US 12,469,258 B2
Inference processing system in which server and edge device cooperate to perform computation, server, edge device, and control method thereof, and storage medium
Hiroshi Kaneko, Kanagawa (JP); Dai Miyauchi, Chiba (JP); and Ryo Ishikawa, Tokyo (JP)
Assigned to CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Feb. 6, 2023, as Appl. No. 18/164,719.
Claims priority of application No. 2022-029809 (JP), filed on Feb. 28, 2022.
Prior Publication US 2023/0274530 A1, Aug. 31, 2023
Int. Cl. G06V 10/77 (2022.01); G06N 5/04 (2023.01)
CPC G06V 10/7715 (2022.01) [G06N 5/04 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An inference processing system that performs, by a server and an edge device, computation of an inference model including an input layer, L intermediate layers, and an output layer,
wherein the inference processing system comprises:
at least one processor; and
at least one memory having stored thereon instructions which, when executed by the at least one processor, cause the inference processing system at least to:
set, by the server, a server-side inference model that is the same as the inference model;
communicate, by the server, data with the edge device;
set, by the edge device, an edge-side inference model including the input layer and first to n-th (L>n>1) intermediate layers among the L intermediate layers;
communicate, by the edge device, data with the server; and
detect, by the edge device, specific information included in an input image input to an input layer of the edge-side inference model, and generate, according to the detected specific information, layer position information indicating a position of a last layer to process the input image in the edge-side inference model,
wherein the edge device inputs the input image to an input layer of the edge-side inference model, and transmits layer data that is a computation result obtained by performing processing from the input layer to a layer indicated by the layer position information, and the layer position information to the server, and
the server receives the layer data and the layer position information, inputs the received layer data to a layer subsequent to a layer indicated by the received layer position information in the server-side inference model, and performs processing up to the output layer.