Searching method and searching device based on text

Abstract

The invention discloses a searching method and searching device based on text. The searching method based on text includes: step 1, acquiring feature words included in text streams which are sent by users, step 2, acquiring a feature probability of every business, which corresponds to every feature word from a pre-built feature probability lexicon, step 3, calculating a joint probability of every business, which corresponds to the text streams, according to the feature probability of every business, which corresponds to every feature word and step 4, outputting final matching business according to the joint probability acquired by calculating, storing every feature word in the feature probability lexicon and updating the corresponding feature probability of the feature word in the feature probability lexicon. According to the searching method and searching device based on text, the searching efficiency can be increased and operating costs can be reduced.

Description

technical field [0001] The invention relates to mobile communication service support technology, in particular to a text-based search method and search device. Background technique [0002] The user handles or cancels the communication service through SMS and other text communication methods, which can effectively save the time for the user to go to the SMS business hall to handle it, and improve the convenience of the user. However, traditional SMS business halls do not support or can only partially support the fuzzy matching function. For SMS business halls that do not support the fuzzy matching function, by accurately matching the content of the SMS with the keyword set mapped to each business preset in the business database, If the matching is successful, the corresponding business will be handled for the user, and if the matching fails, an input error prompt message will be returned to the user. However, as users increasingly use natural language to interact with SMS b...

AI Technical Summary

Problems solved by technology

However, according to the keyword fuzzy matching search method, it is impossible to identify and distinguish synonyms or near synonyms in the content of the user's uplink SMS, missing relevant effective information, and reducing the efficiency of the search; at the same time, the keyword configuration of the business instruction becomes a business instruction The important basis for parsing and processing users’ uplink SMS in the library makes the understanding of users’ uplink SMS content rely on the establishment and maintenance of a large number of business instructions and corresponding keyword mapping relationships, and manual operation is required to complete the selection and supplement of keywords. Not only does it bring a lot of workload to the maintenance and management personnel, but at the same time, with the continuous expansion of the mapping relationship between business instructions and keywords, it will bring another serious problem, that is, the repeated occurrence and use of the same business keyword and the different business keywords The nesting and crossing etc., so that a dozen or even dozens of businesses can be found out when a user sends a text message, although it is still possible to improve and streamline the key Thesaurus, but it will still make the business instruction library difficult to manage and maintain, and the operating cost is high; furthermore, users need to browse and choose from a variety of displayed services, which makes the process of user subscription services relatively cumbersome, which not only reduces the business service It also suppresses the user's new business consumption impulse, making the user's service experience poor and perception not strong

Images