Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Direct conversion" patented technology

A method and device for automatically extracting and outputting structured data of a business document

PendingCN122695639AFlexible configurationreduce configuration
The application relates to the field of data processing and discloses a structured data automatic extraction and output method and device for business bills. The method comprises the following steps: providing a plurality of pre-created and published template snapshots and data structure constraint rules; acquiring a bill image; automatically determining a target template type matched by the bill image, loading corresponding template snapshots and data structure constraint rules according to the target template type; performing optical character (OCR) recognition on the bill image to obtain OCR text; and extracting and outputting corresponding structured business data from the OCR text through an information extraction engine according to extraction prompt words and data structure constraint rules. The embodiment of the application can self-define a template, automatically identify a bill type, perform data extraction through context semantic understanding to break through the difference barrier of field naming, and directly output structured business data, so as to meet the automation, standardization and traceability requirements of enterprise-level bill processing.
Owner:JIANXIANG CLOUD INFORMATION TECH (DONGGUAN) CO LTD

Efficient Simulation Method for Non-Gaussian Processes Based on HPM and JTM Mixture Models

ActiveCN120706247Breduce computing timeAvoid loop nested calculationsStructural dynamicsAlgorithm
This invention discloses an efficient simulation method for non-Gaussian processes based on a hybrid HPM and JTM model, belonging to the field of structural dynamics technology. This invention achieves rapid simulation of non-Gaussian processes through parameter estimation using Hermitian polynomial and Johnson transformation models based on machine learning, explicit transformation from non-Gaussian correlation functions to Gaussian correlation functions, and fast simulation of non-Gaussian processes based on linear filtering. While ensuring accuracy, this method effectively improves the efficiency of non-Gaussian process simulation and is applicable to non-Gaussian process simulation in various engineering fields.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY