S&P Global. has been granted a patent for a computer-implemented method for multi-class text classification. The method involves processing uncoded shipping container descriptions to predict Harmonized System (HS) code segments by cleaning, tokenizing, and scoring text data to establish correlations with HS code labels. GlobalData’s report on S&P Global gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on S&P Global, was a key innovation area identified from patents. S&P Global's grant share as of July 2024 was 57%. Grant share is based on the ratio of number of grants to total number of patents.

Multi-class text classification for shipping container descriptions

Source: United States Patent and Trademark Office (USPTO). Credit: S&P Global Inc

The granted patent US12045570B2 outlines a computer-implemented method and system for text classification specifically tailored for shipping container descriptions. The method begins with the reception of a training set that includes various shipping container descriptions, each associated with a Harmonized System (HS) code. The process involves cleaning the text by removing short words, numbers, and symbols, followed by tokenization into single words and bigrams. The method then accumulates coincidences between HS code labels and tokens, scoring these coincidences to establish a correlation score that reflects the relationship between the tokens and HS codes based on their occurrences.

Additionally, the patent describes a mechanism for predicting HS codes for uncoded shipping container descriptions. This involves cleaning and tokenizing the uncoded text, summing the scores of associated HS code segments, and determining the predicted HS code based on the highest score. The system is designed to support automatic rolling retraining and can facilitate the physical movement of shipping containers based on the classification results. The scoring methods are detailed, including various formulas that incorporate limits and constants to ensure accurate classification. Overall, the patent presents a comprehensive approach to enhancing the efficiency of shipping container classification through advanced text processing techniques.

To know more about GlobalData’s detailed insights on S&P Global, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.