Business data processing method and device and server

Abstract

The invention provides a business data processing method and device and a server. Based on the method, an existing preset OCR model can be used for processing a target image containing target business data, and a target text field is extracted from the target image; according to a target text field library matched with the target business data, whether the target text field belongs to a to-be-corrected special text field or not is determined, and if it is determined that the text field belongs to the to-be-corrected special text field, sound and shape code data containing musical scale codes and font codes at the same time are obtained; further, a reference text field can be screened out from preset special text fields contained in a target text field library according to the phonetic and morphological code data of the target text field and the editing distance between the target text field and the preset special text fields; and the reference text field is utilized to carry out targeted correction processing on the currently obtained target text field, so that the relatively accurate corrected target text field can be obtained.

Description

technical field [0001] This manual belongs to the field of artificial intelligence technology, and in particular relates to a business data processing method, device and server. Background technique [0002] In some business data processing scenarios, image data containing business data may be directly collected. At this time, it is necessary to identify and extract relevant text fields from the above image data, so that the extracted text data can be used later. The text field performs specific business data processing. [0003] Based on the existing business data processing methods, if it is necessary to identify and extract relevant text fields from image data containing certain business data, it is often necessary to first collect a large amount of image data containing business data of this topic type as sample data ; and then use the above sample data to carry out a large number of model training to obtain the OCR (Optical Character Recognition, Optical Character Reco...

AI Technical Summary

Problems solved by technology

[0004] It can be seen that the processing method based on the existing business data needs to spend a lot of resources, time and cost to specially train the OCR recognition model for the subject type of the business data to be processed, which will inevitably increase the processing cost of the business data and reduce the cost. Improve the processing efficiency of business data

[0005] For the above problems, no effective solutions have been proposed so far

Images