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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



