A method for a bill of exchange trading robot to recognize the maturity date of a bill of exchange in natural language

Abstract

The invention discloses a method for a bill of exchange trading robot to identify the due date of a bill of exchange in natural language, which is mainly divided into two steps, namely, date extraction and date cleaning, that is, after the natural language is converted into text information in the chat records of both parties to the transaction , extract a character string from the text information, first determine whether there are date-related keywords in the string, if there are related keywords, then around the keyword, extract more than a dozen characters before and after the keyword to clean, and clean at the same time The date is converted into a standard format, and finally stored in the corresponding storage format and waits for other programs to call until all the strings in all the text information are processed, that is, through the full-coverage date processing of the text information of the chat records, Accurately determining the maturity date of the bill of exchange avoids the occurrence of identification errors and misses the actual due date of the bill of exchange, which also avoids large economic losses and credit risks for market brokers and investors, and improves the security of bill of exchange transactions.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence natural language processing, and in particular relates to a method for identifying the due date of a bill in natural language by a bill trading robot applied to bank acceptance bill transactions in the financial industry. Background technique [0002] According to statistics from the Bureau of Statistics, 80% to 90% of the existing enterprises in my country are small and medium-sized enterprises. These enterprises are at the end of the supply chain, and some upstream enterprises will use drafts for payment. However, a money order of 1 million yuan may only be realized at about 950,000 yuan, and even some small and medium-sized enterprises' money orders cannot be circulated or activated at all. In the traditional transaction mode, both parties to the transaction generally conduct one-to-one inquiry through the phone or WeChat, which is slow, time-consuming and laborious, and it is di...

AI Technical Summary

Problems solved by technology

Since the calculation of the bill of exchange price calculation needs to calculate the number of days of interest accrual, it is very important to extract and identify the due date information of the bill of exchange involving natural language in the chat history. The chat records are used to identify the maturity date information, and then convert it into a standard format. By building a big data database consisting of the bill of exchange maturity date and transaction price, it provides inquiry and calculation functions for other trading parties. This process is time-consuming and laborious, and the efficiency is extremely low. , and there is a problem of low accuracy in manual processing. Once a recognition error occurs, the actual due date of the bill of exchange will be incorrectly determined, and the wrong discount amount will be provided when providing inquiry services to customers, which will give market brokers and investors Those who have greater economic losses and credit risks

Images