JP7790868B2 - Systems, integrated management devices, edge devices - Google Patents

Description

The present invention relates to an integrated management device and a system equipped with an integrated device.

Image recognition and classification processing using machine learning and deep learning are used in a variety of technical fields. Patent Document 1 describes a repository service for managing and distributing machine learning algorithm data (trained models) in containers.

US Patent Application Publication No. 2019/0278640

The management system described in Patent Document 1 facilitates the operation of machine learning by providing a machine learning repository service. However, when using one or more edge devices, each of which includes a photodetector, it is expected that the conditions set for each edge device will be different. Since the conditions set for each edge device are different, there is a possibility that the expected inference accuracy may not be achieved when distributing data to the edge devices.

The purpose of this invention is to improve inference accuracy on edge devices.

In one embodiment, the system includes one or more edge devices and an integrated management device that manages the edge devices, where the edge devices include a photodetector. The integrated management device manages a first trained model in association with first conditions that set conditions for the photodetector used to generate the first trained model, and the integrated management device is configured to distribute the first trained model and the first conditions to the edge devices.

In one embodiment, the system includes two or more edge devices and an integrated management device that manages the two or more edge devices, where the edge devices include a light detection device, and the integrated management device manages a first trained model in association with a first condition that sets the conditions of the light detection device used to generate the first trained model.

In one embodiment, the edge device includes a light detection device, and a first trained model and conditions set when generating the first trained model are distributed to the edge device.

This invention makes it possible to improve inference accuracy on edge devices.

1 is a block diagram illustrating an edge device management system according to a first embodiment. FIG. 1 is a block diagram illustrating a first embodiment and a comparative example. FIG. 2 is a flowchart showing the operation of the first embodiment. 1 is an example of a container according to the first embodiment. FIG. 10 is a block diagram illustrating an edge device management system according to a second embodiment. FIG. 10 is a block diagram illustrating an edge device management system according to a third embodiment. FIG. 10 is a block diagram illustrating an edge device management system according to a fourth embodiment. FIG. 13 is a conceptual diagram showing an application of the fifth embodiment. FIG. 2 is a diagram illustrating an example of a container according to the first embodiment. FIG. 10 is a diagram illustrating another example of the container according to the first embodiment. FIG. 10 is a flow diagram illustrating an example of a deployment flow to an edge device according to the first embodiment.

The embodiments shown below are intended to embody the technical concepts of the present invention and are not intended to limit the scope of the present invention. Note that the size and relative positions of components shown in each drawing may be exaggerated for clarity. In the following description, identical components will be assigned the same numbers and will not be described again.

In the following, when explanations are common, subscripts such as a and b will be omitted.

(Embodiment 1)
An edge device management system (hereinafter referred to as "system") according to a first embodiment will be described with reference to FIGS. 1 to 4 and 9 to 11. FIG.

Figure 1 shows the basic configuration of the system. The system includes one or more edge devices 300 and an integrated management device 200. The edge devices 300 and the integrated management device 200 are connected so that trained models managed by the integrated management device 200 can be deployed to the edge devices 300. The edge devices and the integrated management device may be located in physically separate locations. It is only necessary that data such as trained models can be deployed from the integrated management device 200 to the edge devices 300 using wireless or wired communication. For example, the edge devices 300 may be located in a factory, and the integrated management device 200 may be located in a management center located in a remote location. Furthermore, one of the edge devices 300 and the integrated management device 200 may be located in one country, and the other in a different country.

The system can be used, for example, as an inspection system. The following describes the case where the system is an inspection system. Note that the systems according to each embodiment can be used in various systems in addition to inspection systems. Examples of various systems include an image recognition system that determines whether a specific object is present in image data, and an automatic distribution system for distribution centers.

The system according to this embodiment will be explained below with reference to Figure 1.

(Edge device 300)
The edge device 300 includes a light detection device 301 and a computer device 302. The computer device 302 includes at least an input unit, a storage unit, and an output unit. Information related to the control of the light detection device 301 is transmitted from the integrated management device 200 to the input unit of the computer device 302.

The light detection device 301 can be, for example, an image sensor, a photometric sensor, or a distance sensor. The following describes the case where the light detection device 301 is an image sensor.

The computer device 302 controls the light detection device 301. The computer device 302 can further store the trained model distributed from the integrated management device 200 in a memory unit. The computer device 302 can also store the setting conditions used to create the trained model and the obtained data in a memory unit. In FIG. 1, the integrated management device 200 manages the trained model and imaging conditions in a container, and the container is deployed to the computer device 302. The light detection device 301 is then controlled based on the container information. A container refers to a virtually constructed "execution environment for a specific application." In this embodiment, a container is an execution environment for capturing images using the light detection device 301 and inferring trained data. Introducing a container allows this execution environment to be constructed quickly and easily, reducing the burden of environment management. Specifically, when not managed using a container, as in this case, multiple applications are linked. Therefore, updating a specific application may cause problems in other applications. Introducing a container reduces the likelihood of problems occurring and reduces the management burden. Note that the following describes the use of containers, but methods other than containers can be used as long as they allow for linking and managing imaging conditions and trained models.

(Integrated management device 200)
The integrated managing device 200 controls one or more edge devices 300. In FIG. 1 , the integrated managing device 200 controls two or more edge devices 300, but may also control one edge device 300. The integrated managing device 200 includes at least an edge device environment providing unit 210. In FIG. 1 , the integrated managing device 200 further includes a trained model database 220, an imaging condition database 230, an integrated managing device endpoint 240, and a learning execution unit 250.

The trained model database 220 manages multiple trained models generated under multiple imaging conditions, such as a first trained model of a first object (first work) generated under first imaging conditions and a second trained model of a first work generated under second imaging conditions. In other words, it includes a first trained model and a second trained model generated for the same work under different imaging conditions. Here, the same work does not necessarily have to be the same work. For example, if the work is product A, multiple product A's correspond to the same work. Specifically, if product A is a red ink tank, a red ink tank may be used as the work, and the same type of red ink tank may be used as the same work. The trained model database 220 may also manage a third trained model of a second object (second work) generated under first imaging conditions. In other words, the trained model database 220 may include multiple trained models obtained by imaging the same object under different imaging conditions, or multiple trained models obtained by imaging different objects under the same imaging conditions. Images of different objects may also be captured under different imaging conditions. It may also contain both.

The imaging condition database 230 manages the imaging conditions used when generating the trained models managed in the trained model database 220. The integrated management device 200 is configured to be able to distribute the trained models and the imaging conditions used when generating those trained models.

The edge device environment providing unit 210 distributes the associated trained model and imaging conditions to the edge device 300. In FIG. 1, the trained model and imaging conditions are associated and managed by the container 211, which is then deployed to the edge device 300. In other words, the container 211 associates and manages the trained model with the imaging conditions used to capture the trained model. For example, in FIG. 1, containers 211a to 211c are each captured under the same imaging conditions. Imaging conditions include, for example, exposure time and gain. Specifically, containers 211a to 211c manage the imaging conditions as an exposure time of 1 ms and a double gain. Containers 211a to 211c may be trained models of the same workpiece, or may be trained models of different workpieces as described in embodiment 2. Other imaging conditions include ISO sensitivity settings, F-number settings, whether or not high dynamic range is enabled, and white balance adjustment. It is preferable that the imaging conditions are the conditions of a photodetector included in an edge device managed by the integrated management device, but this is not limited to this. For example, a trained model may be formed based on images obtained by a photodetector included in an edge device not managed by the integrated management device, and the imaging conditions and trained model at this time may be managed in a container.

As shown in FIG. 9, the container 211 may include an inference application 308 and a machine learning library 310 along with imaging parameters 307 and a trained model 309. When the container 211 is deployed to the computer device 302, the edge device environment acquisition unit 311 acquires the imaging conditions, firmware version, installation information, etc. of the edge device 300 through the imaging application 312 and imaging library 313. The imaging parameters 307 in the container are then referenced, and consistency is confirmed before the container 211 is deployed.

In this case, even if an inconsistency occurs, the information in the edge device 300 can be overwritten and used using the flow shown in Figure 11.

Figure 11 shows an example of a deployment flow. In step S1, deployment of the container 211 to the edge device's computer device 302 is initiated. In step S2, the integrated management device 200 acquires edge device information via the edge device environment acquisition unit 311. Then, in step S3, consistency between the edge device information and the container information is confirmed. This information includes, for example, the installation information, library, and firmware version of the imaging device. If consistency is confirmed in step S3, the process proceeds to deploying the container (step S6) and ends the procedure (step S7). If a mismatch is found in step S3, the operator is asked whether to proceed with the update procedure to match the edge device with the container (step S4). If the operator does not agree, the procedure ends (step S7). If the operator agrees, the edge device information is updated (step S5). Updates can be performed automatically via electronic media or communication, or manually. If a manual update is required, the operator can be notified and instructed to do so. When the edge device update is complete, the container is deployed to the edge device (step S6) and the process ends (step S7).

Note that the container 211 may also be configured without including a machine learning library to reduce weight, as shown in Figure 10. That is, the container 211 includes the inference application 308 and the trained model 309, and the machine learning library 310 is located outside the container 211. In this case, consistency between the inference application 308 and the trained model 309 and the machine learning library 310 is required, which is resolved by adding library parameters 314. Library parameters generally have a smaller capacity than the machine learning library 310. Therefore, even if the container 211 includes library parameters 314 instead of the machine learning library 310, it is possible to make the container 211 lighter in weight than if it included the machine learning library 310.

When deploying a container to an edge device, if there is no identical container information and no inconsistency between the container information and the edge device information, similar container information or the most suitable container information may be selected and distributed.

When the operator 700 inputs information about the workpiece to be inspected by each edge device 300 into the integrated management device endpoint 240 of the integrated management device 200, the workpiece information is transmitted from the integrated management device endpoint 240 to the edge device environment providing unit 210. In other words, the operator 700 inputs information for changeover into the integrated management device endpoint 240 of the integrated management device 200. Then, the trained model of the target workpiece and the imaging conditions when the trained model was generated are sent to the edge device environment providing unit 210, where they are linked and managed by the container 211. The target container 211 is then distributed to the corresponding edge device 300. For example, if the same workpiece is to be inspected by edge devices 300a, 300b, and 300c, the information about container 211a is input to computers 302a, 302b, and 302c. Alternatively, container 211a may be distributed to computer device 302a, and containers 211b and 211c, which manage the same information as container 211a, may be distributed to computer devices 302b and 302c, respectively.

Simply inputting a trained model corresponding to the workpiece to be inspected into the edge device 300 may result in inaccurate inspection due to differences in settings such as imaging conditions between the edge device that generated the trained model and the edge device that performs the inspection. In this embodiment, not only the trained model but also the imaging conditions for imaging the trained model are input from the integrated management device 200 to the edge device 300. This allows the trained model to be distributed to the edge device 300, and when inference is performed, imaging can be performed under the same imaging conditions as when the trained model was generated, improving inference accuracy.

The effects of this embodiment will be explained using Figure 2. Assume that a workpiece has a scratch 100 and is being inspected for defects. In each figure, it is assumed that the workpiece is moving from top to bottom. For example, Figure 2(a) shows an image captured by edge device 300a that generated a trained model. Figure 2(b) shows an image captured by edge device 300b, to which a trained model has been input, but no imaging conditions have been input. Figure 2(c) shows an image captured by edge device 300c, to which a trained model has been input, but no imaging conditions have been input. Figures 2(d), 2(e), and 2(f) show images captured by edge devices 300a, 300b, and 300c, to which a trained model and imaging conditions have been input, respectively. Figure 2(a) was captured under appropriate conditions, so scratch 100a on the workpiece can be detected. However, Figure 2(b) was captured under improper exposure conditions, resulting in blurred images, making it impossible to correctly detect scratch 100b. Furthermore, in Figure 2(c), the gain is inappropriate, resulting in overexposure, making it impossible to detect the scratch 100c. On the other hand, as shown in Figures 2(d) to 2(f), an edge device that has input the trained model and imaging conditions can accurately capture images and detect scratches.

Optimal conditions vary depending on the workpiece. For example, in Figure 1, we will explain the case where the imaging conditions when the trained model was generated were condition A and the standard imaging conditions were condition B. In this case, edge device 300a has condition A when the trained model was generated and the trained model, so it can capture images under optimal conditions. On the other hand, edge device 300b is under condition B, so even if only the trained model is input, it cannot achieve optimal conditions, and inspection accuracy may be lower than that of edge device 300a. In contrast, in this embodiment, the optimal conditions for product inspection and the trained model of the workpiece are linked and managed, and both are input to the edge device. Therefore, each edge device can achieve inspection accuracy equivalent to that of edge device 300a.

Next, using Figures 1 and 3, we will explain the execution flow when a trained model trained by edge device 300a is used by other edge devices 300b and 300c.

As shown in Figure 3, the execution flow is divided into a learning flow and a deployment flow.

First, the learning flow will be explained. The photodetector 301a of the edge device 300a is used to capture an image of a workpiece under first conditions (step S101). The first conditions may be, for example, an exposure time of 1 ms and a gain of 2x. The captured image is sent to the learning execution unit 250 of the integrated management device 200.

Learning is performed using the sent images, and a trained model is generated (step S102). The trained model can be generated using machine learning. When an image of a workpiece is input during inspection, the trained model determines whether there are any defects and outputs a pass/fail decision. The trained model is stored in the trained model database 220. The first conditions are also stored in the imaging condition database 230. At this time, the trained model database 220 and the imaging condition database 230 are linked by a relational database or the like, and managed by the edge device environment providing unit 210 (step S103).

Specific machine learning algorithms that may be used include nearest neighbor methods, naive Bayes methods, decision trees, and support vector machines. Deep learning may also be used, which uses neural networks to generate features and connection weighting coefficients for learning. For example, a CNN (Convolutional Neural Network) model may be used as a deep learning model.

To create multiple trained models, change the imaging conditions and workpiece and repeat steps S101 to S103 above.

Next, the deployment flow will be explained. First, in order to deploy the trained model of edge device 300a to other edge devices 300b and 300c, the operator 700 accesses the integrated management device endpoint 240 using a REST API or the like and issues a command (step S201). Note that rather than the operator 700 accessing the system, it is also possible to set up the system to deploy the trained model of edge device 300a to other edge devices 300b and 300c through programming. For example, the trained model may be scheduled using a script or the like, and deployed every weekend.

Upon receiving a command from the integrated management device endpoint 240, the edge device environment providing unit 210 imports into the container a set of a trained model suitable for the edge device from the trained model database and the imaging conditions (step S202). At this time, the trained model is copied from the trained model database 220, and the imaging conditions are copied from the imaging condition database 230 and imported into the container 211. A container orchestration system for deploying, scaling, and managing containerized applications can be used for the mechanism and orchestration of the container 211. Any mechanism can be used for the container orchestration system as long as it can perform similar tasks.

In addition, the container that stores the trained model and the inference container can be managed separately, and each container can be linked and managed.

Next, the central management device 200 distributes containers 211a, 211b, and 211c corresponding to the edge devices 300a, 300b, and 300c, respectively (step S203).

Then, each edge device performs imaging and inference (step S301). If the specified inference accuracy is ensured in step S301, the inspection is carried out using the workpiece to be inspected. If the specified inference accuracy is not ensured in step S301, the imaging conditions are changed and steps S101 to S301 are executed again, and steps S101 to S301 are executed again until the specified inference accuracy is achieved.

The above execution flow allows the trained model trained on edge device 300a to be used on other edge devices 300b and 300c.

Figure 4 shows an example of managing imaging conditions and a trained model together in a container, but this is not limiting. As shown in Figure 4, a system administrator executes Deployment.yaml, which manages imaging conditions and a trained model, via an API or the like. This yaml file is then used to deploy to an edge device. Specifically, in Figure 4, imaging conditions such as exposure time, gain, lighting intensity of the lighting device, and lighting device angle are linked to and managed with the trained model. Although lighting devices are not shown in Figure 1, the angle and lighting intensity are input to the lighting device included in the edge device as shown in Figure 8. The above imaging conditions and trained model are then input to the edge device, and workpiece estimation is performed.

In the above explanation, the integrated management device 200 also distributes the container 211a to the edge device 300a, but since the edge device 300a is the edge device used to generate the trained model, the container 211a does not need to be distributed.

Also, while an example has been described in which the trained model and imaging conditions are managed by the container and the container is distributed, it is also possible to manage the trained model in the container, and manage the imaging conditions separately from the container by linking them to the trained model in the container.

According to this embodiment, the trained model and the conditions for generating the trained model are linked and managed by the integrated management device 200. The trained model and conditions are then distributed to the edge device, which then performs imaging and inference. This improves the inference accuracy of the edge device. Furthermore, it is possible to shorten the dead time before the trained inspection begins during workpiece inspection.

(Embodiment 2)
An edge device management system according to a second embodiment will be described with reference to Fig. 5. The system according to the second embodiment differs from the first embodiment in that the multiple edge devices managed by the integrated management device 200 include an edge device that inspects a first work and an edge device that inspects a second work that is different from the first work. The configuration other than that described below is the same as that of the first embodiment, and therefore, description thereof may be omitted.

As shown in Figure 5, the integrated management device 200 manages edge devices 300a and 300c that inspect the first work (product A) and edge devices 300b and 300d that inspect the second work (product B). Containers suitable for the work to be imaged by the edge devices are distributed to each edge device. For example, in Figure 5, containers 211a and 211c that manage the trained model and imaging conditions corresponding to the first work are distributed to edge devices 300a and 300c. Containers 211b and 211d that manage the trained model and imaging conditions corresponding to the second work are distributed to edge devices 300b and 300d.

The method for creating the trained model and the mechanism for managing the trained model and imaging conditions are the same as in embodiment 1, so explanations will be omitted.

According to this embodiment, the time required to complete a changeover when the product being inspected by an edge device changes can be shortened compared to when only a trained model is input. For example, an edge device may inspect product A for a specified period, and then inspect product B for a specified period using the same edge device. Because the optimal imaging conditions differ for each product, simply inputting a trained model corresponding to the product being inspected into the edge device takes time for the imaging conditions of the edge device to become optimal. Therefore, time is required to complete a changeover each time the product being inspected changes. In contrast, according to this embodiment, the trained model and imaging conditions are distributed to the edge device, thereby shortening the time required to reach optimal imaging conditions and improving inference accuracy. It also becomes possible to inspect different workpieces with each edge device.

(Embodiment 3)
An edge device management system according to a third embodiment will be described with reference to Fig. 6. The system according to the third embodiment differs from the system according to the second embodiment in that each edge device 300 includes a learning execution unit 250. The configuration other than that described below is the same as that of the second embodiment, and therefore, description thereof may be omitted.

In the system according to the third embodiment, each edge device 300a, 300b, and 300c includes a corresponding learning execution unit 250a, 250b, and 250c. The learning execution unit 250 included in the edge device 300 generates a trained model. Specifically, the training model obtained from the light detection device 301 is input to the training execution unit 250, and the trained model is generated by the training execution unit 250.

The trained models generated by each edge device 300 are then input into the trained model database 220 and the imaging condition database 230 of the integrated management device 200. The trained models of multiple edge devices 300 and the imaging conditions used when the trained models were generated are collectively managed by the integrated management device 200.

An example of the flow in this embodiment is described below. First, the operator 700 issues instructions via the integrated management device endpoint 240 regarding whether or not learning should be performed in the learning execution unit 250 and whether or not to update the trained model.

Next, the image captured by the photodetector 301 of the edge device 300 is sent to the learning execution unit 250, where learning is performed.

Once learning has progressed to a certain extent and a predetermined accuracy has been achieved, the trained model is stored in the trained model database 220 of the integrated management device 200. At this time, if a trained model that was stored before learning exists, it may be updated to the newly generated trained model. The predetermined accuracy can be set as appropriate, but for example, it may be an accuracy that results in an 80% or higher probability of pass/fail determination in the inspection process.

When a trained model is stored in the trained model database 220, the imaging conditions used to generate the trained model are also stored in the imaging condition database 230, either at the same time as or before or after the storage. The trained model database 220 and the imaging condition database 230 are managed in association with the corresponding trained model and imaging conditions.

According to this embodiment, the trained model and imaging conditions are managed as a set, and the trained model and imaging conditions are distributed to the edge device, thereby improving inference accuracy. Furthermore, as in this embodiment, by configuring the learning execution unit 250 as part of each edge device 300 and performing re-learning in the edge device, it is also possible to improve the accuracy of the trained model.

(Embodiment 4)
An edge device management system according to the fourth embodiment will be described with reference to FIG. 7 . The system according to the fourth embodiment differs from the first embodiment in that data from the photodetector 301 is input from the edge device 300 to the learning execution unit 250 via the preprocessing unit 303. The system also differs from the first embodiment in that data is input from the learning execution unit 250 to the trained model database 220 via the postprocessing unit 304. The system also differs from the first embodiment in that data is input from the preprocessing unit 303b to the inference execution unit 260 in the inference flow. Configurations other than those described below are the same as those of the second embodiment, and therefore descriptions thereof may be omitted.

In Figure 7, the learning flow is shown from the light detection device 301a to the post-processing device 304a, and the inference flow is shown from the light detection device 301b to the post-processing device 304b. The learning flow and the inference flow differ in the configuration in which data is input from the pre-processing device.

The pre-processing unit 303 and post-processing unit 304 may be included in the integrated management device 200 or in the edge device 300.

The pre-processing unit 303 performs operations such as trimming, identifying target areas, inverting, and correcting the image data obtained by the light detection device 301. Corrections include, for example, averaging, and correcting brightness and contrast. Edge enhancement may also be performed.

When learning in the learning execution unit 250, hyperparameters that control the machine learning algorithm may also be managed additionally.

The post-processing unit 304 can include information on the pass/fail status of the inspection and production line information.

According to this embodiment, a system that manages imaging conditions and trained models can manage a combination of pre-processing and post-processing. This allows for higher inference accuracy and improved reproducibility. Additional learning can also be performed during training. Furthermore, the inclusion of a post-processing unit can be useful for annotation processing, etc. Therefore, it becomes easier to link with various management systems, such as industrial control systems (Supervisory Control and Data Acquisition) and manufacturing execution systems.

(Embodiment 5)
An edge device management system according to a fifth embodiment will be described with reference to Fig. 8. The system according to the fifth embodiment differs from the first embodiment in that the edge devices include a lighting device 305 and a robot 306, and the integrated management device 200 manages not only the imaging conditions but also the operating conditions of devices other than the light detection device. The configuration other than that described below is the same as that of the first embodiment, and therefore the description may be omitted.

Figure 8 shows a conceptual diagram of an edge device management system used as an inspection application. The management system includes a photodetector 301, a lighting device 305, a robot 306, and a production line 600.

The edge device 300 inspects the workpieces moving along the production line 600. The light detection device 301 of the edge device 300 captures an image of the workpiece. Light is irradiated into the image capture range of the light detection device by the lighting device 305. The integrated management device 200 determines whether the workpiece is good or bad based on the image data from the edge device 300. The robot 306 removes any workpieces determined to be defective from the production line.

When inspecting workpieces, various conditions are attached to each component, such as the operating speed of the production line 600, the lighting intensity, angle, and color temperature of the lighting device 305, and the range of motion, operating angle, and angular velocity of the robot 306. At least one of these conditions is managed by the integrated management device 200. When distributing a trained model from the integrated management device 200 to the edge device 300, these conditions are also distributed in addition to the imaging conditions, allowing for accurate imaging. Furthermore, by uniformly managing the range of motion, operating speed, etc. of the robot, it is possible to reduce dead time in the workpiece inspection process.

The features described in embodiments 1 to 5 above can be combined as appropriate.

Furthermore, it is possible to adopt embodiment 1, in which the same workpiece is inspected by multiple edge devices during a specified period, and embodiment 2, in which different workpieces are inspected by each edge device during other periods. In other words, each edge device does not always inspect the same workpiece, but rather can change the workpieces and conditions selected as appropriate depending on the period.

Furthermore, in the above-described first to fifth embodiments, it has been described that the light detection device 301 is an image sensor and the integrated management device 200 manages the trained model and imaging conditions, but the conditions are not limited to imaging conditions. Image parameters such as those in FIG. 7 may also be managed in association with the trained model. Furthermore, if the light detection device 301 is a distance measurement sensor, conditions such as the pulse interval for measuring distance can be distributed to the trained model.

200 Integrated management device 300 Edge device

Claims (12)

a first edge device, a second edge device, and an integrated management device that manages the first edge device and the second edge device;
the first edge device and the second edge device include a light detection device;
the integrated management device manages a first trained model and first imaging conditions that set conditions of a light detection device used to generate the first trained model in a first container in association with each other;
the first imaging condition is at least one of an exposure time, a gain, an ISO sensitivity setting, an F-number setting, whether or not a high dynamic range is used, and an adjustment of a white balance ;
The system, wherein the first container is delivered to the first edge device or the second edge device . The system described in claim 1, characterized in that the integrated management device further manages a second trained model in association with second imaging conditions used when generating the second trained model. The first trained model and the second trained model are trained models based on the same object,
3. The system according to claim 2 , wherein the first imaging condition and the second imaging condition are different imaging conditions. The first trained model and the second trained model are trained models based on different objects,
3. The system according to claim 2 , wherein the first imaging condition and the second imaging condition are the same imaging condition. The first trained model and the second trained model are trained models based on different objects,
3. The system according to claim 2 , wherein the first imaging condition and the second imaging condition are different imaging conditions. the first container is delivered from the integrated management device to the first edge device;
The system described in any one of claims 3 to 5 , characterized in that a second container managing the second trained model and the second imaging conditions is delivered from the integrated management device to the second edge device. the light detection device is an image sensor,
The system according to any one of claims 1 to 6 , wherein the first trained model is generated based on an image obtained from the image sensor of the first edge device. The system of any one of claims 1 to 7 , wherein the first container does not include a machine learning library. the integrated management device includes a learning execution unit,
The system according to any one of claims 1 to 8, characterized in that an image obtained from the first edge device is sent to the learning execution unit, and the first trained model is generated in the learning execution unit. the integrated management device includes a first database and a second database;
The first database manages a plurality of trained models including the first trained model and the second trained model;
7. The system according to claim 2 , wherein the second database manages a plurality of conditions including the first imaging condition and the second imaging condition. The system includes a production line;
11. The system according to claim 1, wherein the first imaging condition includes an operating speed of the production line. the system comprises a robot;
The system of claim 11 , further comprising: moving a workpiece determined to have a defect by the first trained model.