward r according to the user's work efficiency, so the reward criteria can be a criterion based on information representing the user's work efficiency, such as the number of operations, the number of screen transitions, and the operation time, at least one of these. The count of the number of operations, the number of screen transitions, and the operation time are counted for each operating mode during the operation of the machine tool. For example, if the number of operations decreases, the reward r is increased by giving a reward of, for example, "1", and if the number of operations increases, the reward r is decreased by giving a reward of, for example, "-1". Also, if the number of screen transitions decreases, the reward r may be increased, and if the number of screen transitions increases, the reward r may be decreased. Also, if the operation time decreases, the reward r may be increased, and if the operation time increases, the reward r may be decreased. Here, the decision to increase or decrease the reward is based on one of the following: the number of operations, the number of screen transitions, and the operation time. However, the decision may also be based on two of these factors, or on all of them. Furthermore, information other than the number of operations, the number of screen transitions, and the operation time may be used to determine whether to increase or decrease the reward r. The reward calculation unit 143 should increase the reward r when it determines that the user's work efficiency has improved, and decrease the reward r when it determines that the user's work efficiency has decreased.

[0025] The function update unit 144 updates the function for determining the screen display data according to the reward r calculated by the reward calculation unit 143 and outputs it to the trained model storage unit 15. For example, in the case of Q-learning, the action value function Q(s) is expressed by formula (1). t ,a t ) is used as a function to calculate the screen display data.

[0026] The learning device 14 repeatedly performs the learning described above. The learned model storage unit 15 stores the action-value function Q(s) updated by the function update unit 144. t ,a t ), in other words, it memorizes the trained model.

[0027] Next, we will explain the learning process performed by the learning device 14 using Figure 3. Figure 3 is a flowchart of the learning process of the learning device 14.

[0028] The learning data acquisition unit 141 acquires operation log information and operating status information as learning data (step S10).

[0029] The model generation unit 142 calculates the reward r based on the operation log information and the operation status information (step S11). Specifically, the reward calculation unit 143 can calculate the reward r using, for example, a predetermined reward criterion. The reward criterion includes a reward increase criterion for increasing the reward r and a reward decrease criterion for decreasing the reward r. As described above, the reward criterion can be a criterion based on at least one of the information representing the user's work efficiency, such as the number of operations, the number of screen transitions, and the operation time. For example, when using a reward criterion based on the number of operations, the reward calculation unit 143 counts the number of operations for each operation mode based on the operation log information and the operation status information, and determines that the reward increase criterion is met if the number of operations decreases, and determines that the reward decrease criterion is met if the number of operations increases.

[0030] If the reward calculation unit 143 determines that the reward increase criteria are met (Step S11: Reward Increase Criteria), it increases the reward r (Step S12). If the reward calculation unit 143 determines that the reward decrease criteria are met (Step S11: Reward Decrease Criteria), it decreases the reward r (Step S13).

[0031] The function update unit 144 updates the action value function Q(s) represented by formula (1) stored in the trained model memory unit 15, based on the reward r calculated by the reward calculation unit 143. t ,a tUpdate (step S14).

[0032] The learning device 14 repeatedly executes the steps S10 to S14 described above and generates the action value function Q(s t ,a t ) is stored as a trained model.

[0033] In this embodiment, the learning device 14 stores the learned model in a learned model storage unit 15 located outside the learning device 14; however, the learned model storage unit 15 may be located inside the learning device 14.

[0034] <Utilization Phase> Figure 4 is a diagram showing the configuration of an inference device 16 related to a numerical control device 1 for a machine tool. The inference device 16 comprises an inference data acquisition unit 161 and an inference unit 162.

[0035] The inference data acquisition unit 161 acquires operation log information and operating status information.

[0036] The inference unit 162 infers screen display data using a pre-trained model. That is, by inputting the operation log information and operating state information acquired by the inference data acquisition unit 161 into this pre-trained model, it is possible to infer screen display data that is suitable for the operation log information and operating state information.

[0037] In this embodiment, the screen display data is output using a trained model learned by the learning device 14 of the machine tool's numerical control device 1. However, a trained model may be obtained from another numerical control device 1, and the screen display data may be output based on this trained model.

[0038] Next, Figure 5 will be used to explain the process for obtaining screen display data using the trained model. Figure 5 is a flowchart of the inference process of the inference device 16.

[0039] The inference data acquisition unit 161 acquires operation log information and operating status information as inference data (step S20).

[0040] The inference unit 162 inputs operation log information and operating status information to the trained model stored in the trained model storage unit 15 (step S21) and obtains screen display data. The inference unit 162 outputs the obtained screen display data to the output unit 17 (step S22).

[0041] The numerical control device 1 uses the output screen display data to display an operation screen on the display device 4 (step S23). The operation screen displayed here is a new operation screen containing information requested by the user, extracted from multiple existing operation screens. Therefore, even if the multiple pieces of information requested by the user were contained across multiple screens in the existing operation screens, it becomes possible to view all of that information together on a single new operation screen.

[0042] In this embodiment, we have described the case where reinforcement learning is applied to the learning algorithm used by the inference unit 162, but this is not the only possible case. In addition to reinforcement learning, supervised learning, unsupervised learning, or semi-supervised learning can also be applied to the learning algorithm.

[0043] Furthermore, the learning algorithm used in the model generation unit 142 can be deep learning, which learns to extract the features themselves, or machine learning can be performed according to other known methods, such as neural networks, genetic programming, functional logic programming, or support vector machines.

[0044] The learning device 14 and the inference device 16 may be connected to the numerical control unit 1 via a network, for example, and may be separate devices from the numerical control unit 1. Alternatively, the learning device 14 and the inference device 16 may be built into the numerical control unit 1, as shown in Figure 1. Furthermore, the learning device 14 and the inference device 16 may reside on a cloud server.

[0045] Furthermore, the model generation unit 142 may learn screen display data using training data acquired from multiple numerical control devices 1. The model generation unit 142 may acquire training data from multiple numerical control devices 1 used in the same area, or it may learn screen display data using training data collected from multiple numerical control devices 1 operating independently in different areas. It is also possible to add or remove numerical control devices 1 that collect training data as targets during the process. Moreover, a learning device 14 that has learned screen display data for one numerical control device 1 may be applied to another numerical control device 1, and the screen display data for that other numerical control device 1 may be retrained and updated.

[0046] Here, we will describe the operation screen generated using the trained model. Figure 6 is an explanatory diagram of the effect of Embodiment 1. As shown at the top of Figure 6, the existing operation screen has a hierarchical structure. Below the top screen are existing screen #1 and existing screen #2. Below existing screen #1 are existing screen #1-1, existing screen #1-2, and existing screen #1-3. Below existing screen #2 are existing screen #2-1 and existing screen #2-2. Here, the information requested by the user is information #1, information #2, and information #3. Let's assume that information #1 is included in existing screen #1-1, information #2 is included in existing screen #1-3, and information #3 is included in existing screen #2-2. In this case, if only the existing operation screen is used, the user can reach information #1 by performing an operation (1) to transition from the top screen to existing screen #1, and then an operation (2) to transition from existing screen #1 to existing screen #1-1. Subsequently, the user can reach information #2 by performing an operation to return from existing screen #1-1 to existing screen #1 (3), and then an operation to transition from existing screen #1 to existing screen #1-3 (4). Furthermore, the user can reach information #3 by performing an operation to return from existing screen #1-3 to existing screen #1 (5), then an operation to transition from existing screen #1 to the top screen (6), then an operation to transition from the top screen to existing screen #2 (7), and then an operation to transition from existing screen #2 to existing screen #2-2 (8). In other words, it takes eight screen transitions to reach all of information #1, information #2, and information #3 from the top screen. In contrast, the numerical control device 1 according to Embodiment 1 can display a new operation screen, generation screen #1, which includes information #1, information #2, and information #3. As a result, the user can check multiple pieces of information they desire with a single screen transition operation.

[0047] Here, we will explain specific examples of operation screens generated by the numerical control device 1. For example, if an abnormality occurs in a machine tool or peripheral device 3, the user may first check the status of the device that has experienced the abnormality and the nature of the abnormality, and then check the countermeasures for the abnormality. For this reason, in the first example, which assumes a scenario in which an alarm indicating an abnormality in the machine tool occurs during machining, a new operation screen is generated in which the status of the machine tool, detailed information of the alarm, and countermeasures corresponding to the content of the alarm can be checked. In this case, "Status of the machine tool" corresponds to "Information #1" in the example in Figure 6, "Detailed information of the alarm" corresponds to "Information #2", and "Countermeasures corresponding to the content of the alarm" corresponds to "Information #3". In the second example, which assumes a scenario in which communication with peripheral device 3 is unsuccessful, a new operation screen is generated in which the status of the machine tool and peripheral device 3, the communication status such as the number of communication errors with peripheral device 3, and countermeasures can be checked. In this case, "the status of the machine tool and peripheral device 3" corresponds to "Information #1" in the example in Figure 6, "communication status such as the number of communication errors with peripheral device 3" corresponds to "Information #2", and "solution" corresponds to "Information #3".

[0048] Furthermore, if an anomaly occurs and there is insufficient information to determine the information the user is seeking, troubleshooting may be performed through a dialogue with the user. In the third example, when the user inputs their problem in natural language using an input device 5 such as a keyboard or microphone, the numerical control device 1 can generate a new operation screen corresponding to the input text or voice and display it on the display device 4. For example, if the user inputs "I want to back up the set of parameters," the numerical control device 1 generates an operation screen that includes information necessary to solve the user's problem, such as a parameter backup screen and operation guidance, and displays it on the display device 4. The problem may be gradually narrowed down by repeating the dialogue with the user multiple times.

[0049] In the first, second, and third examples described above, the operation screens were explained for when a malfunction occurs in a machine tool or the like. However, in the fourth example, which assumes normal operation other than when a malfunction occurs, the numerical control device 1 generates a new operation screen containing optimal information extracted from the existing operation screens of the numerical control device 1, according to what the user wants to do, and displays it on the display device 4. For example, when the user inputs what they want to do using an input device 5 such as a keyboard or microphone, the numerical control device 1 generates a new operation screen that can realize the user's objective from the functions of the numerical control device 1.

[0050] As described above, the numerical control device 1 according to Embodiment 1 is characterized by comprising: a learning data acquisition unit 141 that acquires learning data including operation log information indicating user operations on the operation screen of the numerical control device 1 that controls a machine tool and information on the operation screen of the target of the operation, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; and a model generation unit 142 that uses the learning data to generate a trained model for inferring screen display data for displaying a new operation screen that includes information extracted from a plurality of existing operation screens from the operation log information and operating state information. Furthermore, the numerical control device 1 is characterized by comprising: an inference data acquisition unit 161 that acquires inference data including operation log information indicating user operations on the operation screen of the numerical control device 1 that controls the machine tool and information on the operation screen of the target operation, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was performed; an inference unit 162 that uses a trained model to infer screen display data for displaying a new operation screen, which includes information extracted from multiple existing operation screens, from the operation log information and operating state information, and outputs screen display data for displaying a new operation screen from the operation log information and operating state information acquired by the inference data acquisition unit 161; and an output unit 17 that causes the display device 4 to output a new operation screen based on the screen display data. This makes it possible to provide the user with an easy-to-use operation screen according to the operating state of the machine tool. For example, as described above with reference to Figure 6, in existing operation screens, when the information requested by the user is spread across multiple screens, the number of operations, screen transitions, and operation time can be reduced by extracting the information requested by the user and generating a new operation screen. This makes it possible to improve the user's work efficiency. Furthermore, in a system where operation screens are prepared in advance according to the operating status of the machine tool, the number of operation screens that need to be prepared in advance will increase because the number of combinations of information that users require will be numerous depending on the state of the machine tool.Therefore, by generating a new operation screen based on operation log information and operating status information, as in the numerical control device 1, it becomes possible to reduce the number of operation screens that need to be prepared in advance, thereby reducing memory usage.

[0051] Furthermore, the new operation screen displayed by the screen display data inferred by the trained model can display multiple pieces of information that were previously scattered across multiple existing operation screens. This is possible because the operation log information acquired as training data shows not only the operation on a single operation screen, but also the history of user operations across multiple existing operation screens. For example, if multiple existing operation screens have a hierarchical structure, the operation log information will show the history of user operations across those hierarchical operation screens.

[0052] Furthermore, the model generation unit 142 includes a reward calculation unit 143 and a function update unit 144. The reward calculation unit 143 increases the reward r when at least one of the number of operations, the number of screen transitions, and the operation time decreases, and decreases the reward r when at least one of the number of operations, the number of screen transitions, and the operation time increases. Therefore, the trained model can infer screen display data for displaying a new operation screen that reduces at least one of the number of operations, the number of screen transitions, and the operation time.

[0053] The new screen display data generated by the numerical control device 1 includes at least one of the following pieces of information: the design of the new operation screen, the timing of information output, the method of information output, and operation guidance, which is information to support user operation.

[0054] Embodiment 2. In Embodiment 2, the information used as input by the learning device 14 and the inference device 16 differs from that in Embodiment 1. The basic configuration of the numerical control device 1 is the same as that of Embodiment 1 shown in Figure 1, so the parts that differ from Embodiment 1 will be mainly described using the reference numerals in Figure 1.

[0055] The operation log acquisition unit 12 acquires time-series data as operation log information, such as coordinate positions entered by the user using a pointing device like a touch panel, key codes for keyboard operations, identification information of the operation screen being operated on, and the hierarchical structure of the operation screen. The numerical control device 1 uses this operation log information to generate a trained model capable of inferring screen display data for displaying a new operation screen with a design that reduces the number of operations of at least one of the operations of scrolling, zooming, and zooming. For example, the reward calculation unit 143 of the model generation unit 142 increases the reward r when the number of operations of dynamic operations such as scrolling, zooming, and zooming decreases, and decreases the reward r when the number of operations of dynamic operations increases. This makes it possible to display the information requested by the user in a size and arrangement that reduces the number of dynamic operations.

[0056] As described above, according to Embodiment 2, the operation log information includes a time-series history of coordinate positions entered by the user. Furthermore, the trained model infers screen display data for displaying a new operation screen with a design that reduces the number of operations of at least one of the operations of scrolling, zooming, and zooming. This makes it possible to reduce not only the number of screen transitions but also the number of operations performed by the user within a single operation screen, and further improves the user's work efficiency.

[0057] Embodiment 3. Embodiment 3 describes a method for receiving feedback on a new operation screen. Since the basic configuration of the numerical control device 1 is the same as in Embodiment 1, the parts that differ from Embodiment 1 will be mainly described below using the reference numerals shown in Figure 1.

[0058] In Embodiment 3, the new operation screen generated by the numerical control device 1 using the inference device 16 includes a feedback receiving unit that receives user feedback on the operation screen.

[0059] Figure 7 shows an example of a new operation screen displayed by the numerical control device 1 according to Embodiment 3. The operation screen shown in Figure 7 includes a first area for displaying detailed alarm information, a second area for displaying machine tool status information indicating the status of the machine tool, and a third area for displaying how to deal with an alarm that is currently occurring. The operation screen shown in Figure 7 also includes an input interface for inputting whether to approve the new operation screen, which serves as a feedback receiving unit 31 for receiving user feedback on the operation screen. This feedback receiving unit 31 includes a message to assist the user, "Do you approve the new operation screen? (Selecting denial will return you to the original screen)," as well as "Approve" and "Deny" buttons. For example, if a user sees the displayed new operation screen and believes it contains the information they are looking for, they can approve the new operation screen by operating the "Approve" button. For example, if the new operation screen is approved, the output unit 17 can terminate the display from the feedback receiving unit 31 and display an operation screen including the first, second, and third areas. Furthermore, if the user believes that the displayed new operation screen does not contain the information they are looking for, or that the layout of the new operation screen makes it difficult to see the information they are looking for, the user can reject the new operation screen by operating the "Reject" button. If the new operation screen is rejected, the output unit 17 can, for example, end the display of the new operation screen shown in Figure 7 and return to the existing screen display.

[0060] Although not shown in the diagram, the feedback receiving unit 31 of the new operation screen may also include an interface for receiving approval or rejection input, as well as comments from the user. Furthermore, while the above described a two-option approach to feedback on the new operation screen ("approve" or "reject"), the system may also allow changes to a portion of the new operation screen according to user input. For example, in the operation screen shown in Figure 7, the user may replace only the content of the third area that displays how to deal with an alarm, change the size of each area of ​​the displayed screen according to user input, or make changes to a portion of the screen display data of the new operation screen. The information received by the feedback receiving unit 31 is used as input to the learning device 14.

[0061] As described above, according to Embodiment 3, the new operation screen includes a feedback receiving unit 31 that receives user feedback on the new operation screen. The feedback receiving unit 31 can also receive feedback that the displayed operation screen should be changed back from the new operation screen to the existing operation screen. This allows the user's intention to be fed back if the new operation screen generated by the numerical control device 1 differs from what the user wants, making it possible to bring the operation screen closer to what the user wants.

[0062] Embodiment 4. Figure 8 shows the functional configuration of the numerical control device 1A according to Embodiment 4. The numerical control device 1A includes a control unit 11, an operation log acquisition unit 12, a data acquisition unit 13, a learning device 14, a trained model storage unit 15, an inference device 16, an output unit 17, and an operator information storage unit 18. The numerical control device 1A has the operator information storage unit 18 in addition to the configuration of the numerical control device 1 according to Embodiment 1. The following mainly describes the parts that differ from the numerical control device 1 according to Embodiment 1.

[0063] The operator information storage unit 18 stores operator information for identifying the user operating the numerical control device 1A. The operator information storage unit 18 stores operator information input using the input device 5 and can output operator information to the data acquisition unit 13. The operator information is used as input data in the learning device 14 and the inference device 16, respectively. As a result, the trained model can infer screen display data from the operation log information, operating status information, and operator information, making it possible to provide an optimized operation screen for each user.

[0064] As described above, according to Embodiment 4, the numerical control device 1A further includes an operator information holding unit 18 that holds operator information for identifying the user of the numerical control device 1A, and the learning device 14 and the inference device 16 each use the operator information as input data. As a result, the trained model infers screen display data from the operator information in addition to the operation log information and operating status information. Therefore, it becomes possible to provide an operation screen tailored to the user.

[0065] Embodiment 5. Embodiment 5 describes an example in which multiple numerical control devices 1 share a trained model. In Embodiments 1 to 4, the numerical control device 1 is equipped with a learning device 14 and an inference device 16, and the inference device 16 uses the trained model generated inside the numerical control devices 1,1A to infer screen display data, thus performing closed processing within a single machine. In contrast, Embodiment 5 describes a method in which a trained model is shared among multiple numerical control devices 1.

[0066] For example, by providing the learning device 14 and the trained model storage unit 15 on a cloud server, multiple numerical control devices 1 can share the trained model. Figure 9 shows an example of how to share a trained model in Embodiment 5. Here, by providing the learning device 14 on a cloud server or the like, multiple numerical control devices 1-1 to 1-N can communicate with the learning device 14 via a communication channel. For example, each of the numerical control devices 1-1 to 1-N has a configuration that omits the learning device 14 and trained model storage unit 15 configuration of the numerical control device 1 shown in Figure 1. In this case, the transmission of training data from the data acquisition unit 13 shown in Figure 1 to the learning device 14 and the transmission of the trained model from the trained model storage unit 15 to the inference device 16 will be performed via a communication channel such as the Internet.

[0067] The configuration described here is merely an example, and the method for sharing a trained model among multiple numerical control devices 1 in Embodiment 5 is not limited to the above example. For example, the learning device 14 and the trained model storage unit 15 are not limited to being located on a cloud server; they can communicate with each of the multiple numerical control devices 1-1 to 1-N via a communication channel. The learning device 14 shown in Figure 9 may also be built into the numerical control device 1. Furthermore, in addition to the example of sharing a trained model generated by a single learning device 14, each of the numerical control devices 1-1 to 1-N may have a learning device 14 and a trained model storage unit 15, and the trained models updated by each numerical control device 1-1 to 1-N may be interconnected and shared.

[0068] As described above, according to Embodiment 5, the learning device 14 can generate a trained model based on operation log information from multiple numerical control devices 1-1 to 1-N and operating status information from multiple machine tools. This learning device 14 may be provided on a cloud server or may be built into the numerical control device 1.

[0069] Embodiment 6. In Embodiment 6, if the operation log information determines that the user is an inexperienced user, the system has the function of issuing warnings for incorrect or potentially dangerous operations, and outputting operation guidance based on the results of learning from the operation log information of an experienced user. Since the basic configuration of the numerical control device 1 in Embodiment 6 is the same as that of Embodiment 1 shown in Figure 1, the following will mainly describe the differences from Embodiment 1.

[0070] Figure 10 is a diagram illustrating the functions of the numerical control device 1 according to Embodiment 6. The numerical control device 1 according to Embodiment 6 includes a proficiency determination unit 19. For example, the proficiency determination unit 19 is included in the data acquisition unit 13. The proficiency determination unit 19 determines the user's proficiency based on operation log information and operating status information, and outputs the determination result to the learning device 14 and the inference device 16, respectively. The determination result is used as input data in the learning device 14 and the inference device 16, respectively.

[0071] The judgment result output by the proficiency determination unit 19 only needs to contain information that can indicate whether the target user is an inexperienced user or not. For example, the judgment result may contain information that includes a flag indicating whether the target user is an inexperienced or experienced user, or it may contain information that includes a numerical value indicating the target user's proficiency level. The proficiency determination unit 19 can identify an inexperienced user, for example, based on operation log information and operation status information, from the time it takes to reach the desired information, the time taken for the operation, the number of operation errors, the number of unnecessary operations, etc.

[0072] The inference device 16 can output screen display data that includes information corresponding to the judgment result of the proficiency determination unit 19. For example, for inexperienced users, the inference device 16 can output screen display data that includes warning information and operation guidance, which is information to support operation.

[0073] As described above, according to Embodiment 6, the numerical control device 1 further includes a proficiency determination unit 19 that determines the user's proficiency during operation based on operation log information and operating status information. In this case, the trained model can infer screen display data for displaying a new operation screen that includes information requested by the user extracted from a plurality of existing operation screens and information corresponding to the determination result, from the operation log information, operating status information, and the proficiency determination result.

[0074] Embodiment 7. Embodiment 7 describes an example of a new operation screen layout. Figure 11 shows an example of a new operation screen displayed by the numerical control device 1A according to Embodiment 7. Since the basic configuration of the numerical control device 1A according to Embodiment 7 is the same as that of Embodiment 4 shown in Figure 8, the parts that differ from Embodiment 4 will be mainly described below using the reference numerals shown in Figure 8.

[0075] As shown in Figure 11, the numerical control device 1A can display a new operation screen that includes a common display area 32 where common information is displayed regardless of the user, and a user-specific display area 33 where information tailored to the user performing the operation is displayed. The new screen display data inferred by the trained model can include information that specifies the information to be displayed in the common display area 32 and the information to be displayed in the user-specific display area 33. For example, examples of information displayed in the common display area 32 include the operating mode indicating the status of the numerical control device 1A, processing time, and time. In addition, the user-specific display area 33 can display advanced menu selection options if the user performing the operation is an experienced user, and a simplified menu with operation guidance if the user performing the operation is an inexperienced user. Furthermore, the numerical control device 1A may also accept an operation to specify areas on the operation screen where the display layout should be maintained. This makes it possible to prevent unintended layout changes by the user.

[0076] As described above, according to Embodiment 7, the new operation screen displayed by the numerical control device 1A includes a common display area 32, which is a common display area regardless of the user, and a user-specific display area 33, which is a display area with different content for each user. By having a common display area 32, information that is required regardless of the user can be displayed in this common display area 32, and by creating a part of the display that does not change, it is possible to reduce the burden on the user to recognize information within the operation screen.

[0077] Embodiment 8. In Embodiment 8, operation log information for a custom screen, which is an operation screen created by the user, can be used as input data. The basic configuration of the numerical control device 1 in Embodiment 8 is the same as that of Embodiment 1 shown in Figure 1, so the parts that differ from Embodiment 1 will be mainly described below using the reference numerals shown in Figure 1.

[0078] The operation log acquisition unit 12 can acquire operation log information for custom screens. By learning from custom screens designed by the user and frequently used by the user, it becomes possible to provide operation support for a wider range of use cases.

[0079] Embodiment 9. Embodiment 9 describes a function that allows for the suggestion of optional functions when the numerical control device 1 has optional functions that cannot be used in the standard state but can be activated by purchase. The basic configuration of the numerical control device 1 according to Embodiment 9 is the same as that of Embodiment 1 shown in Figure 1, so the parts that differ from Embodiment 1 will be mainly described below using the reference numerals shown in Figure 1.

[0080] The trained model generated by the learning device 14 can infer screen display data for displaying a new operation screen that includes information suggesting the purchase of an optional function, if it can determine from the operation log information that the suggestion of an optional function is valid. Here, the new operation screen may include, for example, information showing the effects of using the optional function. For example, the numerical control device 1 can determine that the suggestion of an optional function is valid if it detects from the operation log information that if the user purchases an optional function, effects such as a reduction in the number of operations, a reduction in the number of screen transitions, and a reduction in operation time are likely to be obtained. For this reason, the operation log acquisition unit 12 uses information about an existing operation screen that includes information about a function that has not been activated as input data. Then, if the trained model includes information about a function that the user has not purchased in the output screen display data, it can output screen display data that includes information suggesting the purchase of that function.

[0081] As described above, according to Embodiment 9, the trained model can infer screen display data of the operation screen, which includes information suggesting the purchase of optional functions of the numerical control device 1. The information suggesting the purchase of optional functions may include information showing the effects of using the optional functions. This makes it possible to further improve the user's work efficiency.

[0082] Embodiment 10. In Embodiment 10, it is possible to display an operation screen corresponding to the number of display devices 4 connected to the numerical control device 1. For example, if the numerical control device 1 can utilize multiple display devices 4, including a main monitor and a sub-monitor, it will display information using multiple display devices 4 depending on the situation. Since the basic configuration of the numerical control device 1 in Embodiment 10 is the same as that of Embodiment 1 shown in Figure 1, the parts that differ from Embodiment 1 will be mainly described below using the reference numerals shown in Figure 1.

[0083] The data acquisition unit 13 can acquire information indicating the number of display devices 4 connected to the numerical control device 1 as input data. Here, "display devices 4 connected to the numerical control device 1" includes the built-in display devices 4 if the numerical control device 1 has built-in display devices 4. Also, "display devices 4 connected to the numerical control device 1" may be display devices dedicated to the numerical control device 1, or they may be portable devices such as tablet terminals or smartphones. The trained model infers screen display data from the number of display devices 4 in addition to operation log information and operating status information.

[0084] As described above, according to Embodiment 10, the trained model infers screen display data corresponding to the number of display devices 4 connected to the numerical control device 1. This makes it possible for the numerical control device 1 to make effective use of the available display devices 4, further improving the user's work efficiency.

[0085] Embodiment 11. Embodiment 11 describes an example of utilizing external data obtained from the internet or other sources. Figure 12 is a diagram showing the functional configuration of the numerical control device 1B according to Embodiment 11. The numerical control device 1B includes a control unit 11, an operation log acquisition unit 12, a data acquisition unit 13B, a learning device 14, a trained model storage unit 15, an inference device 16, and an output unit 17.

[0086] The numerical control device 1B differs from the numerical control device 1 in Embodiment 1 in that the data acquired by the data acquisition unit 13B acquires different data. The following mainly describes the differences from Embodiment 1. The data acquisition unit 13B further acquires power information, which is information indicating the power supply to the numerical control device 1B, the drive unit 2 of the machine tool and peripheral devices 3, etc., and the power consumption in the machine tool. The power information acquired by the data acquisition unit 13B includes, for example, the amount of power consumed by the machine tool acquired from the control unit 11 and information regarding power supply included in external data acquired from outside the numerical control device 1B, such as from the internet. The external data includes, for example, information indicating electricity charges, whether renewable energy can be used, and weather. This power information is used as input data in the learning device 14 and the inference device 16. As a result, the trained model can infer screen display data according to the power information. In the learning device 14, a reward r is calculated based on the power information, and a trained model is generated that can infer screen display data that can reduce power usage and electricity charges.

[0087] Specifically, the new screen display data can show a new operation screen that includes at least one piece of environmental information, such as processing time, electricity charges, greenhouse gas emissions, renewable energy usage fees, suggestions for processing schedules that avoid peak electricity usage times, and messages to users to help them save energy.

[0088] As described above, according to Embodiment 11, the trained model can infer screen display data corresponding to power information indicating power supply and power consumption of machine tools. This makes it possible to support appropriate action selection through the operation screen for environmental goals where intuitive action selection is difficult due to the complex interrelationships of each factor. For example, if only the reduction of processing time is prioritized, the user may face negative consequences in achieving environmental goals, such as higher electricity rates during peak hours or the inability to use renewable energy sources like solar power due to bad weather. In contrast, by inferring screen display data corresponding to power information, it becomes possible to support the achievement of environmental goals.

[0089] Next, the hardware configuration of the numerical control devices 1, 1A, and 1B according to embodiments 1 to 11 will be described. The functions of each part of the numerical control devices 1, 1A, and 1B are realized using processing circuits. The processing circuits may be realized by dedicated hardware or by a control circuit using a CPU (Central Processing Unit).

[0090] When the above processing circuits are implemented using dedicated hardware, they are implemented using the processing circuit 90 shown in Figure 13. Figure 13 is a diagram showing the dedicated hardware for realizing the functions of numerical control devices 1, 1A, and 1B according to embodiments 1 to 11. The processing circuit 90 may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

[0091] When the above processing circuit is implemented using a CPU-based control circuit, this control circuit is, for example, a control circuit 91 with the configuration shown in Figure 14. Figure 14 is a diagram showing the configuration of a control circuit 91 for realizing the functions of numerical control devices 1, 1A, and 1B according to embodiments 1 to 11. As shown in Figure 14, the control circuit 91 comprises a processor 92 and a memory 93. The processor 92 is a CPU, also called a processing unit, arithmetic unit, microprocessor, microcomputer, DSP (Digital Signal Processor), etc. The memory 93 is, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (Registered Trademark) (Electrically EPROM), magnetic disk, flexible disk, optical disk, compact disk, minidisc, DVD (Digital Versatile Disk), etc.

[0092] When the above processing circuit is implemented using the control circuit 91, it is implemented by the processor 92 reading and executing the program corresponding to the processing of each component, which is stored in the memory 93. The memory 93 is also used as temporary memory for each process executed by the processor 92. The program may be provided stored on a storage medium or provided via a communication channel such as the internet.

[0093] The configurations shown in the above embodiments are examples only, and it is possible to combine them with other known technologies, combine different embodiments, and omit or modify parts of the configuration without departing from the gist of the invention. For example, in the above embodiments, the technologies described in relation to the parts that differ from Embodiment 1 may be combined with the functions of the numerical control device 1A according to Embodiment 4, or with the functions of the numerical control device 1B according to Embodiment 11. [Explanation of Symbols]

[0094] 1,1A,1B,1-1~1-N Numerical control device, 2 Drive unit, 3 Peripheral device, 4 Display device, 5 Input device, 11 Control unit, 12 Operation log acquisition unit, 13,13B Data acquisition unit, 14 Learning device, 15 Trained model storage unit, 16 Inference device, 17 Output unit, 18 Operator information storage unit, 19 Proficiency determination unit, 31 Feedback reception unit, 32 Common display area, 33 User-specific display area, 90 Processing circuit, 91 Control circuit, 92 Processor, 93 Memory, 141 Training data acquisition unit, 142 Model generation unit, 143 Reward calculation unit, 144 Function update unit, 161 Inference data acquisition unit, 162 Inference unit.

Claims

1. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with The numerical control device according to claim 1, wherein the operation log information includes a time series history of coordinate positions input by the user.

2. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying a new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; an output unit that outputs the new operation screen on a display device based on the screen display data; wherein the operation log information includes a time-series history of coordinate positions input by the user.

3. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, operation status information indicating the state of the machine tool when the operation indicated by the operation log information was being performed, and a judgment result from a proficiency judgment unit that judges the user's proficiency based on the operation log information and the operation status information; a model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens and information corresponding to the determination result of the proficiency, from the operation log information, the operation state information, and the determination result of the proficiency, using the learning data; and A numerical control device comprising:

4. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, operation status information indicating the state of the machine tool when the operation indicated by the operation log information was being performed, and a judgment result of a proficiency judgment unit that judges the proficiency of the user based on the operation log information and the operation status information; an inference unit that infers screen display data for displaying a new operation screen from the operation log information, the operation status information, and the judgment result of the proficiency acquired by the inference data acquisition unit, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens and information corresponding to the judgment result of the proficiency, from the operation log information, the operation status information, and the judgment result of the proficiency; an output unit that outputs the new operation screen on a display device based on the screen display data; A numerical control device comprising:

5. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with The learned model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

6. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying a new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; an output unit that outputs the new operation screen on a display device based on the screen display data; Equipped with The learned model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

7. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with A numerical control device characterized in that the learned model infers the screen display data according to power information indicating power supply and power consumption of the machine tool.

8. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying a new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; an output unit that outputs the new operation screen on a display device based on the screen display data; Equipped with A numerical control device characterized in that the learned model infers the screen display data according to power information indicating power supply and power consumption of the machine tool.

9. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with A numerical control device characterized in that the existing multiple operation screens have a hierarchical structure, and the information of the operation screen to be operated that is obtained as the learning data includes hierarchical structure information that indicates a relationship with other operation screens.

10. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying a new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; an output unit that outputs the new operation screen on a display device based on the screen display data; Equipped with A numerical control device characterized in that the existing multiple operation screens have a hierarchical structure, and the information of the operation screen to be operated obtained as the inference data includes hierarchical structure information indicating a relationship with other operation screens.

11. The numerical control device according to claim 1 , wherein the new operation screen includes information for reducing an operational burden on the user.

12. The numerical control device according to claim 1 , wherein the new operation screen includes information that has a positive effect on an operation result of the user.

13. The numerical control device according to claim 1 , wherein the new operation screen includes a plurality of pieces of information that were previously included in a plurality of the existing operation screens in a divided manner.

14. The numerical control device according to claim 1 , wherein the operation log information indicates a history of operations by the user across a plurality of existing operation screens.

15. A numerical control device as described in any one of claims 1 to 10, characterized in that the operation log information indicates a history of the user's operations across multiple existing operation screens which have a hierarchical structure.

16. The numerical control device according to any one of claims 1 to 10, characterized in that the learned model infers the screen display data for displaying the new operation screen such that at least one of the number of operations, the number of screen transitions, and the operation time is reduced.

17. 11. The numerical control device according to claim 1, wherein the screen display data includes at least one of information on a design of the new operation screen, information output timing, information output method, and operation guidance which is information for assisting the user in operation.

18. 11. The numerical control device according to claim 3, wherein the operation log information includes a time-series history of coordinate positions input by the user.

19. The numerical control device according to any one of claims 1 to 10, characterized in that the learned model infers the screen display data for displaying the new operation screen designed to reduce the number of operations of at least one of a scroll operation, a zoom-in operation, and a zoom-out operation.

20. The numerical control device according to claim 1 , wherein the new operation screen includes a feedback receiving section that receives feedback from the user regarding the new operation screen.

21. The numerical control device according to claim 20, wherein the feedback receiving unit receives, as the feedback, an operation of returning the operation screen to be displayed from the new operation screen to the existing operation screen.

22. an operator information storage unit that stores operator information for identifying the user; Further equipped with The numerical control device according to claim 1 , wherein the trained model uses the operator information as input data to infer the screen display data.

23. The numerical control device according to claim 1, 3, 5, 7 or 9, characterized in that the model generation unit generates the learned model based on the operation log information in a plurality of numerical control devices and the operating status information of a plurality of machine tools.

24. a proficiency level determination unit that determines a proficiency level of the user based on the operation log information and the operation state information; Further equipped with The numerical control device according to any one of claims 1, 2, or 5 to 10, characterized in that the trained model uses the proficiency judgment result as input data to infer screen display data for displaying a new operation screen including information extracted from a plurality of existing operation screens and information corresponding to the proficiency judgment result.

25. 11. The numerical control device according to claim 1, wherein the new operation screen includes a display area that is common to all users and a display area having different content for each user.

26. 11. The numerical control device according to claim 1, wherein the operation log information includes the operation log information for a custom screen that is a screen created by the user.

27. The numerical control device according to any one of claims 1 to 4 or 7 to 10, characterized in that the learned model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

28. 7. The numerical control device according to claim 5, wherein the information proposing the purchase of the optional function includes information indicating an effect of using the optional function.

29. The numerical control device according to any one of claims 1 to 10, wherein the learned model infers the screen display data according to the number of display devices connected to the numerical control device.

30. 11. The numerical control device according to claim 1, wherein the learned model infers the screen display data according to power information indicating a power supply and a power consumption of the machine tool.

31. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with The learning device, wherein the operation log information includes a time-series history of coordinate positions input by the user.

32. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, operation status information indicating the state of the machine tool when the operation indicated by the operation log information was being performed, and a judgment result from a proficiency judgment unit that judges the user's proficiency based on the operation log information and the operation status information; a model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens and information corresponding to the determination result of the proficiency, from the operation log information, the operation state information, and the determination result of the proficiency, using the learning data; and A learning device comprising:

33. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with A learning device characterized in that the trained model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

34. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with A learning device characterized in that the learned model infers the screen display data according to power information indicating the power supply and the power consumption of the machine tool.

35. a learning data acquisition unit that acquires learning data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen that is the target of operation, and operating status information indicating the status of the machine tool when the operation indicated by the operation log information was being performed; A model generation unit that generates a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information using the learning data; Equipped with A learning device characterized in that the existing multiple operation screens have a hierarchical structure, and the information of the operation screen to be operated that is obtained as the learning data includes hierarchical structure information that indicates the relationship with other operation screens.

36. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying the new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; Equipped with The inference device, wherein the operation log information includes a time series history of coordinate positions input by the user.

37. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, operation status information indicating the state of the machine tool when the operation indicated by the operation log information was being performed, and a judgment result of a proficiency judgment unit that judges the proficiency of the user based on the operation log information and the operation status information; an inference unit that infers screen display data for displaying the new operation screen from the operation log information, the operation status information, and the judgment result of the proficiency acquired by the inference data acquisition unit, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens and information corresponding to the judgment result of the proficiency, from the operation log information, the operation status information, and the judgment result of the proficiency; An inference device comprising:

38. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying the new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; Equipped with An inference device characterized in that the learned model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

39. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying the new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; Equipped with An inference device characterized in that the learned model infers the screen display data according to power information indicating the power supply and the power consumption of the machine tool.

40. an inference data acquisition unit that acquires inference data including operation log information indicating a user's operation on an operation screen of a numerical control device that controls a machine tool and information on the operation screen to be operated, and operating state information indicating the state of the machine tool when the operation indicated by the operation log information was being performed; an inference unit that infers screen display data for displaying the new operation screen from the operation log information and the operation status information acquired by the inference data acquisition unit, using a learned model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; Equipped with An inference device characterized in that the existing multiple operation screens have a hierarchical structure, and the information of the operation screen to be operated that is obtained as the inference data includes hierarchical structure information that indicates the relationship with other operation screens.

41. An operation screen display method for a numerical control device that controls a machine tool, comprising: acquiring data for inference including operation log information indicating a user's operation on an operation screen of a numerical control device and information on the operation screen to be operated, and operation status information indicating a status of the machine tool when the operation indicated by the operation log information was being performed; A step of inferring screen display data for displaying the new operation screen from the operation log information and the operation status information acquired in the step of acquiring data for inference, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; outputting the new operation screen on a display device based on the screen display data; Including, 2. A method for displaying an operation screen of a numerical control device, wherein the operation log information includes a time series history of coordinate positions input by the user.

42. An operation screen display method for a numerical control device that controls a machine tool, comprising: acquiring data for inference including operation log information indicating a user's operation on an operation screen of a numerical control device and information on the operation screen to be operated, operation status information indicating the state of the machine tool when the operation indicated by the operation log information was being performed, and a judgment result of a proficiency judgment unit that judges the proficiency of the user based on the operation log information and the operation status information; a step of inferring screen display data for displaying the new operation screen from the operation log information, the operation status information, and the judgment result of the proficiency acquired in the step of acquiring data for inference, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens and information corresponding to the judgment result of the proficiency, from the operation log information, the operation status information, and the judgment result of the proficiency; outputting the new operation screen on a display device based on the screen display data; 13. A method for displaying an operation screen of a numerical control device, comprising:

43. An operation screen display method for a numerical control device that controls a machine tool, comprising: acquiring data for inference including operation log information indicating a user's operation on an operation screen of a numerical control device and information on the operation screen to be operated, and operation status information indicating a status of the machine tool when the operation indicated by the operation log information was being performed; A step of inferring screen display data for displaying the new operation screen from the operation log information and the operation status information acquired in the step of acquiring data for inference, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; outputting the new operation screen on a display device based on the screen display data; Including, An operation screen display method for a numerical control device, characterized in that the learned model is capable of inferring the screen display data of the operation screen including information suggesting the purchase of an optional function of the numerical control device.

44. An operation screen display method for a numerical control device that controls a machine tool, comprising: acquiring data for inference including operation log information indicating a user's operation on an operation screen of a numerical control device and information on the operation screen to be operated, and operation status information indicating a status of the machine tool when the operation indicated by the operation log information was being performed; A step of inferring screen display data for displaying the new operation screen from the operation log information and the operation status information acquired in the step of acquiring data for inference, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; outputting the new operation screen on a display device based on the screen display data; Including, An operation screen display method for a numerical control device, characterized in that the learned model infers the screen display data according to power information indicating power supply and power consumption of the machine tool.

45. An operation screen display method for a numerical control device that controls a machine tool, comprising: acquiring data for inference including operation log information indicating a user's operation on an operation screen of a numerical control device and information on the operation screen to be operated, and operation status information indicating a status of the machine tool when the operation indicated by the operation log information was being performed; A step of inferring screen display data for displaying the new operation screen from the operation log information and the operation status information acquired in the step of acquiring data for inference, using a trained model for inferring screen display data for displaying a new operation screen including information extracted from the existing plurality of operation screens from the operation log information and the operation status information; outputting the new operation screen on a display device based on the screen display data; Including, A method for displaying an operation screen of a numerical control device, characterized in that the existing multiple operation screens have a hierarchical structure, and information on the operation screen to be operated that is obtained as the inference data includes hierarchical structure information that indicates a relationship with other operation screens.