Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Article abstract generation method and system, electronic equipment and readable storage medium

A technology for generating systems and abstracts, applied in the field of information processing, can solve the problems of high cost, long time, and difficult to control the writing quality.

Pending Publication Date: 2019-12-20
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method, system, electronic equipment and a method for generating article summaries in order to overcome the defects in the prior art that the writing quality is difficult to control, time-consuming, and costly when writing product information manually. read storage medium

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
  • Article abstract generation method and system, electronic equipment and readable storage medium
  • Article abstract generation method and system, electronic equipment and readable storage medium
  • Article abstract generation method and system, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0145] An item summary generation method, such as figure 1 As shown, the article summary generation method includes:

[0146] Step 10. Recognize the text description picture of the target item to obtain a plurality of text description sentences;

[0147] Step 20, extracting a plurality of description keywords of the target item from the description sentence;

[0148] Step 30, calculate and obtain the TF-IDF value of each description keyword based on the TF-IDF algorithm;

[0149] Step 40, extracting N objective selling point keywords from multiple text description keywords according to the TF-IDF value; N is a natural number;

[0150] Step 50, select matching matching sentences from the description sentences according to the keywords of the objective selling points; it should be noted that the matching sentences here are sentences containing the keywords of the objective selling points;

[0151] Step 60, generating a summary of the target item according to the matching sent...

Embodiment 2

[0168] The method for generating article abstracts in this embodiment is further improved on the basis of Embodiment 1, such as Figure 4 As shown, before step 50, the article summary generation method also includes:

[0169] Step 41. Obtain multiple comment sentences from the comment data of the target item;

[0170] Step 42, extracting a plurality of comment keywords from the comment statement;

[0171] Step 43, calculating the frequency of each comment keyword;

[0172] Step 44, extracting M subjective selling point keywords from multiple review keywords according to frequency; M is a natural number;

[0173] Step 45, generating abstract keywords of the target item; the abstract keywords include the subjective selling point keywords and the objective selling point keywords;

[0174] Further, step 50 specifically includes:

[0175] Step 510, generating candidate sentences; the candidate sentences include the description sentences and the comment sentences;

[0176] Step...

Embodiment 3

[0183] The article summary generation method of this embodiment is further improved on the basis of Embodiment 2, such as Figure 5 As shown, before step 520, step 50 also includes:

[0184] Step 511, normalize the TF-IDF values ​​of all objective selling point keywords;

[0185] Step 512, the normalized TF-IDF value of each objective selling point keyword is used as the first weight of the objective selling point keyword;

[0186] Step 513, normalize the frequency of all subjective selling point keywords;

[0187] Step 514, taking the normalized frequency of each subjective selling point keyword as the second weight of the subjective selling point keyword;

[0188] Step 515, generate the weight of the abstract keyword; if the abstract keyword is an objective selling point keyword, then the weight of the abstract keyword is the first weight; if the abstract keyword is a subjective selling point keyword, then The weight of the abstract keyword is the second weight, if the ab...

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 an article abstract generation method and system, electronic equipment and a readable storage medium. The article abstract generation method comprises the following steps: identifying a sketch picture of a target article to obtain a plurality of sketch statements; extracting a plurality of sketch keywords of the target object from the sketch statement; calculating to obtaina TF-IDF value of each text tracing keyword based on a TF-IDF algorithm; according to the TF-IDF value, extracting N objective selling point keywords from the plurality of sketch keywords, wherein Nis a natural number; selecting a matched matching statement from the sketch statements according to the objective selling point keyword; and generating an abstract of the target article according to the matching statement. The abstract of the article can be automatically written according to the sketch picture of the article, so that the writing quality is controlled, the writing time is shortened, the writing efficiency is improved, and the writing cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of information processing, and in particular relates to a method, a system, an electronic device and a readable storage medium for generating an item summary. Background technique [0002] Usually Internet sites will set up some columns or channels to display or recommend items to users, such as finding good products, albums they will buy, and so on. In order to attract users, titles, pictures, and text descriptions are added to items, and this application refers to this text description as an abstract. In the prior art, the generation method of the abstract is to directly use the merchant's description of the product, or write it by a specific group of people (such as an expert). Although it is relatively easy to obtain product descriptions directly from merchants, the disadvantages are: the language is relatively blunt and focuses on technical descriptions; while written by a specific group of people, alt...

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): G06F16/34G06F16/335G06K9/34G06Q30/06
CPCG06Q30/0627G06V30/153Y02D10/00
Inventor 简晓容佘志东张震涛江丹丹饶正锋谢蔚
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com