CN116414972B - Method for automatically broadcasting information content and generating short message - Google Patents
Method for automatically broadcasting information content and generating short message Download PDFInfo
- Publication number
- CN116414972B CN116414972B CN202310216474.9A CN202310216474A CN116414972B CN 116414972 B CN116414972 B CN 116414972B CN 202310216474 A CN202310216474 A CN 202310216474A CN 116414972 B CN116414972 B CN 116414972B
- Authority
- CN
- China
- Prior art keywords
- information
- content
- information content
- text
- generating
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims abstract description 32
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000014509 gene expression Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 6
- 230000019771 cognition Effects 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Document Processing Apparatus (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for automatically broadcasting information content and generating newsletters, which belongs to the technical field of newspaper information and comprises the following steps: s1: acquiring information content; s2: extracting the subject content and text abstract content of the information content; s3: according to the user setting parameters and the text abstract content, information content broadcasting is carried out; s4: and generating associated short messages. The invention utilizes the information multi-mode deep semantic understanding model to extract the text abstract of the information content, generates multi-mode feature vectors to connect the user setting parameters and the information content, realizes multi-information fusion of the user setting parameters and the information and the like, generates short messages with high precision, and plays the information content. Meanwhile, the information is visual and popular and easy to understand. The method for realizing unified modeling for understanding and generating information data develops a series of intelligent popup window broadcasting of newspaper and periodical information and automatic drawing and typesetting design of a background diagram according to abstract semantics for different subdivision scenes.
Description
Technical Field
The invention belongs to the technical field of newspaper information, and particularly relates to a method for automatically broadcasting information content and generating short messages.
Background
With the revolution of information technology, media iteration brings everything interconnection and everything, and multi-mode data of information is not only an important support for development of digital virtual worlds, but also a necessary supply for training of an AI algorithm, and the expression and interpretation of media specific information have profound influence on the information transmission efficiency and the audience cognition degree. Through intelligent injection and energization of mass data, virtual and real synchronization can be realized in the future world, and heavyweight breakthrough of an AI model can also occur, so that the agile and accurate data can not only effectively evaluate information transmission efficiency, but also optimally design information processing, expression and transmission mechanisms under media multi-mode fusion.
Information multi-modal refers to different forms of presentation or experience of things, and information multi-modal signals include pictures, sounds, text, video, and the like. Multi-modal signal analysis exists not only in newsfeed, but it also requires interdisciplinary theoretical architecture and knowledge adoption in information science, symbology, linguistics, and psychology. New media multimodal data analysis based on information science, the present invention relates to and processes multimodal information data by modeling. Five levels of data representation, data mapping, data alignment, data fusion, and collaborative learning for multimodal data. Based on the existing mapping relation, the existing multi-mode data symbol is vectorized, the vectorized multi-mode data symbol is used as an input end of the neural network, and is mapped to another mode by combining the existing corresponding relation, and after continuous training based on mass data, a cross-mode data mapping model with universality is obtained. Based on psychology, information perception information aiming at different channels from psychological and physiological measurement dimensions is mainly qualitative, foreign related media transmission efficiency theory and demonstration research not only reveals information cognition and processing processes of audiences, realizes improvement of media transmission efficiency, but also becomes a basis for formulating public policies, and plays a role in promoting and improving social benefits of media content. While domestic research on media performance has just started, students have grown accustomed to obtaining countermeasures to improve media performance by observing individual things or discussing and thinking about related propagation phenomena. The actual evidence research of media efficiency evaluation is carried out by fresh students, the description of static information transmission phenomenon of media is mostly biased, the relational research on how factors such as dynamic audience, media and society act on the media transmission efficiency is very little, the actual evidence research aiming at measuring and developing the theory of propagation science is rare under the guidance of the theory of propagation effect, quantitative and qualitative actual evidence research methods are lacked, and the system explores the mechanisms of information transmission and media transmission efficiency. The invention discloses a method for broadcasting information content and intelligently generating a short message version, which effectively utilizes a multi-mode model to solve the information static and dynamic information transmission phenomenon.
Disclosure of Invention
The invention provides a method for automatically broadcasting information content and generating short messages in order to solve the problems.
The technical scheme of the invention is as follows: a method for automatically broadcasting information content and generating short messages comprises the following steps:
s1: acquiring information content;
s2: extracting the subject content and text abstract content of the information content;
s3: acquiring user setting parameters, and broadcasting information content according to the user setting parameters and the text abstract content;
s4: and generating associated short messages according to the subject content and the abstract background picture associated with the text abstract content.
Further, step S2 comprises the sub-steps of:
s21: constructing an information multi-mode depth semantic understanding model;
s22: extracting a theme feature vector and a text abstract feature vector in the information content by using the information multi-mode deep semantic understanding model;
s23: and obtaining the topic content and the text summary content according to the topic feature vector and the text summary feature vector.
Further, in step S21, the information multi-mode deep semantic understanding model includes a content input layer, a weight extraction layer, and a vector output layer;
the content input layer is used for inputting the information content into the information multi-mode depth semantic understanding model; the weight extraction layer is used for extracting the weight corresponding to the information content; the vector output layer is used for extracting feature vectors according to the weights corresponding to the information content;
wherein, the weight corresponding to the information contentQThe calculation formula of (2) is as follows:
in the method, in the process of the invention,αrepresenting the ratio of the appearance of the subject term in the information content,βrepresenting the ratio of text to information content.
Further, step S3 comprises the sub-steps of:
s31: acquiring user setting parameters and generating a user preference priority order;
s32: extracting a text abstract and a text title according to the text abstract content;
s33: matching the corresponding text abstract and text title according to the priority order of the user preference, and playing corresponding information content according to the text abstract and the text title.
Further, in step S31, the specific method for generating the user preference priority order is as follows: calculating user preference priority, and sequencing the user preference priority from big to small to obtain user preference priority sequence, wherein the user preference priorityP(x|y) The calculation formula of (2) is as follows:
in the method, in the process of the invention,Dindicating that the user has access to the number,Arepresenting the topic feature vector in the user information,Brepresenting the text feature vector in the user information.
Further, step S4 comprises the sub-steps of:
s41: extracting sentence abstract keywords of the information content according to the subject content;
s42: generating a summary background diagram associated with the text summary content according to the sentence summary keywords of the information content;
s43: grid division is carried out on the abstract background graph to obtain a plurality of grids;
s44: labeling a target rectangular block of the abstract background diagram, and constructing a variable matrix corresponding to each grid according to the target rectangular block;
s45: generating a typesetting optimal region of the short messages according to the variable matrixes corresponding to the grids;
s46: filling the information titles and the information abstracts corresponding to the information content keywords into the typesetting optimal area to generate associated short messages.
Further, in step S44, the specific method for constructing the variable matrix corresponding to the grid is as follows: if the grid meetsThe element of the variable matrix is 1, otherwise the element of the variable matrix is 0; wherein,girdthe elements of the matrix of variables are represented,x i the abscissa representing the lower left corner of the target rectangular block,y i representing the ordinate of the lower left corner of the target rectangular block,w i representing the width of the target rectangular block,h i representing the height of the target rectangular block,pthe width of the grid is indicated,qrepresenting the height of the grid.
Further, in step S45, the specific method for generating the typesetting optimal area of the short message is as follows: and constructing a typesetting optimal area model, and determining a typesetting optimal area according to the typesetting optimal area model.
Further, typesetting optimal area modelObjThe expression of (2) is:
in the method, in the process of the invention,w_lirepresenting the length of the typeable rectangle,h_lirepresenting the width of the typeable rectangle,Lrepresenting the number of typeset rectangles.
Further, in step S46, the aspect ratio of the layout optimum region is calculatedr_liIf (if)r_li>And 1, typesetting the short messages according to the horizontal rows, or else typesetting the short messages according to the vertical rows.
The beneficial effects of the invention are as follows: the invention utilizes the information multi-mode deep semantic understanding model to extract the text abstract of the information content, generates multi-mode feature vectors to connect the user setting parameters and the information content, realizes multi-information fusion of the user setting parameters and the information and the like, generates short messages with high precision, and plays the information content. Meanwhile, the information is visual and popular and easy to understand. The method for realizing unified modeling for understanding and generating information data develops a series of intelligent popup window broadcasting of newspaper and periodical information and automatic drawing and typesetting design of a background diagram according to abstract semantics for different subdivision scenes.
Drawings
FIG. 1 is a flow chart of a method for automatically broadcasting information content and generating short messages.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in FIG. 1, the invention provides a method for automatically broadcasting information content and generating short messages, which comprises the following steps:
s1: acquiring information content;
s2: extracting the subject content and text abstract content of the information content;
s3: acquiring user setting parameters, and broadcasting information content according to the user setting parameters and the text abstract content;
s4: and generating associated short messages according to the subject content and the abstract background picture associated with the text abstract content.
In an embodiment of the present invention, step S2 comprises the sub-steps of:
s21: constructing an information multi-mode depth semantic understanding model;
s22: extracting a theme feature vector and a text abstract feature vector in the information content by using the information multi-mode deep semantic understanding model;
s23: and obtaining the topic content and the text summary content according to the topic feature vector and the text summary feature vector.
In the embodiment of the invention, in step S21, the information multi-mode depth semantic understanding model comprises a content input layer, a weight extraction layer and a vector output layer;
the content input layer is used for inputting the information content into the information multi-mode depth semantic understanding model; the weight extraction layer is used for extracting the weight corresponding to the information content; the vector output layer is used for extracting feature vectors according to the weights corresponding to the information content;
wherein, the weight corresponding to the information contentQThe calculation formula of (2) is as follows:
in the method, in the process of the invention,αrepresenting the ratio of the appearance of the subject term in the information content,βrepresenting the ratio of text to information content.
In an embodiment of the present invention, step S3 comprises the sub-steps of:
s31: acquiring user setting parameters and generating a user preference priority order;
s32: extracting a text abstract and a text title according to the text abstract content;
s33: matching the corresponding text abstract and text title according to the priority order of the user preference, and playing corresponding information content according to the text abstract and the text title.
In the embodiment of the present invention, in step S31, the specific method for generating the user preference priority order is as follows: calculating user preference priority, and sequencing the user preference priority from big to small to obtain user preference priority sequence, wherein the user preference priorityP(x|y) The calculation formula of (2) is as follows:
in the method, in the process of the invention,Dindicating that the user has access to the number,Arepresenting the topic feature vector in the user information,Brepresenting the text feature vector in the user information.
In an embodiment of the present invention, step S4 comprises the sub-steps of:
s41: extracting sentence abstract keywords of the information content according to the subject content;
s42: generating a summary background diagram associated with the text summary content according to the sentence summary keywords of the information content;
s43: grid division is carried out on the abstract background graph to obtain a plurality of grids;
s44: labeling a target rectangular block of the abstract background diagram, and constructing a variable matrix corresponding to each grid according to the target rectangular block;
s45: generating a typesetting optimal region of the short messages according to the variable matrixes corresponding to the grids;
s46: filling the information titles and the information abstracts corresponding to the information content keywords into the typesetting optimal area to generate associated short messages.
In the embodiment of the present invention, in step S44, the specific method for constructing the variable matrix corresponding to the grid is as follows: if the grid meetsThe element of the variable matrix is 1, otherwise the element of the variable matrix is 0; wherein,girdthe elements of the matrix of variables are represented,x i the abscissa representing the lower left corner of the target rectangular block,y i representing the ordinate of the lower left corner of the target rectangular block,w i representing the width of the target rectangular block,h i representing the height of the target rectangular block,pthe width of the grid is indicated,qrepresenting the height of the grid.
In the embodiment of the present invention, in step S45, the specific method for generating the typesetting optimal area of the short message is as follows: and constructing a typesetting optimal area model, and determining a typesetting optimal area according to the typesetting optimal area model.
In the embodiment of the invention, the optimal area model is typesetObjThe expression of (2) is:
in the method, in the process of the invention,w_lirepresenting the length of the typeable rectangle,h_lirepresenting the width of the typeable rectangle,Lrepresenting the number of typeset rectangles.
In the embodiment of the present invention, in step S46, the aspect ratio of the layout optimum region is calculatedr_liIf (if)r_li>And 1, typesetting the short messages according to the horizontal rows, or else typesetting the short messages according to the vertical rows.
The title and text of the information are subject to comprehensive modeling to obtain vectors, and each vector represents the symbol information of the information. And calculates the amount of information spread between the audience by similarity of topic vectors between the audience messages of the group.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (5)
1. A method for automatically broadcasting information content and generating short messages is characterized by comprising the following steps:
s1: acquiring information content;
s2: extracting the subject content and text abstract content of the information content;
s3: acquiring user setting parameters, and broadcasting information content according to the user setting parameters and the text abstract content;
s4: generating associated short messages according to the subject content and a abstract background diagram associated with the text abstract content;
said step S4 comprises the sub-steps of:
s41: extracting sentence abstract keywords of the information content according to the subject content;
s42: generating a summary background diagram associated with the text summary content according to the sentence summary keywords of the information content;
s43: grid division is carried out on the abstract background graph to obtain a plurality of grids;
s44: labeling a target rectangular block of the abstract background diagram, and constructing a variable matrix corresponding to each grid according to the target rectangular block;
s45: generating a typesetting optimal region of the short messages according to the variable matrixes corresponding to the grids;
s46: filling the information titles and the information abstracts corresponding to the information content keywords into the typesetting optimal area to generate associated short messages;
in the step S44, the specific method for constructing the variable matrix corresponding to the grid is as follows: if the grid meetsThe element of the variable matrix is 1, otherwise the element of the variable matrix is 0; wherein, gard represents an element of a variable matrix, x i The abscissa, y, representing the lower left corner of the target rectangular block i Representing the ordinate, w, of the lower left corner of the target rectangular block i Represents the width of the target rectangular block, h i Representing the height of the target rectangular block, p representing the width of the grid, q representing the height of the grid;
in the step S45, the specific method for generating the typesetting optimal area of the short message is as follows: constructing a typesetting optimal area model, and determining a typesetting optimal area according to the typesetting optimal area model;
the expression of the typesetting optimal area model Obj is as follows:
wherein w_li represents the length of the typeset rectangle, h_li represents the width of the typeset rectangle, and L represents the number of typeset rectangles;
in the step S46, the aspect ratio r_li of the typesetting optimal area is calculated, if r_li >1, the short messages are typeset according to the horizontal rows, otherwise, the short messages are typeset according to the vertical rows.
2. The method for automatically broadcasting and generating newsletters according to claim 1, wherein the step S2 comprises the following sub-steps:
s21: constructing an information multi-mode depth semantic understanding model;
s22: extracting a theme feature vector and a text abstract feature vector in the information content by using the information multi-mode deep semantic understanding model;
s23: and obtaining the topic content and the text summary content according to the topic feature vector and the text summary feature vector.
3. The method for automatically broadcasting and generating short messages according to claim 2, wherein in said step S21, the information multi-modal deep semantic understanding model includes a content input layer, a weight extraction layer and a vector output layer;
the content input layer is used for inputting information content into the information multi-mode depth semantic understanding model; the weight extraction layer is used for extracting weights corresponding to the information content; the vector output layer is used for extracting feature vectors according to weights corresponding to the information content;
the calculation formula of the weight Q corresponding to the information content is as follows:
where α represents the ratio of occurrence of the subject word in the information content, and β represents the ratio of occurrence of the text in the information content.
4. The method for automatically broadcasting and generating newsletters according to claim 1, wherein the step S3 comprises the following sub-steps:
s31: acquiring user setting parameters and generating a user preference priority order;
s32: extracting a text abstract and a text title according to the text abstract content;
s33: matching the corresponding text abstract and text title according to the priority order of the user preference, and playing corresponding information content according to the text abstract and the text title.
5. The method for automatically broadcasting and generating newsletters according to claim 4, wherein in the step S31, the specific method for generating the preference priority order of the user is as follows: calculating user preference priority, and sequencing the user preference priority from big to small to obtain a user preference priority sequence, wherein the calculation formula of the user preference priority P (x|y) is as follows:
wherein D represents a user access number, a represents a subject feature vector in the user setting parameter, and B represents a text feature vector in the user setting parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216474.9A CN116414972B (en) | 2023-03-08 | 2023-03-08 | Method for automatically broadcasting information content and generating short message |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216474.9A CN116414972B (en) | 2023-03-08 | 2023-03-08 | Method for automatically broadcasting information content and generating short message |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116414972A CN116414972A (en) | 2023-07-11 |
| CN116414972B true CN116414972B (en) | 2024-02-20 |
Family
ID=87055640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310216474.9A Active CN116414972B (en) | 2023-03-08 | 2023-03-08 | Method for automatically broadcasting information content and generating short message |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116414972B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365942A (en) * | 2012-03-28 | 2013-10-23 | 索尼公司 | Display control device, display control method, and program |
| CN105100718A (en) * | 2015-07-29 | 2015-11-25 | 西安冉科信息技术有限公司 | Intelligent video analysis method based on video abstraction |
| WO2015196122A1 (en) * | 2014-06-19 | 2015-12-23 | Contentguard Holdings, Inc. | Rendering content using obscuration techniques |
| CN108062389A (en) * | 2017-12-15 | 2018-05-22 | 北京百度网讯科技有限公司 | Bulletin generation method and device |
| CN109460525A (en) * | 2018-11-07 | 2019-03-12 | 网易（杭州）网络有限公司 | Methods of exhibiting, device, medium and the calculating equipment of news in brief class article |
| CN109508400A (en) * | 2018-10-09 | 2019-03-22 | 中国科学院自动化研究所 | Picture and text abstraction generating method |
| CN110555202A (en) * | 2018-05-30 | 2019-12-10 | 微软技术许可有限责任公司 | method and device for generating abstract broadcast |
| CN110597981A (en) * | 2019-09-16 | 2019-12-20 | 西华大学 | Network news summary system for automatically generating summary by adopting multiple strategies |
| CN111866079A (en) * | 2020-06-19 | 2020-10-30 | 云天弈(广州)智能科技有限公司 | Financial information pushing system and method |
| CN112133279A (en) * | 2019-06-06 | 2020-12-25 | Tcl集团股份有限公司 | Vehicle-mounted information broadcasting method and device and terminal equipment |
| CN112562669A (en) * | 2020-12-01 | 2021-03-26 | 浙江方正印务有限公司 | Intelligent digital newspaper automatic summarization and voice interaction news chat method and system |
| CN112685556A (en) * | 2020-12-29 | 2021-04-20 | 西安掌上盛唐网络信息有限公司 | Automatic news text summarization and voice broadcasting system |
| CN113312503A (en) * | 2021-04-20 | 2021-08-27 | 桂林电子科技大学 | Novel teaching video content abstract and visual browsing method |
| CN113434685A (en) * | 2021-07-06 | 2021-09-24 | 中国银行股份有限公司 | Information classification processing method and system |
| CN115687603A (en) * | 2022-10-28 | 2023-02-03 | 竹间智能科技（上海）有限公司 | Presentation generation method and device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7154638B1 (en) * | 2000-05-23 | 2006-12-26 | Silverbrook Research Pty Ltd | Printed page tag encoder |
| US20060217925A1 (en) * | 2005-03-23 | 2006-09-28 | Taron Maxime G | Methods for entity identification |
-
2023
- 2023-03-08 CN CN202310216474.9A patent/CN116414972B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365942A (en) * | 2012-03-28 | 2013-10-23 | 索尼公司 | Display control device, display control method, and program |
| WO2015196122A1 (en) * | 2014-06-19 | 2015-12-23 | Contentguard Holdings, Inc. | Rendering content using obscuration techniques |
| CN105100718A (en) * | 2015-07-29 | 2015-11-25 | 西安冉科信息技术有限公司 | Intelligent video analysis method based on video abstraction |
| CN108062389A (en) * | 2017-12-15 | 2018-05-22 | 北京百度网讯科技有限公司 | Bulletin generation method and device |
| CN110555202A (en) * | 2018-05-30 | 2019-12-10 | 微软技术许可有限责任公司 | method and device for generating abstract broadcast |
| CN109508400A (en) * | 2018-10-09 | 2019-03-22 | 中国科学院自动化研究所 | Picture and text abstraction generating method |
| CN109460525A (en) * | 2018-11-07 | 2019-03-12 | 网易（杭州）网络有限公司 | Methods of exhibiting, device, medium and the calculating equipment of news in brief class article |
| CN112133279A (en) * | 2019-06-06 | 2020-12-25 | Tcl集团股份有限公司 | Vehicle-mounted information broadcasting method and device and terminal equipment |
| CN110597981A (en) * | 2019-09-16 | 2019-12-20 | 西华大学 | Network news summary system for automatically generating summary by adopting multiple strategies |
| CN111866079A (en) * | 2020-06-19 | 2020-10-30 | 云天弈(广州)智能科技有限公司 | Financial information pushing system and method |
| CN112562669A (en) * | 2020-12-01 | 2021-03-26 | 浙江方正印务有限公司 | Intelligent digital newspaper automatic summarization and voice interaction news chat method and system |
| CN112685556A (en) * | 2020-12-29 | 2021-04-20 | 西安掌上盛唐网络信息有限公司 | Automatic news text summarization and voice broadcasting system |
| CN113312503A (en) * | 2021-04-20 | 2021-08-27 | 桂林电子科技大学 | Novel teaching video content abstract and visual browsing method |
| CN113434685A (en) * | 2021-07-06 | 2021-09-24 | 中国银行股份有限公司 | Information classification processing method and system |
| CN115687603A (en) * | 2022-10-28 | 2023-02-03 | 竹间智能科技（上海）有限公司 | Presentation generation method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Recent automatic text summarization techniques: a survey;Mahak Gambhir;《Artificial Intelligence Review》;第47卷;1-66 * |
| 融合主题信息的抽取生成式摘要技术研究与应用;魏媛媛;《中国优秀硕士学位论文全文数据库 信息科技》;I138-1469 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116414972A (en) | 2023-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582241B (en) | Video subtitle recognition method, device, equipment and storage medium | |
| Torralba et al. | Labelme: Online image annotation and applications | |
| CN110941692A (en) | Method for extracting news events of Internet politics outturn class | |
| Sun et al. | Student Class Behavior Dataset: a video dataset for recognizing, detecting, and captioning students’ behaviors in classroom scenes | |
| CN110795925B (en) | Image-text typesetting method and device based on artificial intelligence and electronic equipment | |
| KR20190108378A (en) | Method and System for Automatic Image Caption Generation | |
| CN113395578A (en) | Method, device and equipment for extracting video theme text and storage medium | |
| Birnbaum et al. | The digital Middle Ages: an introduction | |
| CN113360598A (en) | Matching method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN111126243B (en) | Image data detection method and device and computer readable storage medium | |
| Sun | Design and Construction of University Book Layout Based on Text Image Preprocessing Algorithm in Education Metaverse Environment | |
| CN116414972B (en) | Method for automatically broadcasting information content and generating short message | |
| Lin et al. | Urban space simulation based on wave function collapse and convolutional neural network | |
| CN107506370A (en) | Multi-medium data depth method for digging, storage medium and electronic equipment | |
| CN111858962A (en) | Data processing method, device and computer readable storage medium | |
| KR20110039900A (en) | Iamge data recognition and managing method for ancient documents using intelligent recognition library and management tool | |
| Li | A Data Mining-Based Method for Quality Assessment of Ideological and Political Education in Universities | |
| CN115270943B (en) | Knowledge tag extraction model based on attention mechanism | |
| CN116257618A (en) | Multi-source intelligent travel recommendation method based on fine granularity emotion analysis | |
| CN113887334A (en) | Video knowledge point extraction method and device | |
| CN115130453A (en) | Interactive information generation method and device | |
| Chen et al. | DanmuVis: Visualizing danmu content dynamics and associated viewer behaviors in online videos | |
| Gao et al. | Big data processing: a graduate course for engineering students | |
| Cai et al. | A Study on Integrating Multimodal English and American Literature Resources Using Data Mining | |
| CN117788628A (en) | Creative material generation method based on AIGC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |