Method and system for maintaining language model library using network

A language model library and network language technology, applied in the field of text input, can solve the problems of inability to provide high efficiency, difficult to search terms, and delays, to meet the requirements of input habits, shorten the training process, and improve the speed.

Active Publication Date: 2016-06-08
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even if such a large corpus is only stored on the network side as the Sogou input method seeks, it is difficult or delayed to search for matching terms directly from the network side based on such a massive corpus
More importantly, the use of such a large corpus follows everyone's input habits, which is not associated with the user's personal language model, so it cannot provide the efficiency brought by calling a specific language model for a specific user

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for maintaining language model library using network
  • Method and system for maintaining language model library using network
  • Method and system for maintaining language model library using network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0028] Refer below figure 1 A character input system according to an embodiment of the present invention is described in detail. figure 1 The input system shown includes a network server 10, a user equipment 20 and a language model synchronization device 30, wherein the network server 10 may be a plurality of network servers 10 distributed on the Internet 1 ......10 n . These web servers 10 1 ......10 n Work together to form a server cloud to provide services for a large number of users. The web server 10 can also be one or more servers located on the enterprise LAN.

[0029] To achieve the purpose of the present invention, the web server 10 includes a web corpus 101, which may include a user web corpus 101a and a public web corpus 101b respectively corresponding to each user.

[0030] User web corpus 101a is a backup of each registered user's local co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention relates to a network-assisted input method and system, which uses a network server to maintain a language model library, and completes input by calling a corresponding language model library for users. The system includes: at least one user device configured to be The user uses text input and is configured to build a local language model library based on user input; the network server is configured to build a network language model library based on at least one local language model received and statistical analysis of other corpus; and language model synchronization An apparatus configured to synchronize the local language model repository with the network language model repository. The invention also relates to an input method for implementation with the above system.

Description

technical field [0001] The invention relates to the field of text input, in particular to an input method and system which are implemented with network assistance and improve the maintenance of language model databases. Background technique [0002] Currently popular input methods, such as Sogou and Google Input Methods, have built-in statistical language model algorithms to analyze text input data to generate results that meet user expectations. The statistical language model uses the method of probability and statistics to reveal the inherent statistical laws of language units, among which N-Gram is simple and effective, and is widely used. The N-Gram model is based on the assumption that the appearance of the Nth word is only related to the previous N-1 words, but not to any other words, and the probability of the entire sentence is the product of the occurrence probabilities of each word. These probabilities can be obtained by counting the number of simultaneous occurre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30
Inventor 周志华蒋斌弓辰
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap