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

Method and device for determining entity dependency

A technique for determining dependencies and methods, applied in the Internet field, can solve problems such as inability to obtain more accurate recommendations, and achieve the effect of improving accuracy

Active Publication Date: 2021-02-09
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

"This text, from the text, can identify the four entities of "A location, KFC, B location, McDonald's", and analyze the dependency relationship of these four entities, it is possible to get that A location is a description of McDonald's , location B is the result of describing KFC, but in fact, location A describes KFC, and location B describes McDonald's, so when the user performs the follow-up operation of card selection, more accurate recommendations cannot be obtained

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 device for determining entity dependency
  • Method and device for determining entity dependency
  • Method and device for determining entity dependency

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0105] Example one: Figure 9 It is a schematic diagram of determining the entity dependency relationship in the text to be recognized in the embodiment of the present invention Figure 1 , see Figure 9 As shown, assuming that the text 900 to be recognized is "I go to KFC in Wudaokou, you go to McDonald's in Xierqi", the subtext 901 after splitting is "I go to KFC in Wudaokou", and the subtext 902 after splitting is " You go to the McDonald's in Xierqi", subtext 901 has entity 903 "Wudaokou" and entity 904 "KFC", subtext 902 has entity 905 "Xierqi" and entity 906 "McDonald's", subtext 901 has Two entities, there are two entities in subtext 902, there is no single subtext, then, identify the dependency relationship between entity 903 and entity 904 in subtext 901, get that Wudaokou describes KFC, identify in subtext 902 From the dependency relationship between entity 905 and entity 906, it is obtained that Xierqi describes McDonald's. Finally, the analysis shows that KFC and...

example 2

[0106] Example two: Figure 10 It is a schematic diagram of determining the entity dependency relationship in the text to be recognized in the embodiment of the present invention Figure II , see Figure 10 As shown, assuming that the text 1000 to be recognized is "Go to the Capital Airport to pick up Zhang Xiaoming at nine o'clock tomorrow morning, and then go to Wudaokou Cinema for a meeting", the subtext 1001 after splitting is "nine o'clock tomorrow morning", and the subtext 1002 after splitting is "Go to Capital Airport to pick up Zhang Xiaoming", the split subtext 1003 is "go to Wudaokou Cinema for a meeting again", subtext 1001 has entity 1004 "tomorrow at nine o'clock in the morning", subtext 1002 has entity 1005 "Capital Airport" and Entity 1006 "connects with Zhang Xiaoming", subtext 1003 contains entity 1007 "Wudaokou Cinema" and entity 1008 "meeting", subtext 1001 contains one entity, subtext 1002 contains two entities, and subtext 1003 contains two entities , wh...

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 present invention provide a method and device for determining entity dependency, the method comprising: splitting the text to be recognized into multiple subtexts; identifying entities in each of the multiple subtexts; Entities in each subtext and / or the dependencies of entities in adjacent subtexts to determine the dependencies between entities in the text to be recognized. It can be seen that, compared to directly determining the dependency relationship between all entities in the text to be recognized, using the method and device for determining the entity dependency relationship in the embodiment of the present invention, before determining the dependency relationship between entities, first The text is split into multiple subtexts, and then according to the dependencies of entities in each subtext and / or entities in adjacent subtexts, the dependency relationship between entities in the text to be recognized can be determined, which can avoid unrelated The entities in the text are linked together to improve the accuracy of determining the dependencies between entities in the text.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of the Internet, and in particular, to a method and device for determining entity dependency relationships. Background technique [0002] In the prior art, there is a method for displaying named entities (also called entities, NER) recognized from a piece of text, in which method each named entity is displayed individually. For example, for the text "I went to the Seven Days Hotel at No. 8 Xiaoying Road, Chaoyang District", there are two entities in the text, "No. 8 Xiaoying Road, Chaoyang District" and "Seven Days Hotel", which will be displayed in the user terminal. The cards corresponding to these two entities are displayed separately. In a feasible way, in order to improve user experience, entities with dependencies are generally displayed in one card. [0003] In the process of implementing the embodiments of the present invention, the inventors found that in the prior art, fo...

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): G06F40/30G06F16/28
CPCG06F16/288G06F40/30
Inventor 王卓然亓超马宇驰王东亮陈华荣
Owner TENCENT TECH (SHENZHEN) CO LTD