US-12619858-B2 - Processing system, processing method, and processing program

US12619858B2US 12619858 B2US12619858 B2US 12619858B2US-12619858-B2

Abstract

A processing system is performed by using an edge device and a server device, wherein the edge device includes first processing circuitry configured to input divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and cause inference in each of the first models to be executed, and output, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data, and the server device includes second processing circuitry configured to execute inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.

Inventors

Akira Sakamoto
Ichiro MORINAGA
Kyoku SHI
Shohei ENOMOTO
Takeharu EDA

Assignees

NTT, INC.

Dates

Publication Date: 20260505
Application Date: 20201124

Claims (11)

1 . A processing system performed by using an edge device and a server device, wherein the edge device includes: first processing circuitry configured to: input divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and cause inference in each of the first models to be executed; and output, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data, and the server device includes second processing circuitry configured to execute inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.
2 . The processing system according to claim 1 , wherein the first processing circuitry is further configured to: input the divided data divided to the corresponding first model among the plurality of first models, and cause object detection in each of the first models to be executed, and output, to the server device, the divided data determined in the corresponding first model that at least a predetermined object is included, among the plurality of pieces of the divided data.
3 . The processing system according to claim 2 , wherein the first processing circuitry is further configured to output, to the server device, the divided data that includes the predetermined object and in which a certainty factor, which is a degree of certainty that a result of the object detection by the first model is correct, is greater than or equal to a predetermined threshold, among the plurality of pieces of the divided data.
4 . The processing system according to claim 2 , wherein the first processing circuitry is further configured to: perform object detection and moving object detection on the divided data, and output, to the server device, the divided data that includes the predetermined object and in which moving object detection is made, among the plurality of pieces of the divided data.
5 . The processing system according to claim 2 , wherein the second processing circuitry is further configured to integrate inference results for the respective pieces of the divided data and output an integrated inference result as an inference result for the processing data.
6 . The processing system according to claim 2 , wherein the processing data is one image, and the first processing circuitry is further configured to: input each of a plurality of divided images obtained by dividing the one image to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and output, to the server device, the divided images determined in the respective first models that at least a predetermined subject is included, among the plurality of divided images.
7 . The processing system according to claim 2 , wherein the processing data is a plurality of images captured along a time series, and the first processing circuitry is further configured to: input each of the plurality of images to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and output, to the server device, the images determined in the respective first models that at least a predetermined subject is included, among the plurality of images.
8 . The processing system according to claim 2 , wherein the processing data is a plurality of images captured along a time series, and the first processing circuitry is further configured to: input each of the plurality of images to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, select an image recognized in the corresponding first model that at least a predetermined subject is included, among the plurality of images, input each of a plurality of divided images obtained by dividing the image selected to a corresponding first model among the plurality of first models, and cause subject recognition in each of the first models to be executed, and output, to the server device, the divided images determined in the respective first models that at least a predetermined subject is included, among the plurality of divided images.
9 . The processing system according to claim 2 , wherein the first processing circuitry is further configured to respectively encode the pieces of the divided data determined to be output to the server device and output the encoded pieces of the divided data to the server device, and the second processing circuitry is further configured to respectively decode the pieces of the divided data encoded.
10 . A processing method executed by a processing system performed by using an edge device and a server device, the processing method comprising: inputting divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and causing inference in each of the first models to be executed; outputting, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data; and executing inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.
11 . A non-transitory computer-readable recording medium storing therein a processing program that causes a computer to execute a process comprising: inputting divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and causing inference in each of the first models to be executed; outputting only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data; and executing inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a U.S. National Stage Application filed under 35 U.S.C. § 371 claiming priority to International Patent Application No. PCT/JP2020/043564, filed on 24 Nov. 2020, the disclosure of which is hereby incorporated herein by reference in its entirety. TECHNICAL FIELD The present invention relates to a processing system, a processing method, and a processing program. BACKGROUND ART Since a data volume of data collected by an IoT device represented by a sensor is enormous, an enormous communication amount is generated when data collected by cloud computing is aggregated and processed. For this reason, even in an edge device close to a user, attention is focused on edge computing that processes collected data. However, an amount of computation and resources such as a memory of a device used in the edge device are poor as compared with a device other than the edge device, the device being physically and logically disposed farther from the user than the edge device (hereinafter, the device is described as a cloud for convenience). For this reason, when processing with a large computation load is performed by the edge device, it may take a lot of time to complete the processing, or it may also take time to complete other processing with a small amount of computation. Here, one of types of processing with a large amount of computation is processing related to machine learning. Non Patent Literature 1 proposes application of so-called adaptive learning to the edge cloud. That is, in a method described in Non Patent Literature 1, a learned model learned by using general-purpose learning data in a cloud is developed in an edge device, and learning is performed again on the model learned by the cloud by using data acquired by the edge device, whereby operation utilizing advantages of the cloud and the edge device is implemented. CITATION LIST Non Patent Literature Non Patent Literature 1: Okoshi et al., “Proposal and Evaluation of DNN Model Operation Method with Cloud/Edge Collaboration”, Proceedings of the 80th National Convention, 2018(1), 3-4, 2018 Mar. 13. SUMMARY OF INVENTION Technical Problem However, in a case where data size of processing data is large, such as a high-accuracy (high-definition (4K, 8K)) camera image, if all the processing data that cannot be determined on an edge side is transmitted to a cloud side, there has been a problem that a transmission path is pressed, and also on the server side, processing time for the processing data having a large data size becomes long. The present invention has been made in view of the above, and an object thereof is to provide a processing system, a processing method, and a processing program capable of reducing an amount of data transfer from an edge device to a server device and reducing a computation load in the server device. Solution to Problem To solve the above-described problem and achieve the object, a processing system according to the present invention is a processing system performed by using an edge device and a server device, in which the edge device includes: first processing circuitry configured to: input divided data obtained by dividing processing data into a plurality of pieces to a corresponding first model among a plurality of first models, and cause inference in each of the first models to be executed; and output, to the server device, only the divided data for which it is determined that an inference result in the corresponding first model matches a predetermined condition among a plurality of pieces of the divided data, and the server device includes second processing circuitry configured to: execute inference processing on the divided data output from the edge device by using a second model having a higher amount of computation than that of the first model. Advantageous Effects of Invention According to the present invention, it is possible to reduce the amount of data transfer from the edge device to the server device and to reduce the computation load in the server device. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a diagram illustrating an outline of a processing method of a processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of a DNN1 and a DNN2. FIG. 3 is a diagram schematically illustrating an example of a configuration of the processing system according to the embodiment. FIG. 4 is a flowchart illustrating a flow of processing executed by an edge device illustrated in FIG. 3. FIG. 5 is a flowchart illustrating a flow of processing executed by a server device illustrated in FIG. 3. FIG. 6 is a diagram illustrating an outline of a processing method of a processing system according to Modification 1 of the embodiment. FIG. 7 is a diagram illustrating an outline of a processing method in an edge device of a processing system according to Modification 2 of the embodiment. FIG. 8 is a diagram schematically illustrating an example of a configuration