Unlock instant, AI-driven research and patent intelligence for your innovation.

Natural language semantic calculation method and apparatus based on question semantics

A technology of semantic computing and interrogative operators, applied in the field of information processing, to achieve the effect of high use value

Active Publication Date: 2015-11-18
刘战雄
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiment of the present invention is to propose a method and device for natural language semantic calculation based on interrogative semantics, aiming at solving the problem of how to establish simple and easy-to-understand semantic division rules to process natural language

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
  • Natural language semantic calculation method and apparatus based on question semantics
  • Natural language semantic calculation method and apparatus based on question semantics
  • Natural language semantic calculation method and apparatus based on question semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] refer to figure 1 , figure 1 It is a schematic flowchart of the first embodiment of the method for computing natural language semantics based on interrogative semantics in the embodiment of the present invention.

[0064] In Embodiment 1, the method for computing natural language semantics based on interrogative semantics includes:

[0065] Step 101, designing multiple multi-level interrogative semantic labeling sets, each labeling set is composed of some interrogative words commonly used in modern Chinese, wherein the interrogative words include interrogative pronouns;

[0066] Preferably, the design of multiple multi-level interrogative semantic labeling sets, each labeling set is composed of some commonly used interrogative words in modern Chinese, wherein interrogative words include interrogative pronouns, including:

[0067] According to different semantic scenarios or different application scenarios, multiple multi-level interrogative semantic annotation sets ar...

Embodiment 2

[0149] refer to figure 2 , figure 2 It is a schematic flowchart of the second embodiment of the method for computing natural language semantics based on interrogative semantics in the embodiment of the present invention.

[0150] On the basis of Embodiment 1, the method for computing natural language semantics based on interrogative semantics further includes:

[0151] Step 104, divide the search characters into preset query objects through a preset algorithm;

[0152] Step 105, searching for pre-stored characters according to the divided interrogative pronouns;

[0153] Step 106, if the divided interrogative pronoun corresponds to a pre-stored character, then display the pre-divided character to be processed corresponding to the pre-stored character.

[0154] Specifically, for example, if the user inputs when, who, how, and where, then according to the pre-stored tomorrow / when I will go with you / who / how Beijing / where, it can be searched out that I will go to Beijing with...

Embodiment 3

[0156] refer to image 3 , image 3 It is a schematic flowchart of the third embodiment of the method for computing natural language semantics based on interrogative semantics in the embodiment of the present invention.

[0157] On the basis of Embodiment 1, the method also includes:

[0158] Step 107, receiving the search characters input by the user;

[0159] Step 108, calculating and obtaining a pre-stored character model according to the search character and similarity;

[0160] Step 109, according to the pre-stored character module is divided into pre-set query objects;

[0161] Step 110, searching for pre-stored characters according to the divided interrogative pronouns;

[0162] Step 111 , if the divided interrogative pronoun corresponds to a pre-stored character, then display the un-divided character to be processed corresponding to the pre-stored character.

[0163] Specifically, when processing natural language sentences, since a corresponding query semantic tre...

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

Embodiments of the invention disclose a natural language semantic calculation method and apparatus based on question semantics. The method comprises: designing a plurality of multi-leveled question semantics annotation sets, wherein each annotation set comprises a plurality of common interrogatives in modern Chinese, and the interrogatives comprise interrogative pronouns; and according to a question characteristic of each component in a to-be-treated statement, splitting and annotating each component in the to-be-treated statement to be a question object or a question operator by the question semantics annotation sets, a sentence mold library of the question semantics and a question semantics tree. According to the property and rule of the question object or the question operator, the natural language semantic calculation method disclosed by the embodiment can be used as basic semantic calculation method through the question semantics annotation sets, the sentence mold library of the question semantics and the question semantics tree, so that common processing problems of natural languages can be effectively solved and the method particularly has higher utilization values for fields such as splitting and annotation of the statement, natural language search, machine translation, and man-machine questions and answers.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of information processing, in particular to a method and device for computing natural language semantics based on interrogative semantics. Background technique [0002] Natural language processing is a discipline that studies language problems in human-to-human and human-computer communication. In natural language processing, semantic computing is to interpret the meaning of units at all levels in natural language, namely characters, morphemes, words, phrases, phrases, sentences, sentence groups, paragraphs, chapters, etc., through computers. What did you say. The current technologies mainly include: sememe analysis, semantic field, semantic network, Montague grammar, optimal semantics, concept dependence theory, meaning-text theory and other methods. [0003] In the current technology, the main defects of semantic computing are manifested in two aspects: on the one hand, it focuses o...

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): G06F17/27
Inventor 刘战雄
Owner 刘战雄