US 12,243,338 B1
Method and apparatus for data processing, computer, storage medium, and program product
HoMan Poon, Hong Kong (CN)
Assigned to ICALC HOLDINGS LIMITED, Hong Kong (CN)
Filed by iCALC Holdings Limited, Hong Kong (CN)
Filed on Oct. 29, 2024, as Appl. No. 18/930,226.
Claims priority of application No. 202411295588.8 (CN), filed on Sep. 14, 2024.
Int. Cl. G06K 9/00 (2022.01); G06Q 30/0201 (2023.01); G06V 30/19 (2022.01); G06V 30/422 (2022.01); G07C 5/08 (2006.01)
CPC G06V 30/19173 (2022.01) [G06Q 30/0206 (2013.01); G06V 30/1918 (2022.01); G06V 30/422 (2022.01); G07C 5/085 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for data processing, comprising:
obtaining a service processing instruction and virtual asset-associated data of an aircraft sent by a first service object, and inputting the service processing instruction and the virtual asset-associated data of the aircraft to a target service processing model; wherein the aircraft is composed of at least two components;
obtaining an asset data classification rule, performing data division on the virtual asset-associated data of the aircraft according to N service types in the asset data classification rule and the at least two components to obtain S unit virtual assets, and determining binary group classification information corresponding to each of the S unit virtual assets; wherein the binary group classification information indicates a service type and a component to which a unit virtual asset belongs, and N and S are both positive integers;
obtaining weight model parameters respectively corresponding to the S unit virtual assets from a weight model parameter set in the target service processing model according to binary group classification information respectively corresponding to the S unit virtual assets; wherein the weight model parameter set comprises H weight model parameters respectively representing different influence weights, each weight model parameter corresponds to one piece of binary group classification information, and His a positive integer;
combining data feature vectors respectively corresponding to the S unit virtual assets with the weight model parameters respectively corresponding to the S unit virtual assets to obtain fused feature vectors respectively corresponding to the S unit virtual assets; wherein a fused feature vector is composed of a data feature vector and a weight model parameter;
generating a prompt text for indicating a recognition demand type according to the service processing instruction, determining a target processing network corresponding to the recognition demand type from the target service processing model according to the prompt text, and performing feature processing on the S fused feature vectors and the prompt text via the target processing network, to obtain a feature processing result;
classifying and recognizing the feature processing result to obtain a data recognition result for responding to the service processing instruction.