Machine learning device, information presentation device, and computer-readable recording medium

Abstract

An information presentation device according to the present disclosure comprises: a machine-specific information reception unit that is provided with a trained model that outputs service identification information pertaining to a required service when processing information is input, and that receives machine-specific information for uniquely identifying an industrial machine and a control device; a processing information reception unit that receives processing information including at least a shape to be processed; an estimation unit that estimates, on the basis of the input data, the processing information using the trained model, and estimates service identification information pertaining to a service required to perform processing pertaining to the processing information; a determination unit that acquires configuration information including information pertaining to the configuration of the control device and the machine configuration of the industrial machine that is identified by the machine-specific information, and determines, on the basis of the configuration information and the service identification information, whether the service can be used; and an output unit that outputs the result of the determination.

Description

Machine learning device, information presentation device, and computer-readable recording medium

[0001] The present disclosure relates to a machine learning device, an information presentation device, and a computer-readable recording medium.

[0002] A wide variety of services (functions) are provided by control devices that drive and control industrial machinery. Some of these services are essential for desired machining, while others are recommended for use in conjunction with other services. Devices that provide information necessary for desired machining are known, for example, from Patent Document 1.

[0003] Users of industrial machinery do not necessarily know the information (service name, designated drawing number, and other order information) required to identify the services required to achieve the desired processing. Furthermore, the information required to identify the services described above differs depending on the manufacturer of the industrial machinery or the control device.

[0004] WO 2006 / 137120

[0005] It is difficult for users to determine whether the services required for the desired processing are available for their own industrial machinery. Furthermore, if the services are unavailable, it is also difficult for users to immediately determine whether their industrial machinery meets the service application conditions. Therefore, there is a demand for technology that can present information related to the services required by users in the field.

[0006] The information presentation device according to the present disclosure uses a trained model that has learned the correspondence between desired machining shape information and control device service information required through supervised learning. Processing information, such as the desired shape to be machined, and unique information that can identify the industrial machine to be used are input to this trained model, which then outputs the control device services (functions) required for machining. The device then determines whether the output services are usable by the industrial machine to be used, and outputs the determination result and application conditions, thereby solving the above-mentioned problem.

[0007] One aspect of the present disclosure is an information presentation device that includes: a machine-specific information receiving unit that has a trained model generated by a machine learning device and receives machine-specific information that uniquely identifies an industrial machine and a control device; a processing information receiving unit that receives processing information that includes at least a shape to be processed by the industrial machine and the control device; an estimation unit that performs estimation using the trained model based on the processing information and estimates service-specific information related to a service required to perform processing related to the processing information; a judgment unit that acquires configuration information that includes information related to the mechanical configuration of the industrial machine identified by the machine-specific information and the configuration of the control device, and determines whether the service is available based on the configuration information and the service-specific information; and an output unit that outputs the result of the judgment.

[0008] FIG. 1 is a schematic hardware configuration diagram of a machine learning device according to a first embodiment of the present disclosure. FIG. 2 is a block diagram showing the schematic functions of a machine learning device according to the first embodiment. FIG. 3 is a schematic diagram showing an example of service specifying information. FIG. 4 is a schematic hardware configuration diagram of an information presentation device according to a second embodiment of the present disclosure. FIG. 5 is a block diagram showing the schematic functions of an information presentation device according to the second embodiment. FIG. 6 is a schematic diagram showing an example of configuration information stored in a configuration information storage unit. FIG. 7 is a schematic diagram showing an example of service specifying information estimated by an estimation unit. FIG. 8 is a schematic diagram showing another example of configuration information stored in a configuration information storage unit. FIG. 9 is a schematic diagram showing another example of service specifying information estimated by an estimation unit.

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following description, components having the same or similar functions will be denoted by the same reference numerals. Duplicate descriptions of those components may be omitted.

[0010] In this application, "based on XX" means "based on at least XX," and includes cases where it is based on other elements in addition to XX. Furthermore, "based on XX" is not limited to cases where XX is used directly, but also includes cases where it is based on XX that has been calculated or processed. "XX" is any element (for example, any information).

[0011] First Embodiment Fig. 1 is a schematic hardware configuration diagram showing the main parts of a machine learning device according to a first embodiment of the present disclosure. The machine learning device 1 according to this embodiment is used to generate a trained model to be used by an information presentation device 2. The machine learning device 1 according to this embodiment can be implemented on a computer such as a personal computer, a cell computer, a fog computer 6, or a cloud server 7. This embodiment shows an example in which the machine learning device 1 is implemented on a computer connected via a network to a control device that controls industrial machinery, the fog computer 6, the cloud server 7, etc.

[0012] The CPU 11 included in the machine learning device 1 according to this embodiment is a processor that provides overall control of the machine learning device 1. The CPU 11 reads a system program stored in the ROM 12 via the bus 22 and controls the entire machine learning device 1 in accordance with the system program. The RAM 13 temporarily stores temporary calculation data, display data, various data acquired from the outside, and the like.

[0013] The non-volatile memory 14 is composed of, for example, a battery-backed memory (not shown) or an SSD (Solid State Drive), and retains its stored state even when the machine learning device 1 is powered off. The non-volatile memory 14 stores programs and data read from an external device 72 via the interface 15, programs and data input via the input device 71, and programs and data acquired from the control device 3 that controls the industrial machine 4 or other devices via the network 5. The programs and data stored in the non-volatile memory 14 may be expanded into the RAM 13 when executed / used. In addition, various system programs such as known analysis programs are written in the ROM 12 in advance.

[0014] The interface 15 is an interface for connecting the CPU 11 of the machine learning device 1 to an external device 72 such as a USB device. For example, system programs, data, etc. are read from the external device 72. In addition, programs, data, etc. created or edited within the machine learning device 1 can be stored in external storage means via the external device 72.

[0015] The interface 20 is an interface for connecting the CPU 11 of the machine learning device 1 to a wired or wireless network 5. The network 5 may communicate using technologies such as serial communication such as RS-485, Ethernet (registered trademark), optical communication, wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. The network 5 may be connected to the information presentation device 2, the control device 3 that controls at least one industrial machine 4, the fog computer 6, the cloud server 7, etc.

[0016] The display device 70 displays data and the like obtained as a result of executing various data and programs loaded into memory, output via the interface 17. An input device 71, which is composed of at least one input device such as a keyboard, pointing device, voice input device, imaging device, barcode reader, etc., passes commands, data, etc. based on user operations to the CPU 11 via the interface 18.

[0017] 2 is a schematic block diagram illustrating functions of the machine learning device 1 according to the first embodiment of the present disclosure. Each function of the machine learning device 1 according to this embodiment is realized by the CPU 11 included in the machine learning device 1 shown in FIG. 1 executing a system program and controlling the operation of each unit of the machine learning device 1.

[0018] The machine learning device 1 of this embodiment includes a processing information acquisition unit 100, a service-specific information acquisition unit 110, a learning data generation unit 120, a learning unit 140, and an output unit 180. In addition, the RAM 13 to the nonvolatile memory 14 of the machine learning device 1 are provided in advance with a model storage unit 160, which is an area for storing the trained model generated by the learning unit 140.

[0019] The machining information acquisition unit 100 acquires machining information including at least the shape to be machined. The machining information may be information indicating the machining shape input as text, such as eccentric shaft machining, scroll compressor, or inclined surface drilling. The machining information may also be information indicating the machining shape input as audio. Furthermore, for example, CAD data created by CAD, images of products machined by other industrial machines, or images of hand-drawn drawings may be used as information indicating the machining shape. While it is generally difficult to verbalize a desired machining shape, it is possible to express the machining shape using drawings or images. The machining information acquisition unit 100 may display a GUI for inputting machining information on the display device 70 and accept input of the machining shape from the user using the input device 71 via the GUI. Alternatively, the user may be allowed to select and input CAD data or image data indicating the machining shape. The machining information acquisition unit 100 outputs the acquired machining information to the learning data generation unit 120.

[0020] The service-specific information acquisition unit 110 acquires service-specific information, which is information related to services required for a control device that controls an industrial machine to realize the processing information acquired by the processing information acquisition unit 100. FIG. 3 is a schematic diagram showing an example of service-specific information in the form of a table. The service-specific information may include, for example, the name of the service, the control device that the service is targeted for, the service's design number, the service's application conditions, and recommended functions required to provide the service. The example of service-specific information shown in FIG. 3 shows, for example, the "involute interpolation function," a service required for creating an involute curve trajectory; the "rigid tapping function," a service required for rigid tapping; the "eccentric turning function," a service required for eccentric shaft processing; and the "inclined surface indexing command function," a service required for processing an inclined surface. Each piece of service-specific information includes the model number of the control device that can install the service, the service's design number, the service's application conditions, and other services recommended for use in conjunction with the service. The service specific information may be in any format, for example, as long as it allows each item and item value included in the service specific information to be distinguished, and may be expressed in, for example, XML format, JSON format, or the like. The service specific information acquisition unit 110 may display a GUI for inputting the service specific information on the display device 70 and accept input of the service specific information processing shape from the user using the input device 71 via the GUI. Alternatively, the service specific information may be acquired via the network 5 from a computer of the control device manufacturer that manages the service specific information. The service specific information acquisition unit 110 outputs the acquired service specific information to the learning data generation unit 120.

[0021] The learning data generation unit 120 generates learning data to be used in supervised learning, using the processing information acquired by the processing information acquisition unit 100 as input data and the service specific information acquired by the service specific information acquisition unit 110 as label data. The learning data generation unit 120 associates service specific information related to the service required for the processing with the processing indicated by each piece of processing information. This association may be performed manually by the user. The learning data generation unit 120 generates learning data by associating the processing information with the service specific information based on a user's operation via the input device 71. The learning data may be data in which one piece of processing information is associated with one piece of service specific information. Alternatively, the learning data may be data in which one piece of processing information is associated with two or more pieces of service specific information. This means that two or more services are required to realize one processing shape. The learning data generation unit 120 outputs the generated learning data to the learning unit 140.

[0022] The learning unit 140 performs supervised learning using a predetermined model based on the learning data generated by the learning data generation unit 120. Then, it generates a trained model that outputs service-specific information related to a required service when processed information is input. The trained model outputs one or more pieces of service-specific information from input processed information such as character strings, audio, or images. The model used by the learning unit 140 may be, for example, an encoder-decoder model. In this case, the encoder may be, for example, a convolutional neural network (CNN). Furthermore, the decoder can be a recurrent neural network (RNN) such as a gated recurrent unit (GRU) or a long short-term memory (LSTM). By using such a model, it is possible to generate an intermediate representation vector from an input character string, audio, image, etc. using an encoder. Then, one or more pieces of service specific information can be sequentially generated from the generated intermediate representation vector using a decoder. The learning unit 140 learns the encoding of general character strings, audio, and images and the decoding of service specific information using a general learning algorithm that is suited to the adopted model. As a result, the trained model generated by the learning unit 140 outputs service specific information related to the required service when processing information is input. The learning unit 140 stores the generated trained model in the model storage unit 160.

[0023] The output unit 180 outputs the trained model generated by the training unit 140. The output unit 180 may output the trained model based on an operation instruction from a user. The output unit 180 may output the trained model to, for example, an external device 72. The output unit 180 may also output the trained model to another computer such as the fog computer 6, the cloud server 7, or the information presentation device 2 via the network 5.

[0024] The machine learning device 1 having the above configuration generates a trained model that can be used to estimate information related to services required to realize a predetermined machining shape with industrial machinery. The generated trained model can be used to estimate services required for desired machining with industrial machinery owned by the user and services that are recommended to be used in combination.

[0025] Second Embodiment FIG. 4 is a schematic hardware configuration diagram showing the main parts of an information presentation device according to a second embodiment of the present disclosure. The information presentation device 2 according to this embodiment uses a trained model generated by the machine learning device 1 according to the first embodiment. The information presentation device 2 can be implemented, for example, on a control device that controls industrial machinery. The information presentation device 2 can also be implemented, for example, on a computer such as a personal computer attached to the control device, a personal computer connected to the control device via a wired or wireless network, a cell computer, a fog computer 6, or a cloud server 7. This embodiment shows an example in which the information presentation device 2 is implemented on a computer connected to the control device that controls industrial machinery via a network.

[0026] The CPU 31 included in the information presentation device 2 according to this embodiment is a processor that controls the entire information presentation device 2. The CPU 31 reads a system program stored in the ROM 32 via the bus 42 and controls the entire information presentation device 2 in accordance with the system program. The RAM 33 temporarily stores temporary calculation data, display data, various data acquired from the outside, and the like.

[0027] The non-volatile memory 34 is composed of, for example, a battery-backed memory (not shown) or an SSD (Solid State Drive), and retains its stored state even when the information presentation device 2 is powered off. The non-volatile memory 34 stores programs and data read from an external device 82 via the interface 35, programs and data input via the input device 81, and programs and data acquired via the network 5 from the machine learning device 1, the control device 3 that controls the industrial machine 4, other devices, etc. The programs and data stored in the non-volatile memory 34 may be expanded into the RAM 33 when executed / used. In addition, various system programs such as known analysis programs are written in the ROM 32 in advance.

[0028] The interface 35 is an interface for connecting the CPU 31 of the information presentation device 2 to an external device 82 such as a USB device. For example, system programs, data, etc. are read from the external device 82. In addition, programs, data, etc. created or edited within the information presentation device 2 can be stored in external storage means via the external device 82.

[0029] The interface 40 is an interface for connecting the CPU 31 of the information presentation device 2 to a wired or wireless network 5. The network 5 may communicate using technologies such as serial communication such as RS-485, Ethernet (registered trademark), optical communication, wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. The machine learning device 1, a control device 3 that controls at least one industrial machine 4, a fog computer 6, a cloud server 7, etc. may be connected to the network 5.

[0030] The display device 80 displays data and the like obtained as a result of executing various data and programs loaded into memory, output via the interface 37. An input device 81, which is composed of at least one input device such as a keyboard, pointing device, voice input device, imaging device, barcode reader, etc., passes commands, data, etc. based on user operations to the CPU 31 via the interface 38.

[0031] 5 is a schematic block diagram illustrating functions of the information presentation device 2 according to the second embodiment of the present disclosure. Each function of the information presentation device 2 according to this embodiment is realized by the CPU 31 included in the information presentation device 2 shown in FIG. 4 executing a system program and controlling the operation of each unit of the information presentation device 2.

[0032] The information presentation device 2 of this embodiment includes a machine-specific information receiving unit 200, a processing information receiving unit 210, an estimation unit 230, a determination unit 260, and an output unit 280. The RAM 33 to the nonvolatile memory 34 of the information presentation device 2 also include a model storage unit 240, which is an area for storing the trained model generated by the machine learning device 1 according to the first embodiment, and a configuration information storage unit 250 for pre-storing configuration information that associates the machine-specific information with the mechanical configuration of the industrial machine and the configuration of the control device that are included in the industrial machine identified by the machine-specific information.

[0033] The machine-specific information receiving unit 200 receives machine-specific information that uniquely identifies the industrial machine 4 and the control device 3 that are the target of a service-related inquiry. The machine-specific information may be any information that can identify the industrial machine 4 and the control device 3 used by the user. For example, it may be a number that combines an MTB (Machine Tool Builder) number that uniquely identifies the manufacturer that manufactured the industrial machine 4, a machine user number that uniquely identifies the user who uses the industrial machine, a serial number, etc. The machine-specific information may be composed of a single piece of information that identifies a pair of the industrial machine 4 and the control device 3. The machine-specific information receiving unit 200 may display a GUI (Graphical User Interface) for inputting the machine-specific information on the display device 80 and receive direct input of the machine-specific information from the user using the input device 81 via the GUI. Alternatively, the machine-specific information may be received indirectly by, for example, displaying a list of the industrial machines 4 and the control devices 3 to be managed and allowing the user to select and input. Furthermore, the input of the machine-specific information may be accepted by using a barcode reader, an imaging device, or the like (not shown) to read one-dimensional barcodes or two-dimensional barcodes attached to or engraved on the industrial machine 4 and the control device 3. The machine-specific information accepting unit 200 outputs the accepted machine-specific information to the determining unit 260.

[0034] The machining information receiving unit 210 receives machining information including at least information indicating a desired machining shape to be machined. The machining information may be information indicating the machining shape input as text, such as eccentric shaft machining, scroll compressor, or inclined surface drilling. The machining information may also be information indicating the machining shape input as audio. Furthermore, for example, CAD data created by CAD, images of products machined by other industrial machines, or images of hand-drawn drawings may be used as information indicating the machining shape. While it is generally difficult to verbalize a desired machining shape, it is possible to express the machining shape using drawings or images. The machining information receiving unit 210 may display a GUI for inputting the machining shape on the display device 80 and receive input of the machining shape from the user using the input device 81 via the GUI. Alternatively, the user may be allowed to select and input CAD data or image data indicating the machining shape. The machining information receiving unit 210 outputs the received machining information to the estimation unit 230.

[0035] The estimation unit 230 performs estimation using a trained model stored in the model storage unit 240 based on the processing information received by the processing information receiving unit 210. Then, the estimation unit 230 estimates service-specific information related to services required to perform processing related to the processing information. The model storage unit 240 stores a trained model generated in advance by the machine learning device 1 according to the first embodiment. This trained model outputs service-specific information related to the required services when processing information is input. The estimation unit 230 inputs the processing information received by the processing information receiving unit 210 to the trained model and obtains, as its output, one or more pieces of service-specific information related to services required to realize the processing related to the processing information. The one or more pieces of service-specific information output by the trained model are in the same format as the label data used for learning by the machine learning device 1 according to the first embodiment, such as data in XML format or JSON format. The estimation unit 230 outputs the service-specific information obtained as a result of the estimation to the determination unit 260.

[0036] The determination unit 260 acquires configuration information including the mechanical configuration and control device configuration of the industrial machine identified by the machine-specific information received by the machine-specific information receiving unit 200 from the configuration information storage unit 250. Then, based on the acquired configuration information and the service identification information estimated by the estimation unit 230, the determination unit 260 determines whether the service is available.

[0037] FIG. 6 is an example of configuration information stored in the configuration information storage unit 250. The configuration information associates the machine configuration of the industrial machine 4 identified by the machine unique information and the configuration of the control device 3. The configuration of the control device 3 may include the model number of the control device 3, the names of services already provided by the control device 3, and the drawing number. The machine configuration of the industrial machine 4 may include information such as the model number of the industrial machine 4, the number of control axes, the number of systems, and the axis configuration of the industrial machine 4. In the example of FIG. 6, the model number of the industrial machine with machine unique information "01-00123-01" is "FANUC aaaa aaaa," the number of control axes is "3," the number of control systems is "1," and the axis configuration is "XZC." The model number of the control device is "FANUC Series yyyy yyyy," and currently provided services include a machine control type designation function (drawing number S838#T), a polar coordinate interpolation function (drawing number J815), and an eccentric turning function (drawing number R082). The model number of the industrial machine with machine-specific information "01-00123-02" is "FANUC bbbb bbbb," the number of controlled axes is "5," the number of control systems is "1," and the axis configuration is "XYZBC." The model number of the control device is "FANUC Series zzzz zzzz," and currently provided services include a machine control type designation function (drawing number S838#M), a cylindrical interpolation function (drawing number J816), and an inclined surface indexing command function (drawing number R522). The determination unit 260 refers to the configuration information of the industrial machine 4 and the control device 3 when determining whether or not the service is available in the industrial machine 4 and the control device 3 .

[0038] The determination unit 260 compares the service identification information with configuration information including the mechanical configuration of the industrial machine 4 identified by the machine-specific information and the configuration of the control device 3, and determines whether the service is available based on the results. For example, consider a case where an inquiry is made as to whether "eccentric shaft machining" can be performed on the industrial machine and control device with machine-specific information "01-00123-01" when the configuration information of FIG. 6 is stored. At this time, assume that the estimation unit 230 estimates the service identification information exemplified in FIG. 7 based on machining information including the machining shape of "eccentric shaft machining." In this case, the control device with machine-specific information "01-00123-01" already provides an eccentric turning function, so the determination unit 260 determines that the service is available. On the other hand, consider a case where an inquiry is made as to whether "eccentric shaft machining" can be performed on the industrial machine and control device with machine-specific information "01-00123-02." Similarly, assume that the estimation unit 230 estimates the service identification information exemplified in FIG. 7. In this case, the control device with the machine-specific information "01-00123-02" does not provide the eccentric turning function. Therefore, the determination unit 260 determines that the service is not available. The determination unit 260 outputs the result of this determination to the output unit 280.

[0039] The output unit 280 outputs the result of the determination made by the determination unit 260. The output unit 280 may be configured to display and output on the display device 80. Alternatively, the output may be configured to display and output on a display device (not shown) provided in the control device 3 via the network 5. Furthermore, the output may be transmitted and output to other computers such as the fog computer 6 and the cloud server 7 via the network 5.

[0040] When the judgment unit 260 judges that the service cannot be used, the output unit 280 may output the judgment result together with information on the necessary service and application conditions contained in the service specification information estimated by the estimation unit 230.

[0041] The information presentation device 2 of this embodiment, which has the above-mentioned configuration, allows users of industrial machinery and control devices to instantly determine whether the services required for the desired processing are available for the industrial machinery and control devices they own, and if not, whether the industrial machinery and its control devices they own meet the service application conditions.

[0042] Third Embodiment An information display device according to a third embodiment of the present disclosure will be described below. The information display device 2 according to this embodiment has the same hardware configuration as the information display device 2 according to the second embodiment.

[0043] Like the information presentation device 2 according to the second embodiment, the information presentation device 2 according to the present embodiment includes a machine-specific information receiving unit 200, a processing information receiving unit 210, an estimation unit 230, a determination unit 260, and an output unit 280. The RAM 33 to the nonvolatile memory 34 of the information presentation device 2 also include a model storage unit 240, which is an area that stores the trained model generated by the machine learning device 1 according to the first embodiment, and a configuration information storage unit 250 that stores in advance configuration information that associates the machine-specific information with the mechanical configuration of the industrial machine identified by the machine-specific information and the configuration of the control device.

[0044] The machine specific information receiving unit 200, the processing information receiving unit 210, and the estimation unit 230 included in the information presentation device 2 according to this embodiment have the same functions as those according to the second embodiment.

[0045] The determination unit 260 according to this embodiment, like the determination unit 260 according to the second embodiment, determines whether the service is available based on the acquired configuration information and the service identification information estimated by the estimation unit 230. If it determines that the service is unavailable, it again refers to the configuration information storage unit 250 to search for industrial machines and control devices that provide the service. For example, when the configuration information of FIG. 6 is stored and an inquiry is made as to whether "eccentric shaft machining" can be performed on the industrial machine and control device with machine-specific information "01-00123-02," the determination result is that "eccentric shaft machining" is not possible because the industrial machine and control device with machine-specific information "01-00123-02" do not provide the "eccentric turning function." In such a case, the determination unit 260 further searches the configuration information storage unit 250 for industrial machines and control devices that provide "eccentric turning." It is then determined that the industrial machine and control device with machine-specific information "01-00123-01" provide the "eccentric turning function." The determining unit 260 outputs the result of the determination and the search result of the configuration information storage unit 250 to the output unit 280 .

[0046] The output unit 280 according to this embodiment outputs the result of the determination made by the determination unit 260. When the determination unit 260 determines that the service is unavailable, the output unit 280 displays the determination result together with the machine-specific information of the industrial machine and the control device for which the service is available.

[0047] The information presentation device 2 of this embodiment, which has the above-mentioned configuration, provides information on industrial machines and control devices that can be used for the service from among the industrial machines and control devices owned by the user, even if the desired processing cannot be performed with the industrial machine and control device that the user inquired about, so that the user can immediately know which industrial machines and control devices are appropriate for performing the desired processing.

[0048] Fourth Embodiment An information display device according to a fourth embodiment of the present disclosure will be described below. The information display device 2 according to this embodiment has the same hardware configuration as the information display device 2 according to the second embodiment.

[0049] Like the information presentation device 2 according to the second embodiment, the information presentation device 2 according to the present embodiment includes a machine-specific information receiving unit 200, a processing information receiving unit 210, an estimation unit 230, a determination unit 260, and an output unit 280. The RAM 33 to the nonvolatile memory 34 of the information presentation device 2 also include a model storage unit 240, which is an area that stores the trained model generated by the machine learning device 1 according to the first embodiment, and a configuration information storage unit 250 that stores in advance configuration information that associates the machine-specific information with the mechanical configuration of the industrial machine identified by the machine-specific information and the configuration of the control device.

[0050] The machine specific information receiving unit 200, the processing information receiving unit 210, the estimation unit 230, and the determination unit 260 included in the information presentation device 2 according to this embodiment have the same functions as those of the second embodiment.

[0051] Similar to the determination unit 260 according to the second embodiment, the determination unit 260 according to this embodiment determines whether the service is available based on the acquired configuration information and the service specification information estimated by the estimation unit 230. Furthermore, if the service specification information includes a service recommended for combined use, the determination unit 260 also determines whether the service recommended for combined use is available. The determination unit 260 then outputs the result of this determination to the output unit 280.

[0052] The output unit 280 according to this embodiment outputs the result of the determination made by the determination unit 260. In addition to determining whether a service is available, if there is a service that is recommended for use in combination, the output unit 280 also displays whether the service that is recommended for use in combination is available.

[0053] For example, consider a case where the configuration information illustrated in FIG. 8 is stored in the configuration information storage unit 250. At this time, suppose a user inquires whether the industrial machine and control device identified by the machine-specific information "01-00123-04" can perform "threading on pilot holes drilled on inclined surfaces." The estimation unit 230 then estimates the service-specific information illustrated in FIG. 9. In this case, the control device identified by the machine-specific information "01-00123-04" provides both the rigid tapping function (J828) and the inclined surface indexing command function (R522). Therefore, the determination unit 260 determines that the industrial machine and control device can perform "threading on pilot holes drilled on inclined surfaces." The service-specific information also includes information on recommended services for use in conjunction with each service. It is recommended that the rigid tapping function (J828) be used in conjunction with the smart rigid tapping (J890) service. Additionally, the inclined surface indexing command function (R522) is recommended to be used in conjunction with the service of the workpiece placement error compensation function (S993). Because these recommended functions are not provided by the control device identified by the machine-specific information "01-00123-04," the determination unit 260 commands the output unit 280 to output these recommended functions as well. Then, the output unit 280 outputs these recommended services in addition to the fact that "threading of pilot holes drilled on an inclined surface" is available.

[0054] The information presentation device 2 of this embodiment, which has the above-mentioned configuration, allows users of industrial machinery and control devices to instantly determine not only whether the services required for the desired processing are available for the industrial machinery and control devices they own, but also whether services that are recommended for use in combination are available.

[0055] Other Embodiments In the above-described embodiment, the information presentation device 2 is shown to have a configuration including the model storage unit 240 and the configuration information storage unit 250. However, the model storage unit 240 and the configuration information storage unit 250 may be provided on other devices, such as the fog computer 6 or the cloud server 7. In this case, the information presentation device 2 references the model storage unit 240 and the configuration information storage unit 250 via the network 5. With such a configuration, in an environment where multiple information presentation devices 2 are installed, it becomes possible to use trained models and configuration information in combination among the multiple information presentation devices 2 and to collectively manage the trained models and configuration information.

[0056] Although the embodiments of the present disclosure have been described in detail above, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible in these embodiments without departing from the gist of the invention or the idea and intent of the present disclosure derived from the content described in the claims and their equivalents. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical expressions are used in the description of the above-described embodiments.

[0057] The following are supplementary notes related to embodiments of the present disclosure. (Supplementary Note 1) A machine learning device (1) according to one aspect of the present disclosure includes: a processing information acquisition unit (100) that acquires processing information including at least a shape to be processed; a service-specific information acquisition unit (110) that acquires service-specific information related to a service required for a control device (3) that controls an industrial machine (4) to perform the processing indicated by the processing information on the industrial machine (4); a learning unit (140) that performs supervised learning using the processing information as input data and the service-specific information as label data, and generates a trained model that outputs service-specific information related to the required service when the processing information is input; and an output unit (180) that outputs the trained model. (Supplementary Note 2) The processing information acquired by the machine learning device (1) according to another aspect of the present disclosure is in the form of at least one of a character string, audio, and image, and the service-specific information includes at least one of a service name, information identifying at least one of the industrial machine and the control device, order information, application conditions, and information related to other services that are recommended for use in combination.

[0058] (Supplementary Note 3) An information presentation device (2) according to one aspect of the present disclosure includes: a machine-specific information receiving unit (200) that includes a trained model generated by a machine learning device (1) and receives machine-specific information that uniquely identifies an industrial machine (4) and a control device (3); a processing information receiving unit (210) that receives processing information that includes at least a shape to be processed by the industrial machine (4) and the control device (3); an estimation unit (230) that performs estimation using the trained model based on the processing information and estimates service-specific information related to a service required to perform processing related to the processing information; a determination unit (260) that acquires configuration information including information related to the mechanical configuration of the industrial machine (4) identified by the machine-specific information and the configuration of the control device (3), and determines whether the service is available based on the configuration information and the service-specific information; and an output unit (280) that outputs the result of the determination.

[0059] (Supplementary Note 4) Information related to the mechanical configuration of the industrial machine (4) included in the configuration information acquired by an information presentation device (2) according to another aspect of the present disclosure includes at least one of the number of controlled axes, the number of control systems, and the axis configuration, and the information related to the configuration of the control device (3) included in the configuration information includes information identifying a service being provided by the control device. (Supplementary Note 5) When the service is unavailable, the determination unit (260) included in the information presentation device (2) according to another aspect of the present disclosure determines, based on the configuration information, another industrial machine (4) and control device (3) for which the service is available, which are different from the industrial machine (4) and the control device (3) identified in the machine-specific information. The information presentation device according to claim 3 or 4.

[0060] (Supplementary Note 6) The output unit (280) included in the information presentation device (2) according to another aspect of the present disclosure outputs the application conditions of the service together with the result of the determination. (Supplementary Note 7) The output unit (280) included in the information presentation device (2) according to another aspect of the present disclosure outputs information on other services that are recommended to be used in conjunction with the service together with the result of the determination.

[0061] (Supplementary Note 8) A computer-readable recording medium according to one aspect of the present disclosure records a program that causes a computer to operate as a machine-specific information receiving unit (200) that receives machine-specific information that uniquely identifies an industrial machine (4) and a control device (3); a processing information receiving unit (210) that receives processing information including at least a shape to be processed by the industrial machine (4) and the control device (3); an estimation unit (230) that performs estimation using a trained model that outputs service-specific information related to a required service when processing information is input based on the processing information, and estimates the service-specific information related to a service required to perform the processing related to the processing information; a determination unit (260) that acquires configuration information including information related to the mechanical configuration of the industrial machine (4) identified by the machine-specific information and the configuration of the control device (3), and determines whether the service is available based on the configuration information and the service-specific information; and an output unit (280) that outputs the result of the determination.

[0062] REFERENCE SIGNS LIST 1 machine learning device 3 control device 4 industrial machine 5 network 6 fog computer 7 cloud server 11 CPU 12 ROM 13 RAM 14 non-volatile memory 15, 17, 18, 20 interface 22 bus 70 display device 71 input device 72 external device 100 processing information acquisition unit 110 service specific information acquisition unit 120 learning data generation unit 140 learning unit 160 model storage unit 180 output unit 2 information presentation device 31 CPU 32 ROM 33 RAM 34 non-volatile memory 35, 37, 38, 40 interface 42 bus 80 display device 81 input device 82 external device 200 machine specific information reception unit 210 processing information reception unit 230 estimation unit 240 model storage unit 250 configuration information storage unit 260 Determination unit 280 Output unit

Claims

1. A machine learning device comprising: a processing information acquisition unit that acquires processing information including at least a shape to be processed; a service specification information acquisition unit that acquires service specification information related to a service required for a control device that controls industrial machinery in order to realize the processing indicated by the processing information with the industrial machinery; a learning unit that performs supervised learning using the processing information as input data and the service specification information as label data, and generates a trained model that outputs service specification information related to the required service when the processing information is input; and an output unit that outputs the trained model.

2. The machine learning device of claim 1, wherein the processed information is in the form of at least one of a character string, audio, and image, and the service-specific information includes at least one of a service name, information identifying at least one of the industrial machine and the control device, order information, application conditions, and information related to other services that are recommended for use in conjunction with the service.

3. An information presentation device comprising: a trained model generated by the machine learning device according to claim 1; a machine-specific information receiving unit that receives machine-specific information that uniquely identifies industrial machinery and control devices; a processing information receiving unit that receives processing information that includes at least shapes to be processed by the industrial machinery and the control devices; an estimation unit that performs estimation using the trained model based on the processing information and estimates service-specific information related to services required to perform processing related to the processing information; a determination unit that acquires configuration information including information related to the mechanical configuration of the industrial machinery identified by the machine-specific information and the configuration of the control devices, and determines whether the service is available based on the configuration information and the service-specific information; and an output unit that outputs the results of the determination.

4. An information presentation device as described in claim 3, wherein the information relating to the mechanical configuration of the industrial machinery included in the configuration information includes at least one of the number of controlled axes, the number of control systems, and the axis configuration, and the information relating to the configuration of the control device included in the configuration information includes information specifying the services currently being provided by the control device.

5. An information presentation device as described in claim 3 or 4, wherein, when the service is unavailable, the determination unit determines, based on the configuration information, other industrial machines and control devices that can use the service and are different from the industrial machines and control devices identified by the machine-specific information.

6. The information presentation device according to claim 3, wherein the output unit outputs the application conditions of the service together with the result of the determination.

7. An information presentation device according to any one of claims 3 to 5, wherein the output unit outputs information about other services that are recommended to be used in conjunction with the service, along with the result of the determination.

8. A computer-readable recording medium having recorded thereon a program that causes a computer to operate as: a machine-specific information receiving unit that receives machine-specific information that uniquely identifies industrial machinery and control devices; a processing information receiving unit that receives processing information that includes at least the shape to be processed by the industrial machinery and the control devices; an estimation unit that estimates the processing information based on input data using a trained model that outputs service-specific information related to the required service when processing information is input, and estimates the service-specific information related to the service required to perform the processing related to the processing information; a judgment unit that obtains configuration information including information related to the mechanical configuration of the industrial machinery identified by the machine-specific information and the configuration of the control device, and judges whether the service is available based on the configuration information and the service-specific information; and an output unit that outputs the result of the judgment.

Images