Method, system and equipment for obtaining neology

Abstract

The present invention discloses a method for getting new word. The method contains the following steps: firstly, the alternative character string is gained from the chart data; and secondly, the alternative character string is filtered according to the preset rule and the filtered words are used as new word. The present invention also discloses a system for getting new word and an instant communication user end and a server which completes the getting of the new word. The present invention has the advantages of easily, effectively and in time automatically getting new word based on the word source of the instant communication, and the new word gotten by the present invention has a boarder service scale.

Description

technical field [0001] The invention relates to information extraction technology, in particular to a method and system for obtaining new words by using an instant messaging (IM) system, and an instant messaging client and server for realizing new word acquisition. Background technique [0002] With the rapid development and popularization of informatization, electronics and networking, people will contact or obtain a huge amount of information from various communication networks and the Internet every day; with the massive dissemination of information and the continuous expansion of people's communication content, New vocabulary emerges one after another and is widely used. Since vocabulary is the basis of people's communication, it is very necessary to continuously increase and update the vocabulary. At present, acquisition of new words is widely used in fields such as input method and network search. For input method, it is necessary to continuously update its own databa...

AI Technical Summary

Problems solved by technology

However, these two types of input methods have different degrees of problems in obtaining new words: the keyboard input method obtains new words based on the characteristics of the user's input frequency and times. Store, and then filter and count the stored information according to preset rules, so that although new words can be accurately obtained, the obtained new words only come from a certain user and are only stored on the terminal currently used by the user , not for more users, even if many new words are commonly used by everyone, different users need to obtain them separately through frequent input; moreover, for the same user, since the new words are only stored on the currently used terminal, then replace After the terminal, it needs to be obtained again, for example: many commonly used new words have been obtained on the terminal in the office, but it needs to be obtained again when using the required new words on the terminal at home

However, due to the continuous emergence of new words and scattered in different corpora, it is difficult to identify and update them in a timely and effective manner; moreover, the existing technology usually uses manual participation in the collection, sorting and identification of new words, and then the obtained New words added to the existing thesaurus, so not only time-consuming, costly, but also very low work efficiency

[0004] It can be seen that there are relatively few ways to obtain new words in the existing technology. It mainly collects and counts user input and query keywords, and then obtains new words. At present, other information sources are not used as sources of new words.

Images