Text abstract generation method

Abstract

The invention discloses a text abstract generation method, which comprises the following steps of obtaining the probability of commonly generating words and field words on the basis of contents of aninput text and business information of a field corresponding to the input text; and generating abstract information corresponding to the input text based on the probabilities of the common generated words and the field words and the corresponding vocabularies. The invention also discloses a text abstract generation method, which comprises the following steps of obtaining the probabilities of the common generated word, the duplicated word and the field word corresponding to the input text in real time based on the coded input text, and obtaining abstract information based on the probabilities of the common generated word, the duplicated word and the field word and the corresponding vocabulary. According to the method provided by the invention, the abstract words can be extracted based on the related service information of the corresponding domain library incorporated into the domain in combination with the related service domain, so that the abstract information of the related service process can be summarized more accurately, at the same time, the key information can be accurately identified by integrating multiple mechanisms, the fluency is improved, and the information redundancyis avoided.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and human-computer mutual assistance, in particular to a method for generating text summaries. Background technique [0002] With the rapid development of artificial intelligence, it is increasingly necessary for machines to assist humans to complete tasks. All walks of life need to record past information and form a summary, so article summary technology is particularly necessary. Among them, understanding the intent of the article and obtaining key information are the most critical. [0003] Represented by the public service industry. For example, operators, people will consult various telecommunications issues, and the staff will form a record of the questions answered every day, and will fill in the work order and submit it if it cannot be resolved in time. This technology will assist staff to complete work orders and reduce their workload. [0004] Also for example, i...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a text abstract generation method to overcome the current defects of poor identification of key information, low fluency, and redundant information, and at the same time overcome the inability to accurately generate business processes due to failure to incorporate domain-related business information summary question

Images