Method and system for processing semantic similarity in human-computer natural language interaction

A technology with similar semantics and natural language, applied in the field of natural language human-computer interaction, can solve problems such as low semantic understanding accuracy and human-computer interaction cannot be realized normally, and achieve the effect of improving the accuracy rate

Active Publication Date: 2019-10-29
北京谛听机器人科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a semantic similarity processing method and system in human-computer natural language interaction. question

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 processing semantic similarity in human-computer natural language interaction
  • Method and system for processing semantic similarity in human-computer natural language interaction
  • Method and system for processing semantic similarity in human-computer natural language interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 As shown, this embodiment proposes a semantic similarity processing method in human-computer natural language interaction, which is realized in the following manner:

[0043] S1. Establishing a preliminary query database and receiving user input sentences;

[0044] S2. Screening the sentences in the preliminary query database according to the format of the sentences input by the user;

[0045] S3. Semantically comparing the sentences selected in the preliminary query database with the sentences input by the user, and outputting the final result.

[0046] In this embodiment, at the beginning of processing the user input sentence, first the format used for the input sentence is extracted, and the main part of the extracted question is compared to perform the first step of deletion; the specific process is as follows figure 2 Shown:

[0047] S21. Extracting the subject, predicate and object in the language input by the user;

[0048] S22. Comparing th...

Embodiment 2

[0057] Such as Figure 4 As shown, this embodiment proposes a semantic similarity processing system in human-computer natural language interaction, the system includes:

[0058] Database building module 1, used to set up a preliminary query database and receive user input sentences;

[0059]The sentence screening module 2 is used for screening the sentences in the preliminary query database according to the format of the user input sentence;

[0060] The semantic comparison module 3 is used for semantically comparing the sentences selected in the preliminary query database with the user input sentences, and outputting the final result.

[0061] preferred, such as Figure 5 As shown, the sentence screening module 2 includes:

[0062] Sentence extraction module 4, used to extract the subject, predicate and object in the user input language;

[0063] Format comparison module 5, for comparing the subject, predicate and object in the language input by the user with the subject,...

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 relates to a semantic similarity processing method and system in natural language man-machine interaction, relates to the field of natural language man-machine interaction, and aims to solve the problem that the man-machine interaction cannot be normally realized due to low semantic comprehension accuracy of an existing man-machine interaction technology. The method is implemented by the steps of S1, establishing a preliminary query database and receiving a statement input by a user; S2, screening statements in the preliminary query database according to a format of the statement input by the user; and S3, performing semantic comparison on the statements screened out of the preliminary query database and the statement input by the user, and outputting a final result. According to the method and the system, the statements in the database are preliminarily screened through the format of the statement input by the user at first and then the similarity between the statement input by the user and the problem statements in the database is compared through semantic similarity comparison, so that the correct rate of a robot for semantic comprehension is increased to 10-25%, and the man-machine conversation process is more natural and fluent.

Description

technical field [0001] The invention relates to the field of natural language human-computer interaction. Background technique [0002] At present, in the field of human-computer interaction, when comparing the similarity between two sentences, it does not deal with sentence patterns, does not pay attention to the relationship between words in the sentence, and does not even pay attention to function words. For example, if you enter "Who is better between you and Xiao Ming" and "Xiao Ming is better than you" in the robot, the robot cannot distinguish the difference between these two sentences. For some function words, the robot can't distinguish, such as the difference between "what are you doing" and "what are you doing". [0003] But in the field of customer service, in terms of robot question and answer, as long as the robot cannot accurately distinguish the meaning of two sentences, the robot cannot accurately understand the user's intention and cannot give the user a s...

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): G06F17/27G06F16/33
CPCG06F16/3344G06F40/30
Inventor 彭军辉
Owner 北京谛听机器人科技有限公司
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