[go: up one dir, main page]

IE20230320U1 - Text abstract generation method and system - Google Patents

Text abstract generation method and system

Info

Publication number
IE20230320U1
IE20230320U1 IE20230320U IE20230320U IE20230320U1 IE 20230320 U1 IE20230320 U1 IE 20230320U1 IE 20230320 U IE20230320 U IE 20230320U IE 20230320 U IE20230320 U IE 20230320U IE 20230320 U1 IE20230320 U1 IE 20230320U1
Authority
IE
Ireland
Prior art keywords
text
word
inputting
information
vector
Prior art date
Application number
IE20230320U
Other versions
IES87505Y1 (en
Inventor
Zeng Biqing
Original Assignee
Univ South China Normal
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Univ South China Normal filed Critical Univ South China Normal
Priority to IE20230320U priority Critical patent/IES87505Y1/en
Publication of IE20230320U1 publication Critical patent/IE20230320U1/en
Publication of IES87505Y1 publication Critical patent/IES87505Y1/en

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to a text abstract generation method and system, including: obtaining text information and dividing the text information into multiple words; inputting segmented multiple words into the word embedding model to obtain the word vector of each word; obtaining all the words that make up each word, and inputting all the words that make up the same word into the bidirectional recurrent neural network model in order to obtain the joint vector of each word; inputting the word vector of each word and its corresponding joint vector into the nonlinear model respectively to obtain the fusion feature of each word; combining the fusion features of each word to form a new input text, and inputting the new input text into the convolutional neural network to obtain high-level features representing the text; inputting the high-level features representing the text into the encoding-decoding model to obtain the text abstract. The invention can enhance the key information of the original text and attenuate the non-key information so that the generated text summary can represent the important information of the text in a better way.
IE20230320U 2023-08-08 2023-08-08 Text abstract generation method and system IES87505Y1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
IE20230320U IES87505Y1 (en) 2023-08-08 2023-08-08 Text abstract generation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
IE20230320U IES87505Y1 (en) 2023-08-08 2023-08-08 Text abstract generation method and system

Publications (2)

Publication Number Publication Date
IE20230320U1 true IE20230320U1 (en) 2024-06-19
IES87505Y1 IES87505Y1 (en) 2024-06-19

Family

ID=91899817

Family Applications (1)

Application Number Title Priority Date Filing Date
IE20230320U IES87505Y1 (en) 2023-08-08 2023-08-08 Text abstract generation method and system

Country Status (1)

Country Link
IE (1) IES87505Y1 (en)

Also Published As

Publication number Publication date
IES87505Y1 (en) 2024-06-19

Similar Documents

Publication Publication Date Title
Lai et al. Exploring the Impact of Generative Artificial Intelligence on the Design Process: Opportunities, Challenges, and
US20150339269A1 (en) System and method for generating flowchart from a text document using natural language processing
Moscato et al. Global Narratives of Ecological Modernization: The Construction of Climate Change op-eds in China Daily and the New York Times
Wu et al. Explainable application intent for zero-touch networking: an incorporation of hypergraph and transformer
IE20230320U1 (en) Text abstract generation method and system
Beris et al. Towards a decentralized, trusted, intelligent and linked public sector: A report from the Greek trenches
Baumber et al. Resilient utopias
CN106843822A (en) One kind performs code generating method and equipment
CO2025007284A2 (en) Training consumer participatory machine learning (ML) models on a 5G core network
Castro History of technology in nineteenth and twentieth century Latin America
Xianjin et al. Application of GIS-Based Models for Land-Use Planning in China
Vetter et al. WIKIPEDIA'S ENLIGHTENMENT PROBLEM: DECOLONIZING WESTERN EPISTEMOLOGIES THROUGH CRITICAL OPEN EDUCATION PRACTICES
Zimovets et al. Integration of formalization tools for graphical-analytical “Unit-Function-Object” models
CN106294780B (en) A method for extracting MSVL models from social networks
Atencio et al. Developing a Tool for PBO Design and Analysis: An Integration Between Enterprise Architecture and Project Management Domains
Maleh et al. Guest Editorial AI-Driven Decision-Making: Managerial and Organizational Promise and Potential
Sakr 11. Reframing the Arab Spring: On Data Mining and the Field of Arab Internet Studies
Figueroa Zavala et al. The Illusion of Sustainability: The Economic and Social Consequences of the Mayan Train in the Yucatán Peninsula
Olanipekun et al. Ethical implications of generative AI in journalism: Balancing innovation, truth, and public communication trust
Lindgren et al. Hayek and the Red Tape: The Politics of Evaluation and Quality Assurance Reform–From Shortcut Governing to Policy Rerouting
Fleischmann Ten Years After: Quo Vadis, S-BPM?
Køhlert Drawing Chicago: Chris Ware’s Graphic City
Reddy et al. In-form-ing AI Through Metaphors: Shaping Relations to Conversational Agents
Sadia Ghosts Of Noise
Wilson Making “Sense” of Functions