KR-20260062998-A - Control system and control method

Abstract

A user terminal (1) that generates input information (D11) including information indicating control content required for a target device (2) according to operation by a user (1), and a learning model unit (100) that generates a control technology (D12) based on the input information (D11) generated by the user terminal (1), and a state acquisition unit (130) that acquires information regarding at least one of the operation of the target device (2) or the control technology (D12) generated by the learning model unit (100), and feeds back the said information to at least one of the user terminal (1) or the learning model unit (100).

Inventors

• 오토무라 고타로
• 스가마 야스시
• 미와 쇼타로
• 마에카와 기요시
• 남모토 다카시

Assignees

• 미쓰비시덴키 가부시키가이샤

Dates

Publication Date

20260507

Application Date

20231130

Priority Date

20231109

Claims (20)

1. A user terminal that generates input information including information indicating control content required for a device according to operation by a user, and A state acquisition unit that acquires information regarding at least one of a control description generated by a learning model unit that generates a control description based on input information generated by the user terminal or an operation of the device, and feeds back the said information to at least one of the user terminal or the learning model unit. A control system equipped with
2. In Article 1, It has an execution code generation unit that generates execution code for the device based on control technology generated by the learning model unit above, and The above learning model unit outputs the generated control technology to the above execution code generation unit, and The state acquisition unit acquires information regarding at least one of the control technology generated by the learning model unit, the execution code generated by the execution code generation unit, or the operation of the device, and feeds back the said information to at least one of the user terminal or the learning model unit. A control system characterized by the following.
3. In Article 1, It has an execution code generation unit that generates execution code for the device based on control technology generated by the learning model unit above, and The above learning model unit outputs the generated control technology to the user terminal, and The above user terminal outputs the control technology output by the learning model unit according to the operation by the user to the execution code generation unit, or causes the learning model unit to output the control technology to the execution code generation unit. The state acquisition unit acquires information regarding at least one of the execution code generated by the execution code generation unit or the operation of the device, and feeds back the said information to at least one of the user terminal or the learning model unit. A control system characterized by the following.
4. In any one of paragraphs 1 to 3, A control system characterized by the above-mentioned learning model unit utilizing information stored in a device information storage unit that stores information about the device as additional information when generating control technology.
5. In any one of paragraphs 1 to 4, A control system characterized by the input information generated by the above-mentioned user terminal being at least one of a document string describing specifications, a specification sheet, a specification sheet applied to another device, a design sheet, an operation command, a control code, or a source code.
6. In Article 2 or Article 3, A control system characterized by the above user terminal outputting the generated input information to the learning model unit when it is determined that the generated input information does not match the rule, and outputting the generated input information or the corresponding control technique to the execution code generation unit when it is determined that the generated input information matches the rule.
7. As a control system for supporting work by a person or object using a device, An input interface that receives input of first information indicating a situation or request in a work environment in which the above work is performed, and A model processing unit configured to be accessible to a predetermined learning model, and An output interface that outputs second information to support the above task based on the output from the above learning model Equipped with, The above model processing unit inputs model input data based on the above first information into the learning model, receives model output data corresponding to the model input data from the learning model, and The above model output data includes information used in the above operation, and The above output interface outputs the second information based on the above model output data. A control system characterized by the following.
8. In Article 7, The first information above includes information indicating control or operation details required for the device, and The above model input data is data in which the control content or operation content represented by the above first information is represented in a format that matches the input of the above learning model, and The above model output data includes information used for controlling or operating the device corresponding to the control or operation content represented by the above model input data, and The second information above includes information used for controlling or operating the device included in the model output data, which is described in a predetermined format identifiable at the output destination of the output interface. Control system.
9. In Article 8, The output destination of the above output interface is the device or an interface requesting control from the device, and The device is controlled as a result of the second information being output to the device or an interface requesting control of the device. Control system.
10. In Article 8, The above device further comprises an execution code generation unit that generates and outputs an execution code, which is an executable code, and The output destination of the above output interface is the above execution code generation unit, and The device is controlled by the execution code generated as a result of the second information being output to the execution code generation unit. Control system.
11. In Article 8, The output destination of the above output interface is a user terminal operated by a user, and The device is controlled as a result of the second information being output to the user terminal. Control system.
12. In Article 7, The above first information includes information indicating the situation in the work environment, and The above model input data is data in which the situation of the working environment represented by the above first information matches the input of the above learning model, and The above model output data includes information regarding the analysis results of the working environment situation represented by the above model input data and/or methods for improving said situation, and The second information above includes information regarding the analysis results of the situation in the above-mentioned work environment and/or methods for improving the situation, described in a predetermined format discernible at the output destination of the output interface. Control system.
13. In Article 7, The above model processing unit is configured to be accessible to the first learning model and the second learning model, and The above model processing unit inputs first model input data based on the first information into the first learning model, receives first model output data corresponding to the first model input data from the first learning model, and The above model processing unit inputs second model input data based on the first model output data into the second learning model, receives second model output data corresponding to the second model input data from the second learning model, and The output interface outputs the second information based on the second model output data. Control system.
14. In Article 13, The first information above includes information indicating control or operation details required for the device, and The above first model input data is data represented in a format in which the control content or operation content represented by the above first information matches the input of the above first learning model, and The first model output data includes information in which the control or operation content represented by the first model input data is represented in a more generalized or specific manner, and The above second model input data is data represented in a format in which the control content or operation content represented by the above first model output data matches the input of the above second learning model, and The above second model output data includes information used for controlling or operating the device corresponding to the control content or operation content represented by the above second model input data, and The second information includes information used for controlling or operating the device included in the second model output data, which is described in a predetermined format identifiable at the output destination of the output interface. Control system.
15. In Article 13, The above first information includes information indicating the situation in the work environment, and The above first model input data is data represented in a format in which the situation of the working environment represented by the above first information matches the input of the above first learning model, and The above first model output data includes the analysis result of the situation of the work environment represented by the above model input data, and The above second model input data is data in which the analysis result of the situation of the work environment represented by the above first model output data matches the input of the above second learning model, and The above second model output data includes information regarding a method for improving the situation in the work environment corresponding to the analysis result of the work represented by the above second model input data, and The second information includes information regarding a method for improving the situation in the working environment, at least which is included in the second model output data, described in a predetermined format discernible at the output destination of the output interface. Control system.
16. In Article 7, As a control system for supporting response operations by a person or object using a device, The above first information includes information indicating a response request, which is content requiring a response in a work environment, and The above model input data is data represented in a format in which the response request content represented by the above first information matches the input of the above learning model, and The above model output data includes information used in the response corresponding to the response request content represented by the above model input data, and The second information above includes information used in the response included in the model output data, which is described in a predetermined format identifiable at the output destination of the output interface. Control system.
17. In Article 9, The output destination of the above output interface is a screen operation interface that requests control from the device through an operation screen, and The above model output data is an operation screen for actually performing an operation on the device corresponding to the control content or operation content represented by the above model input data, and includes information of an operation screen described in a predetermined format discernible at the output destination of the above output interface. Control system.
18. In any one of Articles 7 through 17, The above input interface receives input of first information indicating a request in a work environment from a plurality of users, and The above model processing unit inputs model input data including the first information input by the plurality of users into the learning model, and receives model output data corresponding to the model input data from the learning model. Control system.
19. In any one of paragraphs 7 through 18, The above learning model is a control system comprising a language learning model that takes natural language as input and obtains an output result, an image learning model that takes an image as input and obtains an output result, and a multimodal model that takes natural language and an image as input and obtains an output result.
20. In any one of Articles 7 through 19, The above model processing unit is configured to be accessible to the first learning model and the second learning model, and One of the first learning model and the second learning model is a local learning model in which the database of the reference destination is limited to internal information, and The other of the first learning model and the second learning model is a global learning model in which the database of the reference destination is not limited to internal information. Control system.

Description

Control system and control method The present disclosure relates to a control system and a control method. Recently, the utilization of artificial intelligence (AI) has been advancing. In particular, AI capable of generating various content, known as generative AI, has begun to be adopted, and the scope of AI applications is expected to expand. Applications of AI are not limited to tasks within the home; they are being considered for use in various locations and settings, such as within facilities like buildings, factories, stations, schools, hospitals, and commercial establishments, as well as outdoors on roads, outdoor areas, in the air, or at sea. For example, Patent Document 1 describes a processing program generation device that generates a program to control a machine using a large-scale language model. FIG. 1 is a configuration diagram showing an example of a control system according to embodiment 1. Figure 2 is an explanatory diagram showing an example of the configuration of the learning model section. Figure 3 is an explanatory diagram showing an example of another configuration of the learning model section. Figure 4 is an explanatory diagram showing an example of another configuration of the learning model unit. Figure 5 is a configuration diagram showing an example of an information processing device, which is an operating environment of a control unit including a learning model unit. Figure 6 is an explanatory diagram showing an example of model learning in the model generation unit. FIG. 7 is a flowchart showing an example of the operation of a control system according to embodiment 1. FIG. 8 is a configuration diagram showing another example of a control system according to embodiment 1. FIG. 9 is a configuration diagram showing another example of a control system according to embodiment 1. FIG. 10 is a configuration diagram showing another example of a control system according to embodiment 1. FIG. 11 is a configuration diagram showing an example of a control system according to embodiment 2. FIG. 12 is a configuration diagram showing another example of a control system according to embodiment 2. FIG. 13 is a flowchart showing an example of the operation of a control system according to embodiment 2. FIG. 14 is a configuration diagram showing an example of a control system according to embodiment 3. FIG. 15 is a flowchart showing an example of the operation of a control system according to embodiment 3. FIG. 16 is a configuration diagram showing another example of a control system according to embodiment 3. FIG. 17 is a flowchart showing an example of the operation of a modified example according to embodiment 3. FIG. 18 is a configuration diagram showing another example of a control system according to embodiment 3. FIG. 19 is a configuration diagram showing another example of a control system according to embodiment 3. FIG. 20 is a configuration diagram showing another example of a control system according to embodiment 3. FIG. 21 is a configuration diagram showing another example of a control system according to embodiment 3. FIG. 22 is a flowchart showing an example of the operation of a modified example according to embodiment 3. FIG. 23 is a configuration diagram showing an example of a control system according to embodiment 4. FIG. 24 is a flowchart showing an example of the operation of a control system according to embodiment 4. FIG. 25 is a configuration diagram showing another example of a control system according to embodiment 4. FIG. 26 is a flowchart showing an example of the operation of a modified example according to embodiment 4. FIG. 27 is a configuration diagram showing an example of a control system according to embodiment 5. FIG. 28 is a flowchart showing an example of the operation of a control system according to embodiment 5. FIG. 29 is a configuration diagram showing another example of a control system according to embodiment 5. FIG. 30 is a configuration diagram showing another example of a control system according to embodiment 5. FIG. 31 is a configuration diagram showing another example of a control system according to embodiment 5. FIG. 32 is a configuration diagram showing another example of a control system according to embodiment 5. Hereinafter, to explain the present disclosure in more detail, embodiments for implementing the present disclosure will be described with reference to the attached drawings. In the following, the same reference numerals are assigned to identical elements and their descriptions are omitted. Embodiment 1. In this embodiment, an example is described of supporting operations related to code generation of a target device (2) using a learning model. Furthermore, the term "learning model" as used herein is not limited to a model that performs learning, but also includes the meaning of a model that has completed learning. In this regard, the same applies to other embodiments. In addition, the "target device" is sometimes simply referred