Menu field seed word automatic extraction realization method and a storage medium

A technology of automatic extraction and implementation method, which is applied in the field of manual interaction of recipes and smart kitchens, can solve a large number of manual problems, and achieve the effect of speeding up and fast extraction, saving labor cost and time, and saving manual labeling

Pending Publication Date: 2019-06-11
广州索答信息科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above technical problems, the purpose of the present invention is to provide a method and medium for automatically extracting seed words in the field of recipes, to solve the problem that a large amount of labor is required for the deep processing of data in the natural language understanding part, and to apply it to the field of recipes

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
  • Menu field seed word automatic extraction realization method and a storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] Please refer to figure 1 As shown, a method for automatically extracting seed words in the field of recipes includes the following steps:

[0027] Step S100: obtain recipe data;

[0028] Preferably, the recipe data can be obtained by using crawler technology to obtain a large amount of available data, but not limited to crawler technology. For example, the recipe data can also be obtained by manually maintaining and entering data: third-party open platform interface to obtain data and other methods.

[0029] Step S200: set up a semantic model based on word vector and document vector;

[0030] Specifically, the step of establishing a semantic model based on word vectors and document vectors specifically includes:

[0031] Using a large amount of recipe data as training samples, the documents in the recipe data are word-segmented, and the words and documents after word-segmentation are obtained;

[0032] Train the words and documents after word segmentation to obtain a...

specific Embodiment

[0043] Step S1000, obtain a large amount of recipe data, specifically, load the document data from the database, and organize the document data into a single sentence; then, use the open source toolkit jieba Chinese word segmentation component or hanlp Chinese language processing component to perform word segmentation on the document data ;

[0044] The jieba Chinese word segmentation component or the hanlp Chinese language processing component can support three word segmentation modes: precise mode, which tries to cut the sentence most accurately and is suitable for text analysis; full mode, which scans all the words that can be formed into words in the sentence Come out; search engine mode, on the basis of the precise mode, segment long words again to improve the recall rate, suitable for word segmentation in search engines.

[0045] The word segmentation process is as follows: "The taste of Cantonese cuisine is generally lighter" -> "Cantonese cuisine", "of", "taste", "gene...

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 menu field seed word automatic extraction realization method and a storage medium. The method comprises the following steps: obtaining menu data; establishing a semantic model based on the word vectors and the document vectors; pre-defining menu field seed words, and inputting the field seed words into the semantic model to obtain the same group of synonyms of the field seed words. According to the invention, the semantic model is established; The method comprises the steps of defining menu field seed words in advance, inputting the field seed words into a semantic model to obtain the same group of synonyms of the field seed words, accelerating rapid extraction of the field seed words through automatic processing of a program algorithm, saving a large amount of manual annotations, and successfully applying the field seed words to the menu field; While a large amount of labor cost and time are saved, faster and more data sources are provided for downstream semantic understanding services.

Description

technical field [0001] The invention relates to the field of human interaction in smart kitchens, in particular to a method for automatically extracting seed words in the field of recipes and a storage medium. Background technique [0002] Most of the current smart kitchens involve the field of human interaction. At present, the main thing is that the robot must be able to understand the user's language—that is, natural language understanding. The second aspect is to be able to answer, that is to say, on the basis of understanding, to be able to give the most accurate answer requires a huge corpus as a reserve, or the answer as a reserve. [0003] The natural language understanding part is inseparable from the in-depth processing of data, especially the cleaning and extraction of seed words in specific vertical fields. And these cleaning and extraction tasks involve a lot of labor, and for a large amount of data, this must be a time-consuming and labor-intensive process. ...

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): G06F17/27G06Q50/12
Inventor 石忠民林剑周钟力
Owner 广州索答信息科技有限公司
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