Logistics object information processing method and device and computer system

Abstract

The embodiment of the invention discloses a logistics object information processing method and device and a computer system. The method comprises the following steps: determining the text descriptioninformation of a to-be-classified target logistics object, processing the text description information, and determining a contained target feature word; generating a feature word vector correspondingto the target logistics object according to the inclusion condition of the text description information for each target feature word; and inputting the feature word vector into a coding classificationmodel to obtain corresponding classification feature information. Through the embodiment of the invention, automatic classification of logistics object codes can be realized, and the error probability is reduced while the labor cost is reduced.

Description

technical field [0001] The present application relates to the technical field of logistics object information processing, in particular to a logistics object information processing method, device and computer system. Background technique [0002] Hscode (The Harmonization System Code, commodity name and code coordination system code, referred to as customs code) is the core data that must be provided to the customs in the customs clearance process, involving export tax rates and tax refund rates. HS uses a six-digit code to divide all international trade commodities into 22 categories and 98 chapters. Chapters are further divided into headings and subheadings. The first and second digits of the commodity code represent "chapter", the third and fourth digits represent "Heading", and the fifth and sixth digits represent "subheading". The first 6 digits are HS international standard codes. HS has 1241 four-digit tax items and 5113 six-digit sub-items. [0003] In the process...

AI Technical Summary

Problems solved by technology

Therefore, it is a very cumbersome process to classify commodities by Hscode

[0004] At present, most enterprises in the industry use the method of manual pre-classification. However, even for a customs declaration expert with rich experience, it takes about 2 to 15 minutes to classify a SKU (the minimum stock-keeping unit of a commodity). It takes several hours or even longer for some extremely complex products, and the average daily processing is up to 200 sku

Moreover, due to the scarcity of corresponding pre-classification professionals and the high threshold for pre-classification learning, manual pre-classification mainly has problems such as high classification cost, low classification timeliness, and long response time

According to statistics, the cost of classifying a sku is currently 200-500RMB, and for some special categories such as electromechanical, the pre-classification cost is as high as 1500RMB or more

However, in some large-scale cross-border e-commerce trading platforms, the number of SKUs involved is huge, even as high as billions, and this cost is obviously unacceptable

In addition, in the face of B2C cross-border e-commerce's average daily order volume of tens of millions and the grand goal of "72-hour delivery" or even shorter delivery time, the above-mentioned method is obviously unable to handle 200 SKUs per day per capita. Responsive and satisfying

Furthermore, manual classification relies too much on the experience of experts. In the face of the huge workload of classification every day, mistakes are inevitable, and with the increase of workload, the error rate will gradually increase, resulting in the Challenged by customs, corporate qualifications are affected

Images