Self-adaptive identification method and system

Abstract

The invention discloses a self-adaptive identification method and system wherein the system comprises: according to a user's historical corpus, establishing a customized dictionary; clustering the customized words in the user's customized dictionary to obtain the type number of each customized word; constructing language models according to the type numbers of the customized words; during the identification of the inputted information of the user, if the words contained in the information exist in the user's customized dictionary, expanding the de-coding paths according to the type numbers of the customized words corresponding to the words; decoding the information according to the expanded decoding paths to obtain a plurality of selective decoding results; according to the language models, calculating the scores of the language models of the selective decoding results; and selecting the selective decoding result whose language model obtains the highest score as the information identification result. With the method and system of the invention, it is possible to increase the identification accuracy for a user's customized words and the consumption of the system can be reduced.

Description

technical field [0001] The invention relates to the technical field of information interaction, in particular to an adaptive identification method and system. Background technique [0002] With the continuous development of natural language understanding technology, the interaction between users and smart terminals has become more and more frequent, and it is often necessary to input information to smart terminals by voice or pinyin. The smart terminal recognizes the input information and makes corresponding operations according to the recognition results. Under normal circumstances, when the user inputs a common sentence by voice, such as "today's weather is good", "let's go to eat together", etc., the smart terminal system will basically give correct recognition results. However, when the user input information contains user-specific information, the smart terminal system often cannot give correct recognition results. User-specific information generally refers to personal...

AI Technical Summary

Problems solved by technology

However, because the obtained user-related documents often contain a large amount of data information that has nothing to do with the user, such as spam, which directly deviates from the user's personalized data, resulting in less useful user data obtained according to the user-related documents. It is prone to data sparsity, which makes the built user language model less reliable

Moreover, the fusion of the user language model into the general language model tends to reduce the recognition accuracy of the general language model

In addition, the existing recognition system needs to build a language model for each user, and the maintenance of each model consumes a lot of system resources. When the number of users is large, the system overhead is large

Images