Generation method and device of natural language sentence library

A technology of natural language and sentences, applied in the computer field, can solve problems such as complex operation process and achieve high recognition rate

Active Publication Date: 2017-02-01
ZTE CORP
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and device for generating a natural language sentence database, which at least solves the problem that a large amount of manual intervention is required in the construction of a natural language sentence database in the related art, and the operation process is relatively complicated

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
  • Generation method and device of natural language sentence library
  • Generation method and device of natural language sentence library
  • Generation method and device of natural language sentence library

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0187] Example 1. I graduated from university, and I go to school every day (*).

[0188]

[0189]

example 2

[0190] Example 2. I am eight years old this year, and I go to school every day (*).

[0191]

[0192]

[0193] What needs to be explained here is that there are two directions in the training process; one is forward, that is, from left to right; the other is reverse, from right to left, that is, two-way training, and two sets of weight matrices are obtained. The purpose is to : Improve the accuracy of NLP processing.

[0194] In the preferred implementation process, the sentence is predicted through the "prediction interface" in the "NLP online interface", and it is also necessary to interact according to the specified data format;

[0195] For example: the sentence "socialist country" entered by the user, the sending form and returning form of the message are as follows;

[0196] The format of the message sent by the "prediction interface" is as follows

[0197]

[0198]

[0199] 001

[0200] true

[0201] socialist country

[0202] 3

[0203]

[0204...

example 3

[0256] Sentence library usage example 3: Sentence judgment

[0257] Figure 4 It is a schematic diagram of a sentence judgment process executed by using a natural language sentence database according to a preferred embodiment of the present invention. Such as Figure 4 As shown, in the NLP processing process, sometimes it is necessary to judge whether a sentence is a normal sentence, that is, to judge whether a sentence is formed.

[0258] For example: In the intelligent question answering system, some users usually enter some "non-sentence" sentences at will to verify the analysis ability of the system; how to identify these sentences, here you need to use the "sentence judgment" function.

[0259] Assuming that the sentence entered by the user is "Come on, love it to the amount of openness", how to judge whether the sentence is a normal sentence, you can reply "Please speak human words", or "Your expression is very profound" and other replies ; which may include the follo...

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 invention provides a generation method and device of a natural language sentence library. Through the generation method, according to a training data set, word information is obtained; a word vector of a preset dimension is adopted to convert the word information into a test set to be identified; and through a way that the test set to be identified in a RNN (Recurrent neural Network) model is trained to generate the natural language sentence library, the problems that a large quantity of manual intervention is required by a construction way of the natural language sentence library and an operation process is complex in the relevant art are solved so as to achieve effects that an identification rate is high, and the generation method and device is simple and easy in use and can meet the NLP (Natural Language Processing) business requirements of a questioning and answering system, a retrieval system, an expert system, on-line customer service, a mobile phone assistant, a private assistant and the like.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method and device for generating a natural language sentence database. Background technique [0002] With the development of computer and network technology, people can encounter the application of artificial intelligence (AI) everywhere in their daily work and life, and artificial intelligence is closely related to the processing of text, that is, natural language processing (NLP). Further, considering that the natural language sentence database based on words (non-words) is the basis of natural language processing, it is very necessary to build a basic sentence database for words, because the basic sentence database can support natural language processing Many tasks, such as: spelling error correction, input association, sentence judgment, dialogue generation, etc. [0003] Today, with the rapid development of big data and artificial intelligence, text plays an irreplaceable role as...

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 Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/3329G06F16/35G06F40/232G06N3/084G06F40/274G06N3/044
Inventor 牛国扬陈虹温海娇许慢
Owner ZTE CORP
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