Commercial place entity linking method and system, electronic equipment and storage medium

A place and business technology, applied in the field of big data, can solve unrealistic problems, achieve the effect of improving efficiency and accuracy, improving reading experience, and reducing human resources

Pending Publication Date: 2021-10-22
携程旅游信息技术(上海)有限公司
View PDF5 Cites 1 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 overcome the unrealistic defects in the prior art that it is unrealistic to ma

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
  • Commercial place entity linking method and system, electronic equipment and storage medium
  • Commercial place entity linking method and system, electronic equipment and storage medium
  • Commercial place entity linking method and system, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] Such as figure 1 As shown, this embodiment provides a method for linking business place entities. The method for linking business place entities includes:

[0062] S101. Obtain the name of the business place to be linked in the text and the geographical information of the business place to be linked corresponding to the name of the business place.

[0063] In addition to the name of the business place to be linked, the text usually includes geographical information of the business place to be linked corresponding to the name of the business place. For chained commercial places, geographic information in the text can effectively improve the accuracy of identifying the linked commercial places.

[0064] The geographic information of the business place to be linked can be determined in combination with the context in the text, but is not limited to.

[0065] S102. Analyzing the core name from the name of the commercial place, the core name is the core name of the commer...

Embodiment 2

[0080] Such as figure 2 As shown, the business site entity linking method in this embodiment is a further improvement on Embodiment 1, specifically:

[0081] Business location entity linking methods also include:

[0082] S201. Establish an inverted index using the N-gram sequence of the core name of the business place as a search keyword; the inverted index is used to represent the mapping relationship between the business place and the core name.

[0083] Preferably, in the knowledge base, an inverted index is established with the country as the granularity and the 2-gram sequence of the core name of the business place as the search keyword.

[0084] N-gram is an algorithm based on statistical language models. Its basic idea is to perform a sliding window operation with a size of N on the content of the text according to bytes, forming a sequence of byte fragments with a length of N. Each byte fragment is called a gram, which counts the frequency of occurrence of all gra...

Embodiment 3

[0106] Such as image 3 As shown, this embodiment provides a system for linking entities of commercial places. The commercial place entity linking system includes:

[0107] The text processing module 1 is used to obtain the name of the business place to be linked in the text and the geographical information of the business place to be linked corresponding to the name of the business place;

[0108] In addition to the name of the business place to be linked, the text usually includes geographical information of the business place to be linked corresponding to the name of the business place. For chained commercial places, geographic information in the text can effectively improve the accuracy of identifying the linked commercial places.

[0109] The geographic information of the business place to be linked can be determined in combination with the context in the text, but is not limited to.

[0110] The core name parsing module 2 is used to resolve the core name from the name...

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 discloses a commercial place entity linking method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a commercial place name to be linked in a text and corresponding geographic information; analyzing a core name from the commercial place name; determining an initial candidate commercial place matching the core name of the commercial place name according to a pre-established mapping relationship between the commercial place and the core name; screening the initial candidate commercial place by using the geographic information so as to reserve candidate commercial place of a city where the to-be-linked commercial place is located; performing similarity prediction on the candidate commercial places according to the commercial place names and the geographic information, and determining the candidate commercial places with the similarity meeting a preset requirement as target commercial place; and linking the target commercial place with the commercial place name to be linked in the text. Automation of the entity link of the commercial place name in the text is realized.

Description

technical field [0001] The present invention relates to the field of big data technology, in particular to a method, system, electronic equipment and storage medium for entity linking of commercial places. Background technique [0002] In articles that display products, content is meaningful because it fully demonstrates the characteristics and value of the product through various forms such as graphics and text. However, for most of the articles on the OTA (Online Travel Agency, Online Travel Agency) website, they are not directly related to the corresponding business entity during the writing process. For a single business place, it needs to be artificially associated through search and other methods in the middle, which increases the effort of the user. In order to effectively improve the user experience and easily find the corresponding business places in the process of reading and planting grass, the combination of articles and products is inevitable. [0003] Entity ...

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
IPC IPC(8): G06F16/31G06F16/9537G06F16/955
CPCG06F16/319G06F16/9537G06F16/9558
Inventor 刘茜孙玉霞余迁孙知非何蜀波邹宇
Owner 携程旅游信息技术(上海)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