Automatic comparative analysis processing method and system for super-large-scale data

• Main Authors: HAN JINSHUI, LEI HUAIXING, YIN YUMIN, CAO GUANGXUE, LI QINGLI
• Format: Patent
• Language: Chinese; English
• Published: 15.07.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to the technical field of data comparison and analysis, and provides an automatic comparison and analysis processing method and system for super-large-scale data, and the method comprises the steps: inputting target literatures, classifying the target literatures, obtaining a target literature library, and obtaining a target virtual vector value of the target literature library; calculating vectors of the target literature and each literature in the target literature library; calculating a vector difference D1 from the target vector to the target virtual vector value, and calculating a vector difference D2 from the vector of each document in the target document library to the target virtual vector value; and selecting the literature with the vector difference D2 close to the vector difference D1 as a first approximate literature of the target literature. Data indexing is carried out in a vector type indexing mode, the indexing speed is increased by an order of magnitude compared with the