A self-adaptive intelligent document recognition and input device and a use method thereof

Abstract

The invention belongs to the field of image recognition processing. The invention relates to a self-adaptive intelligent document recognition and input device and a use method thereof. A data acquisition module acquires a paper text of a client into a picture file through scanning or shooting, the preprocessing module carries out block processing on the text in an image by utilizing a morphological processing algorithm, lattices in each line or table are made into unequal cell blocks, and the character recognition module carries out binary processing on each cell block; Then, the correlation analysis module performs correlation analysis according to a pre-configured keyword and a pre-configured rule; According to the technical scheme, the relation between text blocks is analyzed, a data extraction module is guided to extract needed field content, a deviation rectification module can perform verification and automatic correction on the extracted content according to previous identification and deviation rectification historical data, and finally a result is stored and returned to a calling party. The system is ingenious in design concept, safe and convenient to use, high in intelligent degree, high in recognition accuracy, friendly to application environment and wide in market prospect.

Description

Technical field: [0001] The invention belongs to the field of image recognition and processing, and relates to a logistics bill recognition device, in particular to an adaptive intelligent bill recognition and input device and a use method thereof. Background technique: [0002] In air freight, sea freight and other import and export business, the formats and types of documents circulated in the business process (such as: customer orders, shipping company booking receipts, etc.) are various, and there are word, excel, textual PDF and other formats that can directly copy the content , and quite a few are files in image format, or simply paper files. Due to historical reasons, there are many types of air and sea freight documents from all over the world. There is no uniform format standard for customer documents in the industry, and even a single customer will provide documents in multiple formats. In this case, for some large-scale logistics or freight forwarding companies, ...

AI Technical Summary

Problems solved by technology

[0006] One is that templates need to be made manually, which increases the workload, especially in the case of supporting a large number of documents, many templates need to be customized, which is very troublesome in the actual operation of the salesman, and the operator will become very troublesome when faced with a large number of templates. cumbersome

[0007] The second is that the frame selection of fixed-format text is sometimes not accurate enough. When the filled information is misplaced and does not completely correspond to the fixed format, it is difficult to locate the size of the frame selection when making a template, especially if the misplaced content is relatively large. For a long time, some content is likely to be missed in the identification;

[0008] The third is that if the format of the small-sized documents is very fixed, it may be possible to achieve relatively high accuracy, but for documents with A4 or larger format, it is more difficult to achieve the purpose through the fixed template for the power of attorney containing more content

Images