JP7421628B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to facilitate the implementation of countermeasures to prevent an application from being stopped when resource usage of a device becomes tight. [Solution] The information processing device is an information processing device that uses an application to analyze a video imaged by a predetermined imaging means, and provides information about the analysis result. As a judgment, it is determined whether the resource usage exceeds a predetermined threshold, and based on the application operating information, the operating conditions of the application are inferred using a learning model, and when the application stops, the resource usage The operating conditions of the application are set based on the determination result of the determination unit that the value exceeds a predetermined threshold. [Selection diagram] Figure 5

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Imaging devices (e.g., cameras that capture images used for human flow analysis using AI (Artificial Intelligence), etc., for grasping the number of visitors to facilities, monitoring their physical condition, and crime prevention; hereinafter referred to as "imaging devices") A technique has been proposed for analyzing a video image (a still image or a moving image captured by an imaging device, hereinafter referred to as "video") captured by an imaging device (notation) and providing an analysis result.

For example, there are known technologies that use an image analysis application to analyze video captured by an imaging device and send it to a management platform, and image analysis devices that control an image analysis application based on instructions from the management platform ( For example, see Patent Document 1).

JP2022-121295A

However, in the above-mentioned conventional technology, it may be difficult to take measures to prevent the application from stopping when the resource usage of the device becomes tight.

For example, in the conventional technology, when the resource usage of an image analysis device becomes tight, the operation of an application may stop. However, in the conventional technology, even when resource usage becomes tight, it may be difficult for an administrator or the like to determine in which module (for example, an application module, etc.) the consumed resource usage is increasing. Furthermore, even if a module that is a bottleneck in resource usage is identified through operations by an administrator, etc., the administrator can implement resource usage control settings for the target module based on an appropriate timing and method. was sometimes difficult.

In order to solve the above problems and achieve the purpose, an information processing device of the present invention provides information processing that analyzes a video imaged by a predetermined imaging means using an application, and provides information about the result of the analysis. The apparatus includes: a determination unit that determines whether resource usage exceeds a predetermined threshold as a predetermined determination based on operating information of the application; and a determination unit that uses a learning model based on the operating information of the application. an inference unit that infers the operating conditions of the application; and a setting that sets the operating conditions of the application based on a determination result of the determination unit that the resource usage exceeds the predetermined threshold when the application is stopped. It is characterized by comprising: and.

Advantageous Effects of Invention According to the present invention, it is possible to easily take measures to prevent an application from stopping when the resource usage of a device becomes tight.

FIG. 1 is a diagram showing an overview of an image analysis system according to this embodiment. FIG. 2 is a diagram illustrating an example of a system configuration of an information processing apparatus according to the base technology of this embodiment. FIG. 3 is a diagram showing an overview of application operation related to the underlying technology of this embodiment. FIG. 4 is a diagram showing an overview of information processing according to the first embodiment. FIG. 5 is a diagram showing an example of the device configuration of the image analysis system according to the first embodiment. FIG. 6 is a diagram showing an overview of the image analysis technology (object detection) related to the base technology of this embodiment. FIG. 7 is a diagram showing an overview of the image analysis technology (object tracking) related to the base technology of this embodiment. FIG. 8 is a diagram showing an overview of information processing according to the second embodiment. FIG. 9 is a diagram showing an example of the device configuration of an image analysis system according to the second embodiment. FIG. 10 is a flowchart illustrating an example of an information processing procedure according to the first embodiment. FIG. 11 is a flowchart illustrating an example of an information processing procedure according to the second embodiment. FIG. 12 is a diagram showing an overview of information processing according to the first modification. FIG. 13 is a diagram showing an overview of information processing according to the second modification. FIG. 14 is a diagram showing an overview of information processing according to the third modification. FIG. 15 is a diagram illustrating a configuration example of an image analysis system according to a modification. FIG. 16 is a flowchart illustrating an example of an information processing procedure according to a modification. FIG. 17 is a diagram illustrating an example of a problem with the conventional technology according to this embodiment. FIG. 18 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to this embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information processing apparatus, an information processing method, and a form for implementing an information processing program (hereinafter referred to as an "embodiment") according to the present invention will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present invention are not limited to this embodiment. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. About the underlying technology]
First, an overview of the image analysis system 1 of this embodiment will be explained using FIG. 1. FIG. 1 is a diagram showing an overview of an image analysis system 1 according to the present embodiment.

As shown in FIG. 1, the image analysis system 1 includes an information processing device 100, an imaging device 200, and an external device 300. The image analysis system 1 is a system in which an application running on the information processing device 100 performs image analysis on a video imaged by the imaging device 200, and provides information on the analysis results.

Note that in this embodiment, the application is defined as an AI application that analyzes a video captured by the imaging device 200 and detects a predetermined event, and the same applies to the following items. Furthermore, the AI application referred to herein is an application that performs human flow analysis (for example, recognition of objects and people, detection of shoplifting, etc.) based on image analysis using AI on captured images.

The information processing device 100 of this embodiment relays between the imaging device 200 and an external device 300 (for example, a cloud server, etc.), as shown in FIG. Specifically, the information processing device 100 uses the network hub 900 to connect the imaging devices 200 (for example, the imaging device 201, the imaging device 202, the imaging device 203, etc.) included in a network configured as a LAN (Local Area Network). management and control ((1) in Figure 1). Note that the number of imaging devices 200 shown in FIG. 1 is not limited.

The information processing device 100 performs a predetermined image analysis on the video imaged by the imaging device 200, and outputs the analysis result to the external device 300 ((2) in FIG. 1). Then, the external device 300 that receives the analysis results output by the information processing device 100 visualizes and displays the analysis results on the terminal device 10 used by the administrator or the like ((3) in FIG. 1).

Next, an overview of the functional system components of the information processing apparatus 100 will be explained using FIG. 2. FIG. 2 is a diagram showing an example of the system configuration of the information processing apparatus 100 according to the base technology of this embodiment. Note that the outline of the system components shown in FIG. 2 is merely an example, and the system configuration is not limited to the described content as long as it can realize the information processing apparatus 100 of this embodiment.

The image analysis system 1 in FIG. 2 includes an information processing device 100, an imaging device 200, and an external device 300. Further, the information processing device 100 is connected to an imaging device 200 and an external device 300 via a predetermined network NW.

The information processing device 100 includes an SoC (System-on-a-Chip) in which a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), etc. are implemented, and an OS (Operating System). . Further, the information processing device 100 includes a Web UI, a DM service, a CM service, a container engine (eg, Moby Engine, etc.), and an IoT edge computing service (eg, Azure IoT Edge, etc.).

The information processing apparatus 100 operates a Device Management Module, a Camera Management Module, and an AI Application Module (for example, an AI application module for image analysis of video) based on the above-mentioned container engine. Note that the AI Application Module is composed of an application and an SDK (Software Development Kit). Further, the information processing device 100 can be operated without limiting the number of containers to be operated based on the container engine.

Next, an overview of the applications running on the information processing device 100 will be explained using FIG. 3. FIG. 3 is a diagram showing an overview of application operation related to the underlying technology of this embodiment. Note that the image analysis system 1 in FIG. 3 has a configuration including an information processing device 100, an imaging device 200, and an external device 300.

The information processing device 100 acquires images from imaging devices (for example, the imaging device 201, the imaging device 202, the imaging device 203, etc.) via the Camera Management Module ((1) in FIG. 3). Note that the number of imaging devices 200 in the image analysis system 1 is not limited.

Next, the applications (application 201A, application 202A, application 203A) running for each module (module 201a, module 202a, module 203a) perform image analysis using the acquired video ((2) in FIG. 3). ). Note that the number of modules and applications that operate in the information processing device 100 is not limited.

The information processing device 100 outputs the results of the image analysis performed by the application to the external device 300 ((3) in FIG. 3). The external device 300 visualizes and displays the image analysis results output by the information processing device 100 on a terminal device such as an administrator (for example, a terminal device 10A, a terminal device 10B, a terminal device 10C, etc.). ((4) in Figure 3). Note that the number of terminal devices 10 on which the external device 300 displays the results is not limited.

[2. First embodiment]
From here, a first embodiment realized by the image analysis system 1 of this embodiment will be described. The first embodiment is an embodiment in which application operating conditions inferred using a learning model that is trained based on information regarding resource usage of the information processing apparatus 100 are set for each application operating status. Note that the first embodiment and the second embodiment and modified examples described below may be implemented individually or in combination.

[2-1. Overview of first embodiment]
Next, an overview of the first embodiment will be described using FIG. 4. FIG. 4 is a diagram showing an overview of information processing according to the first embodiment.

The information processing apparatus 100 in FIG. 4 runs an application 201A, an application 202A, and an application 203A. Note that the other system configurations included in the information processing apparatus 100 are the same as those described in FIG. 2, and will therefore be omitted.

Further, in the example of FIG. 4, the application 201A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 201. Further, the application 202A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 202. Further, the application 203A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 203.

First, the information processing device 100 collects application operation information ((1) in FIG. 4). The application operating information referred to here includes information regarding resource usage for each container (module) (for example, CPU usage rate, GPU usage rate, memory usage rate, etc.) and information regarding the operating status of the application. Further, the operation information of the application may also include information related to modules other than the application (for example, DM Module, CM Module, etc.).

For example, as shown in FIG. 4, the resource usage of the information processing apparatus 100 is 20% for the CM Module, 60% for the application 202A, and 20% for the application 203A. On the other hand, the application 201A is stopped because its resource usage exceeds a predetermined threshold.

The information processing apparatus 100 performs predetermined determination and inference using the collected application operation information. First, as a predetermined determination, the information processing apparatus 100 determines whether or not the stoppage is due to the resource usage of the application exceeding a threshold value, based on the operation information of the application. For example, the information processing apparatus 100 in FIG. 4 determines that the application 201A has stopped operating (eg, image analysis, etc.) because the resource usage amount of the application 201A exceeds the threshold ((2) in FIG. 4).

Next, the information processing apparatus 100 infers the operating conditions of the application based on a learning model that inputs the operating information of the application as a predetermined inference. The information processing apparatus 100 sets the inferred application operating conditions for the application 201A based on the above-described determination result, and then restarts the application 201A ((3) in FIG. 4).

On the other hand, the information processing apparatus 100 determines that the resource usage amount of the application 202A exceeds a predetermined reference value ((4) in FIG. 4). In that case, the information processing apparatus 100 sets the inferred application operating conditions for the application 202A ((5) in FIG. 4).

Up to this point, the explanation has been given on the premise that the information processing device 100 performs inference on the operating conditions of the application, but the external device 300 may perform the inference instead of the information processing device 100. In that case, the information processing device 100 transmits the collected application operating information to the external device 300 ((6) in FIG. 4).

The external device 300 infers the operating conditions of the application as a predetermined inference based on a learning model that receives as input the operating information of the application included in the operating information of the application transmitted by the information processing device 100 . Note that the external device 300 may perform inference using application operation information provided by a plurality of information processing devices 100 (information processing device 100A, information processing device 100B, etc.) (see (7) in FIG. 4). )).

The information processing device 100 acquires the operating conditions of the application inferred by the external device 300 from the external device 300 ((8) in FIG. 4). The information processing apparatus 100 then performs the same process as (3) or (5) above.

[2-2. Image analysis system configuration]
From here, the image analysis system 1 according to the first embodiment will be described. FIG. 5 is a diagram showing an example of the device configuration of the image analysis system 1 according to the first embodiment. As shown in FIG. 5, the image analysis system 1 has a configuration in which an information processing device 100, an imaging device 200, and an information processing device 100 and an external device 300 are each connected via a predetermined network NW. Note that the number of imaging devices 200 included in the image analysis system 1 is not limited, and a plurality of imaging devices 200 may be included.

[2-2-1. Configuration of information processing device]
Next, a configuration example of the information processing device 100 included in the image analysis system 1 according to the first embodiment will be described. The information processing device 100 uses an application to analyze (image analysis) a video imaged by a predetermined imaging means (imaging device 200), and provides information about the results of the analysis (image analysis). As shown in FIG. 5, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130.

(About communication department 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network NW by wire or wirelessly, and transmits and receives information between the information processing device 100 and the imaging device 200, and between the information processing device 100 and the external device 300, for example.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. Furthermore, the storage section 120 includes an operation information storage section 121.

(About the operating information storage unit 121)
The operating information storage unit 121 stores operating information of applications. Note that although it is written as "of the application," it may also include information about the OS and modules.

Specifically, the operating information storage unit 121 stores the processing FPS 121a, camera setting values 121b, resource usage 121c, and operating status as application operating information used for inference of application operating conditions by the inference unit 134, which will be described later. 121d.

(About processing FPS121a)
The processing FPS 121a is information related to FPS (Frame per second) indicating the number of images processed (image analysis) per unit time by the application. Note that the processing FPS 121a is a general index of application detection accuracy that can be calculated in real time in the execution environment.

Here, "object detection" related to the processing FPS 121a will be explained using FIG. 6. FIG. 6 is a diagram showing an overview of the image analysis technology (object detection) related to the base technology of this embodiment. Object detection is a process of recognizing an object included in the field of view of the imaging device 200 based on image analysis by an application. In this object detection, the object detection accuracy is improved by using the model 11a, which is larger than the model 11b, for image analysis, but on the other hand, the processing time increases.

Next, "object tracking" related to the processing FPS 121a will be explained using FIG. 7. FIG. 7 is a diagram showing an overview of the image analysis technology (object tracking) related to the base technology of this embodiment. Object tracking is a process of tracking an object moving within the field of view (detection range) of the imaging device 200 based on the object detection process described above.

The imaging device 200 in FIG. 7 tracks a moving object (in the case of FIG. 7, the person 12) that has entered the field of view of the imaging device 200. For example, the imaging device 200 does not track the persons 12a and 12d outside the field of view, but tracks the persons 12b and 12c included within the field of view. However, in object tracking, as processing time for object detection increases, undetectable frames occur and detection accuracy decreases. Therefore, the imaging device 200 does not track the person 12c that is also included in the field of view.

As mentioned above, in event detection based on image analysis by an application, "frame processing" affects detection accuracy, so "processing FPS", which is an index of frame processing speed, is the performance required by the application. serves as an indicator. Note that the object detection and object tracking described with reference to FIGS. 6 and 7 are basic technologies used in the first embodiment, second embodiment, and modified example below.

(About camera setting value 121b)
Here, we return to FIG. 5 and continue the explanation. The camera setting value 121b is information regarding the imaging conditions of the imaging device 200. For example, the camera setting values 121b may include imaging setting items such as codec, bit rate, and resolution. Note that the operation information storage unit 121 is not limited to the above-mentioned items, and can store any information included in the category of information related to camera setting values as the camera setting value 121b.

(Regarding resource usage 121c)
The resource usage amount 121c is information regarding the resource usage amount of the information processing device 100. For example, the resource usage amount 121c may include a CPU usage rate, a GPU usage rate, a memory usage rate, and the like. Note that the operation information storage unit 121 is not limited to the usage rates described above, and can store any information that falls within the category of information related to resource usage.

(Regarding operating status 121d)
The operating status 121d is information regarding the operating status of an application running on the information processing device 100. For example, the operating status 121d may include information regarding whether the application is operating normally, whether the resource usage exceeds a predetermined threshold and has stopped, and the like. Note that the operating information storage unit 121 is not limited to applications, and may store information regarding the operating status of each OS or module as the operating status 121d.

(About the control unit 130)
The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the information processing device 100 using the RAM as a work area. . Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 130 shown in FIG. 5 includes a collection unit 131, a transmission unit 132, a determination unit 133, an inference unit 134, an acquisition unit 135, and a setting unit 136.

(About the collection unit 131)
The collection unit 131 collects operation information of applications of the information processing device 100. Specifically, the operation information of the application collected by the collection unit 131 includes the processing FPS 121a, camera setting values 121b, resource usage 121c, and operation status 121d. Note that the collection unit 131 is not limited to the above-mentioned information, and can store any information that falls within the category of application operating information.

(About the transmitter 132)
The transmitter 132 transmits the application operating information collected by the collector 131 to a predetermined external device 300. For example, the transmitting unit 132 transmits one or more combinations of the processing FPS 121a, camera setting values 121b, resource usage 121c, and operating status 121d collected by the collecting unit 131 to an external source as application operating information. It can be transmitted to the device 300. Note that the transmitting unit 132 can transmit any information to the external device 300 without limitation as long as it is included in the category of information related to application operating information.

(About the determination unit 133)
The determining unit 133 determines, as a predetermined determination, whether the resource usage exceeds a predetermined threshold based on the resource usage 121c and the operating status 121d included in the application operating information. For example, when the target application exceeds a predetermined threshold of CPU usage rate or memory usage rate and stops, the determination unit 133 may determine that the target application has stopped due to excessive resource usage.

(About the inference unit 134)
The inference unit 134 infers the operating conditions of the application based on the application operating information collected by the collection unit 131 using the learning model. The operating conditions for an application here refer to the amount of usable resources that can be allocated to modules for each application, and include the upper limit of CPU usage rate, upper limit of memory usage rate, etc. that are set when creating the container in which the application runs. It's fine. Note that the inference unit 134 can use any model as the above-mentioned learning model without limitation as long as it is included in the category of learning models of machine learning.

For example, the inference unit 134 uses a learning model that receives as input one or more combinations of the processing FPS 121a, the camera setting value 121b, and the resource usage amount 121c included in the operation information of the application to determine the operation of the application. Can infer conditions.

(About the acquisition unit 135)
The acquisition unit 135 acquires predetermined information from the external device 300 when the external device 300 infers information regarding the operating conditions of the application using the operating information of the application. Specifically, the acquisition unit 135 acquires, from the external device 300, the operating conditions of the application inferred by the inference unit 332 of the external device 300, which will be described later, based on the application operating information transmitted by the transmitting unit 132.

(About the setting section 136)
When the application is stopped, the setting unit 136 sets operating conditions for the application based on the determination result of the determination unit 133 that the amount of resource usage exceeds a predetermined threshold. For example, when the determining unit 133 determines that the application has been stopped due to an excess of resources, the setting unit 136 sets the operating conditions for the application inferred by the inference unit 134 when creating a container for the stopped application, and restarts the application. You can go.

On the other hand, the setting unit 136 sets operating conditions for the application acquired from the external device 300 based on the determination result of the determining unit 133. Specifically, the setting unit 136 may set the operating conditions of the application when creating a container related to the stopped application, based on the operating conditions of the application inferred by the inference unit 332 of the external device 300, which will be described later.

Note that the "predetermined threshold" here may be a preset upper limit of resource usage, or a limit of resource usage that dynamically changes depending on the operating status of the information processing device 100. It may be possible, and there are no particular limitations.

Furthermore, the setting unit 136 may set application operating conditions even for applications that are not stopped. For example, the setting unit 136 may set operating conditions for an application that includes a condition for suppressing resource usage for an application that continues to operate but uses a high amount of resources.

[2-2-2. Configuration of imaging device]
Next, the imaging device 200 included in the image analysis system 1 according to the first embodiment will be described. The imaging device 200 captures images used for image analysis by an application running on the information processing device 100. As shown in FIG. 5, the imaging device 200 includes a communication section 210, a storage section 220, and a control section 230.

(About communication department 210)
The communication unit 210 is realized by, for example, a NIC or the like. The communication unit 210 is connected to the network NW by wire or wirelessly, and transmits and receives information between the information processing device 100 and the imaging device 200, for example.

(About storage unit 220)
The storage unit 220 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 220 stores processing programs, data, and the like for the control unit 230 to realize the functions of the imaging device 200.

(About the control unit 230)
The control unit 230 is realized by the CPU, MPU, or the like executing various programs stored in the storage device inside the imaging device 200 using the RAM as a work area. Then, the control unit 230 executes processing for the imaging device 200 to realize a predetermined function.

[2-2-3. External device configuration]
Next, the external device 300 included in the image analysis system 1 according to the first embodiment will be explained. As shown in FIG. 5, external device 300 includes a communication section 310, a storage section 320, and a control section 330.

(About communication department 310)
The communication unit 310 is realized by, for example, a NIC or the like. The communication unit 310 is connected to the network NW by wire or wirelessly, and transmits and receives information between the information processing device 100 and the external device 300, for example.

(About storage unit 320)
The storage unit 320 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. Furthermore, the storage section 320 includes an operation information storage section 321.

(About the operating information storage unit 321)
The operating information storage unit 321 stores the operating information of the application transmitted by the transmitting unit 132 of the information processing device 100. Specifically, the operating information storage unit 321 stores a processing FPS 321a, a camera setting value 321b, a resource usage amount 321c, and an operating status 321d as operating information of the application.

(About processing FPS321a)
The processing FPS 321a is information regarding FPS indicating the number of images that the application processes (image analysis) per unit time. Note that the operating information storage unit 321 stores the processing FPS 121a stored by the information processing apparatus 100 as the processing FPS 321a as application operating information.

(About camera setting value 321b)
The camera setting value 321b is information regarding the imaging conditions of the imaging device 200. Note that the operating information storage unit 321 stores the camera setting value 121b stored by the information processing apparatus 100 as the camera setting value 321b as the operating information of the application.

(Regarding resource usage 321c)
The resource usage amount 321c is information regarding the resource usage amount of the information processing device 100. Note that the performance information storage unit 321 stores the resource usage amount 121c stored by the information processing device 100 as the resource usage amount 321c as the application performance information.

(About operating status 321d)
The operating status 321d is information regarding the operating status of an application running on the information processing device 100. Note that the operation information storage unit 321 stores the operation status 121d of the information processing device 100 as the operation status 321d as the operation information of the application.

(About the control unit 330)
The control unit 330 is realized by a CPU, an MPU, or the like executing various programs stored in a storage device inside the external device 300 using the RAM as a work area. Further, the control unit 330 is realized by, for example, an integrated circuit such as an ASIC or an FPGA. Further, the control unit 330 includes a reception unit 331 and an inference unit 332.

(About reception department 331)
The receiving unit 331 receives operating information of applications running on the information processing device 100. Note that the accepting unit 331 may accept data transmitted by the transmitting unit 132, or may accept data directly input by an administrator of the external device 300 or the like.

(About the inference unit 332)
The inference unit 332 uses a predetermined learning model to infer the operating conditions of the application based on the application operating information received by the receiving unit 331. Note that the inference unit 332 can use any model as the above-mentioned learning model without limitation as long as it is included in the category of learning models of machine learning.

[3. Second embodiment]
From here, a second embodiment realized by the information processing apparatus 100 of this embodiment will be described. In the second embodiment, when the resource usage of an application exceeds a predetermined threshold, information for suppressing the resource usage is output to an external device 300, and information is sent to an administrator etc. via the external device 300. This is an embodiment in which the screen is displayed on the screen. Note that the second embodiment, the first embodiment, and modifications described below may be implemented individually or in combination.

[3-1. Overview of second embodiment]
Next, an overview of the second embodiment will be described using FIG. 8. FIG. 8 is a diagram showing an overview of information processing according to the second embodiment.

The information processing apparatus 100 in FIG. 8 runs an application 201A, an application 202A, and an application 203A. Note that the other system configurations included in the information processing apparatus 100 are the same as those described in FIG. 2, and will therefore be omitted.

Further, in the example of FIG. 8, the application 201A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 201. Further, the application 202A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 202. Further, the application 203A of the information processing device 100 performs image analysis based on the video imaged by the imaging device 203.

The information processing device 100 collects application operating information. Specifically, the information processing device 100 collects information (for example, CPU usage rate, GPU usage rate, memory usage rate, etc.) regarding the resource usage of each container (module) ((1) in FIG. 8). . Note that the resource usage of the information processing apparatus 100 in FIG. 8 is 20% for the CM Module, 60% for the application 201A, 10% for the application 202A, and 10% for the application 203A.

The information processing apparatus 100 performs a predetermined determination using the collected application operation information. Specifically, the information processing apparatus 100 determines whether the resource usage amount of the application included in the application operating information exceeds a predetermined threshold set in advance. For example, if the predetermined threshold is set as "30% resource usage," the information processing apparatus 100 determines that the resource usage of the application 201A is "60%" and therefore exceeds the resource usage threshold. can.

The information processing device 100 outputs information regarding suppression of the resource usage of the application to the external device 300 based on the above-described determination result ((2) in FIG. 8).

For example, when operating the application 201A normally, the information processing device 100 outputs the first proposal information. As a specific example, the information processing apparatus 100 may output proposal information to stop the application 202A and the application 203A. Furthermore, when the application 201A is operated normally, the information processing apparatus 100 may output suggestion information to adjust the camera settings of the application 201A (for example, change to a lower resolution, etc.).

On the other hand, when operating the application 202A and the application 202A normally, the information processing apparatus 100 outputs the second proposal information. As a specific example, the information processing apparatus 100 may output suggestion information to stop the application 201A. Further, the information processing apparatus 100 outputs proposal information to adjust the camera setting values of the application 202A and the application 202A (for example, change to a lower resolution, etc.) when the application 202A and the application 202A are to operate normally. It's fine.

The external device 300 receives information regarding the suppression of resource usage output from the information processing device 100, and displays it on the terminal device 10 of the administrator or the like ((3) in FIG. 8). For example, in the example shown in FIG. 8, the external device 300 displays the first proposal information ((4) in FIG. 8) and the second proposal information ((5) in FIG. 8) on the terminal device 10 of the administrator, etc. do. Note that the first proposal information and the second proposal information described above are just examples, and the information regarding the suppression of resource usage output by the information processing device 100 and further displayed by the external device 300 may vary depending on the content and number. There are no particular limitations on this.

[3-2. Image analysis system configuration]
From here, the image analysis system 1 according to the second embodiment will be described. FIG. 9 is a diagram showing an example of the device configuration of an image analysis system according to the second embodiment. As shown in FIG. 9, the image analysis system 1 has a configuration in which an information processing device 100, an imaging device 200, and an information processing device 100 and an external device 300 are connected via a predetermined network NW.

[3-2-1. Configuration of information processing device]
Next, the information processing device 100 included in the image analysis system 1 according to the second embodiment will be described. As shown in FIG. 9, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130. Note that descriptions of functional units having the same functions as those in the first embodiment will be omitted.

(About storage unit 120)
The storage unit 120 according to the second embodiment includes an operation information storage unit 121 and a resource usage threshold storage unit 122.

(About the operating information storage unit 121)
The performance information storage unit 121 according to the second embodiment stores, as application performance information, a resource usage amount 121c used for a predetermined determination by the determination unit 133, which will be described later.

(Regarding resource usage 121c)
The resource usage amount 121c is information regarding the resource usage amount of the information processing device 100. For example, the resource usage amount 121c may include a CPU usage rate, a GPU usage rate, a memory usage rate, and the like. Note that the operation information storage unit 121 is not limited to the usage rates described above, and can store any information that falls within the category of information related to resource usage.

(Regarding the resource usage threshold storage unit 122)
The resource usage threshold storage unit 122 stores information regarding the resource usage threshold of an application. For example, the resource usage threshold storage unit 122 can store a CPU usage rate threshold 122a, a GPU usage rate threshold 122b, and a memory usage rate threshold 122c, which are used for a predetermined determination by the determination unit 133, which will be described later.

(Regarding CPU usage rate threshold 122a)
The CPU usage rate threshold 122a is a threshold value set in advance for the CPU usage rate of each application running on the information processing device 100. For example, the CPU usage rate threshold 122a may include information such as "30%" as a value of the CPU usage rate threshold. Note that the CPU usage rate threshold 122a is not limited to the value of the CPU usage rate threshold described above, and can be set to a value as required.

(About GPU usage rate threshold 122b)
The GPU usage rate threshold 122b is a threshold value set in advance for the GPU usage rate of each application running on the information processing device 100. For example, the GPU usage rate threshold 122b may include information such as "30%" as a value of the GPU usage rate threshold. Note that the GPU usage rate threshold 122b is not limited to the value of the GPU usage rate threshold described above, and can be set to a value as required.

(Regarding memory usage threshold 122c)
The memory usage rate threshold 122c is a threshold value set in advance for the memory usage rate of each application running on the information processing device 100. For example, the memory usage rate threshold 122c may include information such as "30%" as a value of the memory usage rate threshold. Note that the memory usage rate threshold 122c is not limited to the value of the memory usage rate threshold described above, and can be set to a value as required.

(About the control unit 130)
The control unit 130 according to the second embodiment includes a collection unit 131, a determination unit 133, and an output unit 137.

(About the collection unit 131)
The collection unit 131 according to the second embodiment collects the resource usage amount 121c of the information processing device 100 as application operation information. For example, the collection unit 131 can collect CPU usage rate, GPU usage rate, memory usage rate, etc. as the resource usage amount 121c described above. Note that the collection unit 131 is not limited to the usage rates described above, and can store any information that is included in the category of information related to resource usage.

(About the determination unit 133)
The determining unit 133 according to the second embodiment determines, as a predetermined determination, whether the resource usage of the application exceeds a predetermined threshold, based on the operation information of the application collected by the collecting unit 131. For example, the determination unit 133 can determine that the CPU usage rate of the target application exceeds the predetermined threshold value based on the preset CPU usage rate threshold value of "30%". .

Note that the determining unit 133 may determine whether or not a predetermined threshold value has been exceeded, based not only on the determination result regarding the CPU usage rate described above but also on information regarding the GPU usage rate, memory usage rate, and the like.

(About the output section 137)
The output unit 137 outputs information regarding suppression of resource usage to the external device 300 when the determination unit 133 determines that the resource usage exceeds the threshold. Specifically, when the determination unit 133 determines that the CPU usage rate of the target application exceeds the threshold, the output unit 137 determines the resource usage, such as stopping other applications or changing the settings of the application. information regarding the suppression of can be output to the external device 300.

Note that the output unit 137 may output information regarding suppression of resource usage to the external device 300 based not only on the determination results regarding the CPU usage rate described above but also on the determination results regarding the GPU usage rate, memory usage rate, etc. .

[3-2-2. Configuration of imaging device]
Next, the imaging device 200 included in the image analysis system 1 according to the second embodiment will be described. The imaging device 200 captures images used for image analysis by an application running on the information processing device 100. As shown in FIG. 9, the imaging device 200 includes a communication section 210, a storage section 220, and a control section 230. Note that since the imaging device 200 of the second embodiment has the same functions as the imaging device 200 of the first embodiment, a detailed description of each functional unit will be omitted.

[3-2-3. External device configuration]
Next, the external device 300 included in the image analysis system 1 according to the second embodiment will be explained. FIG. 9 is a diagram showing a configuration example of an external device 300 according to the second embodiment. As shown in FIG. 9, external device 300 includes a communication section 310, a storage section 320, and a control section 330. Note that descriptions of functional units having the same functions as those in the first embodiment will be omitted.

(About storage unit 320)
The storage unit 320 according to the second embodiment stores processing programs, data, etc. for the control unit 330 to realize the functions of the external device 300.

(About the control unit 330)
The control unit 330 according to the second embodiment includes a display unit 333.

(About the display section 333)
The display unit 333 displays information related to resource usage suppression output from the information processing device 100. For example, when the display unit 333 receives information regarding the above-mentioned resource usage reduction from the information processing device 100, it can display the information on the terminal device 10 of the administrator or the like.

Note that the display unit 333 may display information regarding suppression of resource usage based not only on the determination results regarding the CPU usage rate described above but also on the determination results regarding the GPU usage rate, memory usage rate, and the like. Furthermore, the display unit 333 is not limited to information regarding the suppression of resource usage, and can display other information such as suggestion information for suppressing resource usage on the terminal device 10 as needed.

[4. Processing procedure]
From here, a procedure for information processing by the information processing apparatus 100 according to the present embodiment will be described. Note that since the embodiments are divided into a first embodiment and a second embodiment, flowcharts showing processing procedures will also be described for each embodiment. Note that each step described below may be executed in a different order, or some processing may be omitted. Furthermore, the processing procedures of the first embodiment, the second embodiment, and the modified examples described below may be combined as appropriate.

(First embodiment)
FIG. 10 is a flowchart illustrating an example of an information processing procedure according to the first embodiment. First, the collection unit 131 collects application operating information (step S101). The determining unit 133 determines that the application is stopped because the application exceeds a predetermined resource usage threshold based on the application operation information collected by the collecting unit 131 (Yes in step S102).

Further, if the external device 300 does not perform inference (No in step S103), the inference unit 134 of the information processing device 100 infers the operating conditions of the application using the operating information of the application (step S104).

On the other hand, if the external device 300 performs the inference (Yes in step S103), the transmitter 132 transmits the operation information of the application to the external device 300 (step S105). The inference unit 332 of the external device 300 infers the operating conditions of the application based on the application operating information received by the receiving unit 331 (step S106). The acquisition unit 135 acquires the operating conditions of the application inferred by the inference unit 332 of the external device 300 from the external device 300 (step S107).

Next, the setting unit 136 sets the operating conditions of the application inferred by the inference unit 134 of the information processing device 100 or the inference unit 332 of the external device 300 to the container in which the corresponding application is running (step S108), and executes the process. finish.

On the other hand, the determination unit 133 determines that the application is not stopped due to exceeding a predetermined resource usage threshold based on the application operation information collected by the collection unit 131 (No in step S102). In that case, the process is finished.

(Second embodiment)
FIG. 11 is a flowchart illustrating an example of an information processing procedure according to the second embodiment. First, the collection unit 131 collects application operating information (step S201). The determining unit 133 determines whether the resource usage of the application exceeds a predetermined threshold based on the application operating information collected by the collecting unit 131 (step S202).

Here, the determination unit 133 determines that the amount of resources used by the application exceeds a predetermined threshold (Yes in step S202). In that case, the output unit 137 outputs information related to suppressing the resource usage of the application to the external device 300 (step S203). The display unit 333 displays on the terminal device 10 the information related to suppressing the resource usage of the application outputted by the output unit 137 (step S204), and the process ends.

On the other hand, the determination unit 133 determines that the resource usage amount of the application does not exceed the predetermined threshold (No in step S203). In that case, the process is finished.

[5. Modified example]
From here, a modification realized by the information processing apparatus 100 of this embodiment will be explained. A modified example is an embodiment in which the operation of the application, or the application or device is stopped based on preset conditions.

The modified examples include "first modified example: stopping application inference based on application priority", "second modified example: stopping application or module based on application priority", and "third modified example: stopping application or module inference based on application priority". Modified example: Stopping the target camera based on camera priority. Note that each of the modified examples may be implemented alone, or a plurality of modified examples may be implemented in combination. Further, the embodiment according to the modification may be implemented in combination with the first embodiment or the second embodiment described above.

[5-1. Overview of modified examples]
Here, an outline of the modified example will be explained. A modified example is an embodiment in which inference of the target application or application or module is stopped based on a preset application priority when the resource usage of the application exceeds a predetermined threshold. Furthermore, a modified example is an embodiment in which the camera is stopped based on a preset camera priority when the resource usage amount of the application exceeds a predetermined threshold.

[5-1-1. First modification]
Next, "first modification: stopping application inference based on application priority" will be described using FIG. 12. FIG. 12 is a diagram showing an overview of information processing according to the first modification. Note that the processing of the image analysis system 1 in FIGS. 12 to 14 is the same as that in FIG. 3, and therefore will be omitted.

In the first modification shown in FIG. 12, inference of the target application is stopped based on the preset application priority 123a. Specifically, the information processing apparatus 100 selects the target application based on the information that "Priority A" included in the application priority 123a is "Application 201A" and "Priority B" is "Application 202A, Application 203A". Stop reasoning. For example, the information processing apparatus 100 may stop inference of the application 202A and the application 203A based on the above-described priority.

[5-1-2. Second modification]
Next, "Second Modification: Stopping Application or Module Based on Application Priority" will be described using FIG. 13. FIG. 13 is a diagram showing an overview of information processing according to the second modification.

In the second modification shown in FIG. 13, the target application or the module in which the application is running is stopped based on the preset application priority 123a as in FIG. 12.

Specifically, the information processing device 100 selects the target application or Stop the module. For example, the information processing apparatus 100 may stop the application 202A and the application 203A, or the modules of the application 202A and the application 203A, based on the above-mentioned priorities.

[5-1-3. Third modification]
Next, "Third Modification: Stopping Target Camera Based on Camera Priority" will be described using FIG. 14. FIG. 14 is a diagram showing an overview of information processing according to the third modification.

In the third modification shown in FIG. 14, the target camera (imaging device 200) is stopped based on a preset camera priority 123b. Specifically, in the information processing device 100, "priority A" included in the camera priority 123b is "imaging device 201," "priority B" is "imaging device 202," and "priority C" is "imaging device 201." The target imaging device 200 is stopped based on the information "device 203". For example, the information processing device 100 may stop the imaging device 202 and the imaging device 203 based on the above-mentioned priority.

[5-2. Image analysis system configuration]
Next, an image analysis system 1 according to a modification will be described. FIG. 15 is a diagram showing a configuration example of an image analysis system 1 according to a modification. As shown in FIG. 15, the image analysis system 1 according to the modification has a configuration in which an information processing device 100, an imaging device 200, and an information processing device 100 and an external device 300 are connected via a predetermined network NW. .

[5-2-1. Configuration of information processing device]
Next, the information processing device 100 included in the image analysis system 1 according to a modification will be described. As shown in FIG. 15, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130. Note that the information processing device 100 according to the modified example can be implemented with the same functions as the first embodiment. Therefore, in this section, descriptions of functional units similar to those of the information processing apparatus 100 of the first embodiment will be omitted.

(About storage unit 120)
The storage unit 120 according to the modification includes an operating information storage unit 121, a resource usage threshold storage unit, and an operating condition storage unit 123.

(Regarding the resource usage threshold storage unit 122)
The resource usage threshold storage unit 122 according to the modification stores information regarding the resource usage threshold of an application. For example, the resource usage threshold storage unit 122 can store a CPU usage rate threshold 122a, a GPU usage rate threshold 122b, and a memory usage rate threshold 122c, which are used for a predetermined determination by the determination unit 133, which will be described later. Note that the resource usage threshold storage unit 122 according to the modification has the same functions as in the second embodiment, so a detailed explanation will be omitted.

(About operating condition storage unit 123)
The operating condition storage unit 123 according to the modification stores the priority of each application or camera (imaging device 200) used for determination by the determination unit 133, which will be described later. Specifically, the operating condition storage unit 123 stores an application priority 123a and a camera priority 123b.

(About application priority 123a)
The application priority 123a is information regarding the priority of an application that is set in advance for each application. Note that the priority of each application here refers to the priority of operation, function maintenance, etc. of each application, which is set based on the importance of the function or role.

For example, as shown in FIG. 12, the application priority 123a may include items such as "priority" and "application name."

(About camera priority 123b)
The camera priority 123b is information regarding the camera priority that is set in advance for each camera (imaging device 200). Note that the priority for each camera (imaging device 200) here refers to the priority of operation, function maintenance, etc. for each camera (imaging device 200) that is set based on the importance of function and role.

For example, as shown in FIG. 14, the camera priority 123b may include items such as "priority" and "camera name."

(About the control unit 130)
The control unit 130 according to the modification includes a collection unit 131, a determination unit 133, and a stop unit 138.

(About the determination unit 133)
The determination unit 133 according to the modification determines, based on the operation information of the application collected by the collection unit 131, whether the resource usage amount of the application exceeds a predetermined threshold as a predetermined determination. Note that the determining unit 133 may determine whether or not a predetermined threshold value has been exceeded, based not only on the determination result regarding the CPU usage rate described above but also on information regarding the GPU usage rate, memory usage rate, and the like.

(About the stop part 138)
The stopping unit 138 stops one or more combinations of the application, the module, and the camera based on the determination result of the determining unit 133.

Specifically, when the determination unit 133 determines that the amount of resources used by the application exceeds a predetermined threshold, the suspension unit 138 suspends the inference of the application or the application or module based on the application priority 123a. For example, the stopping unit 138 may stop the inference of the application 202A and the application 203A, or the application or module itself, based on the condition that the priority of the application 201A included in the application priority 123a is “priority A”.

On the other hand, when the determining unit 133 determines that the amount of resources used by the application exceeds the predetermined threshold, the stopping unit 138 stops the target camera (imaging device 200) based on the camera priority 123b. For example, the stopping unit 138 may stop the imaging device 202 and the imaging device 203 themselves based on the condition that the priority of the imaging device 201 included in the camera priority 123b is “priority A”.

[5-2-2. Configuration of imaging device]
Next, the imaging device 200 included in the image analysis system 1 according to a modification will be described. The imaging device 200 of the modified example captures an image used for image analysis by an application running on the information processing device 100. As shown in FIG. 15, the imaging device 200 includes a communication section 210, a storage section 220, and a control section 230. Note that since the imaging device 200 of the modified example has the same functions as the imaging device 200 of the first embodiment, a detailed description of each functional unit will be omitted.

[5-2-3. External device configuration]
Next, the external device 300 included in the image analysis system 1 according to a modification will be described. As shown in FIG. 15, external device 300 includes a communication section 310, a storage section 320, and a control section 330. Note that the external device 300 according to the modified example can be realized with the same functions as the second embodiment except that the external device 300 does not include the display section 333. Therefore, detailed description of the external device 300 will be omitted. Further, when the external device 300 has the same function as the determination unit 133 of the information processing device 100, the external device 300 may perform a predetermined determination process instead of the information processing device 100.

[5-3. Processing procedure of modified example]
From here, the processing procedure of the modified example will be explained. FIG. 16 is a flowchart illustrating an example of an information processing procedure according to a modification. Note that each step described below may be executed in a different order, or some processing may be omitted. Further, the processing procedures of the first embodiment, the second embodiment, and the modified example may be combined as appropriate.

First, the collection unit 131 collects application operating information (step S301). The determining unit 133 determines whether the resource usage of the application exceeds a predetermined threshold based on the application operating information collected by the collecting unit 131 (step S302).

Here, the determination unit 133 determines that the amount of resources used by the application exceeds a predetermined threshold (Yes in step S302). In that case, the stopping unit 138 stops at least one of the target application, module, and camera (step S303), and ends the process.

On the other hand, the determination unit 133 determines that the amount of resources used by the application does not exceed the predetermined threshold (No in step S302). In that case, the process is finished.

[6. effect〕
From here, the effects provided by the information processing device 100 of this embodiment will be explained. First, the problems of the prior art will be supplementarily explained using FIG. 17. FIG. 17 is a diagram illustrating an example of a problem with the conventional technology according to this embodiment.

In FIG. 17, the amount of resources consumed by the CM Module, the application 201A, and the application 203A (13a, 13c, 13d) is increasing. On the other hand, the amount of resources consumed by the application 202A (13b) is decreasing. Therefore, the situation is such that CM Module is "decreased processing FPS (14a)", application 201A and application 203A are "decreased image analysis accuracy (14b, 14d)", and application 202A is "stopped (14c)". .

In this way, even if an event that the administrator, etc. does not want occurs due to a tightening of resource usage due to an increase in the amount of consumed resources, it is possible to determine which module or application is the bottleneck in reducing resource usage. was difficult. In addition, even if a bottleneck module is identified through the operations of an administrator, it may be difficult for the administrator to implement resource usage control settings for the bottleneck module in an appropriate manner and at the appropriate time. was there.

Therefore, the information processing apparatus 100 of the present embodiment uses an application to analyze a video imaged by a predetermined imaging means, and provides information about the result of the analysis. The determination unit 133 of the information processing device 100 determines whether the amount of resource usage exceeds a predetermined threshold value as a predetermined determination based on the operation information of the application. The inference unit 134 of the information processing device 100 uses a learning model to infer the operating conditions of the application based on the operating information of the application. When the application is stopped, the setting unit 136 of the information processing device 100 sets operating conditions for the application based on the determination result of the determination unit 133 that the resource usage exceeds the predetermined threshold.

Thereby, the information processing device 100 provides the effect of facilitating the implementation of countermeasures to prevent the application from being stopped when the resource usage of the device becomes tight. In addition, the information processing device 100 can easily take measures to prevent the application from stopping when the resource usage of the device becomes tight. and create a foundation for technological innovation."

Specifically, the information processing device 100 collects application operating information and provides the information to the administrator, etc., thereby preventing events that the administrator, etc. do not want due to tight resource usage due to an increase in the amount of consumed resources. To provide the effect of making it easy for an administrator, etc. to determine which module or application is causing a bottleneck even when a bottleneck occurs.

Furthermore, the information processing apparatus 100 sets operating conditions for the application, including conditions for suppressing resource usage inferred based on the operating information of the application, in conjunction with the operating status of the application. Thereby, the information processing apparatus 100 provides the effect of making it possible to reduce the resource amount of an application that is a bottleneck in increasing resource usage.

Further, the transmitting unit 132 of the information processing device 100 transmits the collected application operation information to a predetermined external device 300. The inference unit 332 of the external device 300 uses the aforementioned application operating information received from the plurality of information processing devices 100 to infer the operating conditions of the application.

The acquisition unit 135 of the information processing device 100 acquires, from the external device 300, the operating conditions of the application inferred by the external device 300. The setting unit 136 sets operating conditions for the application acquired from the external device 300 based on the determination result of the determination unit 133. Therefore, the information processing device 100 provides the effect that application operating conditions can be set based on more accurate inference results based on the application operating information provided by the plurality of information processing devices 100. .

Furthermore, the determination unit 133 of the information processing device 100 determines whether the amount of resources used by the application exceeds a predetermined threshold. The output unit 137 of the information processing device 100 outputs information regarding suppression of resource usage when the determination unit 133 determines that the resource usage exceeds the threshold. Then, the administrator of the information processing device 100 or the like can change the imaging conditions of the imaging device 200 or the operating conditions of the application based on the output information regarding the suppression of source usage. Therefore, the information processing device 100 provides the effect of facilitating the implementation of countermeasures to prevent the application from stopping when the resource usage of the device becomes tight.

Further, the stopping unit 138 of the information processing device 100 stops one or more combinations of the application, the module, and the camera device based on the determination result of the determining unit 133. Therefore, the information processing device 100 provides the effect of facilitating the implementation of countermeasures to prevent the application from stopping when the resource usage of the device becomes tight.

[7. Hardware configuration]
The information processing device 100 and the imaging device 200 included in the image analysis system 1 described above are realized by, for example, a computer 1000 configured as shown in FIG. 18. The information processing device 100 will be described below as an example. FIG. 18 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to this embodiment. Computer 1000 has CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (communication I/F) 1500, input/output interface (input/output I/F) 1600, and media interface (media I/F) 1700.

CPU 1100 operates based on a program stored in ROM 1300 or HDD 1400, and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs depending on the hardware of the computer 1000, and the like.

HDD 1400 stores programs executed by CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via a predetermined network NW and sends it to CPU 1100, and transmits data generated by CPU 1100 to the other device via predetermined network NW.

The CPU 1100 controls output devices such as a display and printer, and input devices such as a keyboard and mouse via an input/output interface 1600. CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads the program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via a predetermined network NW.

Further, for example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200.

[8. others〕
Further, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed manually. All or part of the process can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the above embodiments can be combined as appropriate within the range that does not conflict with the processing contents.

Some of the embodiments have been described above in detail based on the drawings, but these are merely examples, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the present invention in other forms.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the selection section can be replaced with selection means or selection circuit.

10, 10A, 10B, 10C Terminal device 11a, 11b Model 12, 12a, 12b, 12c, 12d Person 100, 100A, 100B Information processing device 110, 210, 310 Communication unit 120, 220, 320 Storage unit 121 Operation information storage unit 121a, 321a Processing FPS
121b, 321b Camera setting value 121c, 321c Resource usage 122 Resource usage threshold storage 122a CPU usage threshold 122b GPU usage threshold 122c Memory usage threshold 123 Operating condition storage 123a Application priority 123b Camera priority 130, 230 , 330 control unit 131 collection unit 132 transmission unit 133 determination unit 134, 332 inference unit 135 acquisition unit 136 setting unit 137 output unit 138 stop unit 200, 201, 202, 203 imaging device 201a, 202a, 203a module 201A, 202A, 203A Application 300 External device 331 Reception section 333 Display section 900 Network hub 1000 Computer 1100 CPU
1200 RAM
1300 ROM
1400 HDD
1500 Communication interface 1600 Input/output interface 1700 Media interface 1800 Recording medium

Claims (5)

An information processing device that analyzes a video imaged by a predetermined imaging means using an application and provides information about the result of the analysis,
a determination unit that determines, as a predetermined determination, whether the resource usage exceeds a predetermined threshold based on operating information of the application;
an inference unit that uses a learning model to infer operating conditions of the application based on operating information of the application;
a setting unit that sets operating conditions for the application based on a determination result of the determination unit that the resource usage exceeds the predetermined threshold when the application is stopped;
An information processing device comprising: a transmitter that transmits the collected operating information of the application to a predetermined external device;
further comprising: an acquisition unit that acquires the operating conditions of the application inferred by the external device from the external device based on the operating information of the application transmitted by the transmission unit;
The setting unit sets the operating condition of the application acquired from the external device based on the determination result of the determination unit.
The information processing device according to claim 1, characterized in that: further comprising an output unit that outputs information regarding suppression of the resource usage when the determination unit determines that the resource usage exceeds the threshold;
The information processing device according to claim 1, characterized in that: An information processing method for analyzing a video imaged by a predetermined imaging means using an application and providing information about the result of the analysis, the method comprising:
a determination step of determining whether the amount of resource usage exceeds a predetermined threshold as a predetermined determination based on operation information of the application;
an inference step of inferring operating conditions of the application using a learning model based on operating information of the application;
a setting step of setting operating conditions for the application based on a determination result of the determination step that the resource usage exceeds the predetermined threshold when the application is stopped;
An information processing method characterized by comprising: An information processing program that uses an application to analyze a video imaged by a predetermined imaging means and provides information on the results of the analysis,
a determination procedure of determining whether the amount of resource usage exceeds a predetermined threshold as a predetermined determination based on operating information of the application;
an inference procedure for inferring operating conditions of the application using a learning model based on operating information of the application;
a setting step of setting operating conditions for the application based on a determination result of the determination step that the resource usage exceeds the predetermined threshold when the application is stopped;
An information processing program comprising:

Images